DETAILED ACTION
Status of Claims
The Request for Continued Examination filed 11/17/2025 has been acknowledged. Claims 1, 10, 19 are amended. Claims 5, 7, 9, 14, 16, 18 are cancelled.
Claims 1-4, 6, 8, 10-13, 15, 17, 19 are currently pending and have been examined.
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 .
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 1-4, 6, 8, 10-13, 15, 17, 19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites the steps of collecting three sets of data, performing analysis on the sets of data to determine languages and accents of users and generating profiles of the users, segmenting the users based on the language analysis, and triggering the targeting of content to the user based on the segments including modulating the audio of the advertisement.
The limitations of collecting three sets of data, performing analysis on the sets of data to determine languages and accents of users, creating profiles for users, segmenting the users based on the language analysis and profile, and triggering the targeting of content to the user based on the segments, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. That is, other than reciting “system with a/the processor” nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the “system with a/the processor” language, “collecting” in the context of this claim encompasses a person receiving/reviewing available information. The limitation of performing analysis to determine languages and segmenting users, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. For example, but for the “system with a/the processor”, analyzing, profiling, and segmenting in the context of this claim encompasses the user thinking and reviewing the collected information and checking against previously learned knowledge, determining and writing a profile for each individual user such as thinking about the language, accent, and industry of the user, and grouping users based on users using similar types of language and vocabulary. The limitation of triggering a campaign, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components. But for the “system with a/the processor”, triggering a campaign in the context of this claim encompasses the user thinking of which campaign matches a segment based on language characteristics. The step of “modulating” but for the “processor”, can be interpreted as a person altering their speech to be more recognizable to a listener such as using different pronunciation or vocabulary. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
Still furthermore, the claimed invention is directed towards a certain method of organizing human activity, specifically, commercial interactions including advertising, marketing or sales activity or behavior. As currently claimed, the invention is directed towards the targeting and customization content to users based on profiling users. This is similar to In re Maucorp, Affinity Labs of Tex. v. Amazon.com, 838 F.3d 1266, 1270, 120 USPQ2d 1210, 1213 (Fed. Cir. 2016); Affinity Labs of Tex. v. DirecTV, LLC, 838 F.3d 1253, 1262, 120 USPQ2d 1201, 1207 (Fed. Cir. 2016), and Credit Acceptance wherein particular algorithms is used to analyze and profile user information to determine optimal business practice and targeting particular information to specific devices including altering how a consumer is communicated with and engaged with. As such, the claimed invention is further directed towards a certain method of organizing human activity.
This judicial exception is not integrated into a practical application. In particular, the claim recite the additional elements of the processor and using machine learning. The processor in both steps is recited at a high-level of generality (i.e., as a generic processor performing a generic computer function of receiving data, performing analysis/comparison, organizing data, and providing/modifying data based on stored rules/criteria) such that it amounts no more than mere instructions to apply the exception using a generic computer component. Furthermore, while the claims recite utilizing machine learning, machine learning is a computing technique, and is thus still merely instructions applied to a generic computer similar to Example 47 claim 2 of the 2024 AI SME Update. Still furthermore, although the claims has been amended to further determine language proficiency based on keyboard switching, this is still abstract as this is merely describing what the particular information being analyzed is. Accordingly, this additional element does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using a processor to perform the steps and using performing machine learning analysis amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claim is not patent eligible.
The dependent claims are further directed towards the judicial exception without significantly more. The dependent claims provide limitations on the type of information received (such as claims 2-4), the particular rules for segmenting/organizing users (such as claims 6), and property of content provided (such as claim 8). These are still directed towards the judicial exception as these further define the abstract elements such as further defining the information, relationship between the information, and the rules applied to the information. They are not significantly more as they do not further integrate the judicial exception into a practical application and the additional element amounts to no more than mere instructions to apply the exception using a generic computer component. The dependent claims is not patent eligible.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1, 8, 10, 17, 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Banga et al. (US 20080262901 A1) (hereafter Banga), in view of Pasternack et al. (US 20200401657 A1) (hereafter Pasternack), in view of Marttila (US 20130189652 A1) (hereafter Marttila), in view of Sarikaya (US 20180061421 A1) (hereafter Sarikaya), in view of Bojja et al. (WO 2018067440 A1) (hereafter Bojja), in view of Isaacson et al. (US 20170236196 A1) (hereafter Isaacson).
As per claim 1:
A computer-implemented method for adopting user learnings across vernacular contexts, the computer-implemented method comprising:
receiving, at a multi-lingual campaigning system with a processor, a first set of data associated with a plurality of users;
collecting, at the multi-lingual campaigning system with the processor, a second set of data associated with the plurality of users;
fetching, at the multi-lingual campaigning system with the processor, a third set of data associated with one or more communication devices of the plurality of users;
(See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses retrieving multiple data sets for a plurality of users for language based targeting of advertisements.)
Although Banga discloses the above-enclosed invention including the concept of collecting and performing analysis to determine information about users (See Banga ¶0101), Bang fails to explicitly disclose utilizing machine learning to categorize languages of users.
However Pasternack as shown, which talks about language profiling, teaches the concept of utilizing machine learning for categorizing languages.
analyzing, at the multi-lingual campaigning system with the processor, the first set of data, the second set of data, and the third set of data using one or more machine learning algorithms, (See Pasternack ¶0052, “In some example embodiments, the language profiling service accesses demographic prior information 310 about the user that received the text 302. The demographic prior information 310 includes information about the user, such as the information kept in the user's profile, and includes one or more of the name of the client using the language profiling service 130, user identifier (ID), and a conversation ID. As used herein, client refers to the service within the social network that utilizes the language profiling service 1304 predicting the language spoken. For example, the client may be the user feed, the search engine, an advertisements engine, etc. The conversation ID is the identifier for a conversation that includes the user.” Pasternack teaches the concept of analyzing a plurality of data sets.)
wherein the analysis is performed based on training of a machine learning model, (See Pasternack ¶0149, “In one example, calculating the language distribution prediction further comprises utilizing a machine-learning model to calculate the probability for each language that the text is in the language, the machine-learning model include features that comprise the counters, values of the initial prediction, and information about the user, the machine-learning model being trained based on past interactions on the online service by users of the online service.” Pasternack teaches the concept of utilizing machine learning for language analysis.)
wherein the analysis is performed for identifying a plurality of languages across the vernacular contexts of the plurality of users, (See Pasternack ¶0049, “FIG. 3 illustrates the prediction of the language used in a text message, according to some example embodiments. As discussed above, the text message “y?” may mean “Why?” in English or “And?” in Spanish. If the online service knows that the message “y?” came from a user who has spoken only English in the past, has an English default locale, works in a British company, etc., then there is a very high probability that “y?” is intended as English.” Pasternack teaches the concept of identifying languages including accounting for vernacular context.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Pasternack with the invention of Banga. As shown, Banga discloses the concept of collecting and utilizing information for targeting content to users including accounting for language settings. Pasternack further discusses the short comings of utilizing preset language preferences for multi-lingual users and addressing the need for accurately determining user language including for targeting of content (See Pasternack ¶0002-¶0005). Pasternack teaches performing analysis using machine learning to identify possible user languages. Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Pasternack to further improve the identification of languages of users, thereby enabling further targeting and analytics of content.
Although the combination of Banga and Pasternack discloses the above-enclosed invention, the combination fails to explicitly disclose identifying language attributes.
However Marttila as shown, which talks about linguistic profiling, teaches the concept of identifying language attributes.
wherein the analysis is performed for identifying a plurality of language attributes of the plurality of languages across the vernacular contexts of the plurality of users, (See Marttila claim 1, “A method where, in order to measure or define the language proficiency of a person under investigation, particularly the degree of flawlessness in his/her pronunciation and/or in order to investigate the person's own language background and identity, the speech of the person under investigation is compared with a speech sample of a selected reference language, characterized in that from an electronic speech sample of a reference language, there are identified and registered, by using autocorrelation and/or pattern recognition and/or signal processing or some other corresponding method, such sound elements and linguistic features that are repeatedly represented in the reference language speech sample and are typical of said language, and on the basis of the obtained linguistic profile of the reference language, corresponding sound elements and/or linguistic features are searched from an electronically recorded speech sample of the person under investigation, and/or there is defined which of the sound elements or linguistic features of the linguistic profile of the reference language the person under investigation substitutes with such sound elements or linguistic features that deviate from the reference language, and/or there is defined what these substitute sound elements and linguistic features are.” See also Marttila ¶0029, “Unless otherwise stated, the concept `language` refers to a language corresponding to dictionary meanings, i.e. a national language or an official language, as well as to language variations, spoken languages, and languages of different social groups, such as the language spoken at home, youth language, different dialects and slangs.“ Marttila teaches the concept of identifying skilling level and vernacular attributes.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings if Marttila with the combination of Banga and Pasternack. As shown, the combination discloses the concept of targeting content based on language including determining language information of users. Mantilla further teaches the concept of identifying particular language attributes including language skill level. As shown, Marttila teaches the concept to further identify user linguistic attributes for a plurality of purposes including further enhancing consumer interaction (See Marttila ¶0004). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Marttila to further enhance the profiling and comprehension of users by further identifying additional linguistic data points, thereby allowing for additional targeting and adaption for users.
Although the combination of Banga, Pasternack, and Marttila discloses the above-enclosed invention, the combination fails to explicitly disclose detecting accents associated with users.
However Sarikaya as shown, which talks about personalization of digital assistants, teaches the concept of detecting accents associated with users.
wherein the analysis is performed on the second set of data using the one or more machine learning algorithms for detecting an accent associated with each of the plurality of users, (See Sarikaya ¶0023, “According to additional examples, a plurality of user background characteristic and trait models may be used to identify user background characteristics and traits for a specific user. For example, a prebuilt gender detection model may determine whether a specific user is male or female. An age detection model may determine the age or age group for a specific user. An accent detection model may determine an accent for a specific user (e.g., southern, immigrant, Indian, Chinese, German, French, etc.). Other user background characteristic models may also be used to identify additional background traits and characteristics of a user as more fully described below. This information may be compiled into a voice-based profile for each specific user of a group of users.” See Sarikaya ¶0028, “Further acoustic processing and speech and language pattern analysis may be performed on voice, text and gesture input and a determination of whether user input corresponds to a number of categories may be made. For example, acoustic processing and speech pattern and language analysis may be performed such that certain background characteristics and traits of a user may be identified such as age of the user, gender of the user, accent assignment of the user, physical characteristics of the user, social characteristics of the user and emotional state of the user, among others. Machine learning may be used to create voice, speech and language pattern models that may be used to identify a user and assist with categorization of received input. Machine learning may also be used to categorize user input based on natural language processing and identification of one or more personalized topical categories for a user.” Sarikaya teaches the concept of performing accent analysis using machine learning.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Sarikaya with the combination of Banga, Pasternack, and Marttila. As shown, the combination discloses the concept of targeting content based on language including determining language information of users. Sarikaya further teach the concept of performing linguistic analysis including determining properties such as accents. Sarikaya teaches this concept to further accurately profile the user of a digital assistant thereby enabling better responses (See Sarikaya ¶0035). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Sarikaya to further account for accent information to further optimize the understanding of users and provide relevant results.
wherein the analysis is performed in real time; and(See Pasternack ¶0024, “One general aspect includes a method that includes an operation for utilizing, by one or more processors, counters to track use of a plurality of languages by a user of an online service. The counters are updated based on interactions of the user in the online service. Further, the method includes operations for detecting, by the one or more processors, a text entered by the user in the online service, and for obtaining, by a language classifier using the one or more processors, an initial prediction having probabilities for the plurality of languages that the text is in the language. The one or more processors calculate a language distribution prediction based on the initial prediction and the counters for the user. The language distribution prediction comprises a probability, for each language, that the text is in the language. Further, the method includes operations for selecting, by the one or more processors, a language used in the text based on the language distribution prediction, and for causing, by the one or more processors, presentation on a display of a message in the selected language.” Pasternack teaches the concept of actively and continuously tracking and analyzing information to determine language information.)
