DETAILED ACTION
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 .
Election/Restrictions
Applicant’s election without traverse of group II, claims 8-14 in the reply filed on 1/12/26 is acknowledged.
Claims 1-7 and 15-20 are withdrawn from further consideration pursuant to 37 CFR 1.142(b) as being drawn to a nonelected invention, there being no allowable generic or linking claim.
Claim Rejections - 35 USC § 103
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 (i.e., changing from AIA to pre-AIA ) 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.
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) 8-14 are rejected under 35 U.S.C. 103 as being unpatentable over Xie et al (with reliance on https://ojs.aaai.org/index.php/AIIDE/article/view/12905/12753) in view of Heifets et al (US 9,373,059) and Armstrong (US 2022/0339543).
Re claim 8, Xie discloses a computer system comprising a processor, communication interface, and memory (p. 145, the method of churn prediction operates with data obtained from various games, therefore inherently the devices playing the games utilize a processor, communication interface, and memory) causing the processor to: extract raw user data of a plurality of users of an online video game application (p. 145 describing the games analyzed for churn) from a plurality of sources (p. 145 describing the datasets for each game comprising a large number of full gameplay logs); and append the raw user data and generate a dataset therefrom, the dataset comprising a labeled dataset that includes input sequences and corresponding output labels (p. 146 describing the methodology used to analyze the user data from the games and labeling the dataset in the formulas, see “Cohen’s Kappa,” and p. 148 with labeled datasets in table format).
However, while Xie discloses determining user disengagement (referred to as “churn” by Xie), there is no explicit disclosure of encoding the dataset using natural language processing classifying input and output data using one-hot vectors. Xie is additionally silent on exposing a neural network to the encoded dataset to iteratively train the neural network by comparing a predicted outcome to an actual outcome and based thereon generating an error amount, wherein the error amount is back-propagated to the neural network. Finally, Xie does not disclose an additional source of data comprising online resource aggregation profiles of a partner entity that is partnered with an entity that provides the online video game application.
Heifets teaches a system for applying data to a neural network with one-hot encoding and back-propagation for training against errors (col. 20:40-50 and 28:44 to 29:22). It would have been obvious to train a neural network such as the one implemented by Heifets with one-hot encoding and back-propagation with the datasets from Xie in order to improve the quality of analyzed data by utilizing a neural network that improves data based on determined errors, with one-hot vectors providing an easy to design encoding method that improves performance of the system.
Armstrong teaches a method for training a machine learning model that utilizes different data sources ([0038]). It would have been obvious to implement multiple data sources as taught by Armstrong in addition to the already utilized datasets of Xie in order to provide more data to the neural network, strengthening the quality of data used by the neural network and therefore improving the quality of results.
Re claim 9, Xie discloses a plurality of derived attributes including a duration of gameplay (p. 144, “This is defined by observing whether a player played the game at least once between day -14 and day -1. Finally, the last condition takes players who start a 14 consecutive days of inactivity from any days between day 0 and 6 as the churn players”).
Re claim 10, Xie discloses derived attributes including a quantity of instances of gameplay initiated by one or more users of the plurality of users (p. 145, full gameplay logs are considered examples of instances of gameplay initiated by users).
Re claims 11-12, Xie discloses a quantity of resource balance changes of a virtual resource by one or more of the plurality of users or a quantity of resource transactions (p. 146, data includes statistics such as “Last purchase” and “days since last purchase,” therefore the data discloses a change of a balance of virtual resources, as purchases require expenditure of a currency or other resource).
Re claims 13-14, see the rejection to claims 11-12. As Xie discloses data that includes data on “Last purchase” and “Days since last purchase” (p. 146), this is considered a teaching of a quantity of real-world resources or resource balance changes stored to respective locations attributed to the users as the Examiner takes Official Notice that it is notoriously well-known and obvious that purchases can be made with currency such as money (i.e. real-world resources), or other resource balances (i.e. credits, in-game currency, or other representations of currency not necessarily directly tied to actual money).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Sakamoto et al (US 2021/0303937) discloses a neural network with back-propagation used to predict churn rate (see [0030] and [0035]). Agarwal et al (US 10,373,078) discloses a method of predicting churn rate utilizing one-hot encoding.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Kevin Y Kim whose telephone number is (571)270-3215. The examiner can normally be reached Monday-Friday.
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, Xuan Thai can be reached at (571) 272-7147. 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.
/KEVIN Y KIM/Primary Examiner, Art Unit 3715
/XUAN M THAI/Supervisory Patent Examiner, Art Unit 3715