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. Claims 1, 13 and 20 recite(s) the steps of “determining, by the processor, an active behavior timing feature of a target account according to active behavior data of the target account in a virtual gaming environment”, “determining, by the processor, an account feature of the target account according to account data of the target account”,” predicting, by the processor executing a supervised learning model, based on the account feature and the active behavior timing feature, a first probability that the target account is of a target type”, and “determining, in response to the first probability being greater than a target probability threshold, that the target account is of the target type” could reasonably be performed mentally and are merely data gathering and analysis. The amended claim language also recites determining that is directed to the mental step. This judicial exception is not integrated into a practical application because the step of the additional elements recited, “electronic device” “processor” and “memory” ”supervised learning model” amounts to generic computer functionality and the steps recited amounts to mere data gathering and mental steps which falls within mental processes of abstract ideas. The claim(s) does/do not include additional elements that are sufficient to amount to significantly more than the judicial exception because as discussed above, the steps amount to no more than mere instructions to apply which cannot provide an inventive concept. Claims 13 and 20 recites “processors” which is well known and generic computer as described in paragraph 6 of instant application. Dependent claims 2-12, and 14-19 are rejected under 35 USC 101, because they recited only generating notifications (extra solution activity) and do not cure the deficiencies of independent claims 1, 13 and 20.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-2, 7-9, 10-14 and 19-20 are rejected under 35 U.S.C. 103 as being unpatentable over Helwani et al (11468354) in views of applicant’s Admitted prior art in IDS Kornmann et al (10463953), Tu et al (CN 109543200) and Wang et al (CN 109447361).
For claim 1, Helwani teaches a target account detection method, performed by a processor of an electronic device (abstract, lines 1-5), the method comprising: determining, by the processor, an active behavior timing (user target behavior during period of time) feature of a target account according to active behavior data of the target account (each observation represented by the observation data may indicate a specific user and/or user profile, a specific account (e.g., user profile associated with multiple users), a specific location, a specific time period, and/or the like at which a user is detected (e.g., remotely sensed) by the system as Helwani teaches in col.2, lines 20-25 and col.4, lines 39-45), the active behavior data being used for representing whether the target account is active in a target duration (the system 100 may generate a first observation (e.g., first data) indicating that a first user associated with a first user profile is detected at a first location during a first time period as Helwani in col.4, lines 21-25); the active behavior data associated with acquiring one or more virtual assets (Helwani teaches that server may also include one or more virtual machines that emulates a computer system and is run on one or across multiple devices. A server may also include other combinations of hardware, software, firmware, or the like to perform operations discussed herein. The server may be configured to operate using one or more of a client-system model, a computer bureau model, grid computing techniques, fog computing techniques, mainframe techniques, utility computing techniques, a peer-to-peer model, sandbox techniques, or other computing techniques as Helwani teaches in col.30, lines 45-60); determining, by the processor, an account feature of the target account according to account data of the target account (observation data (e.g., combined data) associated with the first user profile may include a plurality of observations (e.g., plurality of locations at which the user is detected), including the first observation and the second observation, enabling the system 100 to track a location of the first user over time as Helwani teaches in col.2, lines 22-26 and col.4, lines 35-40); predicting, by the processor based on the account feature and the active behavior timing feature, a first probability that the target account is of a target type (system may perform adaptive target presence probability estimation by applying a clustering algorithm to the observation data to generate probability distributions (e.g., clusters) associated with discrete locations as Helwani teaches in col.2, lines 26-35 and col.5, lines 30-36).
