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 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Step 1: Claims 1-20 are within the four statutory categories (a process, machine, manufacture or composition of matter)
As to claim 1:
Step 2A Prong 1: this claim recites the following abstract ideas:
Generating synthetic data based on abandoned web activity data (The step of generating data is a mental process that can be performed in the human mind with the physical aid of pen and paper.)
determining that the user abandoned a user activity included in the web activity data for the user, wherein an abandoned user activity relates to a web page that the user has accessed but not returned to for a threshold period of time (The step of determining whether a user abandoned a web activity is a mental process that can be performed in the human mind. The step of wherein a user abandoned a web activity but not returned for a threshold period of time is directed to a mathematical concept.)
inserting, into abandoned web activity data for a plurality of users, the abandoned user activity (The step of inserting data is a mental process that can be performed in the human mind with the physical aid of pen and paper)
to generate a probability for each entry in the abandoned web activity data, wherein each probability for a corresponding entry of the abandoned web activity data indicates a likelihood that the abandoned user activity would have been completed (The step of generating a probability for each entry is directed to a mathematical concept. The step of wherein the probability indicates likelihood the abandoned user activity would have been completed is directed to a mental process of comparison and evaluation.)
generating a synthetic dataset based on entries of the abandoned web activity data combined with the completed activity data. (The step of generating a dataset is a mental process that can be performed in the human mind with the physical aid of pen and paper)
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
A system for (This limitation functions as mere instructions to implement an abstract idea on a generic computer.)
One or more processors (This limitation is directed to generic processors, which is well-understood, routine, conventional activity)
A non-transitory, computer-readable medium storing instructions ((This limitation is directed to generic non-transitory, computer-readable medium storing instructions, which is well-understood, routine, conventional activity)
one or more processors, cause operations comprising: (This limitation is directed to generic processors, which is well-understood, routine, conventional activity)
receiving web activity data for a user, wherein the web activity data relates to a plurality of web pages accessed by the user (This limitation is directed to transmitting data to a generic computer which is well-understood, routine, conventional activity)
processing, using a first machine learning model, the abandoned web activity data, (The limitation is directed to mere instruction to apply the abstract idea on a generic computer to process data)
The additional limitations do not integrate the judicial exception into a practical application and do not amount to significantly more than the judicial exception.
As to claim 2:
Step 2A Prong 1: this claim recites the following abstract ideas:
Generating synthetic data based on abandoned web activity data (The step of generating data is a mental process that can be performed in the human mind with the physical aid of pen and paper.)
determining that the user abandoned a user activity included in the web activity data for the user, wherein an abandoned user activity relates to a web page that the user has accessed but not returned to for a threshold period of time (The step of determining whether a user abandoned a web activity is a mental process that can be performed in the human mind. The step of wherein a user abandoned a web activity but not returned for a threshold period of time is directed to a mathematical concept.)
inserting, into abandoned web activity data for a plurality of users, the abandoned user activity (The step of inserting data is a mental process that can be performed in the human mind with the physical aid of pen and paper)
to generate a probability for each entry in the abandoned web activity data, wherein each probability for a corresponding entry of the abandoned web activity data indicates a likelihood that the abandoned user activity would have been completed (The step of generating a probability for each entry is directed to a mathematical concept. The step of wherein the probability indicates likelihood the abandoned user activity would have been completed is directed to a mental process of comparison and evaluation.)
generating a synthetic dataset based on entries of the abandoned web activity data combined with the completed activity data. (The step of generating a dataset is a mental process that can be performed in the human mind with the physical aid of pen and paper)
wherein the testing dataset comprises data distinctive from the synthetic dataset, and wherein the completed user activities relate to one or more web pages where the user has completed an action. (The step of wherein testing dataset is different from synthetic dataset is a mental process that can be performed by the human mind with the aid of pen and paper. The step of determining completed user activities is a mental process of comparison and evaluation.)
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
A method for (This limitation functions as mere instructions to implement an abstract idea on a generic computer.)
processing, using a first machine learning model, the abandoned web activity data, (The limitation is directed to mere instruction to apply the abstract idea on a generic computer to process data)
training, a second machine learning model, using the synthetic dataset, and testing, the second machine learning model, using a testing dataset based on completed user activities, (The limitation is directed to mere instruction to apply the abstract idea on a generic computer to process data)
The additional limitations do not integrate the judicial exception into a practical application and do not amount to significantly more than the judicial exception.
