DETAILED ACTION
Response to Arguments
The amendments and arguments filed 11/17/2025 have been entered and made of record.
The Applicant's amendments and arguments filed 11/17/2025 have been considered, but are moot in view of the new ground(s) of rejection because the Applicant has amended at least independent claims 1, 49; and similarly to newly added independent claims 95, 125, 155, 185, 215, with incorporated with some contents of the subject matters of previous dependent claim 2 which however has been rejected in previous Office Actions, and Applicant does not raise any arguments regarding above newly add limitations to the independent claims. Applicant's arguments in view of the amendments filed 11/17/2025 have been fully considered but they are not persuasive:
Re Claim 1, Applicant asserts (in pages 51-52 of the Arguments of 11/17/2025, as “maintains all prior remarks, including in Responses of 4/16/2025) that cited references, do not disclose the limitation “the updated personality data of the user is computed using the updated neural network”, and particularly contents that Tiziani does not disclose claimed “the updating the neural network” as the output of “the Updated Neural Network”;
However, the Examiner disagrees, because:
Tiziani clearly discloses “Updated Personality Data” as the output of “the Updated Neural Network”, at least in the following quoted paragraph:
--[0027] In one example, a machine learning model is trained and/or otherwise used to configure a vehicle for a user (e.g., tailor actions performed by the vehicle and/or an personalize an environment of the vehicle such as its interior). For example, the machine learning model may be based on pattern matching in which prior patterns of configuration data, user behavior, and/or other user data is correlated with desired characteristics or configuration(s) for operation of the vehicle. In some cases, the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--
Apparently, above “desired characteristics or configuration(s) for operation of the vehicle”, and, “to configure a vehicle for a user (e.g., tailor actions performed by the vehicle and/or an personalize an environment of the vehicle such as its interior).” read on the claimed “Updated Personality Data” as the output of “the Updated Neural Network”;
And, in response to Applicant’s remarks, it is well known that Tiziani’s teaching of “desired characteristics or configuration(s) for operation of the vehicle” as “Updated Personality Data” the output of the machine learning model of neural network, which has been trained and retrained iteratively with the input of stored personality data and user’s input as well to be “the updated neural network”, whcich then output real-time “Updated Personality Data”, such as in: Tiziani’s
-- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136];
As discussed in previous Office Actions:
Ilmini discloses claimed limitation the neural network has been initially trained before updating the neural network (see Ilmini: e.g., -- inputted to pre-trained deep convolution neural network. The research work [7], the winner at ChaLearn LPA Personality Analysis competition 2016 used deep learning in their bimodal systems
that is single hidden layer neural network was used for audio modality regression, while pre-trained deep convolutional neural networks were used for video representation and regression. In the both research works they have used transfer learning in their researches by using pre-trained deep convolution neural networks.--, in page 3/7, under the B. Video Based Personality Assessment;
also see: -- computational personality assessment with machine learning algorithms and recent trends in computational personality assessment with deep learning…. large scale image classification problems such as AlexNet, GoogLeNet, and Microsoft ResNet and they gave better results in ImageNet classification challenge. These models have been applied and adjusted for recognition of psychological characteristics from the facial features. The use of pre-trained model in new classification task is called as transfer learning. --, in pages 6/7, under the VI. CONCLUSION);
Ilmini discloses updating the neural network includes training the neural network based on the feedback (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
so that Ilmini teaches updating the features extracted to training the neural network, for example, using the cross-validation as the feedback to update/improve the neural network and to get better results, and above “the neural network” is pre-trained deep convolution neural networks, and/or use of pre-trained model, which read on claimed limitation “the neural network has been initially trained”. And, Ilmini’s disclosures of cross-validation is to re-train the pre-trained deep convolution neural networks based on the user’s the feedback, such as Ilmini’s disclosures of features extracted from “authors have used physiognomy”;
Tiziani also discloses updating the neural network based on the feedback, wherein the updating the neural network includes re-training the neural network based on the feedback after the neural network has been initially trained (see Tiziani: e.g., -- a machine learning model is trained and/or otherwise used to configure a vehicle for a user (e.g., tailor actions performed by the vehicle and/or an personalize an environment of the vehicle such as its interior). For example, the machine learning model may be based on pattern matching in which prior patterns of configuration data, user behavior, and/or other user data is correlated with desired characteristics or configuration(s) for operation of the vehicle. In some cases {so that Tiziani’s machine learning model of neural network is pre-trained, or “has been initially trained” based on based on pattern matching in which prior patterns of configuration data}, the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model. {so that, the neural network including the machine learning model is retained with the input of the driver may input selections as the feedback the updated configuration data for the user}--, in [0027]; and, -- an ANN model trained to process input data based on received configuration data of a user and/or collected data for a user may be used in one of many devices--, in [0029], and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]); and,
Ricci, and Tiziani disclose receiving feedback characterizing the user (see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; also see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]);
in above quoted disclosures, feedback can be Ricci’s user profiles and data associated with users, or Tiziani’s the drivers input selections into a user interface, or the data for the user used as input to the machine learning model, these are consistent with Ilmini “extract features” discussed above, used in updating/re-training the neural network in a neural network training process, in which the artificial neural network (ANN), or artificial neural network (ANN) model “has been initially trained” before installed onto the vehicle/server, and before the real time training, and training in real time is updating the pre-trained/initially trained artificial neural network (ANN), or artificial neural network (ANN) model.
Tiziani teaches the updated personality data of the user is computed using the updated neural network (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]; and, --the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]);
herein, particularly, “, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle).” read on the claimed element of “updated personality data of the user”, and such “configuration data” and/or “configuration data in real time” as “updated personality data of the user” is computed using the updated neural network, which is disclosed in: --the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model. {so that, the neural network including the machine learning model is retained with the input of the driver may input selections as the feedback the updated configuration data for the user}--, in [0027];
and, Tiziani’s “Configuration for an ANN model as used in a vehicle can be updated based on the training”, in Tiziani’s [0051]-[0053] read on “the updated neural network”, as see the following detailed discussing about “the updated neural network”, and how “updating the neural network” based on user’s feedback;
Ilmini discloses claimed limitation the neural network has been initially trained before updating the neural network (see Ilmini: e.g., -- inputted to pre-trained deep convolution neural network. The research work [7], the winner at ChaLearn LPA Personality Analysis competition 2016 used deep learning in their bimodal systems
that is single hidden layer neural network was used for audio modality regression, while pre-trained deep convolutional neural networks were used for video representation and regression. In the both research works they have used transfer learning in their researches by using pre-trained deep convolution neural networks.--, in page 3/7, under the B. Video Based Personality Assessment;
also see: -- computational personality assessment with machine learning algorithms and recent trends in computational personality assessment with deep learning…. large scale image classification problems such as AlexNet, GoogLeNet, and Microsoft ResNet and they gave better results in ImageNet classification challenge. These models have been applied and adjusted for recognition of psychological characteristics from the facial features. The use of pre-trained model in new classification task is called as transfer learning. --, in pages 6/7, under the VI. CONCLUSION);
Ilmini discloses updating the neural network includes training the neural network based on the feedback (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
so that Ilmini teaches updating the features extracted to training the neural network, for example, using the features extracted from “authors have used physiognomy”as the feedback to update/improve the neural network and to get better results, and above “the neural network” is pre-trained deep convolution neural networks, and/or use of pre-trained model, which read on claimed limitation “the neural network has been initially trained”. And, Ilmini’s disclosures of re-train the pre-trained deep convolution neural networks based on the user’s the feedback, such as Ilmini’s disclosures of features extracted from “authors have used physiognomy”;
Tiziani also discloses updating the neural network based on the feedback, wherein the updating the neural network includes re-training the neural network based on the feedback after the neural network has been initially trained (see Tiziani: e.g., -- a machine learning model is trained and/or otherwise used to configure a vehicle for a user (e.g., tailor actions performed by the vehicle and/or an personalize an environment of the vehicle such as its interior). For example, the machine learning model may be based on pattern matching in which prior patterns of configuration data, user behavior, and/or other user data is correlated with desired characteristics or configuration(s) for operation of the vehicle. In some cases {so that Tiziani’s machine learning model of neural network is pre-trained, or “has been initially trained” based on based on pattern matching in which prior patterns of configuration data}, the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model. {so that, the neural network including the machine learning model is retained with the input of the driver may input selections as the feedback the updated configuration data for the user}--, in [0027]; and, -- an ANN model trained to process input data based on received configuration data of a user and/or collected data for a user may be used in one of many devices--, in [0029], and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]);
I.C. Applicant further contends that the cited portion of Tiziani is opposite of the claimed “updated Neural Network” at least from an input-side/output-side perspective;
However, the Examiner disagrees, because:
(see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]; and,
--the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]; and,
-- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]
Apparently, in the ANN model is trained using collected user data, collected user data is the input to train “the neural network”, as the results, Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle), herein updated “Configuration data” is the output of the trained neural network, and it is not surprised that resulted “configuration data” also could be applied in training neural network, which could be iteration, contiguous process, and it is opposite to claimed limitations.
