DETAILED ACTION
This Office Action is in response to the correspondence filed by the applicant on 6/5/2026.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
Applicant’s argument, pages 6-8, filed 6/5/2026, with respect to the rejection of claims 103 have been fully considered and are moot upon a further consideration and a new ground(s) of rejection made under AIA 35 U.S.C. 103 as being unpatentable over SERNA (US 20210326940 A1), and in further view of ML (US 2023/0113860 A1) and RAVINDRAN (US 2023/0385884 A1). Please see the rejection below for more details.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The claims in this application are given their broadest reasonable interpretation using the plain meaning of the claim language in light of the specification as it would be understood by one of ordinary skill in the art. The broadest reasonable interpretation of a claim element (also commonly referred to as a claim limitation) is limited by the description in the specification when 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is invoked.
As explained in MPEP § 2181, subsection I, claim limitations that meet the following three-prong test will be interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph:
(A) the claim limitation uses the term “means” or “step” or a term used as a substitute for “means” that is a generic placeholder (also called a nonce term or a non-structural term having no specific structural meaning) for performing the claimed function;
(B) the term “means” or “step” or the generic placeholder is modified by functional language, typically, but not always linked by the transition word “for” (e.g., “means for”) or another linking word or phrase, such as “configured to” or “so that”; and
(C) the term “means” or “step” or the generic placeholder is not modified by sufficient structure, material, or acts for performing the claimed function.
Use of the word “means” (or “step”) in a claim with functional language creates a rebuttable presumption that the claim limitation is to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites sufficient structure, material, or acts to entirely perform the recited function.
Absence of the word “means” (or “step”) in a claim creates a rebuttable presumption that the claim limitation is not to be treated in accordance with 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph. The presumption that the claim limitation is not interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, is rebutted when the claim limitation recites function without reciting sufficient structure, material or acts to entirely perform the recited function.
Claim limitations in this application that use the word “means” (or “step”) are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action. Conversely, claim limitations in this application that do not use the word “means” (or “step”) are not being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, except as otherwise indicated in an Office action.
This application includes one or more claim limitations that do not use the word “means,” but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: a pre-processing module and a post-processing module in claim 7.
Because this/these claim limitation(s) is/are being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it/they is/are being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof.
If applicant does not intend to have this/these limitation(s) interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation(s) to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation(s) recite(s) sufficient structure to perform the claimed function so as to avoid it/them being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102 of this title, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-3, 5-11, 13-17, and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over SERNA (US 20210326940 A1), and in further view of ML (US 2023/0113860 A1) and RAVINDRAN (US 2023/0385884 A1).
REGARDING CLAIM 1, SERNA discloses a method for sentiment analysis regarding a wireless communication network of a communication service provider (CSP), the method comprising:
collecting, using a sentiment analysis system, a set of customer comments and a set of associated data for each customer comment (Fig. 19; Par 175 – “FIG. 19 shows an embodiment of an exemplary customer service request 1902. Such a customer service request 1902 may include a date 1904, a time of initiation 1906, a location of device which is transmitting the information 1908, a device ID number 1910 and/or a message 1912.”) from one or more online platforms (Fig. 1 – “Message (text) 120”; Fig. 4 – “Verbal statements, telephone calls, conversations, …”; Par 51 – “The customer support request may include a message. It should be noted that the message may be derived from the customer support request. When the customer support request is communication by voice, the system may use natural language processing and/or any other suitable voice to text engine. In addition, the customer support request may include voice information associated with the customer support request.”; Par 52 – “The system may further include a processor. The processor may be configured, for each customer support request, to harvest a plurality of artifacts from social media account history and/or other third party data source information associated with a user associated with the device identification number. Each of the plurality of artifacts may include sentiment information relevant to the customer support request.”), wherein each customer comment comprises text (Par 40 – “Support requests, and historical communications-related thereto, in the form of email, Instant Messaging Service (IMS), phone calls, video chats, Twitter communications such as Tweets™, and other elements (e.g., response time, escalations, etc.) may be analyzed to define the sentiment of the interactions of an individual, group and/or entity towards one or more individuals, groups and/or entities and to provide a current snapshot thereof.”) [and is related to the wireless communication network of the CSP], and wherein the set of associated data for each customer comment comprises a location (Fig. 19; Par 175 – “FIG. 19 shows an embodiment of an exemplary customer service request 1902. Such a customer service request 1902 may include a date 1904, a time of initiation 1906, a location of device which is transmitting the information 1908, a device ID number 1910 and/or a message 1912.”);
generating, using a pre-processing module, a profile for each customer comment in the set of customer comments (Par 64 – “The processor may be further configured to build a current profile for the communication device. The current profile may be based on the plurality of artifacts and the historical information.”);