As to claim 3:
Step 2A Prong 1: Claim 3, incorporates the rejection of claim 2, and no other abstract ideas.
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
Wherein web activity data relates to a plurality of web pages accessed by the user (The step of wherein data relates to web pages accessed by the user is a field of use limitation that merely restricts tracking web activity to the internet environment)
As to claim 4:
Step 2A Prong 1: Claim 4, incorporates the rejection of claim 2, and recites the following abstract ideas:
determining a first threshold period of time corresponding to a first user activity; and determining a second threshold period of time corresponding to a second user activity, wherein the second threshold period of time is different from the first threshold period of time (The step of determining the first period of time is a mathematical concept. The step of determining the second period of time is a mathematical concept. The step of wherein second threshold period of time is different than first threshold period of time is a mental process of comparison and evaluation)
Step 2A Prong 2 and 2B: this claim recites no additional elements.
As to claim 5:
Step 2A Prong 1: Claim 4, incorporates the rejection of claim 2, and recites the following abstract ideas:
wherein determining that the user abandoned a user activity included in the web activity data for the user further comprises: identifying a web page associated with a user activity after the threshold period of time; and in response to finding no completed user activity corresponding to the user activity, determining that the user has abandoned the user activity (The step of determining the user abandoned a user activity is a mental process that can be performed in the human mind. The step of identifying a web page is a mental process that can be performed in the human mind. The step of threshold period of time is directed to a mathematical calculation. The step of response to finding no completed user activity is a mental process that can be performed by the human mind. The step of determining that the user has abandoned a web activity is a mental process that can be performed in the human mind.)
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
searching a completed user activity database for the user activity; (The step of searching a database is a generic computer function)
As to Claim 6:Step 2A Prong 1: Claim 6, incorporates the rejection of claim 5, and recites the following abstract ideas:
wherein the completed user activity. (Step of wherein the completed user activity database compromises is a mental process which can be performance by the human mind with aid of pen and paper).
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
database comprises a user identifier, a time identifier, and a web page identifier corresponding to each completed user activity. (The step of database compromising is a field of use limitation that merely restricts the data in database to user identifier, time identifier, and web page identifier. The step of corresponding is a field of use limitation that merely restricts web page identifier to completed user activity.)
As to Claim 7:Step 2A Prong 1: Claim 7, incorporates the rejection of claim 2, and recites the following abstract ideas:
with the likelihood that the abandoned user activity would have been completed, wherein each abandoned user activity entry comprises a user identifier, a time identifier, a web page identifier, and an activity identifier corresponding to the abandoned user activity. (The step of likelihood is directed to a mental process of comparison and evaluation. Step of wherein each entry compromises is a mental process which can be performance by the human mind with aid of pen and paper)
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
storing, in an abandoned user activity database, each abandoned user activity entry (The step of storing abandoned user activity entry is a well understood routine and conventional activity of storing data in memory (MPEP 2106.05(d)(II)(iv)).)
As to Claim 8:
Step 2A Prong 1: Claim 8, incorporates the rejection of claim 2, and recites the following abstract ideas:
identifying a missing identifier for a user activity in a completed user activity database; and generating a value for the missing identifier (The step of identify a missing identifier is a mental process that can be performed in the human mind. The step of generating a value is a mental process that can be performed in the human mind with the physical aid of pen and paper.)
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
using a generative adversarial network, wherein the generative adversarial network is trained using the synthetic dataset. (This limitation is directed to a generic neural network architecture which merely represents instructions to apply the abstract idea on a generic computer).
The additional limitations do not integrate the judicial exception into a practical application and do not amount to significantly more than the judicial exception.
As to Claim 9:
Step 2A Prong 1: Claim 9, incorporates the rejection of claim 2, and recites no other abstract ideas.