I.D. as the summarization of above discussions of I.A, I.B, and I.C, Ricci as modified by Ilmini and Tiziani teach the limitation “the updated personality data of the user is computed using the updated neural network”.
II. A. Applicant states that the Office Action Impermissibly Mixes Unrelated Embodiments of Ilmini Reference,
however the Examiner disagrees, because:
Ilmini discloses updating the neural network includes training the neural network based on the feedback (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
so that Ilmini teaches updating the features extracted to training the neural network, for example, using the features extracted from “authors have used physiognomy” as the feedback to update/improve the neural network and to get better results, and above “the neural network” is pre-trained deep convolution neural networks, and/or use of pre-trained model, which read on claimed limitation “the neural network has been initially trained”. And, Ilmini’s disclosures of re-train the pre-trained deep convolution neural networks based on the user’s the feedback, such as Ilmini’s disclosures of features extracted from “authors have used physiognomy”;
Apparently, and it is obvious that Applicant is confusing, mistakes “used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods”; which are the two different algorithms used in the training process.
IImini’s disclosures are applied in the claim rejections: to further modify Ricci’s method using Ilmini’s teachings by including a neural network trained to compute personality data of a user based on input obtained from the user, and updating the neural network includes training the neural network based on the feedback to Ricci’s “module” of artificial intelligence {fuzzy logic, or combination of hardware and software}, in order to compute personality data of a user based on input obtained from the user (see Ilmini: e.g. in pages 2, and 6).
II.B. Applicant contends that IImini’s Cross-Validation is for training to overcome the fault that may occur due to a less number of training images, and it is not the claimed updated neural network including re-training the neural network based on the claimed received feedback,
However, the Examiner disagrees, because:
Applicant tries to confuse the purpose of training the neural network with the training neural network step, IImini’s Cross-Validation is the purpose in evaluation the results from two different training algorithms, and one of these two algorithms is training, and re-training a deep neural network using the features extracted from “authors have used physiognomy” as the feedback to update/improve the neural network; and above features extracted from “authors have used physiognomy” is being updated, thus the training process is re-training process, since the pre-trained neural network has been initially installed on the vehicle before the test.
So that, IImini’s using the features extracted from “authors have used physiognomy” as the feedback, and as the input in training the deep neural network, and above features extracted from “authors have used physiognomy” is being updated, thus the training process is re-training process. These contents and disclosures of training and re-training step is applied into the claimed rejection.
IImini’s Cross-Validation which merely states the purpose in evaluation the results from two different training algorithms is irrelevant to the claimed rejections. And it should not been brought up into the arguments.
II.C. Applicant again contends that Tiziani’s neural network is opposite of claimed updated neural network at least from an input-side/outside perspective, and it output vehicle configuration, it is not used to computer updated personality data of user.
However, the Examiner disagrees, because:
(see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]; and,
--the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]; and,
-- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053];
Apparently, in the ANN model is trained using collected user data, collected user data is the input to train “the neural network”, as the results, Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle), herein updated “Configuration data” is the output of the trained neural network, and it is not surprised that resulted “configuration data” also could be applied in training neural network, which could be iteration, contiguous process, and it is opposite to claimed limitations.
As disclosed in Tiziani’s [0017]-[0024] as quoted above, Tiziani’s “configuration data” as the output of the neural network include identifying the user, and the personality data and characteristics of the user that would affect the user’s driving habits, preference.. etc. personalized for a user of the vehicle,
--a machine learning model is trained and/or otherwise used to configure a vehicle for a user (e.g., tailor actions performed by the vehicle and/or an personalize an environment of the vehicle such as its interior). For example, the machine learning model may be based on pattern matching in which prior patterns of configuration data, user behavior, and/or other user data is correlated with desired characteristics or configuration(s) for operation of the vehicle. In some cases, the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027].
II.D. Applicant again contends that Ricci is silent regarding Neural Networks,
As discussed in the claim rejections, claims are rejected under 35 USC § 103 as by the combination of Ricci as modified by Ilmini and Tiziani, as clearly stated in the claim rejections:
Ricci discloses artificial intelligence {fuzzy logic, or combination of hardware and software} to compute personality data of a user based on input obtained from the user (see Ricci: e.g., -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]);
Ricci however does not explicitly disclose above “module” of artificial intelligence {fuzzy logic, or combination of hardware and software} is trained neural network,
Ilmini discloses a neural network trained to compute personality data of a user based on input obtained from the user (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
Ricci and Ilmini are combinable as they are in the same field of endeavor: assessment of personality associated with psychology, persons’ behavior and appearance, and analyzing the personality traits. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Ricci’s method using Ilmini’s teachings by including a neural network trained to compute personality data of a user based on input obtained from the user to Ricci’s “module” of artificial intelligence {fuzzy logic, or combination of hardware and software} in order to compute personality data of a user based on input obtained from the user (see Ilmini: e.g. in pages 2, and 6),
Ricci as modified by Ilmini further disclose receiving, from the client device, a request for a digital representation of personality data for a user (see Ricci: e.g., -- the profile identification module 848 may receive requests from a user 216, or device 212, 228, 248, to access a profile stored in a profile database 856 or profile data 252. Additionally or alternatively, the profile identification module 848 may request profile information from a user 216 and/or a device 212, 228, 248, to access a profile stored in a profile database 856 or profile data 252. In any event, the profile identification module 848 may be configured to create, modify, retrieve, and/or store user profiles in the profile database 856 and/or profile data 252.--, in [0235]-0236], [0371], and [0388]);
II.E. as the summarization of above discussions of II.A, II.B, II.C, and II.D., Ricci as modified by Ilmini and Tiziani teach the limitation “updating the neural network based on the feedback wherein the updating the neural network includes re-training the neural network based on the feedback after the neural network has been initially trained”
Ricci, and Tiziani disclose receiving feedback characterizing the user (see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; also see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]);
in above quoted disclosures, feedback can be Ricci’s user profiles and data associated with users, or Tiziani’s the drivers input selections into a user interface, or the data for the user used as input to the machine learning model, these are consistent with Ilmini “extract features” discussed above, used in updating/re-training the neural network in a neural network training process, in which the artificial neural network (ANN), or artificial neural network (ANN) model “has been initially trained” before installed onto the vehicle/server, and before the real time training, and training in real time is updating the pre-trained/initially trained artificial neural network (ANN), or artificial neural network (ANN) model.
