Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
Claims 1-20 are present in this application. Claims 1-20 are pending in this office
action.
This office action is NON-FINAL.
Drawings
The Drawings filed on 01/18/24 are acceptable for examination purposes.
Specification
The Specification filed on 01/18/24 is acceptable for examination purposes.
Information Disclosure Statement
The information disclosure statements (IDS) filed on 09/13/24 has been considered by the Examiner and made of record in the application file.
Claim Rejections 35 U.S.C. §103
6. In the event the determination of the status of the application as subject to AIA 35
U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any
correction of the statutory basis for the rejection will not be considered a new ground of
rejection if the prior art relied upon, and the rationale supporting the rejection, would be
the same under either status.
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 following is a quotation of 35 U.S.C. 103 which forms the basis for all
obviousness rejections set forth in this Office action:
Claims 1-20 are rejected under 35 U.S.C. 103 as being unpatentable over GHOSHAL et al. (US 2022/0012268 A1) in view of Mandal et al. (US 2025/0209300 A1).
Regarding claim 1, GHOSHAL teaches a computer-implemented method, the computer-implemented method comprising:
generating, by one or more processors, a set of recommendation data objects for a user identifier associated with a user interface, (See GHOSHAL paragraph [0136], a user has authored a new article via the user interface 415, and a set of article topics has been identified by an AI-based REST service invoked by the content recommendation engine 425), based on a set of predefined rules associated with input data provided via a user interface workflow associated with the user interface, (See GHOSHAL paragraph [0118], a content authoring user interface 415 or other front end interface may determine one or more content tags based on the input received via the interface. In this example, a single content tag (“waitress”) is determine from the received user input);
generating, by the one or more processors and using a machine learning model, (See GHOSHAL paragraph [0236], For each machine learning model or model type, the trained models may be executed by one or more computing systems), a ranked version of the set of recommendation data objects based on (i) the input data, (See GHOSHAL paragraph [0221], For a content recommendation system that is configured to recommend specific content (content items) in response to input from a client or user, the process of evaluating and ranking the content items relative to each other plays an important role in the overall recommendation),
initiating, by the one or more processors and via the user interface, (See GHOSHAL paragraph [0251], the user interface 4410 may correspond to an interface for a word processor), a rendering of a set of selectable graphical elements based on the ranked version of the set of recommendation data objects, (See GHOSHAL paragraph [0282], the content recommendation system 4220 (e.g., the recommendation selector 4225) may use the ranked list generated in 4316 to select one or more content items to be recommended to the user. In certain scenarios, all the content items in the ranked list may be selected for recommendation).
GHOSHAL does not explicitly disclose (ii) a user behavior data associated with the user identifier, and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects.
However, Mandal teaches (ii) a user behavior data associated with the user identifier, (See Mandal paragraph [0064], a graph embedding structure characterizes each user's behavior including the user's comments, queries, interactions, associations), and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects, (See Mandal paragraph [0061], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…a graphical data structure may be used to generate a graph feature set that includes one or more features associated with the graph data of the graphical data structure); and
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify (ii) a user behavior data associated with the user identifier, and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 2, GHOSHAL taught the computer-implemented method of claim 1, as described above. GHOSHAL further teaches wherein generating the ranked version of the set of recommendation data objects, (See GHOSHAL paragraph [0238], a recommended content item identifier and ranker subsystem 4224 (which may be referred to for brevity as the content item ranker 4224), and (iii) the domain features set to generate the ranked version of the set of recommendation data objects, (See GHOSHAL paragraph [0242], The content item ranker 4224 is configured to generate a ranked list of content items to be recommended to the user in response to the user input received for the user).
GHOSHAL does not explicitly disclose comprises: applying learning-to-rank machine learning to (i) the input data, (ii) the user behavior data.
However, Mandal teaches comprises: applying learning-to-rank machine learning to (i) the input data, (ii) the user behavior data, (See Mandal paragraph [0064], a graph embedding structure characterizes each user's behavior including the user's comments, queries, interactions, associations, or the like).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify comprises: applying learning-to-rank machine learning to (i) the input data, (ii) the user behavior data of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Claim 9 recites the same limitations as claim 2 above. Therefore, claim
9 is rejected based on the same reasoning.