Helwani fails to teach that in a virtual gaming environment, predicting, by the processor executing a supervised learning model, the predicting including: determining, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into the supervised learning model comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer, and determining, in response to the first probability being greater than a target probability threshold, that the target account is of the target type, and the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Kornmann teaches, similar system, a virtual gaming environment (Kornman teaches that’s the game is virtual world as Kornmann teaches in col.3, lines 35-48), determining, in response to the first probability being greater than a target probability threshold, that the target account is of the target type (Kornmann teaches of probability function (p(Δx, Δt)) to determine an event probability, probability function can include a velocity threshold term (v.sub.a) that is function of Δt, robability function can be a logistic function that provides a number between zero and one based on a difference between the inputted inter-event velocity and the velocity threshold term. In such fashion, inter-event velocities that are greater in magnitude than the velocity threshold term are assessed as less probable (i.e. an event probability closer to zero is output) while inter-event velocities that are lesser in magnitude that the velocity threshold term are assessed as more probable (i.e. an event probability closer to one is output by the probability function) as Kornmann teaches in col.4, lines 25-50). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani to include first probability being greater than a target probability threshold as taught and suggested by Kornmann for purpose detecting and preventing cheating in a location-based game and to determine a probability that such game events represent legitimate gameplay (Kornmann, abstract). Helwani, as modified by Kornmann, do not explicitly teach that predicting, by the processor executing a supervised learning model, predicting including: determining, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into the supervised learn model comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer, and the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Tu teaches, similar system, predicting, by the processor executing a supervised learning model (abstract), predicting including: determining, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into the supervised learn model (Tu teaches that relating to the technical field of machine learning, the translation text for translation, text to be translated by encoder to code the processing result of each hidden layer encoder in the fusion, confirming the source end vector representing the sequence. after the decoder decodes the source end vector represents a sequence for decoding, the processing result of each hidden layer decoder for determining the translation of text information fusion to study better hidden representation, reduce the loss of useful information to improve the accuracy of the translation as Tu teaches in abstract) comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer (Tu teaches that of an input layer, a hidden layer and an output layer, wherein the hidden layer is a plurality of text to be translated through a plurality of hidden layer for encoding to obtain each hidden layer output code sequence. Specifically, to be first translated text input encoder layer hidden layer in each hidden layer, carrying out coding process to be translated text by first layer hidden layer, output layer first hidden layer corresponding to coding sequence. then the hidden layer output of first layer coding sequence as the input of the second hidden layer, encoding processing, and outputs the second hidden layer corresponding to the coding sequence of the hidden layer. by parity of reasoning, until obtaining the encoding sequence of at last one layer of hidden layer output and determining fusion of each hidden layer weights according to the output result of each hidden layer encoder and decoder, then the output result of each hidden layer fusion based fusion weights, so aiming at different text to be translated, a coder and a decoder weight of each hidden layer are also different as Tu teaches in par.64 and 81 on machine translation). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann, to include an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer as taught and suggested by Tu for purpose improving the expression ability of encoder and decoder, improves the stability of the translation (Tu, abstract). Helwani, as modified by Kornmann and Tu, do not explicitly teach that the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Wang teaches, similar system, the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer (Wang teaches that in each section the system will monitor game user through reaction daily behaviour characteristics and depth characteristics 10-dimensional (user sex character, user age, user geographical features, user interest, user login feature, user login frequency characteristic. user last login time characteristic, user login duration feature, a user level features and user social relationship characteristic) as Wang teaches in par.20 and 25 on machine translation). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann and Tu, to include , the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer as taught and suggested by Wang for purpose of establishing the game user risk index, using the learning function of the neural network model. establishing a game user loss model, predict future loss of game user condition of high efficiency (Wang, abstract).
For claims 2 and 14, Helwani, as modified by Kommann, Tu, and Wang, further teaches wherein the determining an active behavior timing feature of a target account according to active behavior data of the target account comprises: performing dimension raising on the active behavior data of the target account, to obtain a first feature matrix (Helwani teaches the first cluster (e.g., a list of blocks associated with the first cluster, a range of coordinate values indicating a perimeter of the first cluster , etc.), the coordinates of the center and a variance (e.g., covariance matrix) of the first cluster Helwani teaches col.5, lines 20-39); performing clustering based on the first feature matrix, to obtain at least one cluster (Helwani teaches col.7,lines 5-16); and determining the active behavior timing feature of the target account according to the at least one cluster (Helwani teaches col.6, lines 1-13).