providing the text of each customer comment to a natural language processing (NLP) <neural network> (Par 47 – “It should be noted that the topic analysis could be used for many different type of topics, but that such information could preferably be mined from the customer support request using such utilities as the aforementioned libraries including, but not limited to, the Natural Language Toolkit library.”; Par 73 – “The message may be derived from the customer support request using natural language processing.”; Par 119 – “Polarity-based scoring scale 702 is shown in FIG. 7. In such a scoring scale, each support request is scored on a polar scale using linguistic scoring methodology. Linguistic scoring methodology may utilize various language scoring methods, such as natural language processing, computational linguistics and biometrics. For the purposes of this application, natural language processing should be understood to refer to Natural Language Processing (NLP) is a subfield of linguistics, computer science, information engineering and artificial intelligence concerned with the interactions between computers and human (natural) languages. In particular, NLP refers to how to program computers to process and analyze large amounts of natural language data.”);
generating, using the NLP <neural network>, at least a sentiment classification (Par 119 – “Polarity-based scoring scale 702 is shown in FIG. 7. In such a scoring scale, each support request is scored on a polar scale using linguistic scoring methodology. Linguistic scoring methodology may utilize various language scoring methods, such as natural language processing, computational linguistics and biometrics.”; Par 122 – “It should be appreciated that a polarity-based scale may include two opposite emotions, whether positive and negative, happy and sad or any other suitable opposite emotions. Therefore, each support request scored on a polarity-based score may only be given a sentiment score based on the polarity of the support request. However, at times, in order to compensate for the shortcomings of the polarity-based scoring models, an artifact may be scored on multiple polarity-based scoring models, and, the results of the scoring models may be combined.”; Par 124 – “Vector 834 may be a vector generated from a support request.”; Par 125 – “The sentiment of the support request plotted as vector 834 may be shown in-between intelligent and promoted. It should be appreciated that the multi-dimensional scoring scale may be used to determine the sentiment of a support request—with or without sentiment adjustment associated with retrieved artifacts.”) and an issue classification for each customer comment based on the text of the customer comment (Par 45 – “For example, if the sentiment associated with a user has been determined to be happy (sentiment analysis) and the user is asking questions regarding financial instruments (topic analysis), it could be beneficial to route that customer to a new financial advisor so the new financial advisor could build up their client book with a happy user.”; Par 47 – “It should be noted that the topic analysis could be used for many different type of topics, but that such information could preferably be mined from the customer support request using such utilities as the aforementioned libraries including, but not limited to, the Natural Language Toolkit library.”);
generating, using a post-processing module, one or more reports (Fig. 4 – “support request 412”; Par 75 – “The foregoing are examples of analyses that an AI-bot may |use legacy customer support requests|[SD3], or other, information to tune a response to a current customer request. By forming a historical request profile, legacy information can be leveraged to more appropriately respond to current customer support requests. Additional examples of AI-bot responses are described in more detail below in the portion of the specification corresponding to FIGS. 15-22.”; Par 8 – “The customer support request may include a date of the customer support request, a time of receipt of the customer support request, a location of a communication device that was used to communicate the customer support request, a device identification number associated with the communication device and a message derivable from the customer support request.”; Par 144 – “Once the support requests have been received, the support requests may be parsed by parsing engine 1232 for date, time, location, name of requester and message content. Thereafter, response system 1234 may redirect the support request to either an employee in the support center 1210, auto-response system in the support center 1206 or a manager 1214.”; In other words, The parsed support requests include the messages (i.e., comments) and other information (date, time, location, etc.) associated with the messages. The parsed support requests are routed to a responsible person.) [for a geographic region of the wireless communication network that aggregate a plurality of customer comments from the set of customer comments based on the sentiment classification, the issue classification, and the location of each customer comment] to identify an issue in the geographic region of the wireless communication network (Par 8 – “The customer support request may include a date of the customer support request, a time of receipt of the customer support request, a location of a communication device that was used to communicate the customer support request, a device identification number associated with the communication device and a message derivable from the customer support request.”; Par 144 – “Once the support requests have been received, the support requests may be parsed by parsing engine 1232 for date, time, location, name of requester and message content. Thereafter, response system 1234 may redirect the support request to either an employee in the support center 1210, auto-response system in the support center 1206 or a manager 1214.”; In other words, The parsed support requests include the messages (i.e., comments) and other information (date, time, location, etc.) associated with the messages. The parsed support requests are routed to a responsible person.) and
transmitting, using the sentiment analysis system, at least one report to a department of the CSP based on the sentiment classification, the issue classification, and the location (Par 45 –“For example, if the sentiment associated with a user has been determined to be happy (sentiment analysis) and the user is asking questions regarding financial instruments (topic analysis), it could be beneficial to route that customer to a new financial advisor so the new financial advisor could build up their client book with a happy user.”; Par 90 – “Finally, at step 206, the diagram shows routing the customer support request based on 1) a localized context and various request parameters associated with the request in combination with 2) the customer sentiment derived from social media artifacts.”; Par 144 – “Once the support requests have been received, the support requests may be parsed by parsing engine 1232 for date, time, location, name of requester and message content. Thereafter, response system 1234 may redirect the support request to either an employee in the support center 1210, auto-response system in the support center 1206 or a manager 1214.”).