Although the combination of Banga, Pasternack, Marttila, and Sarikaya discloses the above-enclosed invention, the combination fails to explicitly disclose determining language information of users based on switching keyboard languages.
However Bojja as shown, which talks about language detection, teaches the concept of corelating keyboard changes to user languages.
wherein the multi-lingual campaigning system determines the proficiency in the plurality of languages by analyzing the switching of the language by each of the plurality of users using a keyboard; (See Bojja ¶0069, “FIG. 12 is a flowchart of an example method 1200 for detecting a language in a message. The method uses the detection module 16, the classifier module 18, and the manager module 20 to identify a most likely or best language 1202 for a given input message 1204. The input message 1204 can be accompanied by information about the user or the system(s) used to generate the message. For example, the input message 1204 can be accompanied by a user identification number (or other user identifier), information about the keyboard (e.g., a keyboard language) used to generate the message, and/or information about the operating system (e.g., an operating system language) used to generate the message.” Bojja teaches the concept of tracking keyboard language. See also Bojja ¶0005, “Embodiments of the systems and methods described herein are used to detect the language in a text message based on, for example, content of the message, information about the keyboard used to generate the message, and/or information about the language preferences of the user who generated the message. Compared to previous language detection techniques, the systems and methods described herein are generally faster and more accurate, particularly for short text messages (e.g., of four words or less).” Bojja teaches the concept of associating keyboard language setting with language preference.)
creating, at the multi-lingual campaigning system with the processor, a vernacular profile of each of the plurality of users based on the analysis of the first set of data, the second set of data, and the third set of data using the one or more machine learning algorithms; (See Pasternack ¶0128, “The language profiling service enable a more accurate language detection on short text as well as arrive at a language “profile” of a user by keeping track of language probabilities returned by language detection software over time and combining that information with a demographic prior over each user and context (feed, search, etc.). The language profiling service generates more accurate prediction of the languages users tends to use in a given context, e.g., a user may tend to share in feed in English but message with connections in Spanish.” Pasternack teaches the concept of generating individual user language profiles for each of a plurality of users. See also Pasternack ¶0139, “When the machine-learning program 916 is used to perform an assessment, new data 918 is provided as an input to the trained machine-learning program 916, and the machine-learning program 916 generates the assessment 920 as output. For example, the machine-learning program may be used to provide the language probability distributions for a given text and user.” Pasternack teaches the concept of making predictions using collected information and machine learning. See also Marttila ¶0029, “Unless otherwise stated, the concept `language` refers to a language corresponding to dictionary meanings, i.e. a national language or an official language, as well as to language variations, spoken languages, and languages of different social groups, such as the language spoken at home, youth language, different dialects and slangs.” Marttila further teaches the concept of language profiling to include vernacular definitions.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Bojja with the combination of Banga, Pasternack, Marttila, and Sarikaya. As shown, the combination discloses the concept of analyzing information to determine language properties of users. Bojja further teaches the concept of collecting and analyzing additional information including keyboard settings to determine language information. Bojja teaches this concept to further improve the speed and accuracy of language detection, and further avoid issues relating to misspelling by users (See Bojja ¶0004). Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Bojja to further improve the speed and accuracy of language detection/determination for users.
enabling, at the multi-lingual campaigning system with the processor, segmentation of the plurality of users in one or more segments based on the vernacular profile and one or more patterns of the plurality of languages and the plurality of language attributes, wherein the plurality of users is segmented in the one or more segments in real-time; (See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses grouping users with similar characteristics and profiles.)
triggering, at the multi-lingual campaigning system with the processor, initialization of one or more personalized marketing campaigns for the one or more segments based on the plurality of languages and the plurality of language attributes across the vernacular contexts of the plurality of users, wherein the one or more personalized marketing campaigns are initiated based on the one or more patterns of the one or more segments, wherein the one or more personalized marketing campaigns are initiated in real-time; and
(See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses the concept of targeting content to groups of users based on the characteristics of the group, wherein the characteristics includes linguistic information.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, and Bojja discloses the above-enclosed invention including the concept of customizing content to the user (See Banga ¶0147), the combination fails to explicitly disclose the customization to include specific elements.
However Isaacson as shown, which talks about online purchase interactions, teaches the concept of customizing content for particular users to include a plurality of elements.
Dynamically modulating, at the multi-lingual campaigning system with the processor, the audio of the one or more advertisements associated with the one or more personalized marketing campaigns based on the accent of each of the plurality of users. (See Isaacson ¶0238, “An animated character could also be generated to engage with the buyer and receive questions and provide answers. The character can be chosen based at least in part on characteristics such as friends, family, favorite actors, and so forth. The social networking data obtained about the buyer can be used to select voices, gender, political leanings, race, and so forth of the animated entity that will engage the user in a dialog about the product. Pre-synthesized speech units can be gathered about the product and friends that have purchased the product. Personal information can be incorporated into the dialog as well. For example, the entity can say “Have a great birthday tomorrow Jane, how can I help you with the purchase of this chair, do you want it in black?” Thus, as a user clicks on a purchase process initiation object that transitions them to a dialog, the dialog management system can obtain text and data from various locations such as the merchant for data about the product, product review data, friends/family data associated with the product, social media data about the user, and so forth to generate a domain specific experience in the dialog around that particulate product. The aspects presented can therefore make the user feel more comfortable and in a friendly environment. Accents, personalities, jokes, visual characteristics, dialog responses, timings, and so forth can be tailored for the particular user such that even if they only want to choose red as the color of the chair, they can have a more socially pleasing experience when communicating with that merchant.” Isaacson teaches the concept of customizing content provided to the user to include customizing elements such as audio accent, color, character design/outfits, dialog, brand ambassadors, and theme.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Isaacson with the combination of Banga, Pasternack, Marttila, Sarikaya, and Bojja. As shown, the combination discloses the concept of targeting and customizing content based on known user information including language information. Isaacson further teaches the concept of customizing a plurality of elements based on known user information. Isaacson teaches customizing these elements to further present a comfortable and friendly environment to the user, thereby improving customer interactions (See Isaacson ¶0238). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Isaacson to further provide better customer interactions by tailoring elements for the specific user.
As per claim 8:
The computer-implemented method as recited in claim 1, further comprising dynamically displaying, at the multi-lingual campaigning system with the processor, one or more advertisements associated with the one or more personalized marketing campaigns for the one or more segments in real-time,
wherein the one or more advertisements are displayed to each of the plurality of users on the one or more communication devices based on the one or more patterns, and the vernacular profile,
wherein each of the one or more advertisements adapts a plurality of characteristics according to the vernacular profile, the plurality of languages, and the plurality of language attributes,
(See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses customizing and targeting specific content to users based on language information.)
wherein the plurality of characteristics comprises the accent of audio of the one or more advertisements, colors used in the one or more advertisements, costumes utilized in the one or more advertisements, phrases utilized in the one or more advertisements, brand ambassador of the one or more advertisements, and theme of the one or more advertisements. (See Isaacson ¶0238, “An animated character could also be generated to engage with the buyer and receive questions and provide answers. The character can be chosen based at least in part on characteristics such as friends, family, favorite actors, and so forth. The social networking data obtained about the buyer can be used to select voices, gender, political leanings, race, and so forth of the animated entity that will engage the user in a dialog about the product. Pre-synthesized speech units can be gathered about the product and friends that have purchased the product. Personal information can be incorporated into the dialog as well. For example, the entity can say “Have a great birthday tomorrow Jane, how can I help you with the purchase of this chair, do you want it in black?” Thus, as a user clicks on a purchase process initiation object that transitions them to a dialog, the dialog management system can obtain text and data from various locations such as the merchant for data about the product, product review data, friends/family data associated with the product, social media data about the user, and so forth to generate a domain specific experience in the dialog around that particulate product. The aspects presented can therefore make the user feel more comfortable and in a friendly environment. Accents, personalities, jokes, visual characteristics, dialog responses, timings, and so forth can be tailored for the particular user such that even if they only want to choose red as the color of the chair, they can have a more socially pleasing experience when communicating with that merchant.” Isaacson teaches the concept of customizing content provided to the user to include customizing elements such as audio accent, color, character design/outfits, dialog, brand ambassadors, and theme.)
As per claim 10:
A computer system comprising:
one or more processors; and
a memory coupled to the one or more processors, the memory for storing instructions which, when executed by the one or more processors, cause the one or more processors to perform a method for adopting user learnings across vernacular contexts, the method comprising:
(See Banga ¶0150, “In some embodiments, the AP server may be comprised of: (1) a processor; (2) a configuration component/module; and (3) processing software; and (4) appropriate memory, storage, networking capabilities and associated peripherals. All of these elements can be unitary or distributed.” Banga discloses a processor and memory.)
receiving, at a multi-lingual campaigning system, a first set of data associated with a plurality of users;
collecting, at the multi-lingual campaigning system, a second set of data associated with the plurality of users;
fetching, at the multi-lingual campaigning system, a third set of data associated with one or more communication devices of the plurality of users;
(See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses retrieving multiple data sets for a plurality of users for language based targeting of advertisements.)
Although Banga discloses the above-enclosed invention including the concept of collecting and performing analysis to determine information about users (See Banga ¶0101), Bang fails to explicitly disclose utilizing machine learning to categorize languages of users.
However Pasternack as shown, which talks about language profiling, teaches the concept of utilizing machine learning for categorizing languages.
analyzing, at the multi-lingual campaigning system, the first set of data, the second set of data, and the third set of data using one or more machine learning algorithms, (See Pasternack ¶0052, “In some example embodiments, the language profiling service accesses demographic prior information 310 about the user that received the text 302. The demographic prior information 310 includes information about the user, such as the information kept in the user's profile, and includes one or more of the name of the client using the language profiling service 130, user identifier (ID), and a conversation ID. As used herein, client refers to the service within the social network that utilizes the language profiling service 1304 predicting the language spoken. For example, the client may be the user feed, the search engine, an advertisements engine, etc. The conversation ID is the identifier for a conversation that includes the user.” Pasternack teaches the concept of analyzing a plurality of data sets.)
wherein the analysis is performed based on training of a machine learning model, (See Pasternack ¶0149, “In one example, calculating the language distribution prediction further comprises utilizing a machine-learning model to calculate the probability for each language that the text is in the language, the machine-learning model include features that comprise the counters, values of the initial prediction, and information about the user, the machine-learning model being trained based on past interactions on the online service by users of the online service.” Pasternack teaches the concept of utilizing machine learning for language analysis.)
wherein the analysis is performed for identifying a plurality of languages across the vernacular contexts of the plurality of users, (See Pasternack ¶0049, “FIG. 3 illustrates the prediction of the language used in a text message, according to some example embodiments. As discussed above, the text message “y?” may mean “Why?” in English or “And?” in Spanish. If the online service knows that the message “y?” came from a user who has spoken only English in the past, has an English default locale, works in a British company, etc., then there is a very high probability that “y?” is intended as English.” Pasternack teaches the concept of identifying languages including accounting for vernacular context.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Pasternack with the invention of Banga. As shown, Banga discloses the concept of collecting and utilizing information for targeting content to users including accounting for language settings. Pasternack further discusses the short comings of utilizing preset language preferences for multi-lingual users and addressing the need for accurately determining user language including for targeting of content (See Pasternack ¶0002-¶0005). Pasternack teaches performing analysis using machine learning to identify possible user languages. Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Pasternack to further improve the identification of languages of users, thereby enabling further targeting and analytics of content.