For claims 7, Helwani, as modified by Kommann, Tu, and Wang, further teaches wherein the predicting comprises: predicting, according to the account feature and the active behavior timing feature, a second probability that the target account is of the target type; predicting, according to the account data of the target account (Helwani teaches col.6, lines 15-27), a third probability that the target account is of a target value type (Helwani teaches col.24,lines 45-60); and determining the first probability according to the second probability and the third probability (Helwani teaches col.17, lines 45-65).
For claim 8 and 19, Helwani, as modified by Kommann, Tu, and Wang, further teaches wherein the predicting, according to the account data of the target account, a third probability that the target account is of a target value type comprises: determining a second value parameter corresponding to duration data in the account data; determining a third value parameter corresponding to consumption data in the account data (Helwani teaches col.24,lines 45-60); and predicting, according to the first value parameter, the second value parameter, and the third value parameter, the third probability that the target account is of the target value type (Helwani teaches col.24,lines 45-60).
For claim 9, Helwani, as modified by Kommann, Tu, and Wang, teaches all the limitations as previously set forth and Helwani further teaches wherein the determining, according to a user portrait in the account data, first value parameters corresponding to features comprised in the user portrait comprises: mapping the features comprised in the user portrait, to obtain a fourth feature matrix (Helwani teaches col.7, lines 5-20 and col.24, 33-40); and estimating first value parameters corresponding to the features based on the fourth feature matrix and at least one value parameter that is preset (Helwani teaches col.7, lines 5-20 and col.24, 33-40).
Helwani fails to teach the account data into vectors.
Tu teaches, similar system, the account data into vectors (Tu, abstract). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann, to include the account data into vectors as taught and suggested by Tu for purpose improving the expression ability of encoder and decoder, improves the stability of the translation (Tu, abstract).
For claim 10, Helwani, as modified by Kommann, Tu, and Wang, further teaches wherein the determining that the target account is of the target type comprises: first, second and third probabilities and determining the highest possible probability as Helwani teaches in col.7, lines 30-50) but fails to explicitly teaches of reducing, in response to the second probability being greater than a first probability threshold, and the third probability is greater than a second probability threshold, a confidence that the target account is of the target type, the confidence being used for representing whether a prediction result is logical; increasing, in response to the second probability being greater than the first probability threshold, and the third probability is less than the second probability threshold, the confidence that the target account is of the target type; increasing, in response to the second probability being less than the first probability threshold, and the third probability is greater than the second probability threshold, the confidence that the target account is of the target type; and keeping, in response to the second probability being less than the first probability threshold, and the third probability is less than the second probability threshold, the confidence that the target account is of the target type unchanged.
Kornmann further teaches teaches reducing, in response to the second probability being greater than a first probability threshold, and the third probability is greater than a second probability threshold, a confidence that the target account is of the target type, the confidence being used for representing whether a prediction result is logical (Kornmann teaches col.4,lines 45-60); increasing, in response to the second probability being greater than the first probability threshold, and the third probability is less than the second probability threshold, the confidence that the target account is of the target type (Kornmann teaches col.6, lines 19-35 and col.8, lines 60-68); increasing, in response to the second probability being less than the first probability threshold, and the third probability is greater than the second probability threshold, the confidence that the target account is of the target type; and keeping, in response to the second probability being less than the first probability threshold, and the third probability is less than the second probability threshold, the confidence that the target account is of the target type unchanged (Kornmann teaches col.8, lines 25-35). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani to include to reduce or increasing the second probability being less than the first probability threshold, and the third probability is greater than the second probability threshold as taught and suggested by Kornmann for purpose detecting and preventing cheating in a location-based game and to determine a probability that such game events represent legitimate gameplay (Kornmann, abstract).