SERNA does not explicitly teach the [square-bracketed] and <angle-bracketed> limitations.
Regarding the [square-bracketed] limitations, SERNA teaches generating issue reports based on the sentiment (e.g., negative and/or positive sentiment of the customer), the issue classification (type of the issue), and the location (e.g., the location of the requester and/or device), but does not explicitly teach the report is based on aggregated customer comments related to a wireless communication network.
ML discloses the [square-bracketed] limitations. ML discloses a method/system to identify aggregated issues at a location comprising:
collecting, using a sentiment analysis system, a set of customer comments and a set of associated data for each customer comment (ML Par 36 – “Turning to client mnemonics 104, PPA 102 may initiate execution of a script for receiving information relating to a network quality issue that a client has reported, the information including client mnemonics 104. For example, PPA 102 may receive information such as, for example, a name or unique identifier of the client, a type or kind of the network quality issue, a number or quantity corresponding to a server that is associated with the network quality issue of the client, a physical or virtual location of the client, a physical or virtual location of the server, and the like.”; Par 39 – “Turning to PPA intelligent mapper 110, PPA intelligent mapper 110 comprises intelligent mapper database 112, natural language processor (NLP) 114, and keyword learning 116 for generating a dataset for subsequent electronic documentation of the network quality issue. For example, intelligent mapper database 112 can store data processed by NLP 114, such as data associated with the network quality issue, with historical network quality issues associated with the same client and/or with other clients, and with incoming network quality issues occurring simultaneously or within temporal proximity to one or more occurrences of the network quality issue.”) from one or more online platforms (ML Par 12 – “Electronic documentation may comprise a problem ticket, which is a report of a computing issue including information about a symptom of the computing issue (e.g., such as those generated in a help-desk or call-center environment).”), wherein each customer comment comprises text (LM Par 15 – “As used herein, a “problem keyword” or a “keyword” refers to a key term that is associated with a technological problem or computing issue that causes a reduction in the quality of a service provided by a network. The problem keyword or the keyword may be used in text mining, information retrieval, and natural language processing. For example, a keyword may be used for querying a central database comprising electronic documentation for information within the central database that contains the keyword being searched.”) [and is related to the wireless communication network of the CSP] (ML Par 14 – “The term “mnemonic” and “mnemonics” are used interchangeably to refer to information relating to a network quality issue that a client has reported. Client mnemonics may refer to a name or unique identifier of the client. Mnemonics may also include mnemonic codes a client uses to specify computing instructions, such as a computing function, service, or process (e.g., moving data from one computer storage location to another). A first client may use a different mnemonic code for a first function than a second client, in some embodiments.”), and wherein the set of associated data for each customer comment comprises a location (ML Par 36 – “For example, PPA 102 may receive information such as, for example, a name or unique identifier of the client, a type or kind of the network quality issue, a number or quantity corresponding to a server that is associated with the network quality issue of the client, a physical or virtual location of the client, a physical or virtual location of the server, and the like. In aspects, the client mnemonics 104 include navigational mnemonics for locating functions performed that are associated with tasks and the network quality issue.”);
