DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statements (IDSs) submitted on 07/09/2024 and 05/08/2025 were filed in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statements are being considered by the examiner.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-8, 10-17, 19, and 20 rejected under 35 U.S.C. 101 because the claimed invention is directed to abstract idea without significantly more. Independent claims 1, 3, and 12 relate to the statutory category of method/process and machine/apparatus. The claim recite “receiving first data to determine a predicted action of a user, wherein the first data indicates at least one or more inferred interests of the user; generating first prompt data including the first data and a request to determine the predicted action based on the first data; using a language model to process the first prompt data and determine a description of the predicted action; performing a semantic query of a system-performable action storage to determine a system-performable action whose description is semantically similar to the description of the predicted action as determined by the language model; determining one or more tasks to be performed to execute the system-performable action; generating second prompt data including two or more trigger events and a request to determine one or more, of the two or more trigger events, for triggering performance of the one or more tasks; storing first proactive task plan data including a user identifier of the user, second data representing the one or more tasks, and third data representing the one or more trigger events; after storing the first proactive task plan data, receiving event data indicating the one or more trigger events has occurred; based on the event data corresponding to the one or more trigger events, identifying the first proactive task plan data in a storage component; after identifying the first proactive task plan data in the storage component, causing the one or more tasks to be performed to generate first proactive output data; and outputting the first proactive output data using one or more devices associated with the user identifier”.
Independent claims 3 and 12 recite “receiv(ing) first data indicating one or more interests of a user; generat(ing) first prompt data requesting a generative model determine a predicted action of the user based on the first data; using the generative model to process the first prompt data and determine the predicted action; determin(ing) one or more tasks to be performed to execute the predicted action; determin(ing) one or more trigger events for triggering performance of the one or more tasks; after determin(ing) the one or more trigger events, determining the one or more trigger events has occurred; based on the one or more trigger events occurring, caus(ing) the one or more tasks to be performed to generate first proactive output data; and output(ting) the first proactive output data using one or more devices of the user”.
The limitations of claim 1 of “”receiving…”, “generating…”, “using…, “performing…”, “determining…”, “generating…”, “storing…”, “…receiving…”, “…identifying…”, “…causing…”, “…outputting…” as drafted covers mental activity. More specifically, a human receives data and determines what the next action will be based on what the data indicates is the user’s interest. They are then prompted to determine the next action based on the received data. The prompt is then processed and the predicted action is described. A query is performed to determine if the action is semantically comparable to the predicted action. Determination is made to figure out the tasks needed to performed to complete the action. A second prompt is generated that triggers one or more of the tasks that need to be performed. A table is proactively generated that lists the user id, the one or more tasks that need to be performed and the triggering events that the tasks need to be performed. Notification is made as the triggering events have occurred. Based on the notifications, the user is identified as listed on the table. After the user is identified, the tasks assigned to the user are performed and the proactive data is output. A human after hearing about a user’s intent or interest, will proactively predict what the next action will be in response to the intent or interest and they can also determine what tasks need to be performed in order to complete the action. Also, they can determine if there is a trigger or a cause to perform the specific tasks.
The limitations of claims 3 and 12 of “”receiving…”, “generating…”, “using…, “determining…”, “determining…”,“…determining…”, “…causing…”, “…outputting…” as drafted covers mental activity. More specifically, a human after hearing about a user’s intent or interest, will proactively predict what the next action will be in response to the intent or interest and they can also determine what tasks need to be performed in order to complete the action. Also, they can determine if there is a trigger or a cause to perform the specific tasks.
This judicial exception is not integrated into a practical application, In particular, claim 12 recites the additional elements of “processor” and “memory”, which are recited generally in the specification. For example, in paragraph [00230] of the as filed specification, there is a description of using a general purpose operating system. Accordingly, these additional elements do not integrate the abstract idea int a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to the integrating of the abstract idea int a practical application, the additional element using a computer as a general computer is noted. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept. The claims are not patent eligible.
With respect to claims 2, 4, and 13, the claims relate determining that dialog with the user has ended and the proactive data has been presented to the user. Once the proactive content has been presented to the user, multiple tasks are assigned to the user id. Determination is made if the proactive content is capable of being presented to the user. A second task plan is created by analyzing the proactive task plan and the proactive content. One or more tasks from the second task plan are performed to generate second output data. The claims relate to a mental activity of determining the proactive task from a list of previous tasks that have been associated with the user. No additional limitations are present.
With respect to claims 5 and 14, the claims relate to determining if there is a trigger or cause which leads to a predicted action. The claims relate to a mental activity for determining if there is something specific that happens to lead to a predicted action. No additional limitations are present.