For claim 11, Helwani, as modified by Kommann, Tu, and Wang, further teaches wherein after the determining that the target account is of the target type, the method further comprises: obtaining an account processing rule corresponding to the target type; and processing the target account according to the account processing rule (Helwani teaches col.2, lines 23-30).
For claim 12, Helwani, as modified by Kommann, Tu, and Wang, further teaches wherein before the determining an active behavior timing feature of a target account according to active behavior data of the target account, the method further comprises: performing outlier processing on collected data, to obtain the account data of the target account (Helwani teaches col.22, lines 23-30); dividing the account data into a plurality of types of data, the active behavior data comprising at least one type of data (Helwani teaches col.22, 33-40); and performing normalization on the plurality of types of data, the normalization being used for changing a value range of the data into a target value rang (Helwani teaches col.22,lines 45-68).
For claim 13, Helwani teaches target account detection apparatus (abstract), comprising: at least one memory configured to store program code (col.33, lines 35-45); and at least one processor configured to read the program code and operate as instructed by the program code (col.33, lines 35-45), the program code comprising: determining code configured to cause the at least one processor to determine an active behavior timing feature of a target account according to active behavior data of the target account (each observation represented by the observation data may indicate a specific user and/or user profile, a specific account (e.g., user profile associated with multiple users), a specific location, a specific time period, and/or the like at which a user is detected (e.g., remotely sensed) by the system as Helwani teaches in col.2, lines 20-25 and col.4, lines 39-45), the active behavior data being used for representing whether the target account is active in a target duration (the system 100 may generate a first observation (e.g., first data) indicating that a first user associated with a first user profile is detected at a first location during a first time period as Helwani in col.4, lines 21-25), the active behavior data associated with acquiring one or more virtual assets (Helwani teaches that server may also include one or more virtual machines that emulates a computer system and is run on one or across multiple devices. A server may also include other combinations of hardware, software, firmware, or the like to perform operations discussed herein. The server may be configured to operate using one or more of a client-system model, a computer bureau model, grid computing techniques, fog computing techniques, mainframe techniques, utility computing techniques, a peer-to-peer model, sandbox techniques, or other computing techniques as Helwani teaches in col.30, lines 45-60) the determining code being further configured to determine an account feature of the target account according to account data of the target account (observation data (e.g., combined data) associated with the first user profile may include a plurality of observations (e.g., plurality of locations at which the user is detected), including the first observation and the second observation, enabling the system 100 to track a location of the first user over time as Helwani teaches in col.2, lines 22-26 and col.4, lines 35-40); and prediction code configured to cause the at least one processor to predict, based on the account feature and the active behavior timing feature, a first probability that the target account is of a target type (the system may perform adaptive target presence probability estimation by applying a clustering algorithm to the observation data to generate probability distributions (e.g., clusters) associated with discrete locations as Helwani teaches in col.2, lines 26-35 and col.5, lines 30-36).