Therefore, claims 1, 3-18, 20-25, 27-42, and 44-244 are still not patentably distinguishable over the prior art reference(s). Further discussions are addressed in the prior art rejection section below.
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.
Claims 1, 3-11, 16-18, 20-25, 27-35, and 40-42, 44-58, 63-104, 109-134, 139-164, 169-194, 199-224, and 229-244 are rejected under 35 U.S.C. 103 as being unpatentable over Ricci (US 20140309790 A1, provided in IDS), in view of Ilmini (“Computational Personality Traits Assessment: A Review” Computational Personality Traits Assessment: A Review” IEEE, 2017, Pages 1-6, as provided in IDS), and further in view of Tiziani US (20190291719 A1, DATE FILED: 2018-03-21, provided in IDS).
Re Claim 1, Ricci discloses a method including a retrieval of a digital representation of personality data of a user by a client device from a server (see Ricci: e.g., --The stored data 232, being stored in a cloud or in a distant facility, may be exchanged among vehicles 104 or may be used by a user 216 in different locations or with different vehicles 104. Additionally or alternatively, the server may be associated with profile data 252--, in [0118]-[0120], {herein “the vehicle control system 204” is a client device, and “profile data 252” is “a digital representation of personality data of a user”}, also see: -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]),
the method being performed by the server and comprising:
storing artificial intelligence {fuzzy logic, or combination of hardware and software} to compute personality data of a user based on input obtained from the user (see Ricci: e.g., -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]);
Ricci however does not explicitly disclose above “module” of artificial intelligence {fuzzy logic, or combination of hardware and software} is trained neural network,
Ilmini discloses a neural network trained to compute user personality data based on user input (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
Ricci and Ilmini are combinable as they are in the same field of endeavor: assessment of personality associated with psychology, persons’ behavior and appearance, and analyzing the personality traits. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Ricci’s method using Ilmini’s teachings by including a neural network trained to compute user personality data based on user input to Ricci’s “module” of artificial intelligence {fuzzy logic, or combination of hardware and software} in order to compute personality data of a user based on input obtained from the user (see Ilmini: e.g. in pages 2, and 6),
Ricci as modified by Ilmini further disclose receiving, from the client device, a request for a digital representation of personality data for the user (see Ricci: e.g., -- the profile identification module 848 may receive requests from a user 216, or device 212, 228, 248, to access a profile stored in a profile database 856 or profile data 252. Additionally or alternatively, the profile identification module 848 may request profile information from a user 216 and/or a device 212, 228, 248, to access a profile stored in a profile database 856 or profile data 252. In any event, the profile identification module 848 may be configured to create, modify, retrieve, and/or store user profiles in the profile database 856 and/or profile data 252.--, in [0235]-0236], [0371], and [0388]);
and sending, to the client device, the requested digital representation of the personality data of the user (see Ricci: e.g., -- the profile identification module 848 may receive requests from a user 216, or device 212, 228, 248, to access a profile stored in a profile database 856 or profile data 252. Additionally or alternatively, the profile identification module 848 may request profile information from a user 216 and/or a device 212, 228, 248, to access a profile stored in a profile database 856 or profile data 252. In any event, the profile identification module 848 may be configured to create, modify, retrieve, and/or store user profiles in the profile database 856 and/or profile data 252.--, in [0235]-0236], -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371], -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381], and [0388]),
the digital representation of the personality data of the user is applied at the client device to provide a user-adapted service to the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]),
Ricci as modified by Ilmini however do not explicitly disclose that the personality data of the user is processed at the client device
Tiziani teaches the personality data of the user is processed at the client device to configure at least one setting of at least one device providing a user adapted service to the user, the at least one device being operated according to the at least one setting configured according to the processing of the digital representation of the personality data {to determine a vehicle configuration which is adapted to the personality of the user} (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]),
Ricci (as modified by Ilmini) and Tiziani are combinable as they are in the same field of endeavor: configuration of vehicle based on user’s personality data. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Ricci (as modified by Ilmini)’s method using Tizani’s teachings by including the personality data of the user is processed at the client device to configure at least one setting of at least one device providing a user adapted service to the user, the at least one device being operated according to the at least one setting configured according to the processing of the digital representation of the personality data {to determine a vehicle configuration which is adapted to the personality of the user} to Ricci’s client device in order to configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle) (see Tiziani: e.g. in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]);
Ricci as modified by Ilmini and Tiziani further disclose wherein the personality data of the user is computed using the neural network based on input obtained from the user (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2; and, .,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3); and wherein the method further comprises:
receiving feedback characterizing the user; updating the neural network based on the feedback wherein the updating the neural network includes re-training the neural network based on the feedback after the neural network has been initially trained (see Ilmini: e.g., -- inputted to pre-trained deep convolution neural network. The research work [7], the winner at ChaLearn LPA Personality Analysis competition 2016 used deep learning in their bimodal systems
that is single hidden layer neural network was used for audio modality regression, while pre-trained deep convolutional neural networks were used for video representation and regression. In the both research works they have used transfer learning in their researches by using pre-trained deep convolution neural networks.--, in page 3/7, under the B. Video Based Personality Assessment;
also see: -- computational personality assessment with machine learning algorithms and recent trends in computational personality assessment with deep learning…. large scale image classification problems such as AlexNet, GoogLeNet, and Microsoft ResNet and they gave better results in ImageNet classification challenge. These models have been applied and adjusted for recognition of psychological characteristics from the facial features. The use of pre-trained model in new classification task is called as transfer learning. --, in pages 6/7, under the VI. CONCLUSION);
Ilmini discloses updating the neural network includes training the neural network based on the feedback (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
So that Ilmini teaches updating the features extracted to training the neural network, for example, using the features extracted from “authors have used physiognomy” as the feedback to update/improve the neural network and to get better results, and above “the neural network” is pre-trained deep convolution neural networks, and/or use of pre-trained model, which read on claimed limitation “the neural network has been initially trained”. And, Ilmini’s disclosures of re-train the pre-trained deep convolution neural networks based on the user’s the feedback, such as Ilmini’s disclosures of features extracted from “authors have used physiognomy”;
also see Tiziani: e.g., -- a machine learning model is trained and/or otherwise used to configure a vehicle for a user (e.g., tailor actions performed by the vehicle and/or an personalize an environment of the vehicle such as its interior). For example, the machine learning model may be based on pattern matching in which prior patterns of configuration data, user behavior, and/or other user data is correlated with desired characteristics or configuration(s) for operation of the vehicle {highlighted as read on claimed “Updated Personality date” which is output from the machine learning model}. In some cases {so that Tiziani’s machine learning model of neural network is pre-trained, or “has been initially trained” based on based on pattern matching in which prior patterns of configuration data}, the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model. {so that, the neural network including the machine learning model is retained with the input of the driver may input selections as the feedback the updated configuration data for the user}--, in [0027]; and, -- an ANN model trained to process input data based on received configuration data of a user and/or collected data for a user may be used in one of many devices--, in [0029], and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]; and,
see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135];
{in above quoted disclosures, feedback can be Ricci’s user profiles and data associated with users, or Tiziani’s the drivers input selections into a user interface, or the data for the user used as input to the machine learning model {as disclosed in in Tiziani’ [0027]}, these are consistent with Ilmini “extract features” discussed above, used in updating/re-training the neural network in a neural network training process, in which the artificial neural network (ANN), or artificial neural network (ANN) model “has been initially trained” before installed onto the vehicle/server, and before the real time training, and training in real time is updating the pre-trained/initially trained artificial neural network (ANN), or artificial neural network (ANN) model}); and
sending, to the client device, a digital representation of updated personality data of the user, wherein the updated personality data of the user is computed using the updated neural network (see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027];also see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; and, -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re Claims 3, 27 and 50, Ricci as modified by Ilmini and Tiziani further disclose wherein the at least one device comprises the client device (see Ricci: e.g., --The stored data 232, being stored in a cloud or in a distant facility, may be exchanged among vehicles 104 or may be used by a user 216 in different locations or with different vehicles 104. Additionally or alternatively, the server may be associated with profile data 252--, in [0118]-[0120], {herein “the vehicle control system 204” is a client device, and “profile data 252” is “a digital representation of personality data of a user”}, also see: -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]).