Regarding claim 3, GHOSHAL taught the computer-implemented method of claim 1, as described above. GHOSHAL further teaches wherein generating the ranked version of the set of recommendation data objects comprises, (See GHOSHAL paragraph [0238], a recommended content item identifier and ranker subsystem 4224 (which may be referred to for brevity as the content item ranker 4224): generating, using the machine learning model, (See GHOSHAL paragraph [0236], a model training system may generate one or more models, which may be trained in advance using machine-learning), the ranked version of the set of recommendation data objects based on (i) the input data, (See GHOSHAL paragraph [0242], The content item ranker 4224 is configured to generate a ranked list of content items to be recommended to the user in response to the user input received for the user).
GHOSHAL does not explicitly disclose (ii) the user behavior data, (iii) the domain features set, and (iv) a demographics features set associated with the input data. However, Mandal teaches (ii) the user behavior data, (iii) the domain features set, and (iv) a demographics features set associated with the input data, (See Mandal paragraph [0061], Graphical data structures may be related to events and/or other dynamic data related to an application framework. Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify (ii) the user behavior data, (iii) the domain features set, and (iv) a demographics features set associated with the input data of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Claim 10 recites the same limitations as claim 3 above. Therefore, claim
10 is rejected based on the same reasoning.
Regarding claim 4, GHOSHAL taught the computer-implemented method of claim 1, as described above.
GHOSHAL does not explicitly disclose further comprising: receiving the user behavior data from a third-party data source; transforming the user behavior data into a user behavior features set; and applying the machine learning model to the user behavior features set.
However, Mandal teaches further comprising: receiving the user behavior data from a third-party data source; (See Mandal paragraph [0061], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services), transforming the user behavior data into a user behavior features set; and applying the machine learning model to the user behavior features set, (See Mandal paragraph [0028], The graphical representation layer can also interact with a deep learning model, a machine learning API system, one or more augmentation or transformation layers, data stores (e.g., graph store layer), machine learning models, See Mandal paragraph [0061], Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify further comprising: receiving the user behavior data from a third-party data source; transforming the user behavior data into a user behavior features set; and applying the machine learning model to the user behavior features set of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Claim 11 recites the same limitations as claim 4 above. Therefore, claim
11 is rejected based on the same reasoning.
Regarding claim 5, GHOSHAL taught the computer-implemented method of claim 1, as described above.
GHOSHAL does not explicitly disclose wherein the user behavior data comprises a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, and wherein generating the ranked version of the set of recommendation data objects, comprises: applying the machine learning model to the set of binary encodings.
However, Mandal teaches further teaches wherein the user behavior data, (See Mandal paragraph [0061], Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services), comprises a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, (See Mandal paragraph [0082], a user identifier, a component identifier, a page or document identifier, one or more object types, feature extraction data, one or more text features, one or more numeric features, binary encoding data, text vectorization data, segmentation data, one or more NLP features, word encodings), and wherein generating the ranked version of the set of recommendation data objects, (See Mandal paragraph [0139], The message may be configured, for example, to render visual data associated with the respective response data objects 904 via a user interface of the client device…the visual data may be related to a resolution and/or a ranked list of recommended resolutions for an incident), comprises: applying the machine learning model to the set of binary encodings, (See Mandal paragraph [0082], one or more numeric features, binary encoding data, text vectorization data, segmentation data, one or more NLP features, word encodings).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify wherein the user behavior data comprises a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, and wherein generating the ranked version of the set of recommendation data objects, comprises: applying the machine learning model to the set of binary encodings of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 6, GHOSHAL taught the computer-implemented method of claim 1, as described above.
GHOSHAL does not explicitly disclose further teaches wherein the user behavior data comprises website activity data associated with the user identifier, and wherein generating the ranked version of the set of recommendation data objects comprises, applying the machine learning model to the website activity data.
However, Mandal teaches further teaches wherein the user behavior data comprises website activity data associated with the user identifier, (See Mandal paragraph [0082], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services), and wherein generating the ranked version of the set of recommendation data objects comprises, (See Mandal paragraph [0139], The message may be configured, for example, to render visual data associated with the respective response data objects 904 via a user interface of the client device…the visual data may be related to a resolution and/or a ranked list of recommended resolutions for an incident): applying the machine learning model to the website activity data, (See Mandal paragraph [0082], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify wherein the user behavior data comprises website activity data associated with the user identifier, and wherein generating the ranked version of the set of recommendation data objects comprises, applying the machine learning model to the website activity data of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 7, GHOSHAL taught the computer-implemented method of claim 1, as described above. GHOSHAL further teaches wherein initiating the rendering of the set of selectable graphical elements comprises, (See GHOSHAL paragraph [0243], the recommendation selector 4225 is configured to select one or more particular content items): transmitting the ranked version of the set of recommendation data objects to an application programming interface (API) associated with the user interface, (See GHOSHAL paragraph [0134], the content recommendation engine 425 may transmit the determined image tag(s) to a search API associated with an image content repository 440…transmitted back and embedded within the user interface at 415 (at screen region 2810)).