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
generating for display completed and abandoned user activities on a user device associated with the user (The step of generating data is a well-understood, routine, conventional activity, of displaying data. (2106.05(d)(II)(iv))
transmitting a first request to a completed user activity database for completed user activity entries associated with the user; (This limitation is directed to transmitting data to a generic computer which is well-understood, routine, conventional activity. (2106.05(d)(II)(iv))
transmitting a second request to an abandoned user activity database for abandoned user activity entries associated with the user; (This limitation is directed to transmitting data to a generic computer which is well-understood, routine, conventional activity. (2106.05(d)(II)(iv))
and in response to receiving the completed user activity entries and the abandoned user activity entries, (This limitation is directed to transmitting data to a generic computer which is well-understood, routine, conventional activity. (2106.05(d)(II)(iv))
The additional limitations do not integrate the judicial exception into a practical application and do not amount to significantly more than the judicial exception.
As to Claim 10:
Step 2A Prong 1: Claim 10, incorporates the rejection of claim 2, and recites the following abstract ideas: wherein the output comprises a likelihood for the user to complete a future user activity. (The step of wherein the output comprises a likelihood is directed to a mental process of comparison and evaluation.)
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
generating an output (The step of generating is a well-understood, routine, conventional activity, for making an output (2106.05(d)(II)(iv))
using the second machine learning model, (The limitation is directed to mere instruction to apply the abstract idea on a generic computer)
The additional limitations do not integrate the judicial exception into a practical application and do not amount to significantly more than the judicial exception.
As to Claim 11:
Step 2A Prong 1: Claim 11, incorporates the rejection of claim 2, and recites the following abstract ideas:
wherein determining that a user abandoned a user activity included in web activity data for the user further comprises detecting, in web activity data for the user, an interruption, wherein the interruption is associated with a new user activity, and wherein the new user activity relates to a web page that the user has accessed after an abandoned user activity. (The step of determining whether a user abandoned a web activity is a mental process that can be performed in the human mind. The step of detecting an interruption is a mental process that can be performed in the human mind. The step of wherein new user activity was accessed after abandoned user activity is a mental process that can be performed in the human mind.)
Step 2A Prong 2 and 2B: this claim recites no additional elements.
As to Claim 12:
Step 2A Prong 1: Claim 12, incorporates the rejection of claim 2, and recites the following abstract ideas:
generates the likelihood that the abandoned user activity would have been completed based on previous activities (The step of generating the likelihood an abandoned activity would have been completed is a mathematical calculation)
Step 2A Prong 2 and 2B: this claim recites the following additional elements:
first machine learning model (The limitation is directed to mere instruction to apply the abstract idea on a generic computer)
With respect to claim 13:
The claim recites similar limitations as corresponding claim 1. Therefore, the same subject matter analysis that was utilized for claim 1, as described above, is equally applicable to claim 14.
With respect to claim 14:
The claim recites similar limitations as corresponding claim 2. Therefore, the same subject matter analysis that was utilized for claim 2, as described above, is equally applicable to claim 14.
With respect to claim 15:
The claim recites similar limitations as corresponding claim 8. Therefore, the same subject matter analysis that was utilized for claim 8, as described above, is equally applicable to claim 15.
With respect to claim 16:
The claim recites similar limitations as corresponding claim 9. Therefore, the same subject matter analysis that was utilized for claim 9, as described above, is equally applicable to claim 16.
With respect to claim 17:
The claim recites similar limitations as corresponding claim 5. Therefore, the same subject matter analysis that was utilized for claim 5, as described above, is equally applicable to claim 17.
With respect to claim 18:
The claim recites similar limitations as corresponding claim 6. Therefore, the same subject matter analysis that was utilized for claim 6, as described above, is equally applicable to claim 18.
With respect to claim 19:
The claim recites similar limitations as corresponding claim 4. Therefore, the same subject matter analysis that was utilized for claim 4, as described above, is equally applicable to claim 19.
With respect to claim 20:
The claim recites similar limitations as corresponding claim 10. Therefore, the same subject matter analysis that was utilized for claim 10, as described above, is equally applicable to claim 20.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claim(s) 1, 13 are rejected under 35 U.S.C. 103 as being unpatentable over Rivera et al. (US 11188840 B1) in view of Tian et al. (US 20180349953 A1).