Helwani fails to teach a virtual gaming environment, predict, by executing a supervised learning model, the determining code being further configured to determine, in response to the first probability being greater than a target probability threshold, that the target account is of the target type, the prediction code further configured to cause the at least one processor to: determine, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into the supervised learn model comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer and the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Kornmann teaches, similar system, a virtual gaming environment (Kornman teaches that’s the game is virtual world as Kornmann teaches in col.3, lines 35-48), the determining code being further configured to determine, in response to the first probability being greater than a target probability threshold, that the target account is of the target type (Kornmann teaches of probability function (p(Δx, Δt)) to determine an event probability, probability function can include a velocity threshold term (v.sub.a) that is function of Δt, robability function can be a logistic function that provides a number between zero and one based on a difference between the inputted inter-event velocity and the velocity threshold term. In such fashion, inter-event velocities that are greater in magnitude than the velocity threshold term are assessed as less probable (i.e. an event probability closer to zero is output) while inter-event velocities that are lesser in magnitude that the velocity threshold term are assessed as more probable (i.e. an event probability closer to one is output by the probability function) as Kornmann teaches in col.4, lines 25-50). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani to include first probability being greater than a target probability threshold as taught and suggested by Kornmann for purpose detecting and preventing cheating in a location-based game and to determine a probability that such game events represent legitimate gameplay (Kornmann, abstract). Helwani, as modified by Kornmann, do not explicity teach that predicting including: determining, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into a supervised learn model comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer, and the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Tu teaches, similar system, predict, by executing a supervised learning model (abstract), predicting including: determining, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into the supervised learn model (Tu teaches that relating to the technical field of machine learning, the translation text for translation, text to be translated by encoder to code the processing result of each hidden layer encoder in the fusion, confirming the source end vector representing the sequence. after the decoder decodes the source end vector represents a sequence for decoding, the processing result of each hidden layer decoder for determining the translation of text information fusion to study better hidden representation, reduce the loss of useful information to improve the accuracy of the translation as Tu teaches in abstract) comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer (Tu teaches that of an input layer, a hidden layer and an output layer, wherein the hidden layer is a plurality of text to be translated through a plurality of hidden layer for encoding to obtain each hidden layer output code sequence. Specifically, to be first translated text input encoder layer hidden layer in each hidden layer, carrying out coding process to be translated text by first layer hidden layer, output layer first hidden layer corresponding to coding sequence. then the hidden layer output of first layer coding sequence as the input of the second hidden layer, encoding processing, and outputs the second hidden layer corresponding to the coding sequence of the hidden layer. by parity of reasoning, until obtaining the encoding sequence of at last one layer of hidden layer output and determining fusion of each hidden layer weights according to the output result of each hidden layer encoder and decoder, then the output result of each hidden layer fusion based fusion weights, so aiming at different text to be translated, a coder and a decoder weight of each hidden layer are also different as Tu teaches in par.64 and 81 on machine translation). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann, to include an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer as taught and suggested by Tu for purpose improving the expression ability of encoder and decoder, improves the stability of the translation (Tu, abstract). Helwani, as modified by Kornmann and Tu, do not explicitly teach that the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Wang teaches, similar system, the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer (Wang teaches that in each section the system will monitor game user through reaction daily behaviour characteristics and depth characteristics 10-dimensional (user sex character, user age, user geographical features, user interest, user login feature, user login frequency characteristic. user last login time characteristic, user login duration feature, a user level features and user social relationship characteristic) as Wang teaches in par.20 and 25 on machine translation). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann and Tu, to include , the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer as taught and suggested by Wang for purpose of establishing the game user risk index, using the learning function of the neural network model. establishing a game user loss model, predict future loss of game user condition of high efficiency (Wang, abstract).
For claim 20, Helwani teaches non-transitory computer readable storage medium, storing a computer program that when executed by at least one processor causes the at least one processor to (col.33, lines 35-45): determine an active behavior timing feature of a target account according to active behavior data of the target account (each observation represented by the observation data may indicate a specific user and/or user profile, a specific account (e.g., user profile associated with multiple users), a specific location, a specific time period, and/or the like at which a user is detected (e.g., remotely sensed) by the system as Helwani teaches in col.2, lines 20-25 and col.4, lines 39-45), the active behavior data being used for representing whether the target account is active in a target duration (the system 100 may generate a first observation (e.g., first data) indicating that a first user associated with a first user profile is detected at a first location during a first time period as Helwani in col.4, lines 21-25); the active behavior data associated with acquiring one or more virtual assets (Helwani teaches that server may also include one or more virtual machines that emulates a computer system and is run on one or across multiple devices. A server may also include other combinations of hardware, software, firmware, or the like to perform operations discussed herein. The server may be configured to operate using one or more of a client-system model, a computer bureau model, grid computing techniques, fog computing techniques, mainframe techniques, utility computing techniques, a peer-to-peer model, sandbox techniques, or other computing techniques as Helwani teaches in col.30, lines 45-60); determine an account feature of the target account according to account data of the target account; predict (observation data (e.g., combined data) associated with the first user profile may include a plurality of observations (e.g., plurality of locations at which the user is detected), including the first observation and the second observation, enabling the system 100 to track a location of the first user over time as Helwani teaches in col.2, lines 22-26 and col.4, lines 35-40), based on the account feature and the active behavior timing feature, a first probability that the target account is of a target type (the system may perform adaptive target presence probability estimation by applying a clustering algorithm to the observation data to generate probability distributions (e.g., clusters) associated with discrete locations as Helwani teaches in col.2, lines 26-35 and col.5, lines 30-36).