Regarding claim 8, GHOSHAL teaches a computing system comprising memory and one or more processors communicatively coupled to the memory, the one or more processors configured to, (See GHOSHAL paragraph [0456], perform the operation, such as by executing computer instructions or code, or processors or cores programmed to execute code or instructions stored on a non-transitory memory…for inter-process communication):
generate a set of recommendation data objects for a user identifier associated with a user interface, (See GHOSHAL paragraph [0136], a user has authored a new article via the user interface 415, and a set of article topics has been identified by an AI-based REST service invoked by the content recommendation engine 425), based on a set of predefined rules associated with input data provided via a user interface workflow associated with the user interface, (See GHOSHAL paragraph [0118], a content authoring user interface 415 or other front end interface may determine one or more content tags based on the input received via the interface. In this example, a single content tag (“waitress”) is determine from the received user input);
generate, using a machine learning model, (See GHOSHAL paragraph [0236], For each machine learning model or model type, the trained models may be executed by one or more computing systems), a ranked version of the set of recommendation data objects based on (i) the input data, (See GHOSHAL paragraph [0221], For a content recommendation system that is configured to recommend specific content (content items) in response to input from a client or user, the process of evaluating and ranking the content items relative to each other plays an important role in the overall recommendation),
initiate, via the user interface, a rendering of a set of selectable graphical elements based on the ranked version of the set of recommendation data objects, See GHOSHAL paragraph [0285], (the content recommendation system 4220 has selected, from the ranked list of images, the four highest-ranked content item images for recommendation to the user. Information related to these top four ranked images is displayed in order of their rank within a dedicated portion 4714 of the user interface 4700 for showing content item recommendations).
GHOSHAL does not explicitly disclose (ii) a user behavior data associated with the user identifier, and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects.
However, Mandal teaches (ii) a user behavior data associated with the user identifier, (See Mandal paragraph [0064], a graph embedding structure characterizes each user's behavior including the user's comments, queries, interactions, associations), and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects, (See Mandal paragraph [0061], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…a graphical data structure may be used to generate a graph feature set that includes one or more features associated with the graph data of the graphical data structure); and
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify (ii) a user behavior data associated with the user identifier, and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 12, GHOSHAL taught the computing system of claim of claim 8, as described above.
GHOSHAL does not explicitly disclose wherein the user behavior data comprises a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, and the one or more processors further configured to: apply the machine learning model to the set of binary encodings.
However, Mandal teaches further teaches wherein the user behavior data, (See Mandal paragraph [0061], Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services), comprises a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, (See Mandal paragraph [0082], a user identifier, a component identifier, a page or document identifier, one or more object types, feature extraction data, one or more text features, one or more numeric features, binary encoding data, text vectorization data, segmentation data, one or more NLP features, word encodings), and wherein generating the ranked version of the set of recommendation data objects, (See Mandal paragraph [0139], The message may be configured, for example, to render visual data associated with the respective response data objects 904 via a user interface of the client device…the visual data may be related to a resolution and/or a ranked list of recommended resolutions for an incident), and the one or more processors, (See Mandal paragraph [0088], one or more processors), further configured to: apply the machine learning model to the set of binary encodings, (See Mandal paragraph [0082], one or more numeric features, binary encoding data, text vectorization data, segmentation data, one or more NLP features, word encodings).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify wherein the user behavior data comprises a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, and the one or more processors further configured to: apply the machine learning model to the set of binary encodings of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 13, GHOSHAL taught the computer-implemented method of claim 8, as described above.
GHOSHAL does not explicitly disclose further teaches wherein the user behavior data comprises website activity data associated with the user identifier, and the one or more processors further configured to: apply the machine learning model to the website activity data.
However, Mandal teaches further teaches wherein the user behavior data comprises website activity data associated with the user identifier, (See Mandal paragraph [0082], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services), and the one or more processors further configured to: apply the machine learning model to the website activity data, (See Mandal paragraph [0082], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify further teaches wherein the user behavior data comprises website activity data associated with the user identifier, and the one or more processors further configured to: apply the machine learning model to the website activity data of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 14, GHOSHAL taught the computing system of claim 8, as described above. GHOSHAL further teaches the one or more processors further configured to, (See Mandal paragraph [0088], one or more processors):
transmit the ranked version of the set of recommendation data objects to an application programming interface (API) associated with the user interface, (See GHOSHAL paragraph [0134], the content recommendation engine 425 may transmit the determined image tag(s) to a search API associated with an image content repository 440…transmitted back and embedded within the user interface at 415 (at screen region 2810)).