Regarding claim 1, Rivera teaches the following:
A system for generating synthetic training data based on abandoned web activity data, comprising: one or more processors; (Rivera, Col. 1 lines 46-49, “One embodiment of the present disclosure includes a system comprising: one or more processors and memory storing one or more instructions that, when executed on the one or more processors, cause the system to:”)
And a non-transitory, computer-readable medium storing instructions that, when executed by the one or more processors, cause operations comprising: (Rivera, Col. 2 Lines 46-49, “Another embodiment provides a computer-readable storage medium having instructions, which, when executed on a processor, perform an operation that generally includes:”)
receiving web activity data for a user, wherein the web activity data relates to a plurality of web pages accessed by the user; (Rivera, Col. 7 lines 40-43, "The training data 210 may comprise composite information, for example in the form of composite data sets, describing previous interaction sessions between users and the web application 132")
inserting, into abandoned web activity data for a plurality of users, the abandoned user activity; (Rivera, Col. 8 lines 12-19, “For example, if a user ultimately abandoned an interaction session described by a particular set of input features, a training instance including those input features can be labeled with a zero (the target retention-prediction value) to indicate the target action was not completed or a one (or some other non-zero value) to indicate the target action was completed”)
processing, using a first machine learning model, the abandoned web activity data, to generate a probability for each entry in the abandoned web activity data, wherein each probability for a corresponding entry of the abandoned web activity data indicates a likelihood that the abandoned user activity would have been completed; (Rivera, Col. 1 lines 57-61, “via a first machine-learning model based on the composite data set, a retention-prediction value indicating a probability that the user will complete a target action in the application before the interaction session terminates;”)
and generating a synthetic dataset based on entries of the abandoned web activity data combined with the completed activity data (Rivera, Col. 8 lines 11-20, “The target retention-prediction value may be a label that has been empirically verified for the training instance. For example, if a user ultimately abandoned an interaction session described by a particular set of input features, a training instance including those input features can be labeled with a zero (the target retention-prediction value) to indicate the target action was not completed or a one (or some other non-zero value) to indicate the target action was completed. The composite data set for a single interaction session may be used to generate multiple training instances.”)
As outline above, Rivera teaches receiving web activity data for users, inserting abandoned activity for users, and processing the abandoned web activity using a machine learning model to find probability indicating an abandoned user activity would have been completed. Furthermore, Rivera teaches generating synthetic dataset based on abandoned web activity and completed web activity. Rivera does not explicitly disclose:
determining that the user abandoned a user activity included in the web activity data for the user, wherein an abandoned user activity relates to a web page that the user has accessed but not returned to for a threshold period of time
However, Rivera in view of Tian teaches the limitations:
determining that the user abandoned a user activity included in the web activity data for the user (Tian, Col. 5 paragraph 0042, “For example, in an embodiment where application 112 is a web browser, monitoring program 122 may monitor user activity and determine that the user has navigated away from a first article on a website (the activity being performed) to another website or webpage prior to completing the first article, and therefore, determine that the activity that was being performed has been abandoned”)
wherein an abandoned user activity relates to a web page that the user has accessed but not returned to for a threshold period of time (Tian, Col. 3, paragraph 0025, “For example, if monitoring program 122 identifies based on analyzing the user activity that the user of computing device 110 has navigated away from application 112 for longer than a threshold period of time, or that application 112 has been closed by the user and has not been reopened within a certain period of time, monitoring program 122 determines that the purchase corresponding to the item added to the ecommerce purchase flow has been abandoned)
Rivera in view of Tian is analogous art because they are from the same field of endeavor and their application relates to user web activity abandonment.
Accordingly, it would have been obvious to a person having ordinary skill in the art, before the effective filling date of the claimed invention, to modify the invention of Rivera to incorporate Tian’s technique of determining a user abandoned a web page by checking the threshold period of time a user has accessed but not returned to for a web page. One would have been motivated to make such a combination in order to solve the problem of predicting whether the user intended to complete the activity.
Regarding claim 13, the claim recites similar limitation as corresponding claim 1 and is rejected for similar reasons as claim 1 using similar teachings and rationale. Claim 1 is directed to a system, and claim 13 is directed to a computer device.