Although the combination of Banga and Pasternack discloses the above-enclosed invention, the combination fails to explicitly disclose identifying language attributes.
However Marttila as shown, which talks about linguistic profiling, teaches the concept of identifying language attributes.
wherein the analysis is performed for identifying a plurality of language attributes of the plurality of languages across the vernacular contexts of the plurality of users, (See Marttila claim 1, “A method where, in order to measure or define the language proficiency of a person under investigation, particularly the degree of flawlessness in his/her pronunciation and/or in order to investigate the person's own language background and identity, the speech of the person under investigation is compared with a speech sample of a selected reference language, characterized in that from an electronic speech sample of a reference language, there are identified and registered, by using autocorrelation and/or pattern recognition and/or signal processing or some other corresponding method, such sound elements and linguistic features that are repeatedly represented in the reference language speech sample and are typical of said language, and on the basis of the obtained linguistic profile of the reference language, corresponding sound elements and/or linguistic features are searched from an electronically recorded speech sample of the person under investigation, and/or there is defined which of the sound elements or linguistic features of the linguistic profile of the reference language the person under investigation substitutes with such sound elements or linguistic features that deviate from the reference language, and/or there is defined what these substitute sound elements and linguistic features are.” See also Marttila ¶0029, “Unless otherwise stated, the concept `language` refers to a language corresponding to dictionary meanings, i.e. a national language or an official language, as well as to language variations, spoken languages, and languages of different social groups, such as the language spoken at home, youth language, different dialects and slangs.“ Marttila teaches the concept of identifying skilling level and vernacular attributes.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings if Marttila with the combination of Banga and Pasternack. As shown, the combination discloses the concept of targeting content based on language including determining language information of users. Mantilla further teaches the concept of identifying particular language attributes including language skill level. As shown, Marttila teaches the concept to further identify user linguistic attributes for a plurality of purposes including further enhancing consumer interaction (See Marttila ¶0004). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Marttila to further enhance the profiling and comprehension of users by further identifying additional linguistic data points, thereby allowing for additional targeting and adaption for users.
wherein the analysis is performed in real time; (See Pasternack ¶0024, “One general aspect includes a method that includes an operation for utilizing, by one or more processors, counters to track use of a plurality of languages by a user of an online service. The counters are updated based on interactions of the user in the online service. Further, the method includes operations for detecting, by the one or more processors, a text entered by the user in the online service, and for obtaining, by a language classifier using the one or more processors, an initial prediction having probabilities for the plurality of languages that the text is in the language. The one or more processors calculate a language distribution prediction based on the initial prediction and the counters for the user. The language distribution prediction comprises a probability, for each language, that the text is in the language. Further, the method includes operations for selecting, by the one or more processors, a language used in the text based on the language distribution prediction, and for causing, by the one or more processors, presentation on a display of a message in the selected language.” Pasternack teaches the concept of actively and continuously tracking and analyzing information to determine language information.)
Although the combination of Banga, Pasternack, and Marttila discloses the above-enclosed invention, the combination fails to explicitly disclose detecting accents associated with users.
However Sarikaya as shown, which talks about personalization of digital assistants, teaches the concept of detecting accents associated with users.
wherein the analysis is performed on the second set of data using the one or more machine learning algorithms for detecting an accent associated with each of the plurality of users, (See Sarikaya ¶0023, “According to additional examples, a plurality of user background characteristic and trait models may be used to identify user background characteristics and traits for a specific user. For example, a prebuilt gender detection model may determine whether a specific user is male or female. An age detection model may determine the age or age group for a specific user. An accent detection model may determine an accent for a specific user (e.g., southern, immigrant, Indian, Chinese, German, French, etc.). Other user background characteristic models may also be used to identify additional background traits and characteristics of a user as more fully described below. This information may be compiled into a voice-based profile for each specific user of a group of users.” See Sarikaya ¶0028, “Further acoustic processing and speech and language pattern analysis may be performed on voice, text and gesture input and a determination of whether user input corresponds to a number of categories may be made. For example, acoustic processing and speech pattern and language analysis may be performed such that certain background characteristics and traits of a user may be identified such as age of the user, gender of the user, accent assignment of the user, physical characteristics of the user, social characteristics of the user and emotional state of the user, among others. Machine learning may be used to create voice, speech and language pattern models that may be used to identify a user and assist with categorization of received input. Machine learning may also be used to categorize user input based on natural language processing and identification of one or more personalized topical categories for a user.” Sarikaya teaches the concept of performing accent analysis using machine learning.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Sarikaya with the combination of Banga, Pasternack, and Marttila. As shown, the combination discloses the concept of targeting content based on language including determining language information of users. Sarikaya further teach the concept of performing linguistic analysis including determining properties such as accents. Sarikaya teaches this concept to further accurately profile the user of a digital assistant thereby enabling better responses (See Sarikaya ¶0035). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Sarikaya to further account for accent information to further optimize the understanding of users and provide relevant results.
Although the combination of Banga, Pasternack, Marttila, and Sarikaya discloses the above-enclosed invention, the combination fails to explicitly disclose determining language information of users based on switching keyboard languages.
However Bojja as shown, which talks about language detection, teaches the concept of corelating keyboard changes to user languages.
wherein the multi-lingual campaigning system determines the proficiency in the plurality of languages by analyzing the switching of the language by each of the plurality of users using a keyboard; (See Bojja ¶0069, “FIG. 12 is a flowchart of an example method 1200 for detecting a language in a message. The method uses the detection module 16, the classifier module 18, and the manager module 20 to identify a most likely or best language 1202 for a given input message 1204. The input message 1204 can be accompanied by information about the user or the system(s) used to generate the message. For example, the input message 1204 can be accompanied by a user identification number (or other user identifier), information about the keyboard (e.g., a keyboard language) used to generate the message, and/or information about the operating system (e.g., an operating system language) used to generate the message.” Bojja teaches the concept of tracking keyboard language. See also Bojja ¶0005, “Embodiments of the systems and methods described herein are used to detect the language in a text message based on, for example, content of the message, information about the keyboard used to generate the message, and/or information about the language preferences of the user who generated the message. Compared to previous language detection techniques, the systems and methods described herein are generally faster and more accurate, particularly for short text messages (e.g., of four words or less).” Bojja teaches the concept of associating keyboard language setting with language preference.)
creating, at the multi-lingual campaigning system, a vernacular profile of each of the plurality of users based on the analysis of the first set of data, the second set of data, and the third set of data using the one or more machine learning algorithms; (See Pasternack ¶0128, “The language profiling service enable a more accurate language detection on short text as well as arrive at a language “profile” of a user by keeping track of language probabilities returned by language detection software over time and combining that information with a demographic prior over each user and context (feed, search, etc.). The language profiling service generates more accurate prediction of the languages users tends to use in a given context, e.g., a user may tend to share in feed in English but message with connections in Spanish.” Pasternack teaches the concept of generating individual user language profiles for each of a plurality of users. See also Pasternack ¶0139, “When the machine-learning program 916 is used to perform an assessment, new data 918 is provided as an input to the trained machine-learning program 916, and the machine-learning program 916 generates the assessment 920 as output. For example, the machine-learning program may be used to provide the language probability distributions for a given text and user.” Pasternack teaches the concept of making predictions using collected information and machine learning. See also Marttila ¶0029, “Unless otherwise stated, the concept `language` refers to a language corresponding to dictionary meanings, i.e. a national language or an official language, as well as to language variations, spoken languages, and languages of different social groups, such as the language spoken at home, youth language, different dialects and slangs.” Marttila further teaches the concept of language profiling to include vernacular definitions.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Bojja with the combination of Banga, Pasternack, Marttila, and Sarikaya. As shown, the combination discloses the concept of analyzing information to determine language properties of users. Bojja further teaches the concept of collecting and analyzing additional information including keyboard settings to determine language information. Bojja teaches this concept to further improve the speed and accuracy of language detection, and further avoid issues relating to misspelling by users (See Bojja ¶0004). Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Bojja to further improve the speed and accuracy of language detection/determination for users.
enabling, at the multi-lingual campaigning system, segmentation of the plurality of users in one or more segments based on the vernacular profile and one or more patterns of the plurality of languages and the plurality of language attributes, wherein the plurality of users is segmented in the one or more segments in real-time; (See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses grouping users with similar characteristics and profiles.)
triggering, at the multi-lingual campaigning system, initialization of one or more personalized marketing campaigns for the one or more segments based on the plurality of languages and the plurality of language attributes across the vernacular contexts of the plurality of users, wherein the one or more personalized marketing campaigns are initiated based on the one or more patterns of the one or more segments, wherein the one or more personalized marketing campaigns are initiated in real-time; and (See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses the concept of targeting content to groups of users based on the characteristics of the group, wherein the characteristics includes linguistic information.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, and Bojja discloses the above-enclosed invention including the concept of customizing content to the user (See Banga ¶0147), the combination fails to explicitly disclose the customization to include specific elements.
However Isaacson as shown, which talks about online purchase interactions, teaches the concept of customizing content for particular users to include a plurality of elements.
Dynamically modulating, at the multi-lingual campaigning system with the processor, the audio of the one or more advertisements associated with the one or more personalized marketing campaigns based on the accent of each of the plurality of users. (See Isaacson ¶0238, “An animated character could also be generated to engage with the buyer and receive questions and provide answers. The character can be chosen based at least in part on characteristics such as friends, family, favorite actors, and so forth. The social networking data obtained about the buyer can be used to select voices, gender, political leanings, race, and so forth of the animated entity that will engage the user in a dialog about the product. Pre-synthesized speech units can be gathered about the product and friends that have purchased the product. Personal information can be incorporated into the dialog as well. For example, the entity can say “Have a great birthday tomorrow Jane, how can I help you with the purchase of this chair, do you want it in black?” Thus, as a user clicks on a purchase process initiation object that transitions them to a dialog, the dialog management system can obtain text and data from various locations such as the merchant for data about the product, product review data, friends/family data associated with the product, social media data about the user, and so forth to generate a domain specific experience in the dialog around that particulate product. The aspects presented can therefore make the user feel more comfortable and in a friendly environment. Accents, personalities, jokes, visual characteristics, dialog responses, timings, and so forth can be tailored for the particular user such that even if they only want to choose red as the color of the chair, they can have a more socially pleasing experience when communicating with that merchant.” Isaacson teaches the concept of customizing content provided to the user to include customizing elements such as audio accent, color, character design/outfits, dialog, brand ambassadors, and theme.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Isaacson with the combination of Banga, Pasternack, Marttila, Sarikaya, and Bojja. As shown, the combination discloses the concept of targeting and customizing content based on known user information including language information. Isaacson further teaches the concept of customizing a plurality of elements based on known user information. Isaacson teaches customizing these elements to further present a comfortable and friendly environment to the user, thereby improving customer interactions (See Isaacson ¶0238). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Isaacson to further provide better customer interactions by tailoring elements for the specific user.