.
Regarding claim 15, GHOSHAL teaches One or more non-transitory computer-readable storage media including instructions that, when executed by one or more processors, cause the one or more processors to, (See GHOSHAL paragraph [0456], perform the operation, such as by executing computer instructions or code, or processors or cores programmed to execute code or instructions stored on a non-transitory memory medium),
generate a set of recommendation data objects for a user identifier associated with a user interface, (See GHOSHAL paragraph [0136], a user has authored a new article via the user interface 415, and a set of article topics has been identified by an AI-based REST service invoked by the content recommendation engine 425), based on a set of predefined rules associated with input data provided via a user interface workflow associated with the user interface; (See GHOSHAL paragraph [0118], a content authoring user interface 415 or other front end interface may determine one or more content tags based on the input received via the interface. In this example, a single content tag (“waitress”) is determine from the received user input);
generate, using a machine learning model, (See GHOSHAL paragraph [0236], For each machine learning model or model type, the trained models may be executed by one or more computing systems), a ranked version of the set of recommendation data objects based on (i) the input data, (See GHOSHAL paragraph [0221], For a content recommendation system that is configured to recommend specific content (content items) in response to input from a client or user, the process of evaluating and ranking the content items relative to each other plays an important role in the overall recommendation),
initiate, via the user interface, a rendering of a set of selectable graphical elements based on the ranked version of the set of recommendation data objects, See GHOSHAL paragraph [0285], (the content recommendation system 4220 has selected, from the ranked list of images, the four highest-ranked content item images for recommendation to the user. Information related to these top four ranked images is displayed in order of their rank within a dedicated portion 4714 of the user interface 4700 for showing content item recommendations).
GHOSHAL does not explicitly disclose (ii) a user behavior data associated with the user identifier, and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects.
However, Mandal teaches ii) a user behavior data associated with the user identifier, (See Mandal paragraph [0064], a graph embedding structure characterizes each user's behavior including the user's comments, queries, interactions, associations), and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects, (See Mandal paragraph [0061], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…a graphical data structure may be used to generate a graph feature set that includes one or more features associated with the graph data of the graphical data structure); and
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify (ii) a user behavior data associated with the user identifier, and (iii) a domain features set associated with respective domain classifications for the set of recommendation data objects of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 16, GHOSHAL taught the one or more non-transitory computer-readable storage media of claim 15, as described above. GHOSHAL further teaches
wherein the one or more processors are further caused to, (See Mandal paragraph [0002], one or more processors), and (iii) the domain features set to generate the ranked version of the set of recommendation data objects, . (See GHOSHAL paragraph [0242], The content item ranker 4224 is configured to generate a ranked list of content items to be recommended to the user in response to the user input received for the user).
GHOSHAL does not explicitly disclose :apply learning-to-rank machine learning to (i) the input data, (ii) the user behavior data.
However, Mandal teaches apply learning-to-rank machine learning to (i) the input data, (ii) the user behavior data, (See Mandal paragraph [0064], a graph embedding structure characterizes each user's behavior including the user's comments, queries, interactions, associations, or the like).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify apply learning-to-rank machine learning to (i) the input data, (ii) the user behavior data of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 17, GHOSHAL taught the one or more non-transitory computer-readable storage media of claim 15, as described above. GHOSHAL further teaches wherein the one or more processors are further caused to, (See Mandal paragraph [0002], one or more processors),
generate, using the machine learning model, (See GHOSHAL paragraph [0236], a model training system may generate one or more models, which may be trained in advance using machine-learning), the ranked version of the set of recommendation data objects based on (i) the input data, (See GHOSHAL paragraph [0242], The content item ranker 4224 is configured to generate a ranked list of content items to be recommended to the user in response to the user input received for the user).
GHOSHAL does not explicitly disclose (ii) the user behavior data, (iii) the domain features set, and (iv) a demographics features set associated with the input data.