Claim(s) 2, 3, 4, 5, 6, 7, 9, 10, 11, 12, 14, 16, 17, 18, 19, 20 are rejected under 35 U.S.C. 103 as being unpatentable over Rivera et al. (US 11188840 B1) in view of Tian et al. (US 20180349953 A1) and Watson et al. (US 20200218638 A1).
Regarding claim 2, Rivera teaches the following:
inserting, into abandoned web activity data for a plurality of users, the abandoned user activity; (Rivera, Col. 8 lines 12-19, “For example, if a user ultimately abandoned an interaction session described by a particular set of input features, a training instance including those input features can be labeled with a zero (the target retention-prediction value) to indicate the target action was not completed or a one (or some other non-zero value) to indicate the target action was completed”)
processing, using a first machine learning model, the abandoned web activity data, to generate a probability for each entry in the abandoned web activity data, wherein each probability for a corresponding entry of the abandoned web activity data indicates a likelihood that the abandoned user activity would have been completed; (Rivera, Col. 1 lines 57-61, “via a first machine-learning model based on the composite data set, a retention-prediction value indicating a probability that the user will complete a target action in the application before the interaction session terminates;”)
and generating a synthetic dataset based on entries of the abandoned web activity data combined with the completed activity data (Rivera, Col. 8 lines 11-20, “The target retention-prediction value may be a label that has been empirically verified for the training instance. For example, if a user ultimately abandoned an interaction session described by a particular set of input features, a training instance including those input features can be labeled with a zero (the target retention-prediction value) to indicate the target action was not completed or a one (or some other non-zero value) to indicate the target action was completed. The composite data set for a single interaction session may be used to generate multiple training instances.”)
As outline above, Rivera teaches inserting abandoned activity for users, and processing the abandoned web activity using a machine learning model to find probability indicating an abandoned user activity would have been completed. Furthermore, Rivera teaches generating synthetic dataset based on abandoned web activity and completed web activity. Rivera does not explicitly disclose:
determining that the user abandoned a user activity included in the web activity data for the user, wherein an abandoned user activity relates to a web page that the user has accessed but not returned to for a threshold period of time
training, a second machine learning model, using the synthetic dataset, and testing, the second machine learning model, using a testing dataset based on completed user activities, wherein the testing dataset comprises data distinctive from the synthetic dataset, and wherein the completed user activities relate to one or more web pages where the user has completed an action.
However, Rivera in view of Tian teaches the limitations:
determining that the user abandoned a user activity included in the web activity data for the user (Tian, Col. 5 paragraph 0042, “For example, in an embodiment where application 112 is a web browser, monitoring program 122 may monitor user activity and determine that the user has navigated away from a first article on a website (the activity being performed) to another website or webpage prior to completing the first article, and therefore, determine that the activity that was being performed has been abandoned”)
wherein an abandoned user activity relates to a web page that the user has accessed but not returned to for a threshold period of time (Tian, Col. 3, paragraph 0025, “For example, if monitoring program 122 identifies based on analyzing the user activity that the user of computing device 110 has navigated away from application 112 for longer than a threshold period of time, or that application 112 has been closed by the user and has not been reopened within a certain period of time, monitoring program 122 determines that the purchase corresponding to the item added to the ecommerce purchase flow has been abandoned”)
As outline above, Rivera in view of Tian teaches determining user abandoned a user activity included in the web activity data and abandoned user activity relates to a web page that the user has accessed but not returned to for a threshold period of time Rivera does not explicitly disclose:
training, a second machine learning model, using the synthetic dataset, and testing, the second machine learning model, using a testing dataset based on completed user activities, wherein the testing dataset comprises data distinctive from the synthetic dataset, and wherein the completed user activities relate to one or more web pages where the user has completed an action
However, Rivera in view of Tian and Watson teaches the limitations:
training, a second machine learning model, using the synthetic dataset, and testing, the second machine learning model, using a testing dataset based on completed user activities, wherein the testing dataset comprises data distinctive from the synthetic dataset, and wherein the completed user activities relate to one or more web pages where the user has completed an action (Watson, Abstract, “An exemplary system, method, and computer-accessible medium can include, for example, receiving an original dataset(s), receiving a synthetic dataset(s), training a model(s) using the original dataset(s) and the synthetic dataset(s), and evaluating the synthetic dataset(s) based on the training of the model(s). The model(s) can include a first model and a second model, and the first model can be trained using the original dataset(s) and the second model can be trained using the synthetic dataset(s). The synthetic dataset(s) can be evaluated by comparing first results from the training of the first model to second results from the training of the second model.”)