Re Claims 4, 28, and 51, Ricci as modified by Ilmini and Tiziani further disclose wherein the digital representation of the updated personality data of the user is processed at the client device to refine a configuration of the at least one device providing the service to the user (see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; and, -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]; also see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]).
Re Claims 5, 29 and 52, Ricci as modified by Ilmini and Tiziani further disclose wherein the feedback includes behavioral data reflecting behavior of the user monitored at the at least one device when using the service provided by the at least one device (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]; also see Ilmini: e. g.,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3).
Re Claims 6, 30 and 53, Ricci as modified by Ilmini and Tiziani further disclose wherein the behavioral data is monitored using measurements performed by the at least one device providing the service to the user (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]; also see Ilmini: e. g.,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3).
Re Claims 7, 31 and 54, Ricci as modified by Ilmini and Tiziani further disclose wherein the at least one device comprises a vehicle and wherein the behavioral data comprises data reflecting a driving behavior of the user (see Ricci: e.g., -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]; -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]; also see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]).
Re Claims 8, 32 and 55, Ricci as modified by Ilmini and Tiziani further disclose wherein the feedback is indicative of the personality of the user (see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; also see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]).
Re Claims 9, 33 and 56, Ricci as modified by Ilmini and Tiziani further disclose wherein the personality data of the user is indicative of at least one of: psychological characteristics of the user, and preferences of the user (see Ilmini: e. g.,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3; also see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; also see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]).
Re Claims 10, 34 and 57, Ricci as modified by Ilmini and Tiziani further disclose wherein the input obtained from the user corresponds to regarding at least one answer regarding at least one of personality, goals and motivations of the user, the at least one answer given in response to at least one question posed to the user (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2; and, .,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3).
Re Claims 11, 35 and 58, Ricci as modified by Ilmini and Tiziani further disclose wherein the at least one answer regarding the personality of the user corresponds to at least one question of at least one of: an International Personality Item Pool, IPIP, a HEXACO-60 pool, a Big-Five-Inventory-10, BFI-10, pool, questions on psychological characteristics of the user, and questions on preferences of the user (see Ilmini: e. g.,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3).
Re Claims 16, 40, and 63 Ricci as modified by Ilmini and Tiziani further disclose wherein the personality data of the user is computed prior to receiving the request from the client device and wherein the request includes an access code previously provided by the server to the user upon computing the personality data of the user, the access code allowing the user to access the digital representation of the personality data of the user from different client devices (see Ricci: e.g., -- the user may provide a unique code to the vehicle control system 204 or provide some other type of data that allows the vehicle control system 204 to identify the user. The features or characteristics of the user are then stored in portion 1212.--, in [0302]).
Re Claims 17, 41, and 64, Ricci as modified by Ilmini and Tiziani further disclose wherein providing the user-adapted service to the user includes stimulating a brain, and wherein the digital representation of the personality data of the user is processed at the client device to adapt a stimulation procedure for a brain based on a personality of the user (see Ricci: e.g., --detecting a person via at least one image sensor associated with the vehicle. Aspects of the above method include wherein determining the identity of the user further comprises: identifying facial features associated with the person detected via the at least one image sensor….determining, based at least partially on the context of the input, a content of the virtual personality to suit the emotional state of the user.--, in [0007]; and, --The term "gesture" refers to a user action that expresses an intended idea, action, meaning, result, and/or outcome. The user action can include manipulating a device (e.g., opening or closing a device, changing a device orientation, moving a trackball or wheel, etc.), movement of a body part in relation to the device, movement of an implement or tool in relation to the device, audio inputs, etc. A gesture may be made on a device (such as on the screen) or with the device to interact with the device. [0040] The term "gesture capture" refers to a sense or otherwise a detection of an instance and/or type of user gesture. The gesture capture can be received by sensors in three-dimensional space.--, in [0039]-[0040]).
Re Claims 18, 42 and 65, Ricci as modified by Ilmini and Tiziani further disclose wherein providing the user-adapted service to the user includes:
- adapting a vehicle’s driving configuration, wherein the at least one device comprises a vehicle and wherein the digital representation of the personality data of
the user is processed at the client device to adapt a driving configuration of the vehicle to a personality of the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re Claims 20, 44 and 74, Ricci as modified by Ilmini and Tiziani further disclose wherein providing the user-adapted service to the user includes providing a vehicle configuration adapted to the personality to the user, and wherein the digital representation of the personality data of the user is processed at the client device to determine a vehicle configuration which is adapted to the personality of the user (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]).
Re Claims 21, 45 and 75, Ricci as modified by Ilmini and Tiziani further disclose wherein a vehicle is manufactured based on the determined vehicle configuration (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]; also see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re Claims 22, 46 and 76, Ricci as modified by Ilmini and Tiziani further disclose wherein the digital representation of the updated personality data of the user is processed at the client device to refine the vehicle configuration (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]; also see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re Claims 23, 47 and 77, Ricci as modified by Ilmini and Tiziani further disclose wherein the feedback is gathered at the client device (see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; also see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]).
Re Claims 24, 48 and 78, Ricci as modified by Ilmini and Tiziani further disclose wherein
(a) the input obtained from the user corresponds to one or more digital scores, each digital score reflecting one of the at least answer, and wherein each digital score is used as input to a separate input node of the neural network when computing the personality data of the user using the neural network (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2; and, .,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3);
(b) providing the user-adapted service to the user is further performed in consideration of body scan data indicative of characteristics of the user derivable by scanning at least a portion of the body of the user (see Ricci: e.g., --The term "gesture" refers to a user action that expresses an intended idea, action, meaning, result, and/or outcome. The user action can include manipulating a device (e.g., opening or closing a device, changing a device orientation, moving a trackball or wheel, etc.), movement of a body part in relation to the device, movement of an implement or tool in relation to the device, audio inputs, etc. A gesture may be made on a device (such as on the screen) or with the device to interact with the device. [0040] The term "gesture capture" refers to a sense or otherwise a detection of an instance and/or type of user gesture. The gesture capture can be received by sensors in three-dimensional space.--, in [0039]-[0040]); or
(a) and (b).