generating, using a post-processing module, one or more reports (ML Par 61 – “For example, the notification may be transmitted for display on a graphical user interface of the user device. In aspects when a second electronic documentation is generated for a second recurring issue that satisfied the threshold 324, the notification may indicated that both the electronic documentation and the second electronic documentation associated with a second recurring issue have been created. In some aspects, as discussed in more detail above, the threshold 324 (i.e., the condition for root cause investigation for the recurring issue) for the recurring issue is different than the threshold 324 for the second recurring issue. Furthermore, the notification may comprise an image or an alert. As such, the method 300 ends at 330.”) [for a geographic region of the wireless communication network that aggregate a plurality of customer comments from the set of customer comments based on the sentiment classification, the issue classification, and the location of each customer comment] (ML Par 68 – “In some aspects, the data that was cleansed and indexed is aggregated. The data may be aggregated via a script, and may be aggregated based on a client, a network quality issue type, a location, and a keyword. In some aspects, the aggregated data is stored in the central database and used to identify current network issues. In some aspects, the current network issue is identified by mining the aggregated data and identifying a pattern. In aspects, the pattern is associated with prior solutions to the network issue identified. For example, the pattern may be identified upon aggregating data associated with a particular client, having the same network quality issue type, and located in a particular index of the central database, wherein the index location is determined based on a particular keyword.”; Par 16 – “As used herein, a “source” of data refers to data from a particular client device, a particular set of data (e.g., a particular table or dataset), data from a particular entity (e.g., data from one corporation or one specific department of that corporation, data from one hospital or from one department of the hospital, or data from a particular group of client devices associated with a particular manager), and so forth.”; Par 88 – “Although illustrated as a single device, the remote computers 506 may include multiple computing devices. In an aspect having a distributed network, the remote computers 506 may be located at one or more different geographic locations. In an aspect where the remote computers 506 is a plurality of computing devices, each of the plurality of computing devices may be located across various locations, such as buildings in a campus, medical and research facilities at a medical complex, offices or “branches” of a banking/credit entity, etc. In an aspect, the remote computers 506 are mobile devices that are wearable or carried by personnel, attached to one or more vehicles, or trackable items in a warehouse, for example.”) to identify an issue in the geographic region of the wireless communication network (ML Par 69 – “Continuing the example, the plurality of sources may be provided as electronic documents reporting network errors and/or issues from a first hospital and a second hospital, wherein the first hospital is an acute care hospital and the second hospital is a rural hospital. Further continuing the example, all of the aggregated data may correspond to one particular type of network issue or two or more related types of network issues.”; Par 89 – “In some aspects, the remote computers 506 are physically located in a medical setting such as, for example, a laboratory, inpatient room, an outpatient room, a hospital, a medical vehicle, a veterinary environment, an ambulatory setting, a medical billing office, a financial or administrative office, hospital administration setting, an in-home medical care environment, and/or medical professionals' offices.”) and
transmitting, using the sentiment analysis system, at least one report to a department of the CSP based on the sentiment classification, the issue classification, and the location (ML Par 61 – “For example, the notification may be transmitted for display on a graphical user interface of the user device. In aspects when a second electronic documentation is generated for a second recurring issue that satisfied the threshold 324, the notification may indicated that both the electronic documentation and the second electronic documentation associated with a second recurring issue have been created. In some aspects, as discussed in more detail above, the threshold 324 (i.e., the condition for root cause investigation for the recurring issue) for the recurring issue is different than the threshold 324 for the second recurring issue. Furthermore, the notification may comprise an image or an alert. As such, the method 300 ends at 330.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method/system of SERNA to include aggregated comments regarding communication issues, as taught by ML.
One of ordinary skill would have been motivated to include aggregated comments regarding communication issues, in order to provide a variety of enterprise solutions faster and more accurately (Par 49).
Regarding <angle-bracketed> limitation, SERNA in view ML does not explicitly teach analyzing textual data using a NLP <neural network>.