Rivera in view of Tian and Watson are analogous art because they are from the same field of endeavor and their application relates to using models on user data.
Accordingly, it would have been obvious to a person having ordinary skill in the art, before the effective filling date of the claimed invention, to modify the invention of Rivera to incorporate Tian’s technique of determining a user abandoned a web page by checking the threshold period of time a user has accessed but not returned to for a web page and Watson’s technique of training a second model using synthetic data and testing the second model using test dataset distinct from the synthetic dataset. One would have been motivated to make such a combination in order to solve the problem of predicting whether the user intended to complete the activity and overcome limitations of synthetic datasets not being suitable for model training.
Regarding claim 3, Rivera teaches the elements of claim 2 as outlined above, and further teaches:
teaches web activity data relates to a plurality of web pages accessed by the user (Rivera, Col. 2, 31-36, “sending one or more pages for display to a user via a network during an interaction session between the user and an application, wherein the one or more web pages include elements for collecting response data from the user; receiving, via the pages, the response data from the user”)
Regarding claim 4, Rivera in view of Tian teaches the elements of claim 2 as outlined above, and further teaches:
determining a first threshold period of time corresponding to a first user activity (Tian, Col. 2, paragraph 0024, “For example, monitoring program 122 may monitor user activity and determine that the item has remained in an ecommerce shopping cart, with a purchase being made, for a period of time.”)
And determining a second threshold period of time corresponding to a second user activity, wherein the second threshold period of time is different from the first threshold period of time (Tian, Col. 2, paragraph 0024, “Monitoring program 122 compares the period of time the item has remained in the ecommerce shopping cart to a threshold period of time, and if the period of time the item has remained in the ecommerce shopping cart exceeds the threshold period of time, monitoring program 122 determines that the purchase corresponding to the item has been abandoned.”)
Regarding claim 5, Rivera in view of Tian teaches the elements of claim 2 as outlined above, and further teaches:
determining that the user abandoned a user activity included in the web activity data for the user further comprises: (Tian, Col. 5, paragraph 0042, “For example, in an embodiment where application 112 is a web browser, monitoring program 122 may monitor user activity and determine that the user has navigated away from a first article on a website (the activity being performed) to another website or webpage prior to completing the first article, and therefore, determine that the activity that was being performed has been abandoned”)
identifying a web page associated with a user activity after the threshold period of time; (Tian, Col. 3, paragraph 0025, “For example, if monitoring program 122 identifies based on analyzing the user activity that the user of computing device 110 has navigated away from application 112 for longer than a threshold period of time, or that application 112 has been closed by the user and has not been reopened within a certain period of time, monitoring program 122 determines that the purchase corresponding to the item added to the ecommerce purchase flow has been abandoned.”)
searching a completed user activity database for the user activity; (Tian, Col. 4, paragraph 0036, “For example, monitoring program 122 may reference user database 124 and identify, based on the information (such as historical usage information) associated with the user of computing device 110 in user database 124, a pattern of usage that includes the user logging into a specific social media app every morning.”)
in response to finding no completed user activity corresponding to the user activity, determining that the user has abandoned the user activity: (Tian, Col. 2, paragraph 0024, “For example, monitoring program 122 may monitor user activity and determine that the item has remained in an ecommerce shopping cart, with a purchase being made, for a period of time. Monitoring program 122 compares the period of time the item has remained in the ecommerce shopping cart to a threshold period of time, and if the period of time the item has remained in the ecommerce shopping cart exceeds the threshold period of time, monitoring program 122 determines that the purchase corresponding to the item has been abandoned.”)