As per claim 17:
The computer system as recited in claim 10, further comprising dynamically displaying, at the multi-lingual campaigning system, one or more advertisements associated with the one or more personalized marketing campaigns for the one or more segments in real-time,
wherein the one or more advertisements are displayed to each of the plurality of users on the one or more communication devices based on the one or more patterns, and the vernacular profile,
wherein each of the one or more advertisements adapts a plurality of characteristics according to the vernacular profile, the plurality of languages, and the plurality of language attributes,
(See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses customizing and targeting specific content to users based on language information.)
wherein the plurality of characteristics comprises the accent of audio of the one or more advertisements, colors used in the one or more advertisements, costumes utilized in the one or more advertisements, phrases utilized in the one or more advertisements, brand ambassador of the one or more advertisements, and theme of the one or more advertisements. (See Isaacson ¶0238, “An animated character could also be generated to engage with the buyer and receive questions and provide answers. The character can be chosen based at least in part on characteristics such as friends, family, favorite actors, and so forth. The social networking data obtained about the buyer can be used to select voices, gender, political leanings, race, and so forth of the animated entity that will engage the user in a dialog about the product. Pre-synthesized speech units can be gathered about the product and friends that have purchased the product. Personal information can be incorporated into the dialog as well. For example, the entity can say “Have a great birthday tomorrow Jane, how can I help you with the purchase of this chair, do you want it in black?” Thus, as a user clicks on a purchase process initiation object that transitions them to a dialog, the dialog management system can obtain text and data from various locations such as the merchant for data about the product, product review data, friends/family data associated with the product, social media data about the user, and so forth to generate a domain specific experience in the dialog around that particulate product. The aspects presented can therefore make the user feel more comfortable and in a friendly environment. Accents, personalities, jokes, visual characteristics, dialog responses, timings, and so forth can be tailored for the particular user such that even if they only want to choose red as the color of the chair, they can have a more socially pleasing experience when communicating with that merchant.” Isaacson teaches the concept of customizing content provided to the user to include customizing elements such as audio accent, color, character design/outfits, dialog, brand ambassadors, and theme.)
As per claim 19:
A non-transitory computer-readable storage medium encoding computer executable instructions that, when executed by at least one processor, performs a method for adopting user learnings across vernacular contexts, the method comprising:
(See Banga ¶0150, “In some embodiments, the AP server may be comprised of: (1) a processor; (2) a configuration component/module; and (3) processing software; and (4) appropriate memory, storage, networking capabilities and associated peripherals. All of these elements can be unitary or distributed.” Banga discloses a storage memory for storing executable instructions.)
receiving, at a computing device, a first set of data associated with a plurality of users;
collecting, at the computing device, a second set of data associated with the plurality of users;
fetching, at the computing device, a third set of data associated with one or more communication devices of the plurality of users;
(See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses retrieving multiple data sets for a plurality of users for language based targeting of advertisements.)
Although Banga discloses the above-enclosed invention including the concept of collecting and performing analysis to determine information about users (See Banga ¶0101), Bang fails to explicitly disclose utilizing machine learning to categorize languages of users.
However Pasternack as shown, which talks about language profiling, teaches the concept of utilizing machine learning for categorizing languages.
analyzing, at the computing device, the first set of data, the second set of data, and the third set of data using one or more machine learning algorithms,
(See Pasternack ¶0052, “In some example embodiments, the language profiling service accesses demographic prior information 310 about the user that received the text 302. The demographic prior information 310 includes information about the user, such as the information kept in the user's profile, and includes one or more of the name of the client using the language profiling service 130, user identifier (ID), and a conversation ID. As used herein, client refers to the service within the social network that utilizes the language profiling service 1304 predicting the language spoken. For example, the client may be the user feed, the search engine, an advertisements engine, etc. The conversation ID is the identifier for a conversation that includes the user.” Pasternack teaches the concept of analyzing a plurality of data sets.)
wherein the analysis is performed based on training of a machine learning model, (See Pasternack ¶0149, “In one example, calculating the language distribution prediction further comprises utilizing a machine-learning model to calculate the probability for each language that the text is in the language, the machine-learning model include features that comprise the counters, values of the initial prediction, and information about the user, the machine-learning model being trained based on past interactions on the online service by users of the online service.” Pasternack teaches the concept of utilizing machine learning for language analysis.)
wherein the analysis is performed for identifying a plurality of languages across the vernacular contexts of the plurality of users, (See Pasternack ¶0049, “FIG. 3 illustrates the prediction of the language used in a text message, according to some example embodiments. As discussed above, the text message “y?” may mean “Why?” in English or “And?” in Spanish. If the online service knows that the message “y?” came from a user who has spoken only English in the past, has an English default locale, works in a British company, etc., then there is a very high probability that “y?” is intended as English.” Pasternack teaches the concept of identifying languages including accounting for vernacular context.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Pasternack with the invention of Banga. As shown, Banga discloses the concept of collecting and utilizing information for targeting content to users including accounting for language settings. Pasternack further discusses the short comings of utilizing preset language preferences for multi-lingual users and addressing the need for accurately determining user language including for targeting of content (See Pasternack ¶0002-¶0005). Pasternack teaches performing analysis using machine learning to identify possible user languages. Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Pasternack to further improve the identification of languages of users, thereby enabling further targeting and analytics of content.
Although the combination of Banga and Pasternack discloses the above-enclosed invention, the combination fails to explicitly disclose identifying language attributes.
However Marttila as shown, which talks about linguistic profiling, teaches the concept of identifying language attributes.
wherein the analysis is performed for identifying a plurality of language attributes of the plurality of languages across the vernacular contexts of the plurality of users, (See Marttila claim 1, “A method where, in order to measure or define the language proficiency of a person under investigation, particularly the degree of flawlessness in his/her pronunciation and/or in order to investigate the person's own language background and identity, the speech of the person under investigation is compared with a speech sample of a selected reference language, characterized in that from an electronic speech sample of a reference language, there are identified and registered, by using autocorrelation and/or pattern recognition and/or signal processing or some other corresponding method, such sound elements and linguistic features that are repeatedly represented in the reference language speech sample and are typical of said language, and on the basis of the obtained linguistic profile of the reference language, corresponding sound elements and/or linguistic features are searched from an electronically recorded speech sample of the person under investigation, and/or there is defined which of the sound elements or linguistic features of the linguistic profile of the reference language the person under investigation substitutes with such sound elements or linguistic features that deviate from the reference language, and/or there is defined what these substitute sound elements and linguistic features are.” See also Marttila ¶0029, “Unless otherwise stated, the concept `language` refers to a language corresponding to dictionary meanings, i.e. a national language or an official language, as well as to language variations, spoken languages, and languages of different social groups, such as the language spoken at home, youth language, different dialects and slangs.“ Marttila teaches the concept of identifying skilling level and vernacular attributes.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings if Marttila with the combination of Banga and Pasternack. As shown, the combination discloses the concept of targeting content based on language including determining language information of users. Mantilla further teaches the concept of identifying particular language attributes including language skill level. As shown, Marttila teaches the concept to further identify user linguistic attributes for a plurality of purposes including further enhancing consumer interaction (See Marttila ¶0004). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Marttila to further enhance the profiling and comprehension of users by further identifying additional linguistic data points, thereby allowing for additional targeting and adaption for users.
Although the combination of Banga, Pasternack, and Marttila discloses the above-enclosed invention, the combination fails to explicitly disclose detecting accents associated with users.
However Sarikaya as shown, which talks about personalization of digital assistants, teaches the concept of detecting accents associated with users.
wherein the analysis is performed on the second set of data using the one or more machine learning algorithms for detecting an accent associated with each of the plurality of users, (See Sarikaya ¶0023, “According to additional examples, a plurality of user background characteristic and trait models may be used to identify user background characteristics and traits for a specific user. For example, a prebuilt gender detection model may determine whether a specific user is male or female. An age detection model may determine the age or age group for a specific user. An accent detection model may determine an accent for a specific user (e.g., southern, immigrant, Indian, Chinese, German, French, etc.). Other user background characteristic models may also be used to identify additional background traits and characteristics of a user as more fully described below. This information may be compiled into a voice-based profile for each specific user of a group of users.” See Sarikaya ¶0028, “Further acoustic processing and speech and language pattern analysis may be performed on voice, text and gesture input and a determination of whether user input corresponds to a number of categories may be made. For example, acoustic processing and speech pattern and language analysis may be performed such that certain background characteristics and traits of a user may be identified such as age of the user, gender of the user, accent assignment of the user, physical characteristics of the user, social characteristics of the user and emotional state of the user, among others. Machine learning may be used to create voice, speech and language pattern models that may be used to identify a user and assist with categorization of received input. Machine learning may also be used to categorize user input based on natural language processing and identification of one or more personalized topical categories for a user.” Sarikaya teaches the concept of performing accent analysis using machine learning.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Sarikaya with the combination of Banga, Pasternack, and Marttila. As shown, the combination discloses the concept of targeting content based on language including determining language information of users. Sarikaya further teach the concept of performing linguistic analysis including determining properties such as accents. Sarikaya teaches this concept to further accurately profile the user of a digital assistant thereby enabling better responses (See Sarikaya ¶0035). Thus it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Sarikaya to further account for accent information to further optimize the understanding of users and provide relevant results.
wherein the analysis is performed in real time; (See Pasternack ¶0024, “One general aspect includes a method that includes an operation for utilizing, by one or more processors, counters to track use of a plurality of languages by a user of an online service. The counters are updated based on interactions of the user in the online service. Further, the method includes operations for detecting, by the one or more processors, a text entered by the user in the online service, and for obtaining, by a language classifier using the one or more processors, an initial prediction having probabilities for the plurality of languages that the text is in the language. The one or more processors calculate a language distribution prediction based on the initial prediction and the counters for the user. The language distribution prediction comprises a probability, for each language, that the text is in the language. Further, the method includes operations for selecting, by the one or more processors, a language used in the text based on the language distribution prediction, and for causing, by the one or more processors, presentation on a display of a message in the selected language.” Pasternack teaches the concept of actively and continuously tracking and analyzing information to determine language information.)
Although the combination of Banga, Pasternack, Marttila, and Sarikaya discloses the above-enclosed invention, the combination fails to explicitly disclose determining language information of users based on switching keyboard languages.