RAVINDRAN discloses the <angle-bracketed> limitations. RAVINDRAN discloses a method/system to identify issues from user comments comprising:
providing the text of each customer comment (RAVINDRAN Par 89 – “Step 300 includes receiving natural language text generated by different sources of information. Receiving the natural language text may be performed as described with respect to step 200 of FIG. 2 . However, in step 300, many different sources of information are accessed, and the raw natural language text collated for processing.” to a natural language processing (NLP) <neural network> (RAVINDRAN Par 83 – “As part of pre-processing, the method may also include vectorizing the natural language text to generate the first input to the MLM at step 202. Vectorizing may include inputting the natural language text to a third MLM, such as a bi-directional long short term memory neural network. Vectorizing also may include receiving, as output from the third MLM, a matrix of numbers representing both the natural language text and contexts of sentences in the natural language text.”);
generating, using the NLP <neural network> (RAVINDRAN Par 48 – “Other types of models may be used for the second machine learning model (120B). For example, a Multi-Layer Perceptron Model (MLP) may be used to categorize the negative reviews. A MLP is a fully connected class of feed forward artificial neural networks. However, other models may be used, like XGBoost, which is a decision-tree-based ensemble machine learning algorithm that uses a gradient boosting framework. Recurrent neural networks can also be used to categorize the reviews.”), at least a sentiment classification (RAVINDRAN Par 90 – “Step 302 includes pre-processing the natural language text by cleaning and vectorizing the natural language text. Pre-processing, cleaning, and vectorizing may be performed as described with respect to step 202 of FIG. 2 . The pre-processing controller (128) of FIG. 1A may perform the cleaning and vectorizing of the natural language text.”; Par 83 – “Vectorizing may include inputting the natural language text to a third MLM, such as a bi-directional long short term memory neural network.”; Par 91 – “Step 304 includes extracting negative reviews from the natural language text by executing a first machine learning model (MLM). Extracting the negative reviews may be performed as described with respect to step 202 of FIG. 2 . Thus, for example, a first input to the first MLM is the natural language text and a first output of the first MLM is first probabilities that corresponding instances of the natural language text have negative sentiments.”) and an issue classification for each customer comment based on the text of the customer comment (RAVINDRAN Par 112 – “Next, during categorization (432), the negative reviews are categorized into two or more different categories. Categorization is described with respect to step 204 of FIG. 2 or step 306 of FIG. 3 . In other words, the negative reviews are sorted by category, such as by application type (e.g., whether the negative reviews relate to the enterprise system (400), the financial management web application (402), the tax preparation web application (404), and/or the online presence web application (406)) of FIG. 4A.”);
generating, using a post-processing module, one or more reports for a specific provider (RAVINDRAN Par 56 – “Continuing the above example, the negative review A (122B) may be categorized under “PROVIDER NAME”, because the highest averaged probability for the negative review A (122B) is associated with the category “PROVIDER NAME.””; Note ML already teaches generating reports for a specific geographic region. RAVINDRAN teaches generating an issue report for a specific provider) of the wireless communication network that aggregate a plurality of customer comments from the set of customer comments (RAVINDRAN Par 77 – “Step 208 includes providing the name of the target and at least one category. Providing may be performed by transmitting the name of the target and the category into which the target falls to a software application for further processing. Providing may also be performed by displaying the name of the target and the category to a programmer or technician for review. Providing may also be performed by integrating the name of the target and the category into a dashboard or other GUI, that also displays other targets and categories, as shown in FIG. 4C through FIG. 4F.”) based on the sentiment classification (RAVINDRAN Par 46 – “The first probability (106) is compared to the threshold value (116). If the threshold value (116) is not satisfied, then the natural language text (102) of FIG. 1A is classified as having a positive sentiment (output A (116B)). The natural language text (102) is then discarded or ignored during further processing. If the threshold value (116) is satisfied, then the natural language text (102) is classified as having a negative sentiment (output B (118B)).”), the issue classification, and the location of each customer comment (RAVINDRAN Par 78 – “For example, the negative review (and possibly other information, such as the category) may include an identified indication that the target (which is financial management software) is not communicating with a particular bank. The technical issue may be that the application programming interface of the financial management software is not properly configured to communicate with the bank's communication protocols.”) to identify an issue in the the specific provider of the wireless communication network (Note ML already teaches identifying an issue in a specific geographic region. RAVINDRAN teaches identifying an issues with a specific provider; RAVINDRAN Fig. 4D – “Provider … Issue Category”; Par 25 – “Examples of the ontological groupings may be names of software programs, names of software providers, identifiers of individual features within software programs, categories of technical difficulties (e.g., communication faults, latency, incorrect classification of financial transactions by a financial management software application, and the like), as well as many other possible ontological groupings.”); and
transmitting, using the sentiment analysis system, at least one report to a department of the CSP (RAVINDRAN Par 77 – “Step 208 includes providing the name of the target and at least one category. Providing may be performed by transmitting the name of the target and the category into which the target falls to a software application for further processing. Providing may also be performed by displaying the name of the target and the category to a programmer or technician for review. Providing may also be performed by integrating the name of the target and the category into a dashboard or other GUI, that also displays other targets and categories, as shown in FIG. 4C through FIG. 4F.”) based on one or more of the sentiment classification, the issue classification (RAVINDRAN Par 78 – “For example, the negative review (and possibly other information, such as the category) may include an identified indication that the target (which is financial management software) is not communicating with a particular bank. The technical issue may be that the application programming interface of the financial management software is not properly configured to communicate with the bank's communication protocols.”), and the provider (RAVINDRAN Par 56 – “Continuing the above example, the negative review A (122B) may be categorized under “PROVIDER NAME”, because the highest averaged probability for the negative review A (122B) is associated with the category “PROVIDER NAME.””; Note ML already teaches generating reports for a specific geographic region. RAVINDRAN teaches generating an issue report for a specific provider).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method/system of SERNA in view of ML to include analyzing textual data with neural networks, as taught by RAVINDRAN.