Regarding claim 6, Rivera teaches the elements of claim 5 as outlined above, and further teaches:
completed user activity database comprises a user identifier, a time identifier, and a web page identifier corresponding to each completed user activity: (Rivera, Col. 5, lines 34-49, “response data may include values such as: a name, a birthdate, an address, a number of dependents, an income amount, one or more tax deductions, one or more tax credits, a filing status, one or more moving expenses, a federal tax withholding, or the like. The additional data may include, for example, the amount of time the user has spent on a page currently being displayed; the amounts of time the user spent on previously displayed pages, respectively; the cumulative amount of time spent during the current interaction session; the numbers of different types of events (e.g., click events, mouse-over events, etc.) initiated by the user on each page; the cumulative numbers of different types of events initiated by the user during the interaction session; how many times a “back” button in the browser 122 has been clicked during the interaction session; how many times the user has returned to previously displayed pages;” )
Regarding claim 7, Rivera teaches the elements of claim 2 as outlined above, and further teaches:
storing, in an abandoned user activity database, each abandoned user activity entry with the likelihood that the abandoned user activity would have been completed, (Rivera, Col. 7, lines 40-51, “the training data 210 may comprise composite information, for example in the form of composite data sets, describing previous interaction sessions between users and the web application 132. In addition, the training data 210 may also comprise attributes and labels that describe any intervention actions taken during those previous interaction sessions, whether the users completed the target actions for the previous interactions sessions, and the underlying reasons (e.g., as predicted by the third machine learning model 216 or as verified by surveying the users) why any of those users did not complete the target actions during the previous interaction sessions”)
wherein each abandoned user activity entry comprises a user identifier, a time identifier, a web page identifier, and an activity identifier corresponding to the abandoned user: (Rivera, col. 11, lines 29-44, “The composite information set may include both the explicit response data provided by the user and additional data that characterizes the user's current interaction session with the web application 132. For example, in the context of an example tax preparation web application, the explicit response data may include values such as: a name, a birthdate, an address, a number of dependents, an income amount, one or more tax deductions, one or more tax credits, a filing status, one or more moving expenses, a federal tax withholding, or the like. The additional data may include, for example, the amount of time the user has spent on a page currently being displayed; the amounts of time the user spent on previously displayed pages, respectively; the cumulative amount of time spent during the current interaction session; the numbers of different types of events (e.g., click events, mouse-over events, etc.) initiated by the user on each page”)
Regarding claim 9, Rivera in view of Tian teaches the elements of claim 2 as outlined above, and further teaches:
Transmitting a first request to a completed user activity database for completed user activity entries associated with the user; (Tian, Col. 4, paragraph 0036, “For example, monitoring program 122 may reference user database 124 and identify, based on the information (such as historical usage information) associated with the user of computing device 110 in user database 124, a pattern of usage that includes the user logging into a specific social media app every morning.”)
transmitting a second request to an abandoned user activity database for abandoned user activity entries associated with the user; (Tian, Col. 5, paragraph 0045, “Furthermore, monitoring program 122 may reference user database 124 and identify patterns corresponding to how often that the user of computing device 110 completes a specific activity, such as viewing an article, when the activity is interrupted by a message.”)
and in response to receiving the completed user activity entries and the abandoned user activity entries, generating for display completed and abandoned user activities on a user device associated with the user: (Tian, Col. 2, paragraph 0020, “In addition, monitoring program 122 is capable of updating user database 124 based on the collected monitored information.”)