Helwani fails to teach a virtual gaming environment, predict, by executing a supervised learning model, determine, in response to the first probability being greater than a target probability threshold, that the target account is of the target type, the prediction including: determining, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into a supervised learn model comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer and the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Kornmann teaches, similar system, a virtual gaming environment (Kornman teaches that’s the game is virtual world as Kornmann teaches in col.3, lines 35-48), determine, in response to the first probability being greater than a target probability threshold, that the target account is of the target type (Kornmann teaches of probability function (p(Δx, Δt)) to determine an event probability, probability function can include a velocity threshold term (v.sub.a) that is function of Δt, robability function can be a logistic function that provides a number between zero and one based on a difference between the inputted inter-event velocity and the velocity threshold term. In such fashion, inter-event velocities that are greater in magnitude than the velocity threshold term are assessed as less probable (i.e. an event probability closer to zero is output) while inter-event velocities that are lesser in magnitude that the velocity threshold term are assessed as more probable (i.e. an event probability closer to one is output by the probability function) as Kornmann teaches in col.4, lines 25-50). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani to include first probability being greater than a target probability threshold as taught and suggested by Kornmann for purpose detecting and preventing cheating in a location-based game and to determine a probability that such game events represent legitimate gameplay (Kornmann, abstract). Helwani, as modified by Kornmann, do not explicity teach that predict, by executing a supervised, learning model, predicting including: determining, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into a supervised learn model comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer and the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Tu teaches, similar system, predict, by executing a supervised learning model (abstract), predicting including: determining, according to a user portrait in account data, first value parameters corresponding to features comprised in the user portrait by mapping the features in the account data into vectors that are input into a supervised learn model (Tu teaches that relating to the technical field of machine learning, the translation text for translation, text to be translated by encoder to code the processing result of each hidden layer encoder in the fusion, confirming the source end vector representing the sequence. after the decoder decodes the source end vector represents a sequence for decoding, the processing result of each hidden layer decoder for determining the translation of text information fusion to study better hidden representation, reduce the loss of useful information to improve the accuracy of the translation as Tu teaches in abstract) comprising an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer (Tu teaches that of an input layer, a hidden layer and an output layer, wherein the hidden layer is a plurality of text to be translated through a plurality of hidden layer for encoding to obtain each hidden layer output code sequence. Specifically, to be first translated text input encoder layer hidden layer in each hidden layer, carrying out coding process to be translated text by first layer hidden layer, output layer first hidden layer corresponding to coding sequence. then the hidden layer output of first layer coding sequence as the input of the second hidden layer, encoding processing, and outputs the second hidden layer corresponding to the coding sequence of the hidden layer. by parity of reasoning, until obtaining the encoding sequence of at last one layer of hidden layer output and determining fusion of each hidden layer weights according to the output result of each hidden layer encoder and decoder, then the output result of each hidden layer fusion based fusion weights, so aiming at different text to be translated, a coder and a decoder weight of each hidden layer are also different as Tu teaches in par.64 and 81 on machine translation). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann, to include an input layer, an embedding layer connected to an output of the input layer, a plurality of parameter hidden layers for a plurality of features included in the user portrait in the account data connected to the embedding layer, a fusion layer that fuses each hidden layer, a link calculation layer connected to the fusion layer, and an output layer connected to an output of the link calculation layer as taught and suggested by Tu for purpose improving the expression ability of encoder and decoder, improves the stability of the translation (Tu, abstract). Helwani, as modified by Kornmann and Tu, do not explicitly teach that the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer.