One of ordinary skill would have been motivated to include analyzing textual data with neural networks, in order to enable more accurate analyses.
REGARDING CLAIM 2, SERNA in view of ML and RAVINDRAN discloses the method according to claim 1, wherein the profile generated for each customer comment includes the associated data for the customer comment (SERNA Par 42 – “This data may then be parsed and transformed into structured data which is then stored in a database. For the purposes of this disclosure, at least the following data points may be tracked: date, time, location username and message.”; Par 62 –“ The system may also include a processor. The processor may be configured to harvest, for each customer support request, a plurality of artifacts from social media account history and/or other third party data source information. The artifacts may be associated with a user. The user may be associated with the device identification number. Each of the plurality of artifacts may include sentiment information relevant to the customer support request.”; Par 64 – “The processor may be further configured to build a current profile for the communication device. The current profile may be based on the plurality of artifacts and the historical information.”; Par 177 – “FIG. 20 shows using microprocessor 2008 to convert historical sentiment value 2002, current sentiment value 2004 and message information 2006 into a current profile 2010.”).
REGARDING CLAIM 3, SERNA in view of ML and RAVINDRAN discloses the method according to claim 1, wherein the one or more online platforms is one or more of an online marketplace, a web site, or a social media platform (SERNA Par 40 – “Support requests, and historical communications-related thereto, in the form of email, Instant Messaging Service (IMS), phone calls, video chats, Twitter communications such as Tweets™, and other elements (e.g., response time, escalations, etc.) may be analyzed to define the sentiment of the interactions of an individual, group and/or entity towards one or more individuals, groups and/or entities and to provide a current snapshot thereof.”; Par 91 – “FIG. 3 shows a more specific rendering of an illustrative flow diagram for a method associated with a customer support request routing system. In the diagram in FIG. 3, an API, such as Twitter™, receives a support request. This is shown at step 302.”; Par 144 – “API feed 1230 preferably acts as a conduit to receive support requests in the form of social media communications such as Tweets.”).
REGARDING CLAIM 5, SERNA in view of ML and RAVINDRAN discloses the method according to claim 1, wherein the sentiment classification is one of positive, negative, or neutral (SERNA Par 122 – “It should be appreciated that a polarity-based scale may include two opposite emotions, whether positive and negative, happy and sad or any other suitable opposite emotions. Therefore, each support request scored on a polarity-based score may only be given a sentiment score based on the polarity of the support request.”).
REGARDING CLAIM 6, SERNA in view of ML and RAVINDRAN discloses the method according to claim 1.
RAVINDRAN further discloses the method/system wherein the issue classification includes one or more categories of issues related to performance of the communication network of the CSP (RAVINDRAN Par 78 – “Step 210 includes determining, based on the negative review, a technical issue with the target. For example, the target may be a software application. In this case, a technical issue with the software application may be determined. The determination may be performed by a computer technician but may also be performed automatically. For example, the negative review (and possibly other information, such as the category) may include an identified indication that the target (which is financial management software) is not communicating with a particular bank. The technical issue may be that the application programming interface of the financial management software is not properly configured to communicate with the bank's communication protocols. This technical problem may then be returned as the determined technical issue.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method/system of SERNA to include comments regarding communication issues, as taught by RAVINDRAN.
One of ordinary skill would have been motivated to include comments regarding communication issues, in order to enable provide a variety of enterprise solutions with more accurate analyses.