Regarding claim 10, Rivera teaches the elements of claim 2 as outlined above, and further teaches:
The method of claim 2, further comprising generating an output using the second machine learning model, wherein the output comprises a likelihood for the user to complete a future user activity. (Rivera, Col. 7, lines 7-10, “The retention module 134 may predict the next action via a fourth machine-learning model (as described in greater detail in FIG. 2) based on the retention-prediction value,”)
Regarding claim 11, Rivera in view of Tian teaches the elements of claim 2 as outlined above, and further teaches:
determining that a user abandoned a user activity included in web activity data for the user further comprises detecting, in web activity data for the user, an interruption, wherein the interruption is associated with a new user activity, and wherein the new user activity relates to a web page that the user gas accessed after an abandoned user activity (Tian, Col. 5, paragraph 0042, “Monitoring program 122 determines whether the activity that was being performed has been abandoned (decision 304). In the example embodiment, monitoring program 122 determines whether the activity that was being performed has been abandoned based on detecting that the user of computing device 110 has navigated away from application 112 or alternatively has navigated to a different resource within application 112. For example, in an embodiment where application 112 is a web browser, monitoring program 122 may monitor user activity and determine that the user has navigated away from a first article on a website (the activity being performed) to another website or webpage prior to completing the first article, and therefore, determine that the activity that was being performed has been abandoned. ”)
Regarding claim 12, Rivera in view of Tian teaches the elements of claim 2 as outlined above, and further teaches:
first machine learning model generates the likelihood that the abandoned user activity would have been completed based on previous activities: (Rivera, Col. 11, lines 51-58, “first machine-learning model based on the composite data set, a retention-prediction value indicating a probability that the user will complete a target action in the application before the interaction session terminates. If a previous retention-prediction value for the interaction session has been calculated, the retention-prediction value determined in block 310 may be an updated retention-prediction values based on an updated composite data set.”)
Regarding claim 14, the claim recites similar limitations as corresponding claim 2 and is rejected for similar reasons as claim 2 using similar teachings and rationale.
Regarding claim 16, the claim recites similar limitation as corresponding claim 9 and is rejected for similar reasons as claim 9 using similar teachings and rationale.
Regarding claim 17, the claim recites similar limitation as corresponding claim 5 and is rejected for similar reasons as claim 5 using similar teachings and rationale.
Regarding claim 18, the claim recites similar limitation as corresponding claim 6 and is rejected for similar reasons as claim 6 using similar teachings and rationale.
Regarding claim 19, the claim recites similar limitation as corresponding claim 4 and is rejected for similar reasons as claim 4 using similar teachings and rationale.
Regarding claim 20, the claim recites similar limitation as corresponding claim 10 and is rejected for similar reasons as claim 10 using similar teachings and rationale.
Claim(s) 8, 15 are rejected under 35 U.S.C. 103 as being unpatentable over the combination of Rivera, Tian, and Watson as outlined above, and further in view of Jihsung et al. (GAIN: Missing Data Imputation using Generative Adversarial Nets, 2018, Introduction & Conclusion).
Regarding claim 8, Rivera in view of Tian teaches the elements of claim 2 as outlined above, and Jihsung further teaches:
identifying a missing identifier for a user activity in a completed user activity database; (Jihsung, Introduction, “Data may be missing because it was never collected, records were lost or for many other reasons. In the medical domain, the respiratory rate of a patient may not have been measured (perhaps because it was deemed unnecessary/unimportant) or accidentally not recorded (Yoon et al., 2017; Alaa et al., 2018).”“Prepare your dataset, ensuring to mark areas with missing values.” )
and generating a value for the missing identifier using a generative adversarial network, wherein the generative adversarial network is trained using the synthetic dataset. (Jihsung, Conclusion, “
“We propose a generative model for missing data imputation, GAIN. This novel architecture generalizes the well-known GAN such that it can deal with the unique characteristics of the imputation problem. Various experiments with real world datasets show that GAIN significantly outperforms state-of-the-art imputation techniques. The development of a new, state-of-the-art technique for imputation can have transformative impacts; most datasets in medicine as well as in other domains have missing data.”
“Create a GAN model where the generator takes known data points and learns to create plausible data for the missing entries.
Train your model using the paired data, continuously refining it by adjusting the weights based on the”)
Train your model using the paired data, continuously refining it by adjusting the weights based on the discriminator’s feedback.
Once trained, use the generator to produce missing data points that align with the overall data distribution.”
Regarding claim 15, the claim recites similar limitation as corresponding claim 8 and is rejected for similar reasons as claim 8 using similar teachings and rationale.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AYUSH MALPEDDI whose telephone number is (571)270-0244. The examiner can normally be reached 7:30am-5:00pm.
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, Li Zhen can be reached at 5712723768. 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.
/AYUSH REDDY MALPEDDI/Examiner, Art Unit 2121
/Li B. Zhen/Supervisory Patent Examiner, Art Unit 2121
Prosecution Insights