However Bojja as shown, which talks about language detection, teaches the concept of corelating keyboard changes to user languages.
wherein the multi-lingual campaigning system determines the proficiency in the plurality of languages by analyzing the switching of the language by each of the plurality of users using a keyboard; (See Bojja ¶0069, “FIG. 12 is a flowchart of an example method 1200 for detecting a language in a message. The method uses the detection module 16, the classifier module 18, and the manager module 20 to identify a most likely or best language 1202 for a given input message 1204. The input message 1204 can be accompanied by information about the user or the system(s) used to generate the message. For example, the input message 1204 can be accompanied by a user identification number (or other user identifier), information about the keyboard (e.g., a keyboard language) used to generate the message, and/or information about the operating system (e.g., an operating system language) used to generate the message.” Bojja teaches the concept of tracking keyboard language. See also Bojja ¶0005, “Embodiments of the systems and methods described herein are used to detect the language in a text message based on, for example, content of the message, information about the keyboard used to generate the message, and/or information about the language preferences of the user who generated the message. Compared to previous language detection techniques, the systems and methods described herein are generally faster and more accurate, particularly for short text messages (e.g., of four words or less).” Bojja teaches the concept of associating keyboard language setting with language preference.)
creating, at the computing device, a vernacular profile of each of the plurality of users based on the analysis of the first set of data, the second set of data, and the third set of data using the one or more machine learning algorithms; (See Pasternack ¶0128, “The language profiling service enable a more accurate language detection on short text as well as arrive at a language “profile” of a user by keeping track of language probabilities returned by language detection software over time and combining that information with a demographic prior over each user and context (feed, search, etc.). The language profiling service generates more accurate prediction of the languages users tends to use in a given context, e.g., a user may tend to share in feed in English but message with connections in Spanish.” Pasternack teaches the concept of generating individual user language profiles for each of a plurality of users. See also Pasternack ¶0139, “When the machine-learning program 916 is used to perform an assessment, new data 918 is provided as an input to the trained machine-learning program 916, and the machine-learning program 916 generates the assessment 920 as output. For example, the machine-learning program may be used to provide the language probability distributions for a given text and user.” Pasternack teaches the concept of making predictions using collected information and machine learning. See also Marttila ¶0029, “Unless otherwise stated, the concept `language` refers to a language corresponding to dictionary meanings, i.e. a national language or an official language, as well as to language variations, spoken languages, and languages of different social groups, such as the language spoken at home, youth language, different dialects and slangs.” Marttila further teaches the concept of language profiling to include vernacular definitions.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Bojja with the combination of Banga, Pasternack, Marttila, and Sarikaya. As shown, the combination discloses the concept of analyzing information to determine language properties of users. Bojja further teaches the concept of collecting and analyzing additional information including keyboard settings to determine language information. Bojja teaches this concept to further improve the speed and accuracy of language detection, and further avoid issues relating to misspelling by users (See Bojja ¶0004). Therefore it would have been obvious to one of ordinary skill in the art at the time of filing to have utilized the teachings of Bojja to further improve the speed and accuracy of language detection/determination for users.
enabling, at the computing device, segmentation of the plurality of users in one or more segments based on the vernacular profile and one or more patterns of the plurality of languages and the plurality of language attributes, wherein the plurality of users is segmented in the one or more segments in real-time; (See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses grouping users with similar characteristics and profiles.)
triggering, at the computing device, initialization of one or more personalized marketing campaigns for the one or more segments based on the plurality of languages and the plurality of language attributes across the vernacular contexts of the plurality of users, wherein the one or more personalized marketing campaigns are initiated based on the one or more patterns of the one or more segments, wherein the one or more personalized marketing campaigns are initiated in real-time; and (See Banga ¶0140, “The Engine includes an analytics components to carry out the various data processing operations, such as collection/distribution of information and profiling. In some embodiments, a method of collecting/assimilating data and distributing relevant information to users is disclosed, comprising: (a) implementing a system comprising a business partner, (b) obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point; (c) creating a profile based on each MAC/UID, formulated from location, time of day and frequency; (d) creating a profile ID associated with each of the one or more MAC/UIDs; (e) creating profile groups; (f) associating the MAC/UIDs with profile groups; and (g) comparing the profile groups with the desired audience of the business partner's data/information/product; wherein, based on the results of the analysis, associating the target information provided by the business partner and delivering to the user with the response via the network or system.” Banga discloses the concept of targeting content to groups of users based on the characteristics of the group, wherein the characteristics includes linguistic information.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, and Bojja discloses the above-enclosed invention including the concept of customizing content to the user (See Banga ¶0147), the combination fails to explicitly disclose the customization to include specific elements.
However Isaacson as shown, which talks about online purchase interactions, teaches the concept of customizing content for particular users to include a plurality of elements.
Dynamically modulating, at the multi-lingual campaigning system with the processor, the audio of the one or more advertisements associated with the one or more personalized marketing campaigns based on the accent of each of the plurality of users. (See Isaacson ¶0238, “An animated character could also be generated to engage with the buyer and receive questions and provide answers. The character can be chosen based at least in part on characteristics such as friends, family, favorite actors, and so forth. The social networking data obtained about the buyer can be used to select voices, gender, political leanings, race, and so forth of the animated entity that will engage the user in a dialog about the product. Pre-synthesized speech units can be gathered about the product and friends that have purchased the product. Personal information can be incorporated into the dialog as well. For example, the entity can say “Have a great birthday tomorrow Jane, how can I help you with the purchase of this chair, do you want it in black?” Thus, as a user clicks on a purchase process initiation object that transitions them to a dialog, the dialog management system can obtain text and data from various locations such as the merchant for data about the product, product review data, friends/family data associated with the product, social media data about the user, and so forth to generate a domain specific experience in the dialog around that particulate product. The aspects presented can therefore make the user feel more comfortable and in a friendly environment. Accents, personalities, jokes, visual characteristics, dialog responses, timings, and so forth can be tailored for the particular user such that even if they only want to choose red as the color of the chair, they can have a more socially pleasing experience when communicating with that merchant.” Isaacson teaches the concept of customizing content provided to the user to include customizing elements such as audio accent, color, character design/outfits, dialog, brand ambassadors, and theme.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Isaacson with the combination of Banga, Pasternack, Marttila, Sarikaya, and Bojja. As shown, the combination discloses the concept of targeting and customizing content based on known user information including language information. Isaacson further teaches the concept of customizing a plurality of elements based on known user information. Isaacson teaches customizing these elements to further present a comfortable and friendly environment to the user, thereby improving customer interactions (See Isaacson ¶0238). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Isaacson to further provide better customer interactions by tailoring elements for the specific user.
Claims 2, 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Banga et al. (US 20080262901 A1) (hereafter Banga), in view of Pasternack et al. (US 20200401657 A1) (hereafter Pasternack), in view of Marttila (US 20130189652 A1) (hereafter Marttila), in view of Sarikaya (US 20180061421 A1) (hereafter Sarikaya), in view of Bojja et al. (WO 2018067440 A1) (hereafter Bojja), in view of Isaacson et al. (US 20170236196 A1) (hereafter Isaacson), in view of Bojja et al. (WO 2018067440 A1) (hereafter Bojja) in view of Ramer et al. (US 20130053005 A1) (hereafter Ramer), in view of Takakura et al. (US 20030195801 A1) (hereafter Takakura).
As per claim 2:
The computer-implemented method as recited in claim 1, wherein the first set of data comprises
name data,
native language data,
(See Banga ¶0140, “obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point;“ See Also Banga ¶0108, “a unique identifier (serial number, or name, or other)” Banga discloses collecting information including name information and native language data.)
demographic data, (See Banga ¶0149, “Embodiments of the invention also relate to business methods, which allow for the creation and/or identification of demographically alike but geographically dispersed communities and make targeted content delivery possible to these communities.” Banga discloses collecting demographic data.)
real-time geographical location data,
past geographical location data,
(See Banga ¶0013, “Geographic information gathered by the network about the device's current location as well as its historical data of prior locations and therefore a "geo/location tag"” Banga discloses collecting current and past location data.)
interests data.
age data,
gender data,
relationship status data,
profession data,
(See Pasternack ¶0033, “In some example embodiments, when a user 136 initially registers to become a user 136 of the social networking service provided by the social networking server 112, the user 136 is prompted to provide some personal information, such as name, age (e.g., birth date), gender, interests, contact information, home town, address, spouse's and/or family users' names, educational background (e.g., schools, majors, matriculation and/or graduation dates, etc.), employment history (e.g., companies worked at, periods of employment for the respective jobs, job title), professional industry (also referred to herein simply as “industry”), skills, professional organizations, and so on. This information is stored, for example, in the user profile database 120. Similarly, when a representative of an organization initially registers the organization with the social networking service provided by the social networking server 112, the representative may be prompted to provide certain information about the organization, such as a company industry. This information may be stored, for example, in the user profile database 120.” Pasternack further teaches collecting additional data points including interest, gender, age, marital status, and professional status.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson discloses the above-enclosed invention, the combination fails to explicitly disclose collecting the additional information for profiling and targeting users.
However Ramer as shown, which talks about targeting advertisements to mobile users, teaches the concept of collecting a plurality of data points to further profile and target users.
e-mail identity data,
contact number data,
(See Ramer ¶0143, “Personally identifiable data is information that can be used to identify a person uniquely and reliably, including but not limited to name, address, telephone number, e-mail address and account, or other personal identification number, as well as any accompanying data linked to the identity of that person (e.g., the account data stored by the wireless provider 108). “ Ramer further teaches collecting email and number data.)
Geo-IP data,
(See Ramer ¶0957, “For example, the user characteristic, home address, may be used to determine, in part, the relevancy of news headlines that derive from news websites using IP addresses associated in some manner with the user's home address.” Ramer teaches collecting Geo-IP data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ramer with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson. As shown, the combination discloses the concept of collecting a plurality of data points for profiling and identifying the user. Ramer further teaches the concept of collecting a plurality of additional data points to further enhance the profiling and targeting of users (See Ramer ¶0005-¶0010). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ramer to further improve the profiling and targeting of users by utilizing additional known information to further improve the accuracy of the targeted content.
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, Isaacson, and Ramer discloses the above-enclosed invention, the combination fails to explicitly disclose the collected information to include native place and hobby data.
However Takakura as shown, which talks about targeting advertisements to users in conversation, teaches the concept of collecting native place and hobby data.
native place data,
hobbies data, and
(See Takakura ¶0152, “In this case, in the member DB 10 (a user attribute storage unit) of the server apparatus 1, arbitrary information for specifying the attributes of a user, e.g., the address, the age, the sex, the occupation, the native place, and the hobby of the user is stored. The attributes can be acquired when the user performs member registration in this system. The chat processing section 16d uses the attributes stored in the member DB 10 as matching keys to perform matching to the advertisement data stored in the advertisement DB 13, and determines advertisement data having the highest matching rate as advertisement data to be added to chat data.” Takakura teaches further collecting native place and hobby data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Takakura with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, Isaacson, and Ramer. As shown, the combination discloses the concept of collecting user information to profile and target content to the users. Takakura further teaches collecting and utilizing additional data points to further improve the targeting of content (See Takakura ¶0152). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have further utilized the teachings of Takakura to further enhance the targeting/matching of content to users by matching additional data points for targeting.