Wang teaches, similar system, the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer (Wang teaches that in each section the system will monitor game user through reaction daily behaviour characteristics and depth characteristics 10-dimensional (user sex character, user age, user geographical features, user interest, user login feature, user login frequency characteristic. user last login time characteristic, user login duration feature, a user level features and user social relationship characteristic) as Wang teaches in par.20 and 25 on machine translation). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann and Tu, to include , the plurality of hidden layers comprising an age hidden layer, a province hidden layer, a game duration hidden layer, and a game consumption amount hidden layer as taught and suggested by Wang for purpose of establishing the game user risk index, using the learning function of the neural network model. establishing a game user loss model, predict future loss of game user condition of high efficiency (Wang, abstract).
Claim(s) 3, 6, 15 and 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Helwani et al (11468354) in views of applicant’s Admitted prior art in IDS Kornmann et al (10463953), Tu et al (CN 109543200) and Wang et al (CN 109447361) as applied to claims above, and further in view of Depalov et al (9020262).
For claims 3 and 15, Helwani, as modified by Kornmann, Wang and Tu, teaches all the limitations as previously set forth except for transforming the active behavior data of the target account into a form of a binomial bitmap, the binomial bitmap referring to that elements in the binomial bitmap are represented by 0 and 1.
Depalov teaches, similar system, transforming the active behavior data of the target account into a form of a binomial bitmap, the binomial bitmap referring to that elements in the binomial bitmap are represented by 0 and 1 (Depalov teaches col.4,lines 63-col. 5, line 24, and col.11, lines 20-40). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann, Wang and Tu, to include the binomial bitmap as taught and suggested by Depalov for purpose getting a new probability estimation, which can be used to obtain the total number of bits estimation (Depalov, col.4,lines 63-68).
For claims 6 and 18, Helwani, as modified by Kornmann, Wang and Tu, teaches all the limitations as previously set forth and Helwani further teaches that wherein the determining code is further configured to cause the at least one processor to obtain, in the at least one cluster, a third clustering center of a first cluster and a fourth clustering center of a second cluster (Helwani teaches in col.17, lines 45-65 and col.24, lines 45-68), the first cluster being a cluster corresponding to accounts of the target type, and the second cluster being a cluster corresponding to accounts of non-target types (Helwani teaches in col.17, lines 45-65 and col.24, lines 45-68); and process the third clustering center, the fourth clustering center (Helwani teaches in col.17, lines 45-65 and col.24, lines 45-68).
Helwani, as modified by Kornmann, Wang and Tu, fails to teach the first feature matrix respectively by using a Hamming weight and a Hamming distance, to obtain the active behavior timing feature of the target account, the Hamming weight being used for quantizing an activity level similarity, and the Hamming distance being used for quantizing an activity regularity similarity.
Depalov teaches the first feature matrix respectively by using a Hamming weight and a Hamming distance, to obtain the active behavior timing feature of the target account, the Hamming weight being used for quantizing an activity level similarity, and the Hamming distance being used for quantizing an activity regularity similarity (Depalov teaches col.5, lines 26-38). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann, Wang and Tu, to include the Hamming weight and distance as taught and suggested by Depalov for purpose getting a new probability estimation, which can be used to obtain the total number of bits estimation and to use a more computationally efficient method to match each symbol to a dictionary entry. Some previous coding approaches make the assumption that the more similar a symbol is to a given dictionary entry, the smaller the number of bits needed to encode it (Depalov, col.4,lines 63-68).
Claim(s) 4-5, and 16-17 is/are rejected under 35 U.S.C. 103 as being unpatentable over Helwani et al (11468354) in views of applicant’s Admitted prior art in IDS Kornmann et al (10463953), Tu et al (CN 109543200) and Wang et al (CN 109447361) as applied to claims above, and further in view of Tadayon et al (2014/0079297).