REGARDING CLAIM 7, SERNA in view of ML and RAVINDRAN discloses a system for sentiment analysis regarding a wireless communication network of a communication service provider (CSP), the system comprising:
an input (SERNA Fig. 4 –“Support Request”) to perform the collecting step of claim 1;
a pre-processing module coupled to the input and configured to perform the generating a profile step of claim 1 (SERNA Par 64 – “The processor may be further configured to build a current profile for the communication device. The current profile may be based on the plurality of artifacts and the historical information.”);
a natural language processing (NLP) neural network coupled to the pre-processing module (SERNA Par 43 – Natural Language Toolkit Sentiment Library; RAVINDRAN Par 83 – “a bi-directional long short term memory neural network.”) and configured to perform generating at least sentiment classification step of claim 1; and
a post-processing module coupled to the NLP neural network (SERNA Par 143 – a parsing engine) and configured to perform the generating one or more reports steps of claim 1; thus, the claim is rejected under same rationale explained in the rejection of claim 1.
REGARDING CLAIM 8, SERNA in view of ML and RAVINDRAN discloses the system according to claim 7, wherein the system for sentiment analysis system is further configured to transmit at least one report to a department of the CSP based on one or more of the sentiment classification, the issue classification and the location (SERNA Par 45 –“For example, if the sentiment associated with a user has been determined to be happy (sentiment analysis) and the user is asking questions regarding financial instruments (topic analysis), it could be beneficial to route that customer to a new financial advisor so the new financial advisor could build up their client book with a happy user.”; Par 90 – “Finally, at step 206, the diagram shows routing the customer support request based on 1) a localized context and various request parameters associated with the request in combination with 2) the customer sentiment derived from social media artifacts.”; Par 144 – “Once the support requests have been received, the support requests may be parsed by parsing engine 1232 for date, time, location, name of requester and message content. Thereafter, response system 1234 may redirect the support request to either an employee in the support center 1210, auto-response system in the support center 1206 or a manager 1214.”; ML also teaches transmitting the report: ML Par 61 – “For example, the notification may be transmitted for display on a graphical user interface of the user device. In aspects when a second electronic documentation is generated for a second recurring issue that satisfied the threshold 324, the notification may indicated that both the electronic documentation and the second electronic documentation associated with a second recurring issue have been created. In some aspects, as discussed in more detail above, the threshold 324 (i.e., the condition for root cause investigation for the recurring issue) for the recurring issue is different than the threshold 324 for the second recurring issue. Furthermore, the notification may comprise an image or an alert. As such, the method 300 ends at 330.”; RAVINDRAN also teaches transmitting the report: Par 77 – “Step 208 includes providing the name of the target and at least one category. Providing may be performed by transmitting the name of the target and the category into which the target falls to a software application for further processing. Providing may also be performed by displaying the name of the target and the category to a programmer or technician for review. Providing may also be performed by integrating the name of the target and the category into a dashboard or other GUI, that also displays other targets and categories, as shown in FIG. 4C through FIG. 4F.”).
REGARDING CLAIM 9, SERNA in view of ML and RAVINDRAN discloses the system according to claim 8, wherein the department of the CSP is one or more of network support, customer support, product development, marketing, or billing (SERNA Par 144 – “Thereafter, response system 1234 may redirect the support request to either an employee in the support center 1210, auto-response system in the support center 1206 or a manager 1214.”).
REGARDING CLAIM 10, SERNA in view of ML and RAVINDRAN discloses the system according to claim 7, and wherein the profile generated for each customer comment includes the associated data for the customer comment (SERNA Par 42 – “This data may then be parsed and transformed into structured data which is then stored in a database. For the purposes of this disclosure, at least the following data points may be tracked: date, time, location username and message.”; Par 62 –“ The system may also include a processor. The processor may be configured to harvest, for each customer support request, a plurality of artifacts from social media account history and/or other third party data source information. The artifacts may be associated with a user. The user may be associated with the device identification number. Each of the plurality of artifacts may include sentiment information relevant to the customer support request.”; Par 64 – “The processor may be further configured to build a current profile for the communication device. The current profile may be based on the plurality of artifacts and the historical information.”; Par 177 – “FIG. 20 shows using microprocessor 2008 to convert historical sentiment value 2002, current sentiment value 2004 and message information 2006 into a current profile 2010.”).
Claim 11 is similar to claim 3; thus, it is rejected under the same rationale.
REGARDING CLAIM 13, SERNA in view of ML and RAVINDRAN discloses the system according to claim 7.