As per claim 11:
The computer system as recited in claim 10, wherein the first set of data comprises
name data,
native language data,
(See Banga ¶0140, “obtaining RAW DATA, including MAC/UID and location information [and, optionally, survey information], such as: End User MAC/UID, Local IP Address, Default Home Page URL, Network Device ID, Network IP Address, Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the computing device, the user's behavior, or information concerning either, generated at or by the Access Point;“ See Also Banga ¶0108, “a unique identifier (serial number, or name, or other)” Banga discloses collecting information including name information and native language data.)
demographic data, (See Banga ¶0149, “Embodiments of the invention also relate to business methods, which allow for the creation and/or identification of demographically alike but geographically dispersed communities and make targeted content delivery possible to these communities.” Banga discloses collecting demographic data.)
real-time geographical location data,
past geographical location data,
(See Banga ¶0013, “Geographic information gathered by the network about the device's current location as well as its historical data of prior locations and therefore a "geo/location tag"” Banga discloses collecting current and past location data.)
interests data.
age data,
gender data,
relationship status data,
profession data,
(See Pasternack ¶0033, “In some example embodiments, when a user 136 initially registers to become a user 136 of the social networking service provided by the social networking server 112, the user 136 is prompted to provide some personal information, such as name, age (e.g., birth date), gender, interests, contact information, home town, address, spouse's and/or family users' names, educational background (e.g., schools, majors, matriculation and/or graduation dates, etc.), employment history (e.g., companies worked at, periods of employment for the respective jobs, job title), professional industry (also referred to herein simply as “industry”), skills, professional organizations, and so on. This information is stored, for example, in the user profile database 120. Similarly, when a representative of an organization initially registers the organization with the social networking service provided by the social networking server 112, the representative may be prompted to provide certain information about the organization, such as a company industry. This information may be stored, for example, in the user profile database 120.” Pasternack further teaches collecting additional data points including interest, gender, age, marital status, and professional status.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson discloses the above-enclosed invention, the combination fails to explicitly disclose collecting the additional information for profiling and targeting users.
However Ramer as shown, which talks about targeting advertisements to mobile users, teaches the concept of collecting a plurality of data points to further profile and target users.
e-mail identity data,
contact number data,
(See Ramer ¶0143, “Personally identifiable data is information that can be used to identify a person uniquely and reliably, including but not limited to name, address, telephone number, e-mail address and account, or other personal identification number, as well as any accompanying data linked to the identity of that person (e.g., the account data stored by the wireless provider 108). “ Ramer further teaches collecting email and number data.)
Geo-IP data,
(See Ramer ¶0957, “For example, the user characteristic, home address, may be used to determine, in part, the relevancy of news headlines that derive from news websites using IP addresses associated in some manner with the user's home address.” Ramer teaches collecting Geo-IP data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ramer with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson. As shown, the combination discloses the concept of collecting a plurality of data points for profiling and identifying the user. Ramer further teaches the concept of collecting a plurality of additional data points to further enhance the profiling and targeting of users (See Ramer ¶0005-¶0010). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ramer to further improve the profiling and targeting of users by utilizing additional known information to further improve the accuracy of the targeted content.
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, Isaacson, and Ramer discloses the above-enclosed invention, the combination fails to explicitly disclose the collected information to include native place and hobby data.
However Takakura as shown, which talks about targeting advertisements to users in conversation, teaches the concept of collecting native place and hobby data.
native place data,
hobbies data, and
(See Takakura ¶0152, “In this case, in the member DB 10 (a user attribute storage unit) of the server apparatus 1, arbitrary information for specifying the attributes of a user, e.g., the address, the age, the sex, the occupation, the native place, and the hobby of the user is stored. The attributes can be acquired when the user performs member registration in this system. The chat processing section 16d uses the attributes stored in the member DB 10 as matching keys to perform matching to the advertisement data stored in the advertisement DB 13, and determines advertisement data having the highest matching rate as advertisement data to be added to chat data.” Takakura teaches further collecting native place and hobby data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Takakura with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, Isaacson, and Ramer. As shown, the combination discloses the concept of collecting user information to profile and target content to the users. Takakura further teaches collecting and utilizing additional data points to further improve the targeting of content (See Takakura ¶0152). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have further utilized the teachings of Takakura to further enhance the targeting/matching of content to users by matching additional data points for targeting.
Claims 3, 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Banga et al. (US 20080262901 A1) (hereafter Banga), in view of Pasternack et al. (US 20200401657 A1) (hereafter Pasternack), in view of Marttila (US 20130189652 A1) (hereafter Marttila), in view of Sarikaya (US 20180061421 A1) (hereafter Sarikaya), in view of Bojja et al. (WO 2018067440 A1) (hereafter Bojja), in view of Isaacson et al. (US 20170236196 A1) (hereafter Isaacson), in view of Ramer et al. (US 20130053005 A1) (hereafter Ramer).
As per claim 3:
The computer-implemented method as recited in claim 1, wherein the second set of data corresponds to audio data of the plurality of users, wherein the second set of data is collected from a set of audio sensors, wherein the second set of data comprises
recorded speech data,
real-time speech data,
(See Pasternack ¶0020, “A method according to a preferred embodiment of the invention is illustrated as a flow diagram in FIG. 1. The method can be used for example for detecting the possible mother tongue of a person. In step 11 of the method, there is first made a sample of the person's speech. It can be either an auditory perception or a recorded sample. In step 12, there is composed a list of the phonemes contained in the sample.” Pasternack teaches the concept of collecting speech data including past speech and actively gathered speech.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson discloses the above-enclosed invention, the combination fails to explicitly disclose collecting voice command data.
However Ramer as shown, which talks about targeting advertisements to mobile users, teaches the concept of collecting voice command data.
past voice command data, and
real-time voice command data.
(See Ramer ¶0045, “The voice entry 122 function of the mobile communication facility may be used through the speaker-receiver device of the mobile communication facility 102 or by use of the standard SMS lexicon and syntax, and it may be adaptive to individual users' voice commands and usage patterns that are stored on and accessed from the mobile subscriber characteristics database 112. The voice entry 122 function may permit voice dialing, voice memo, voice recognition, speech recognition, or other functions related to audible input.” Ramer teaches the concept of collecting voice command data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ramer with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson. As shown, the combination discloses the concept of collecting a plurality of information to profile and target content to the user including speech data to profile a user. Ramer further teaches the concept of collecting speech data to include voice command data. Ramer teaches the concept of adaptive voice entry by collecting and storing user voice commands in the user characteristics, thereby enabling further understanding of the user. Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have further collected and utilized voice commands issued by the user to further learn and profile the user’s linguistic habits.
As per claim 12:
The computer system as recited in claim 10, wherein the second set of data corresponds to audio data of the plurality of users, wherein the second set of data is collected from a set of audio sensors, wherein the second set of data comprises
recorded speech data,
real-time speech data,
See Pasternack ¶0020, “A method according to a preferred embodiment of the invention is illustrated as a flow diagram in FIG. 1. The method can be used for example for detecting the possible mother tongue of a person. In step 11 of the method, there is first made a sample of the person's speech. It can be either an auditory perception or a recorded sample. In step 12, there is composed a list of the phonemes contained in the sample.” Pasternack teaches the concept of collecting speech data including past speech and actively gathered speech.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson discloses the above-enclosed invention, the combination fails to explicitly disclose collecting voice command data.
However Ramer as shown, which talks about targeting advertisements to mobile users, teaches the concept of collecting voice command data.
past voice command data, and
real-time voice command data.
(See Ramer ¶0045, “The voice entry 122 function of the mobile communication facility may be used through the speaker-receiver device of the mobile communication facility 102 or by use of the standard SMS lexicon and syntax, and it may be adaptive to individual users' voice commands and usage patterns that are stored on and accessed from the mobile subscriber characteristics database 112. The voice entry 122 function may permit voice dialing, voice memo, voice recognition, speech recognition, or other functions related to audible input.” Ramer teaches the concept of collecting voice command data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ramer with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson. As shown, the combination discloses the concept of collecting a plurality of information to profile and target content to the user including speech data to profile a user. Ramer further teaches the concept of collecting speech data to include voice command data. Ramer teaches the concept of adaptive voice entry by collecting and storing user voice commands in the user characteristics, thereby enabling further understanding of the user. Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have further collected and utilized voice commands issued by the user to further learn and profile the user’s linguistic habits.
Claims 4, 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Banga et al. (US 20080262901 A1) (hereafter Banga), in view of Pasternack et al. (US 20200401657 A1) (hereafter Pasternack), in view of Marttila (US 20130189652 A1) (hereafter Marttila), in view of Sarikaya (US 20180061421 A1) (hereafter Sarikaya), in view of Bojja et al. (WO 2018067440 A1) (hereafter Bojja), in view of Isaacson et al. (US 20170236196 A1) (hereafter Isaacson), in view of Rousso et al. (US 20100287049 A1) (hereafter Rousso), in view of Khoe et al. (US 20140035823 A1) (hereafter Khoe).
As per claim 4:
The computer-implemented method as recited in claim 1, wherein the third set of data comprises
past typing data,
real-time typing data,
(See Pasternack ¶0022, “The language profiling service provides language detection on short text items by leveraging language detection methods for the given short text item (e.g., feed post, comment, message) and by accumulating probability counters for each of the supported languages over time. The counters may be for both the user issuing the text item and for the context in which the text item is issued (e.g., user feed, search query, messaging). Over time, the counters are used to identify the languages used by the users or used in user conversations. The probabilities for the use of each of the languages greatly improve the language prediction capabilities for short text items.” Pasternack teaches collecting text information entered including both current and past text data.)
speech language data. (See Marttila ¶0028, “The concept `speech sample in electronic form` refers, for instance, to a sound signal converted to an electronic signal by a microphone or a recording device. A `speech sample` refers, for instance, to the recorded speech of a person speaking a reference language, or of a person under investigation. A speech sample in electronic form can be analyzed for example by electrically calculating the number of sound elements represented in the sample. Here the term `electric calculation` refers to digitally performing the calculations of a computer program.” Marttila teaches the concept of gathering speech language data.)
primary language preference data of the one or more communication devices, (See Banga ¶127, “In step 705 as shown in FIG. 7, the DTD Server 160 receives a request for the local Terms & Condition (T&C) Page from the end user. During these initial exchanges, the following exemplary information may be acquired by the DTD Server and recorded in the Profile Engine: identifier information such as end user MAC Address, Local IP Address, Default Home Page URL, RCD and/or Network Device ID, Network IP Address (e.g., for RCD, Network Device, etc.), Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the access device, the user's behavior, or information concerning the user generated at or by the RCD.” Banga discloses collecting language preference of the device.)
Although the combination of Banga, Pasternack, Sarikaya, Marttila, Bojja, and Isaacson discloses the above-enclosed invention, the combination fails to explicitly disclose collecting a plurality of language preferences.
However Rousso as shown, which talks about language neutral searching, teaches the concept of collecting a plurality of language preferences.
secondary language preference data of the one or more communication devices, (See Rousso ¶0042, “In a further embodiment, the system may allow a user to specify more than one language preference and/or order language preferences (i.e., for multi-lingual user). For example, the system may provide a list of check-box items 196b that allows a user to select primary, secondary, tertiary, etc. languages and order the languages; this ordering may be used in subsequent language-preference specific processes performed by the system.” Rousso teaches collecting multiple language preferences.)
browser language data, (See Rousso ¶0023, “a) Browser language preference settings (e.g., the language preference settings in Apple's Safari or Microsoft's Explorer web browsers);” Rousso discloses collecting browser language data.)
application language data, (See Rousso ¶0028, “f) An indicator of language preference (e.g., a user interface widget such as a pop-up menu indicating language preference);” Rousso discloses collecting application language data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Rousso with the combination of Banga, Pasternack, Sarikaya, Marttila, Bojja, and Isaacson. As shown, the combination discloses the concept of collecting a plurality of information to profile and target content to the user including language and speech related data. Rousso further teaches the concept of targeting content to users based on language preferences including utilizing additional language related data (See Rousso ¶0030-¶0032). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Rousso to further improve the targeting of content by collecting additional information regarding user language preferences and thereby accounting for multiple languages.