For claims 4 and 16, Helwani, as modified by Kornmann, Wang and Tu, teaches all the limitations as previously set forth and Helwani further teaches that wherein the performing clustering based on the first feature matrix, to obtain at least one cluster comprises: combining the first feature matrix and a second feature matrix of at least one sample account into a third feature matrix, a type of the sample account being known (Helwani teaches col.7, lines 5-20 and col.22, 33-40); dividing the third feature matrix into a plurality of feature groups according to a time dimension (Helwani teaches col.22, 33-40); determining similarities between the plurality of feature groups (Helwani teaches col.7, lines 5-20 and col.22, 33-40); and dividing the plurality of feature groups into the at least one cluster according to the similarities between the plurality of feature groups (Helwani teaches col.22,lines 45-68).
Helwani, as modified by Kornmann, Wang and Tu, fails to teach according to a cosine value of a polar coordinate system.
Tadayon teaches, similar system, of using according to a cosine value of a polar coordinate system (Tadayon teaches in par.926, lines 2-5). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann and Tu, to include a cosine value of a polar coordinate system as taught and suggested by Tadayon for purpose getting reliability of an expert module that is trained by correlating the features indicating the domain of the expert module with the error encountered by the expert module (Tadayon, par.312).
For claims 5 and 17, Helwani, as modified by Kornmann, Wang and Tu, teaches all the limitations as previously set forth and Helwani further teaches wherein after the dividing the plurality of feature groups into the at least one cluster, the method further comprises: determining, in response to any cluster comprising a largest quantity of sample accounts, a displacement coefficient of the cluster, the displacement coefficient being a ratio of a quantity of sample accounts not comprised in the cluster to a total quantity of sample accounts (Helwani teaches col.5, lines 63-68 to col.6, lines 1-10); determining a target distance according to a distance between a first clustering center of the cluster and a preset second clustering center and the displacement coefficient, the second clustering center being a clustering center (Helwani teaches col.18, lines 34-56); and moving the first clustering center by the target distance in a direction pointing to the second clustering center (Helwani teaches col.7, lines 10-30).
Helwani, as modified by Kornmann, Wang and Tu, fails to teach determined in a heuristic clustering manner.
Tadayon teaches, similar system, determined in a heuristic clustering manner (Tadayon par.289, lines 2-5). It would have been obvious to one ordinary skill in the art before effective filling date to modify Helwani, as modified by Kornmann and Tu, to include heuristic as taught and suggested by Tadayon for purpose getting reliability of an expert module that is trained by correlating the features indicating the domain of the expert module with the error encountered by the expert module (Tadayon, par.312).
Response to Amendments/Arguments
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
With respect to applicant argument of 101 rejection that the current amendment overcome the 101 rejections, however, the examiner respectfully disagrees with applicant because claims still do not include additional elements that are sufficient to amount to significantly more than the judicial exception. The newly amended language still directed to steps of determining i.e. also categorized as mental steps. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of processor, memory and supervised learning model are recited at a high level of generality and are generic computer components such that they amount to no more than mere instructions to apply the exception using a generic computer. Accordingly, these additional elements do not integrate the abstract idea into a practical application because they do not impose any meaningful limits on practicing the abstract idea. Thus, the claimed elements, either individually, or in the ordered combination do not add significantly more to the abstract idea.
The applicant’s arguments regarding the amendment limitation in claims 1, 13 and 20, has been considered but is moot, because the examiner applied new art, Wang et al (CN 109447361), that covers newly claimed limitation.
Regarding dependent claims arguments, said arguments are moot because the applied references are not considered to have alleged differences, and therefore are considered to properly show that for which they were cited.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AYUB A MAYE whose telephone number is (571)270-5037. The examiner can normally be reached Monday-Friday 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, SHEWAYE GELAGAY can be reached at 571-272-4219. 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.
/AYUB A MAYE/Examiner, Art Unit 2436
/SHEWAYE GELAGAY/Supervisory Patent Examiner, Art Unit 2436
Prosecution Insights