However, Mandal teaches (ii) the user behavior data, (iii) the domain features set, (See Mandal paragraph [0064], a graph embedding structure characterizes each user's behavior including the user's comments, queries, interactions, associations, or the like), and (iv) a demographics features set associated with the input data, (See Mandal paragraph [0061], Graphical data structures may be related to events and/or other dynamic data related to an application framework. Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify (ii) the user behavior data, (iii) the domain features set, and (iv) a demographics features set associated with the input data of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 18, GHOSHAL taught the one or more non-transitory computer-readable storage media of claim 15, as described above. GHOSHAL further teaches wherein the one or more processors are further caused to, (See Mandal paragraph [0002], one or more processors).
GHOSHAL does not explicitly disclose receive the user behavior data from a third-party data source; transform the user behavior data into a user behavior features set; and apply the machine learning model to the user behavior features set.
However, Mandal teaches receive the user behavior data from a third-party data source; (See Mandal paragraph [0061], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services), transform the user behavior data into a user behavior features set; and apply the machine learning model to the user behavior features set, (See Mandal paragraph [0028], The graphical representation layer can also interact with a deep learning model, a machine learning API system, one or more augmentation or transformation layers, data stores (e.g., graph store layer), machine learning models, See Mandal paragraph [0061], Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify receive the user behavior data from a third-party data source; transform the user behavior data into a user behavior features set; and apply the machine learning model to the user behavior features set of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 19, GHOSHAL taught the one or more non-transitory computer-readable storage media of claim 15, as described above.
GHOSHAL does not explicitly disclose wherein the user behavior data comprises a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, and the one or more processors are further caused to: apply the machine learning model to the set of binary encodings.
However, Mandal teaches further teaches wherein the user behavior data comprises, (See Mandal paragraph [0064], a graph embedding structure characterizes each user's behavior including the user's comments, queries, interactions, associations, or the like), a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, (See Mandal paragraph [0082], a user identifier, a component identifier, a page or document identifier, one or more object types, feature extraction data, one or more text features, one or more numeric features, binary encoding data, text vectorization data, segmentation data, one or more NLP features, word encodings), and the one or more processors, (See Mandal paragraph [0002], one or more processors), are further caused to: apply the machine learning model to the set of binary encodings, (See Mandal paragraph [0082], one or more numeric features, binary encoding data, text vectorization data, segmentation data, one or more NLP features, word encodings).
It would have been obvious to one with ordinary skill in the art before the effective filing date of the claimed invention was made, to modify wherein the user behavior data comprises a set of binary encodings for particular attributes related to one or more different user interface workflows associated with the user identifier, and the one or more processors are further caused to: apply the machine learning model to the set of binary encodings of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Regarding claim 20, GHOSHAL taught the one or more non-transitory computer-readable storage media of claim 15, as described above.
GHOSHAL does not explicitly disclose wherein the user behavior data comprises website activity data associated with the user identifier, and the one or more processors are further caused to: apply the machine learning model to the website activity data.
However, Mandal teaches further teaches wherein the user behavior data comprises website activity data associated with the user identifier, (See Mandal paragraph [0082], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services), and the one or more processors (See Mandal paragraph [0002], one or more processors), are further caused to: apply the machine learning model to the website activity data, (See Mandal paragraph [0082], a graphical data structure may be based on data within one or more graph stores descriptive of historical user interactions…Graphical data structures may be used to characterize behaviors of users and or relationships across multiple domains of interactions and services).
It would have been obvious to one with ordinary skill in the art before the
effective filing date of the claimed invention was made, to modify wherein the user behavior data comprises website activity data associated with the user identifier, and the one or more processors are further caused to: apply the machine learning model to the website activity data of Mandal in order to provide the graph embedding structure to one or more machine learning models…to generate one or more predictive inferences related to the graph data.
Conclusions/Points of Contacts
The prior art made of record and not relied upon is considered pertinent to
applicant’s disclosure. See form PTO-892.
Xu et al. (US 2022/0253721 A1), tem recommendations can assist a user when selecting items online. For example, when a user views an anchor item, one or more recommended items can be displayed, which can be items that are similar and/or complementary to the anchor item. Many recommendations models are used conventionally.
ALAHMADY (US 2021/0304285 A1) provide a recommendation platform that utilizes machine learning models to generate content package recommendations for current and prospective customers. For example, the recommendation platform may receive, from a user device, user data and a request associated with content, where the user data may identify an action of a user of the user device, a behavior of the user, a feature associated with the user.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MULUEMEBET GURMU whose telephone number is (571)270-7095. The examiner can normally be reached M-F 9am - 5pm.
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, Tony Mahmoudi can be reached at 5712724078. 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.
/MULUEMEBET GURMU/Primary Examiner, Art Unit 2163
Prosecution Insights