Re Claim 25, Ricci discloses a method including a retrieval of a digital representation of personality data of a user by a client device from a server (see Ricci: e.g., --The stored data 232, being stored in a cloud or in a distant facility, may be exchanged among vehicles 104 or may be used by a user 216 in different locations or with different vehicles 104. Additionally or alternatively, the server may be associated with profile data 252--, in [0118]-[0120], {herein “the vehicle control system 204” is a client device, and “profile data 252” is “a digital representation of personality data of a user”}, also see: -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]), the method being performed by the client device and comprising:
sending, to the server, a request for a digital representation of personality data for the user (see Ricci: e.g., -- the profile identification module 848 may receive requests from a user 216, or device 212, 228, 248, to access a profile stored in a profile database 856 or profile data 252. Additionally or alternatively, the profile identification module 848 may request profile information from a user 216 and/or a device 212, 228, 248, to access a profile stored in a profile database 856 or profile data 252. In any event, the profile identification module 848 may be configured to create, modify, retrieve, and/or store user profiles in the profile database 856 and/or profile data 252.--, in [0235]-0236], [0371], and [0388]);
receiving, from the server, the requested digital representation of the personality data of the user, the personality data of the user being computed, based on input obtained from the user, using artificial intelligence {fuzzy logic, or combination of hardware and software} to compute user personality data for based on user input (see Ricci: e.g., -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]);
Ricci however does not explicitly disclose above “module” of artificial intelligence {fuzzy logic, or combination of hardware and software} is trained neural network,
Ilmini discloses a neural network trained to compute personality data of a user based on input obtained from the user (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
Ricci and Ilmini are combinable as they are in the same field of endeavor: assessment of personality associated with psychology, persons’ behavior and appearance, and analyzing the personality traits. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Ricci’s method using Ilmini’s teachings by including a neural network trained to compute personality data of a user based on input obtained from the user to Ricci’s “module” of artificial intelligence {fuzzy logic, or combination of hardware and software} in order to compute personality data of a user based on input obtained from the user (see Ilmini: e.g. in pages 2, and 6),
Ricci as modified by Ilmini further disclose apply the digital representation of the personality data of the user at the client device to provide a user-adapted service to the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]),
Ricci as modified by Ilmini however do not explicitly disclose processing the digital representation of the personality data to configure at least one setting of at least one device providing a user adapted service to the user, and operating the at least one device according to the at least one setting configured according to the processing of the digital representation of the personality data {to determine a vehicle configuration which is adapted to the personality of the user}
Tiziani teaches processing the digital representation of the personality data to configure at least one setting of at least one device providing a user adapted service to the user, and operating the at least one device according to the at least one setting configured according to the processing of the digital representation of the personality data {to determine a vehicle configuration which is adapted to the personality of the user} (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]),
Ricci (as modified by Ilmini) and Tiziani are combinable as they are in the same field of endeavor: configuration of vehicle based on user’s personality data. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Ricci (as modified by Ilmini)’s method using Tizani’s teachings by including processing the digital representation of the personality data to configure at least one setting of at least one device providing a user adapted service to the user, and operating the at least one device according to the at least one setting configured according to the processing of the digital representation of the personality data {to determine a vehicle configuration which is adapted to the personality of the user} to Ricci’s client device in order to configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle) (see Tiziani: e.g. in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]), Ricci as modified by Ilmini and Tiziani further disclose wherein the method further comprises:
sending, to the server, feedback characterizing the user (see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; also see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]); and
receiving, from the server, a digital representation of updated personality data of the user, wherein the updated personality data of the user is computed using the neural network being updated based on the feedback (see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027];also see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; and, -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re 49, Ricci discloses a method including a retrieval of a digital representation of personality data of a user, the digital representation of the personality data being processed to provide a user-adapted service to the user (see Ricci: e.g., --The stored data 232, being stored in a cloud or in a distant facility, may be exchanged among vehicles 104 or may be used by a user 216 in different locations or with different vehicles 104. Additionally or alternatively, the server may be associated with profile data 252--, in [0118]-[0120], {herein “the vehicle control system 204” is a client device, and “profile data 252” is “a digital representation of personality data of a user”}, also see: -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]), the method comprising:
obtaining a digital representation of personality data of the user, the personality data of the user being computed, based on input obtained from the user (see Ricci: e.g., -- The personality module 2004 may be configured to present a virtual personality to a user 216 associated with a vehicle 104 via one or more displays, screens, speakers, and/or devices, associated with the vehicle 104. As can be appreciated, the virtual personality may be presented to a user 216 in at least one of an audible, visual, and tactile form. The personality module 2004 may be configured to interact with one or more users 216 of a vehicle 104…. The personality matching module 2008 may communicate with a user profile stored in profile data memory 252. The user profile may have a corresponding user interface or personality defined or configured by the user 216--, in [0368]-[0371]);
Ricci however does not explicitly disclose above the user personality data being computed using a trained neural network,
Ilmini discloses a neural network trained to compute user personality data based on input obtained from the user (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
Ricci and Ilmini are combinable as they are in the same field of endeavor: assessment of personality associated with psychology, persons’ behavior and appearance, and analyzing the personality traits. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Ricci’s method using Ilmini’s teachings by including a neural network trained to compute user personality data based on input obtained from the user to Ricci’s “module” of artificial intelligence {fuzzy logic, or combination of hardware and software} in order to compute personality data of a user based on input obtained from the user (see Ilmini: e.g. in pages 2, and 6),
Ricci as modified by Ilmini however do not explicitly disclose processing the digital representation of the personality data to configure at least one setting of at least one device providing a user-adapted service to the user, and operating the at least one device according to the at least one setting configured according to the processing of the digital representation of the personality data {to determine a vehicle configuration which is adapted to the personality of the user},
Tiziani discloses processing the digital representation of the personality data to provide a user-adapted service to the user {such as to determine a vehicle configuration which is adapted to the personality of the user} (see Tiziani: e.g., -- configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle). For example, the vehicle can be personalized for a user of the vehicle so that operation of the vehicle is more aggressive in rate of acceleration, turning, passing, etc…. the vehicle that is personalized is, for example, a manually-driven vehicle or an autonomous vehicle (e.g., a car, truck, aircraft, drone, watercraft, etc.). The configuration is based on identifying the user that is, for example, currently operating, or will be operating in the future, the vehicle…. configuration data is retrieved (e.g., from the mobile device of the user) after identifying the user. The configuration data is transmitted to the vehicle and used to configure at least one action performed by the vehicle (e.g., an action to be performed in the future when the user is operating or riding in the vehicle). In some examples, the configuration can be implemented in real-time (e.g., based on new data collected regarding the user and/or via the vehicle). The configuration data can be, for example, stored in memory of the vehicle after being received by the vehicle--, in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]),
Ricci (as modified by Ilmini) and Tiziani are combinable as they are in the same field of endeavor: configuration of vehicle based on user’s personality data. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Ricci (as modified by Ilmini)’s method using Tizani’s teachings by including processing the digital representation of the personality data to configure at least one setting of at least one device providing a user adapted service to the user, and operating the at least one device according to the at least one setting configured according to the processing of the digital representation of the personality data {to determine a vehicle configuration which is adapted to the personality of the user} to Ricci’s client device in order to configure a vehicle (e.g., that has been rented by a user) to perform at least one action in a way that is personalized for one or more preferences of the user (e.g., control of acceleration of the vehicle) (see Tiziani: e.g. in [0017]-[0024], [0032]-[0034], [0073], and [0134]-[0136]), Ricci as modified by Ilmini and Tiziani further disclose wherein the method further comprises:
obtaining feedback characterizing the user (see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; also see Tiziani: e.g., -- the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model.--, in [0027]); and
obtaining a digital representation of updated personality data of the user, wherein the updated personality data of the user is computed using the neural network being in a state in which updating the neural network has been performed based on the feedback, wherein the updating the neural network includes re-training the neural network based on the feedback after the neural network has been initially trained (see Ilmini: e.g., -- inputted to pre-trained deep convolution neural network. The research work [7], the winner at ChaLearn LPA Personality Analysis competition 2016 used deep learning in their bimodal systems
that is single hidden layer neural network was used for audio modality regression, while pre-trained deep convolutional neural networks were used for video representation and regression. In the both research works they have used transfer learning in their researches by using pre-trained deep convolution neural networks.--, in page 3/7, under the B. Video Based Personality Assessment;
also see: -- computational personality assessment with machine learning algorithms and recent trends in computational personality assessment with deep learning…. large scale image classification problems such as AlexNet, GoogLeNet, and Microsoft ResNet and they gave better results in ImageNet classification challenge. These models have been applied and adjusted for recognition of psychological characteristics from the facial features. The use of pre-trained model in new classification task is called as transfer learning. --, in pages 6/7, under the VI. CONCLUSION);
Ilmini discloses updating the neural network includes training the neural network based on the feedback (see Ilmini: e. g., -- To extract features, both the authors have used physiognomy, and in the training process, they have used Nfold cross-validation to overcome the fault that may occur due to less no of training images. In the training process [3] have used the artificial neural network and multi class support vector machine algorithms separately to compare results obtained from both methods and as they stated better results have been obtained from artificial neural network.--, in page 2);
So that Ilmini teaches updating the features extracted to training the neural network, for example, using the features extracted from “authors have used physiognomy” as the feedback to update/improve the neural network and to get better results, and above “the neural network” is pre-trained deep convolution neural networks, and/or use of pre-trained model, which read on claimed limitation “the neural network has been initially trained”. And, Ilmini’s disclosures of re-train the pre-trained deep convolution neural networks based on the user’s the feedback, such as Ilmini’s disclosures of features extracted from “authors have used physiognomy”;
also see Tiziani: e.g., -- a machine learning model is trained and/or otherwise used to configure a vehicle for a user (e.g., tailor actions performed by the vehicle and/or an personalize an environment of the vehicle such as its interior). For example, the machine learning model may be based on pattern matching in which prior patterns of configuration data, user behavior, and/or other user data is correlated with desired characteristics or configuration(s) for operation of the vehicle. In some cases {so that Tiziani’s machine learning model of neural network is pre-trained, or “has been initially trained” based on based on pattern matching in which prior patterns of configuration data}, the machine learning model may further use driver user inputs collected during usage of the vehicle to control actions of the vehicle. For example, the driver may input selections into a user interface located in the vehicle. In some cases, configuration data for the user is updated in real-time and used as an input to the machine learning model. {so that, the neural network including the machine learning model is retained with the input of the driver may input selections as the feedback the updated configuration data for the user}--, in [0027]; and, -- an ANN model trained to process input data based on received configuration data of a user and/or collected data for a user may be used in one of many devices--, in [0029], and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053];
also see Ricci: e.g., -- any necessary files for performing the functions attributed to the vehicle control system 204 may be stored locally on the respective vehicle control system 204 and/or remotely, as appropriate. The databases or data stores may be a relational database, and the data storage module 320 may be adapted to store, update, and retrieve data in response to specifically-formatted commands. The data storage module 320 may also perform data management functions for any flat file, object oriented, or other type of database or data store. [0134] A first data store that may be part of the vehicle control environment 300 is a profile data store 252 for storing data about user profiles and data associated with the users. A system data store 208 can include data used by the vehicle control system 204 and/or one or more of the components 324-352--, in [0133]-[0135]; and, -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381];
{in above quoted disclosures, feedback can be Ricci’s user profiles and data associated with users, or Tiziani’s the drivers input selections into a user interface, or the data for the user used as input to the machine learning model {as disclosed in in Tiziani’ [0027]}, these are consistent with Ilmini “extract features” discussed above, used in updating/re-training the neural network in a neural network training process, in which the artificial neural network (ANN), or artificial neural network (ANN) model “has been initially trained” before installed onto the vehicle/server, and before the real time training, and training in real time is updating the pre-trained/initially trained artificial neural network (ANN), or artificial neural network (ANN) model}).
Re Claims 66, 79, 87 Ricci as modified by Ilmini and Tiziani further disclose wherein the at least one device comprises a transport means, wherein providing a user-adapted service to the user adapting an environmental condition in a passenger cabin of a transport means, wherein the at least one device comprises the transport means and wherein the digital representation of the personality data of the user is processed at the client device to adapt an environmental condition in a passenger cabin of the transport means to a personality of the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re Claims 67, 69, 80, 82, 88, 90, Ricci as modified by Ilmini and Tiziani further disclose when the at least one device comprises the transport means, providing the user- adapted service to the user is further performed in consideration of sensor data indicative of an attention level of the user obtained in a passenger cabin of the transport means (see Ricci: e.g., --detecting a person via at least one image sensor associated with the vehicle. Aspects of the above method include wherein determining the identity of the user further comprises: identifying facial features associated with the person detected via the at least one image sensor….determining, based at least partially on the context of the input, a content of the virtual personality to suit the emotional state of the user.--, in [0007]).
Re Claims 68, 81, 89 Ricci as modified by Ilmini and Tiziani further disclose adapting a user-specific setting regarding a passenger cabin of the transport means, wherein the at least one device comprises the transport means and wherein the digital representation of the personality data of the user is processed at the client device to adapt a user-specific setting regarding a passenger cabin of the transport means to a personality of the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381])
Re Claims 70, 83, 91, Ricci as modified by Ilmini and Tiziani further disclose adapting a configuration of a smart home appliance, wherein the at least one device comprises a smart home appliance and wherein the digital representation of the personality data of the user is processed at the client device to adapt a configuration of the smart home appliance to a personality of the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re Claims 71, 84, 92, Ricci as modified by Ilmini and Tiziani further disclose adapting a configuration of a robot, wherein at least one device comprises a robot, and wherein the digital representation of the personality data of the user is processed at the client device to adapt a configuration of the robot to a personality of the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]),
Re Claims 72, 85, 93 Ricci as modified by Ilmini and Tiziani further disclose adapting a configuration of a virtual robot, wherein the at least one device executes a virtual robot and wherein the digital representation of the personality data of the user is processed at the client device to adapt a configuration of the virtual robot to a personality of the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re Claims 73, 86, 94 Ricci as modified by Ilmini and Tiziani further disclose adapting a configuration of a medical device, wherein the at least one device comprises a medical device and wherein the digital representation of the personality data of the user is processed at the client device to adapt a configuration of the medical device to a personality of the user (see Ricci: e.g., -- presenting the virtual personality to a user 216 may include altering one or more features of the vehicle 104. For instance, one or more features of the vehicle 104 may be altered to change a mood associated with the virtual personality. Continuing this example, the personality module 2004 may communicate with the vehicle control system 204 to change an internal lighting, an infotainment setting, a temperature, an oxygen level, an air composition, a comfort setting, a seat position, a transmission setting (e.g., automatic to manual, paddle shifting, and more), a navigation output, etc., and/or combinations thereof.--, in [0380]-[0381]).