Although the combination of Banga, Pasternack, Sarikaya, Marttila, Bojja, Isaacson, and Rousso discloses the above-enclosed invention, the combination fails to explicitly disclose utilizing keyboard data.
However Khoe as shown, which talks about context based language determination, teaches the concept of utilizing keyboard data.
installed keyboard data and (See Khoe ¶0038, “Context determiner 215 in some embodiments can determine a set of contextual attributes surrounding the message composition. In some embodiments, context determiner 215 can determine a type of application that the user is using for the message composition, user preferences and history (e.g., including a set of languages frequently used by the user, the user's preferences or past language selections), a number of keyboard languages loaded/active on the electronic device, the different keyboard layouts active on the device, the intended recipient and languages associated with the intended recipient, a location, a time, one or more words being typed that is identifiable in a different language dictionary (and/or frequently typed by the user), etc.” Khoe teaches the concept of utilizing keyboard data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Khoe with the combination of Banga, Pasternack, Sarikaya, Marttila, Bojja, Isaacson and Rousso. As shown, the combination discloses collecting and utilizing a plurality of language preferences for profiling and targeting content to the user. Khoe further teaches language preferences to include keyboard data. Khoe teaches this concept to further profile and understand the user’s use of languages in particular contexts (See Khoe ¶0038). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Khoe to further understands the user’s usage of language in different contexts.
As per claim 13:
The computer system as recited in claim 10, wherein the third set of data comprises
past typing data,
real-time typing data,
(See Pasternack ¶0022, “The language profiling service provides language detection on short text items by leveraging language detection methods for the given short text item (e.g., feed post, comment, message) and by accumulating probability counters for each of the supported languages over time. The counters may be for both the user issuing the text item and for the context in which the text item is issued (e.g., user feed, search query, messaging). Over time, the counters are used to identify the languages used by the users or used in user conversations. The probabilities for the use of each of the languages greatly improve the language prediction capabilities for short text items.” Pasternack teaches collecting text information entered including both current and past text data.)
speech language data. (See Marttila ¶0028, “The concept `speech sample in electronic form` refers, for instance, to a sound signal converted to an electronic signal by a microphone or a recording device. A `speech sample` refers, for instance, to the recorded speech of a person speaking a reference language, or of a person under investigation. A speech sample in electronic form can be analyzed for example by electrically calculating the number of sound elements represented in the sample. Here the term `electric calculation` refers to digitally performing the calculations of a computer program.” Marttila teaches the concept of gathering speech language data.)
primary language preference data of the one or more communication devices, (See Banga ¶127, “In step 705 as shown in FIG. 7, the DTD Server 160 receives a request for the local Terms & Condition (T&C) Page from the end user. During these initial exchanges, the following exemplary information may be acquired by the DTD Server and recorded in the Profile Engine: identifier information such as end user MAC Address, Local IP Address, Default Home Page URL, RCD and/or Network Device ID, Network IP Address (e.g., for RCD, Network Device, etc.), Location ID, Local Language on Computer, Operating System/Device Specific Information, Nest Requested Home Page, Survey Results, Date and Time Information, as well as other information derived from the access device, the user's behavior, or information concerning the user generated at or by the RCD.” Banga discloses collecting language preference of the device.)
Although the combination of Banga, Pasternack, Sarikaya, Marttila, and Bojja discloses the above-enclosed invention, the combination fails to explicitly disclose collecting a plurality of language preferences.
However Rousso as shown, which talks about language neutral searching, teaches the concept of collecting a plurality of language preferences.
secondary language preference data of the one or more communication devices, (See Rousso ¶0042, “In a further embodiment, the system may allow a user to specify more than one language preference and/or order language preferences (i.e., for multi-lingual user). For example, the system may provide a list of check-box items 196b that allows a user to select primary, secondary, tertiary, etc. languages and order the languages; this ordering may be used in subsequent language-preference specific processes performed by the system.” Rousso teaches collecting multiple language preferences.)
browser language data, (See Rousso ¶0023, “a) Browser language preference settings (e.g., the language preference settings in Apple's Safari or Microsoft's Explorer web browsers);” Rousso discloses collecting browser language data.)
application language data, (See Rousso ¶0028, “f) An indicator of language preference (e.g., a user interface widget such as a pop-up menu indicating language preference);” Rousso discloses collecting application language data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Rousso with the combination of Banga, Pasternack, Marttila, Sarikaya, and Bojja. As shown, the combination discloses the concept of collecting a plurality of information to profile and target content to the user including language and speech related data. Rousso further teaches the concept of targeting content to users based on language preferences including utilizing additional language related data (See Rousso ¶0030-¶0032). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Rousso to further improve the targeting of content by collecting additional information regarding user language preferences and thereby accounting for multiple languages.
Although the combination of Banga, Pasternack, Sarikaya, Marttila, Bojja, and Rousso discloses the above-enclosed invention, the combination fails to explicitly disclose utilizing keyboard data.
However Khoe as shown, which talks about context based language determination, teaches the concept of utilizing keyboard data.
installed keyboard data and (See Khoe ¶0038, “Context determiner 215 in some embodiments can determine a set of contextual attributes surrounding the message composition. In some embodiments, context determiner 215 can determine a type of application that the user is using for the message composition, user preferences and history (e.g., including a set of languages frequently used by the user, the user's preferences or past language selections), a number of keyboard languages loaded/active on the electronic device, the different keyboard layouts active on the device, the intended recipient and languages associated with the intended recipient, a location, a time, one or more words being typed that is identifiable in a different language dictionary (and/or frequently typed by the user), etc.” Khoe teaches the concept of utilizing keyboard data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Khoe with the combination of Banga, Pasternack, Sarikaya, Marttila, Bojja, and Rousso. As shown, the combination discloses collecting and utilizing a plurality of language preferences for profiling and targeting content to the user. Khoe further teaches language preferences to include keyboard data. Khoe teaches this concept to further profile and understand the user’s use of languages in particular contexts (See Khoe ¶0038). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Khoe to further understands the user’s usage of language in different contexts.
Claims 6, 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Banga et al. (US 20080262901 A1) (hereafter Banga), in view of Pasternack et al. (US 20200401657 A1) (hereafter Pasternack), in view of Marttila (US 20130189652 A1) (hereafter Marttila), in view of Sarikaya (US 20180061421 A1) (hereafter Sarikaya), in view of Bojja et al. (WO 2018067440 A1) (hereafter Bojja), in view of Isaacson et al. (US 20170236196 A1) (hereafter Isaacson), in view of Bojja et al. (WO 2018067440 A1) (hereafter Bojja), in view of Ginsberg (US 20180204568 A1) (hereafter Ginsberg), in view of Park (US 20100173613 A1) (hereafter Park).
As per claim 6:
The computer-implemented method as recited in claim 1, wherein the plurality of language attributes comprises
language proficiency in the plurality of languages across the vernacular contexts of each of the plurality of users, (See Marttila claim 1, “A method where, in order to measure or define the language proficiency of a person under investigation, particularly the degree of flawlessness in his/her pronunciation and/or in order to investigate the person's own language background and identity, the speech of the person under investigation is compared with a speech sample of a selected reference language, characterized in that from an electronic speech sample of a reference language, there are identified and registered, by using autocorrelation and/or pattern recognition and/or signal processing or some other corresponding method, such sound elements and linguistic features that are repeatedly represented in the reference language speech sample and are typical of said language, and on the basis of the obtained linguistic profile of the reference language, corresponding sound elements and/or linguistic features are searched from an electronically recorded speech sample of the person under investigation, and/or there is defined which of the sound elements or linguistic features of the linguistic profile of the reference language the person under investigation substitutes with such sound elements or linguistic features that deviate from the reference language, and/or there is defined what these substitute sound elements and linguistic features are.” Marttila teaches determining language proficiency of the user.)
a regional dialect across the vernacular contexts of each of the plurality of users, (See Marttila ¶0029, “Unless otherwise stated, the concept `language` refers to a language corresponding to dictionary meanings, i.e. a national language or an official language, as well as to language variations, spoken languages, and languages of different social groups, such as the language spoken at home, youth language, different dialects and slangs.” Marttila teaches the concept of determining dialect information.)
pitch of the audio data,
tone of the audio data,
intensity of the audio data,
(See Marttila ¶0043, “Prosody and prosodic include the stress and timing of words, the length of word elements, tone and pitch of voice, melody and intonation as well as any intensifying of communication or complementing of significance that is carried out by means of said language features. Prosodic features vary in the languages of the world. There is no prosodic feature that would occur in all languages of the world. For example, in Finnish intonation does not carry meaning, but in French a declaratory sentence can be converted to interrogative by raising the intonation towards the end of the sentence. Prosodic features are linguistic features.” Marttila teaches the concept of determining tone, pitch, and intensity of audio information.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson discloses the above-enclosed invention, including the concept of performing audio signal analysis (See Marttila ¶0034), the combination fails to explicitly disclose determining frequency, wavelength, and amplitude of the audio data.
However Ginsberg as shown, which talks about performing speech analysis, teaches determining and analyzing frequency, wavelength, and amplitude of the audio data.
frequency of the audio data,
wavelength of the audio data,
amplitude of the audio data,
(See Ginsberg ¶0024, “Referring now to FIG. 4, the wavelength image data is represented by the waveform. For each word articulated by the subject, one frame of sampled speech 34 is processed. The waveform is a curve showing the shape of a wave at a given time. The vertical scale represents sound pressure, the horizontal scale represents time. FIG. 4 shows the sound pressure of a particular tone relative to the atmospheric pressure. The magnitude of the sound pressure alterations, measured from 0, is known as amplitude, which corresponds roughly to loudness or audibility. Brief moments of silence occur during occlusions of unvoiced stop constants, or regular breathing pauses dependable on audible respiration. The frequency of a periodic wave is the number of cycles that occur per second, represented by Hertz. Most speech activity occurs between 100 Hz and 8000 Hz. A transient is a sudden and brief burst of acoustic energy that occur in speech as the plosive releases of stop consonants.” Ginsberg teaches the concept of determining and determining frequency, wavelength, and amplitude of voice data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ginsberg with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson. As shown, Marttila teaches the concept of performing voice analysis including audio signal analysis. Ginsberg further teaches performing audio signal analysis and using said information with visual lip tracking to further improve the identification of language proficiency (See Ginsberg ¶0004-¶0005). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ginsberg to further improve the analysis and identification user language profiles by further improving the accuracy of proficiency determination.
an accent associated with each of the plurality of users, (See Sarikaya ¶0023, “According to additional examples, a plurality of user background characteristic and trait models may be used to identify user background characteristics and traits for a specific user. For example, a prebuilt gender detection model may determine whether a specific user is male or female. An age detection model may determine the age or age group for a specific user. An accent detection model may determine an accent for a specific user (e.g., southern, immigrant, Indian, Chinese, German, French, etc.). Other user background characteristic models may also be used to identify additional background traits and characteristics of a user as more fully described below. This information may be compiled into a voice-based profile for each specific user of a group of users.” Sarikaya teaches the concept of determining accent of users.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, Isaacson, and Ginsberg discloses the above-enclosed invention, the combination fails to explicitly disclose determining speed and tempo data of users.