RAVINDRAN discloses a method/system to identify issues from user comments, wherein the NLP neural network is an artificial neural network (RAVINDRAN Par 48 – “Other types of models may be used for the second machine learning model (120B). For example, a Multi-Layer Perceptron Model (MLP) may be used to categorize the negative reviews. A MLP is a fully connected class of feed forward artificial neural networks. However, other models may be used, like XGBoost, which is a decision-tree-based ensemble machine learning algorithm that uses a gradient boosting framework. Recurrent neural networks can also be used to categorize the reviews.”; Par 83 – “As part of pre-processing, the method may also include vectorizing the natural language text to generate the first input to the MLM at step 202. Vectorizing may include inputting the natural language text to a third MLM, such as a bi-directional long short term memory neural network. Vectorizing also may include receiving, as output from the third MLM, a matrix of numbers representing both the natural language text and contexts of sentences in the natural language text.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method/system of SERNA to include neural networks, as taught by RAVINDRAN.
One of ordinary skill would have been motivated to include comments regarding neural networks, in order to enable provide a variety of enterprise solutions with more accurate analyses.
REGARDING CLAIM 14, SERNA in view of ML and RAVINDRAN discloses a non-transitory, computer readable medium storing instructions that, when executed by one or more electronic processors, perform a set of functions, the set of functions comprising: performing the steps of claim 1; thus, it is rejected under the same rationale.
Claim 15 is similar to claim 2; thus, it is rejected under the same rationale.
REGARDING CLAIM 16, SERNA in view of ML and RAVINDRAN discloses the non-transitory computer-readable medium according to claim 15, wherein the associated data further comprises one or more of an IP address, a device used to post the customer comment, a user ID, a date of posting the customer comment, or a time of posting the customer comment (SERNA Par 42 – “This data may then be parsed and transformed into structured data which is then stored in a database. For the purposes of this disclosure, at least the following data points may be tracked: date, time, location username and message.”; Par 62 –“ The system may also include a processor. The processor may be configured to harvest, for each customer support request, a plurality of artifacts from social media account history and/or other third party data source information. The artifacts may be associated with a user. The user may be associated with the device identification number. Each of the plurality of artifacts may include sentiment information relevant to the customer support request.”; Par 64 – “The processor may be further configured to build a current profile for the communication device. The current profile may be based on the plurality of artifacts and the historical information.”).
Claim 17 is similar to claim 3; thus, it is rejected under the same rationale.
Claim 19 is similar to claim 5; thus, it is rejected under the same rationale.
Claim 20 is similar to claim 6; thus, it is rejected under the same rationale.
Claims 4, 12, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over SERNA in view of ML and RAVINDRAN, and in further view of MOUNIER (US 2021/0390563 A1).
REGARDING CLAIM 4, SERNA in view of RAVINDRAN discloses the method according to claim 1, further comprising generating, using the NLP neural network, a predicted location for at least one customer comment of the set of customer comments (SERNA Par 144 – “API feed 1230 preferably acts as a conduit to receive support requests in the form of social media communications such as Tweets. Once the support requests have been received, the support requests may be parsed by parsing engine 1232 for date, time, location, name of requester and message content.”) [based on the text of the at least one customer comment].
SERNA in view of ML and RAVINDRAN does not explicitly teach the [square-bracketed] limitations.
MOUNIER disclose a method/system for analyzing customer comments comprising: generating, using the NLP neural network, a predicted location for at least one customer comment of the set of customer comments [based on the text of the at least one customer comment] (MOUNIER Claim 2 – “using natural language processing to extract organization names, people names and locations from the text, and categorizing opinions in the text, and determining if the text is positive, negative or neutral toward a topic.”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the method/system of SERNA in view of LM and RAVINDRAN to include extracting location information from text, as taught by MOUNIER.
One of ordinary skill would have been motivated to include extracting location information from text in order to efficiently extract relevant information associated with a user with the given data.
Claim 12 is similar to claim 4; thus, it is rejected under the same rationale.
Claim 18 is similar to claim 4; thus, it is rejected under the same rationale.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHAN C KIM whose telephone number is (571)272-3327. The examiner can normally be reached Monday to Friday 8:00 AM thru 4:00 PM EST.
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, Andrew C Flanders can be reached at 571-272-7516. 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.
/JONATHAN C KIM/Primary Examiner, Art Unit 2655
Prosecution Insights