Re Claims 95-104, 109-134, 139-164, and 169-184, claims 95-104, 109-134, 139-164, and 169-184 are corresponding medium claim to claims 1, 3-11, 16-18, 20-25, 27-35, 40-42, 44-58, 63-94 respectively. Claims 95-104, 109-134, 139-164, and 169-184 thus are rejected for the similar reasons for claims 1, 3-11, 16-18, 20-25, 27-35, 40-42, 44-58, 63-94. See above discussions with regard to claims 1, 3-11, 16-18, 20-25, 27-35, 40-42, 44-58, 63-94 respectively. Ricci as modified by Ilmini and Tiziani further disclose One or more non-transitory computer readable recording mediums storing a
computer program product executable by a server {a client device} for at least a retrieval of a digital representation of personality data of a user by a client device from the server to perform the method (see Ricci: e.g., -- [0008] Embodiments include a non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, perform operations comprising the above methods. Embodiments include a device, means, and/or system configured to perform the above methods. [0009] Embodiments include a vehicle control system, comprising a personality module contained in a memory and executed by a processor of the vehicle control system, the personality module configured to determine a presence of a user inside a vehicle; determine an identity of the user, receive input provided by the user, the input having a context associated therewith, and retrieve, based at least partially on the input provided by the user, a virtual personality for presentation to at least one device associated with the vehicle.--, in [0008]-[0009]).
Re Claims 185-194, and 199-214, claims 185-194, and 199-214 are corresponding medium claim to claims 1, 3-11, 16-18, 20-24, and 66-73 respectively. Claims 185-194, and 199-214 thus are rejected for the similar reasons for claims 1, 3-11, 16-18, 20-24, and 66-73. See above discussions with regard to claims 1, 3-11, 16-18, 20-24, and 66-73 respectively. Ricci as modified by Ilmini and Tiziani further disclose a server comprising at least one processor and at least one memory, the at least one memory containing instructions executable by the at least one processor at least for a retrieval of a digital representation of personality data of a user by a client device from the server, the at least one memory containing the instructions executable by the at least one processor such that the server is operable at least to perform the method (see Ricci: e.g., -- [0008] Embodiments include a non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, perform operations comprising the above methods. Embodiments include a device, means, and/or system configured to perform the above methods. [0009] Embodiments include a vehicle control system, comprising a personality module contained in a memory and executed by a processor of the vehicle control system, the personality module configured to determine a presence of a user inside a vehicle; determine an identity of the user, receive input provided by the user, the input having a context associated therewith, and retrieve, based at least partially on the input provided by the user, a virtual personality for presentation to at least one device associated with the vehicle.--, in [0008]-[0009]; and, and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]).
Re Claims 185-194, and 199-214, claims 185-194, and 199-214 are corresponding server claim to claims 1, 3-11, 16-18, 20-24, and 66-73 respectively. Claims 185-194, and 199-214 thus are rejected for the similar reasons for claims 1, 3-11, 16-18, 20-24, and 66-73. See above discussions with regard to claims 1, 3-11, 16-18, 20-24, and 66-73 respectively. Ricci as modified by Ilmini and Tiziani further disclose a server comprising at least one processor and at least one memory, the at least one memory containing instructions executable by the at least one processor at least for a retrieval of a digital representation of personality data of a user by a client device from the server, the at least one memory containing the instructions executable by the at least one processor such that the server is operable at least to perform the method (see Ricci: e.g., -- [0008] Embodiments include a non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, perform operations comprising the above methods. Embodiments include a device, means, and/or system configured to perform the above methods. [0009] Embodiments include a vehicle control system, comprising a personality module contained in a memory and executed by a processor of the vehicle control system, the personality module configured to determine a presence of a user inside a vehicle; determine an identity of the user, receive input provided by the user, the input having a context associated therewith, and retrieve, based at least partially on the input provided by the user, a virtual personality for presentation to at least one device associated with the vehicle.--, in [0008]-[0009]; and, and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]).
Re Claims 215-224, and 229-244, claims 215-224, and 229-244 are corresponding client device claim to claims 1, 3-11, 16-18, 20-24, and 66-73 respectively. Claims 215-224, and 229-244 thus are rejected for the similar reasons for claims 1, 3-11, 16-18, 20-24, and 66-73. See above discussions with regard to claims 1, 3-11, 16-18, 20-24, and 66-73 respectively. Ricci as modified by Ilmini and Tiziani further disclose a client deivce comprising at least one processor and at least one memory, the at least one memory containing instructions executable by the at least one processor at least for a retrieval of a digital representation of personality data of a user by a client device from the server, the at least one memory containing the instructions executable by the at least one processor such that the client device is operable at least to perform the method (see Ricci: e.g., -- [0008] Embodiments include a non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, perform operations comprising the above methods. Embodiments include a device, means, and/or system configured to perform the above methods. [0009] Embodiments include a vehicle control system, comprising a personality module contained in a memory and executed by a processor of the vehicle control system, the personality module configured to determine a presence of a user inside a vehicle; determine an identity of the user, receive input provided by the user, the input having a context associated therewith, and retrieve, based at least partially on the input provided by the user, a virtual personality for presentation to at least one device associated with the vehicle.--, in [0008]-[0009]; and, and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]).
Claims 12-15, 36-39, 59-62, 105-108, 135-138, 165-168, 195-198, and 225-228 are rejected under 35 U.S.C. 103 as being unpatentable over Ricci as modified by Ilmini and Tiziani, and further in view of Moturu (US 20170004260 A1, provided in IDS).
Re Claims 12, 36, and 59, Ricci as modified by Ilmini and Tiziani however do not explicitly disclose the at least one question correspond to at least one question selected from a set of questions representative of an optimally achievable result of computing personality data of a user, and wherein the at least one selected question corresponds to at least one question of the set of questions determined to be most influential with respect to the optimally achievable result, and, optionally: wherein the number of the selected questions is less than 10% of the number of questions included in the set of questions,
Moturn discloses the at least one question correspond to at least one question selected from a set of questions representative of an optimally achievable result of computing personality data of a user, and wherein the at least one selected question corresponds to at least one question of the set of questions determined to be most influential with respect to the optimally achievable result, and, optionally: wherein the number of the selected questions is less than 10% of the number of questions included in the set of questions (see Moturn: e.g., -- to reduce questions from provided surveys to a subset of effective questions, and other statistical methods and statistic fitting techniques to select a subset of features having high efficacy--, in [0098]);
Ricci (as modified by Ilmini and Tiziani) and Moturn are combinable as they are in the same field of endeavor: assessment of personality data, and analyzing the personality traits. Therefore it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to further modify Ricci (as modified by Ilmini and Tiziani)’s method using Moturn’s teachings by including the at least one question correspond to at least one question selected from a set of questions representative of an optimally achievable result of computing personality data of a user, and wherein the at least one selected question corresponds to at least one question of the set of questions determined to be most influential with respect to the optimally achievable result, and, optionally: wherein the number of the selected questions is less than 10% of the number of questions included in the set of questions, and, optionally: wherein the number of the selected questions is less than 10% of the number of questions included in the set of questions to Ricci (as modified by Ilmini and Tiziani)’s questions in order to reduce questions from provided surveys to a subset of effective questions for personality assessment (see Morturn: e.g. in [0098]).