However Park as shown, which talks about analyzing voice patterns for phonebook updating, teaches the concept of determining accent, speed, and tempo data of users.
speed of the audio data, and
tempo of the audio data.
(See Park ¶0020, “The term `voice pattern` refers to data to identify a voice of other party. Differences in the structure of the larynx, vocal tract and articulators lead to different voice characteristics. That is, people have different voice patterns due to the different lengths and features of vocal cords. Portable terminals can extract a voice pattern from a received voice signal and identify a voice of the other party. The voice pattern can include a plurality of parameters, such as, a sound pitch (frequency), a sound intensity (amplitude), a voice tone (inherent characteristic of a waveform), speed of pronunciation, pronunciation features (tempo, intonation, accent, the use of words), and the like.” Park teaches the concept of identifying voice patterns including the parameters of tempo, accent, and speed.)
Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Park with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, Isaacson, and Ginsberg as the claimed invention is merely a combination of old elements, and in combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. As shown, the combination discloses the concept of performing voice audio analysis including identifying specific parameters of a voice/audio sample. Park further teaches additional parameters which further define the voice pattern/profile of a user. Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Park as Park further teaches additional known parameters which further define specific voice and language characteristics of users used to distinguish users.
As per claim 15:
The computer system as recited in claim 10, wherein the plurality of language attributes comprises
language proficiency in the plurality of languages across the vernacular contexts of each of the plurality of users, (See Marttila claim 1, “A method where, in order to measure or define the language proficiency of a person under investigation, particularly the degree of flawlessness in his/her pronunciation and/or in order to investigate the person's own language background and identity, the speech of the person under investigation is compared with a speech sample of a selected reference language, characterized in that from an electronic speech sample of a reference language, there are identified and registered, by using autocorrelation and/or pattern recognition and/or signal processing or some other corresponding method, such sound elements and linguistic features that are repeatedly represented in the reference language speech sample and are typical of said language, and on the basis of the obtained linguistic profile of the reference language, corresponding sound elements and/or linguistic features are searched from an electronically recorded speech sample of the person under investigation, and/or there is defined which of the sound elements or linguistic features of the linguistic profile of the reference language the person under investigation substitutes with such sound elements or linguistic features that deviate from the reference language, and/or there is defined what these substitute sound elements and linguistic features are.” Marttila teaches determining language proficiency of the user.)
a regional dialect across the vernacular contexts of each of the plurality of users, (See Marttila ¶0029, “Unless otherwise stated, the concept `language` refers to a language corresponding to dictionary meanings, i.e. a national language or an official language, as well as to language variations, spoken languages, and languages of different social groups, such as the language spoken at home, youth language, different dialects and slangs.” Marttila teaches the concept of determining dialect information.)
pitch of the audio data,
tone of the audio data,
intensity of the audio data,
(See Marttila ¶0043, “Prosody and prosodic include the stress and timing of words, the length of word elements, tone and pitch of voice, melody and intonation as well as any intensifying of communication or complementing of significance that is carried out by means of said language features. Prosodic features vary in the languages of the world. There is no prosodic feature that would occur in all languages of the world. For example, in Finnish intonation does not carry meaning, but in French a declaratory sentence can be converted to interrogative by raising the intonation towards the end of the sentence. Prosodic features are linguistic features.” Marttila teaches the concept of determining tone, pitch, and intensity of audio information.)
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson discloses the above-enclosed invention, including the concept of performing audio signal analysis (See Marttila ¶0034), the combination fails to explicitly disclose determining frequency, wavelength, and amplitude of the audio data.
However Ginsberg as shown, which talks about performing speech analysis, teaches determining and analyzing frequency, wavelength, and amplitude of the audio data.
frequency of the audio data,
wavelength of the audio data,
amplitude of the audio data,
(See Ginsberg ¶0024, “Referring now to FIG. 4, the wavelength image data is represented by the waveform. For each word articulated by the subject, one frame of sampled speech 34 is processed. The waveform is a curve showing the shape of a wave at a given time. The vertical scale represents sound pressure, the horizontal scale represents time. FIG. 4 shows the sound pressure of a particular tone relative to the atmospheric pressure. The magnitude of the sound pressure alterations, measured from 0, is known as amplitude, which corresponds roughly to loudness or audibility. Brief moments of silence occur during occlusions of unvoiced stop constants, or regular breathing pauses dependable on audible respiration. The frequency of a periodic wave is the number of cycles that occur per second, represented by Hertz. Most speech activity occurs between 100 Hz and 8000 Hz. A transient is a sudden and brief burst of acoustic energy that occur in speech as the plosive releases of stop consonants.” Ginsberg teaches the concept of determining and determining frequency, wavelength, and amplitude of voice data.)
Therefore it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ginsberg with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, and Isaacson. As shown, Marttila teaches the concept of performing voice analysis including audio signal analysis. Ginsberg further teaches performing audio signal analysis and using said information with visual lip tracking to further improve the identification of language proficiency (See Ginsberg ¶0004-¶0005). Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Ginsberg to further improve the analysis and identification user language profiles by further improving the accuracy of proficiency determination.
Although the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, Isaacson, and Ginsberg discloses the above-enclosed invention, the combination fails to explicitly disclose determining accent, speed, and tempo data of users.
However Park as shown, which talks about analyzing voice patterns for phonebook updating, teaches the concept of determining accent, speed, and tempo data of users.
an accent associated with each of the plurality of users,
speed of the audio data, and
tempo of the audio data.
(See Park ¶0020, “The term `voice pattern` refers to data to identify a voice of other party. Differences in the structure of the larynx, vocal tract and articulators lead to different voice characteristics. That is, people have different voice patterns due to the different lengths and features of vocal cords. Portable terminals can extract a voice pattern from a received voice signal and identify a voice of the other party. The voice pattern can include a plurality of parameters, such as, a sound pitch (frequency), a sound intensity (amplitude), a voice tone (inherent characteristic of a waveform), speed of pronunciation, pronunciation features (tempo, intonation, accent, the use of words), and the like.” Park teaches the concept of identifying voice patterns including the parameters of tempo, accent, and speed.)
Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Park with the combination of Banga, Pasternack, Marttila, Sarikaya, Bojja, Isaacson, and Ginsberg as the claimed invention is merely a combination of old elements, and in combination each element merely would have performed the same function as it did separately, and one of ordinary skill in the art would have recognized that the results of the combination were predictable. As shown, the combination discloses the concept of performing voice audio analysis including identifying specific parameters of a voice/audio sample. Park further teaches additional parameters which further define the voice pattern/profile of a user. Thus it would have been obvious to one of ordinary skill in the art at the time of the invention to have utilized the teachings of Park as Park further teaches additional known parameters which further define specific voice and language characteristics of users used to distinguish users.
Response to Arguments
Applicant's arguments filed 11/17/2025 have been fully considered but they are not persuasive.
In response to the Applicant’s arguments as directed towards the 35 U.S.C. 101 rejection, the Examiner respectfully disagrees. The Applicant asserts the claimed invention is not directed towards a certain method of organizing human activity as the claimed invention requires specific technological implementation such as the collection and analysis of information using machine learning including utilizing multiple large data sets. The Examiner notes as discussed in MPEP 2106.05(a), the ability of a computer to take in and process large qualities of information does not render a claim patent eligible (as discussed FairWarning IP, LLC v. Iatric Sys., 839 F.3d 1089, 1095, 120 USPQ2d 1293, 1296 (Fed. Cir. 2016) and Credit Acceptance Corp. v. Westlake Services, 859 F.3d 1044, 1055, 123 USPQ2d 1100, 1108-09 (Fed. Cir. 2017)). Still furthermore, as discussed in Example 48 of the July 2024 SME, the recitation of using a machine learning algorithm is still abstract as this is still utilizing a specific formula. Still furthermore, although the claims further recite the step of dynamically modulating audio, this is still abstract as this is managing interactions with people as discussed in Interval Licensing LLC v. AOL, Inc., 193 F. Supp.3d 1184, 1188 (W.D. 2014). As such, the Examiner asserts the invention as claimed is directed towards a judicial exception.
The Applicant further asserts the claimed invention is integrated into a practical application. The Applicant asserts the claimed invention requires a concrete, rule-bound, multi-stage workflow to ultimately produce the dynamic modulation of audio content. The Examiner notes that the production and modification content including providing of content does not automatically integrate an abstract idea into a practical application as discussed in Content Extraction, 776 F.3d at 1345, 113 USPQ2d at 1356 and Intellectual Ventures I v. Capital One Fin. Corp., 850 F.3d 1332, 121 USPQ2d 1940 (Fed. Cir. 2017). Furthermore, the recitation of machine learning, even while reciting the inputs and outputs of the machine learning, is still recited at a high level of generality similar to Examples 48 and 49 of the July 2024 SME Update. Still furthermore, although the claimed invention further recites modulating the audio content based on user accent information, this is still abstract as this is similar to Example 4 of the July 2024 SME, wherein the limitation does not specifically limit how the modulation occurs and does not provide meaningful constraints on how the use of accent information further improves the functioning of online platforms. Still furthermore, although the claims further recite the step of dynamically modulating audio, this fails to recite how a solution to a problem is accomplished. As discussed in MPEP 2106.05(f), the modification of dynamic content does not integrate an abstract idea into a practical application (as discussed in Intellectual Ventures I v. Capital One Fin. Corp., 850 F.3d 1332, 121 USPQ2d 1940 (Fed. Cir. 2017)). As such, the Examiner further asserts the claimed invention is not integrated into a practical application.
The Applicant further asserts the claimed invention is significantly more as the ordered combination of steps and dynamically modulating the audio is a technical transformation of content. The Examiner notes as currently claimed, the step of dynamically modulating the audio content, as discussed in page 34 line 17, the “modulating” is described as selecting particular audio and video files to be provided based on the profiling of the user. This is still directed towards the collection and analysis of information and providing targeted content to consumers similar to Mortgage Grader, 811 F.3d at 1318, 117 USPQ2d at 1695. Still furthermore, although the invention does recite utilizing computer technology, the invention as claimed is not directed towards an improvement in the functioning of a computer or other technology as defined in MPEP 2106.05(a). Thus the Examiner asserts the claimed invention is not significantly more than the judicial exception.
As such, the Examiner has determined the claimed invention to be directed towards a judicial exception without significantly more and the 35 U.S.C. 101 rejection has been maintained.
Applicant’s arguments with respect to claim(s) 1-4, 6, 8, 10-13, 15, 17, 19 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. In response to the Applicant’s arguments as directed towards the 35 U.S.C. 103 rejection, the Examiner notes Isaacson teaches the concept of providing dynamic interactions including the concept of utilizing different accents based on language processing as shown above.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to VINCENT M CAO whose telephone number is (571)270-5598. The examiner can normally be reached Monday - Friday 11-7.
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, ILANA SPAR can be reached at (571) 270-7537. 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.
/VINCENT M CAO/ Primary Examiner, Art Unit 3622