Re Claims 13, 37, and 60 Ricci as modified by Ilmini and Tiziani and Moturn further disclose wherein the number of the at least one selected question is less than 10% of the number of questions included in the set of questions (see Moturn: e.g., -- to reduce questions from provided surveys to a subset of effective questions, and other statistical methods and statistic fitting techniques to select a subset of features having high efficacy--, in [0098]).
Re Claims 14, 38, and 61, Ricci as modified by Ilmini and Tiziani and Moturn further disclose (a) wherein the at least one question selected from the set of questions
based on correlating results achievable by each single question of the set of questions with the optimally achievable result and selecting at least one question from the set of
questions having a highest correlation with the optimally achievable result (see Ilmini: e. g.,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3), or
wherein the at least one question is selected iteratively from the set of questions, wherein, in each iteration, a next question is selected depending on an answer of the user to a previous question, wherein, in each iteration, the next question is selected as a question of the set of questions which is determined to be most influential on an achievable result for computing personality data of the user (see Moturn: e.g., -- to reduce questions from provided surveys to a subset of effective questions, and other statistical methods and statistic fitting techniques to select a subset of features having high efficacy--, in [0098]).
Re Claims 15, 39, and 62, Ricci as modified by Ilmini and Tiziani and Moturn further disclose wherein, in the case of (b): the input obtained from the user corresponds to one or more digital scores, each digital score reflecting one of the at least one answer, wherein each digital score is used as input to a separate input node of the neural network when computing the personality data of the user using the neural network, the neural network comprises a plurality of output nodes representative of a probability curve of a result of the personality data of the user, and determining the most influential question of the set of questions as the next question of the respective iteration includes determining, for each input node of the neural network, a degree according to which a change in the digital score input to the respective input node of the neural network changes the probability curve (see Ilmini: e. g.,-- Big Five structure has the advantage that everybody can understand the words that define the factors and disagreements about their meanings can be reconciled by establishing their most common usage. The “Big Five Inventory” a questionnaire which is used to measure Big Five personality traits depend on the scoring values given by the user--, and, -- Their system takes two inputs: first one is unlabeled text data with the authors and the second one is a set of correlations between personality traits and linguistic features. The system generates two outputs, first one is one model of personality for each author and second one is a confidence score for each personality trait of models. They have built a correlation between personality and written text (Facebook comments) to assess personality traits from Facebook interaction style. The research work [17] has done a study on identifying correlations between users’ personality and the properties of their Facebook profiles with regression algorithms.--, in pages 1-3).
Re Claims 105-108, 135-138, and 165-168, claims 105-108, 135-138, and 165-168 are corresponding medium claim to claims 12-15, 36-39, and 59-62 respectively. Claims 105-108, 135-138, and 165-168 thus are rejected for the similar reasons for claims 12-15, 36-39, and 59-62. See above discussions with regard to claims 12-15, 36-39, and 59-62 respectively. Ricci as modified by Ilmini and Tiziani and Moturn further disclose one or more non-transitory computer readable recording mediums storing a computer program product executable by a server for at least a retrieval of a digital representation of personality data of a user by a client device from the server to perform the method (see Ricci: e.g., -- [0008] Embodiments include a non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, perform operations comprising the above methods. Embodiments include a device, means, and/or system configured to perform the above methods.
[0009] Embodiments include a vehicle control system, comprising a personality module contained in a memory and executed by a processor of the vehicle control system, the personality module configured to determine a presence of a user inside a vehicle; determine an identity of the user, receive input provided by the user, the input having a context associated therewith, and retrieve, based at least partially on the input provided by the user, a virtual personality for presentation to at least one device associated with the vehicle.--, in [0008]-[0009]).
Re Claims 195-198, claims 195-198 are corresponding server claim to claims 12-15 respectively. Claims 195-198 thus are rejected for the similar reasons for claims 12-15. See above discussions with regard to claims 12-15 respectively. Ricci as modified by Ilmini and Tiziani and Moturn further disclose a server comprising at least one processor and at least one memory, the at least one memory containing instructions executable by the at least one processor at least for a retrieval of a digital representation of personality data of a user by a client device from the server, the at least one memory containing the instructions executable by the at least one processor such that the server is operable at least to perform the method (see Ricci: e.g., -- [0008] Embodiments include a non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, perform operations comprising the above methods. Embodiments include a device, means, and/or system configured to perform the above methods. [0009] Embodiments include a vehicle control system, comprising a personality module contained in a memory and executed by a processor of the vehicle control system, the personality module configured to determine a presence of a user inside a vehicle; determine an identity of the user, receive input provided by the user, the input having a context associated therewith, and retrieve, based at least partially on the input provided by the user, a virtual personality for presentation to at least one device associated with the vehicle.--, in [0008]-[0009]; and, and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]).
Re Claims 225-228, claims 225-228 are corresponding client device claim to claims 12-15 respectively. Claims 225-228 thus are rejected for the similar reasons for claims 12-15. See above discussions with regard to claims 12-15 respectively. Ricci as modified by Ilmini and Tiziani and Moturn further disclose a client device comprising at least one processor and at least one memory, the at least one memory containing instructions executable by the at least one processor at least for a retrieval of a digital representation of personality data of a user by a client device from the server, the at least one memory containing the instructions executable by the at least one processor such that the client device is operable at least to perform the method (see Ricci: e.g., -- [0008] Embodiments include a non-transitory computer readable medium having instructions stored thereon that, when executed by a processor, perform operations comprising the above methods. Embodiments include a device, means, and/or system configured to perform the above methods. [0009] Embodiments include a vehicle control system, comprising a personality module contained in a memory and executed by a processor of the vehicle control system, the personality module configured to determine a presence of a user inside a vehicle; determine an identity of the user, receive input provided by the user, the input having a context associated therewith, and retrieve, based at least partially on the input provided by the user, a virtual personality for presentation to at least one device associated with the vehicle.--, in [0008]-[0009]; and, and, -- the server 101 includes a supervised training module 117 to train, generate, and update ANN model 119 that includes neuron biases 121, synaptic weights 123, and activation functions 125 of neurons in a network used for processing configuration data of a user and/or sensor data generated in the vehicles 111,… the ANN model is trained using collected user data. The training can be performed on a server and/or the vehicle. Configuration for an ANN model as used in a vehicle can be updated based on the training (e.g., by sending configuration data for a user to the vehicle). The training can be performed in some cases while the vehicle is being operated. {herein “The training can be performed in some cases while the vehicle is being operated” align with re-train a pretrained artificial neural network (ANN) model --, in [0051]-[0053]).
Conclusion
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 extension fee 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 date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to WEI WEN YANG whose telephone number is (571)270-5670. The examiner can normally be reached on 8:00 - 5:00 pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Amandeep Saini can be reached on 571-272-3382. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/WEI WEN YANG/Primary Examiner, Art Unit 2662