With respect to claims 6 and 15, the claims relate to determining what information is necessary (user interests, user feedback, or user actions) in order generate the predicted action. The claims relate to a mental activity of determining why the predicted action is necessary. No other limitations are present.
With respect to claims 7 and 16, the claims relate to determining if the user data has been updated and determining if the updated data was used for the predicted action. The claims relate to a mental activity of perform the predicted action and determining if the predicted action was in response to the most recent data stored in a user profile. No other limitations are present.
With respect to claims 8 and 17, the claims relate to either getting updates on the topics being discussed or by determining if there is information that the user is prevented from getting. The predicted action is completed based on what information is received. The claims relate to a mental activity of predicting an action based on the information received or not received No other limitations are present.
With respect to claims 10 and 19, the claims relate to determining if the utterance corresponding to the predicted action is grammatically similar to the response data related to the predicted action. The claims relate to a mental activity of determining if the language of the predicted action and the action to be performed are semantically similar.. No other limitations are present.
With respect to claims 11 and 20, the claims relate to determining if the predicted action is related to a particular event that is occurring and what tasks need to be performed in order for the event to occur. The claims relate a mental activity of determining the tasks that are necessary to be performed in order for an event to occur. No other limitations are present.
Claim Rejections - 35 USC § 102
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Presant et al. (US 2021/0117214).
Regarding Claim 1, Presant et al discloses a computer-implemented method comprising:
receiving first data to determine a predicted action of a user, wherein the first data indicates at least one or more inferred interests of the user (At step 1140, the assistant system 140 may determine an initial intent associated with the first user based on the one or more inputs) (page 23, paragraph [0120]);
generating first prompt data (The assistant application 136 may communicate the user input to the assistant system 140. Based on the user input, the assistant system 140 may generate responses) (page 4, paragraph [0036])including the first data and a request to determine the predicted action based on the first data (At step 1120, the assistant system 140 may determine whether the first user is eligible to receive proactive suggestions based on one or more of a proactive policy, user context data associated with the first user, task history data associated with the first user, or user memory associated with the first user) (page 23, paragraph [0120]);
using a language model (When a user requests assistance, the assistant system 140 may then swap these pre-computed language models quickly so that the personalized language model may be optimized locally by the assistant system 140 at run time based on user activities) (page 9, paragraph [0059])to process the first prompt data and determine a description of the predicted action (At step 1150, the assistant system 140 may determine, based on a machine-learning model, a subsequent intent associated with the first user based on the initial intent, wherein the machine-learning model is trained based on data associated with a plurality of intent-pairs, and wherein the data associated with the plurality of intent-pairs comprises data associated with an intent-pair between the initial intent and the subsequent intent) (page 23, paragraph [0120]);
performing a semantic query of a system-performable action storage (In particular embodiments, the capabilities of memories may enable the assistant system 140 to remember which social connections a user previously called or interacted with, write into memory and query memory at will (i.e., open dictation and auto tags), extract richer preferences based on prior interactions and long-term learning, remember a user's life history, extract rich information from egocentric streams of data and auto catalog, and write to memory in structured form to form rich short, episodic and long-term memories) (page 12, paragraph [0075]) to determine a system-performable action whose description is semantically similar to the description of the predicted action as determined by the language model (In particular embodiments, the NLU module 210 may identify one or more of a domain, an intent, or a slot from the user input in a personalized and context-aware manner. As an example and not by way of limitation, a user input may comprise “show me how to get to the coffee shop”. The NLU module 210 may identify the particular coffee shop that the user wants to go based on the user's personal information and the associated contextual information) (page 8, paragraph [0053]);
determining one or more tasks to be performed to execute the system-performable action (Given suggested candidate tasks, the action selector 341 may decide on the actions to take in order to fulfill the tasks. Validations such as whether the task is ready to be executed/delivered may be done by the action selector 341) (page 19, paragraph [0102]);
generating second prompt data including two or more trigger events and a request to determine one or more trigger events, of the two or more trigger events, for triggering performance of the one or more tasks (In particular embodiments, the dialog state tracker 337 may track the events related to a user and suggest candidate tasks based on one or more of the intents, the slots, the multimodal events, the world events, or the social events. Both user state (e.g., user's current activity) and task state (e.g., triggering conditions) may be tracked. Given the current state, the dialog state tracker 337 may suggest candidate tasks the assistant system 140 may do for the user. As an example and not by way of limitation, the candidate tasks may be “show suggestion”, “get weather information”, or “take photo”) (page 19, paragraph [0102]);
storing first proactive task plan data including a user identifier of the user (the dialog state tracker 337 may track the events related to a user) (It is being interpreted by the examiner if tasks are assigned to a user, then the user has been identified.), second data representing the one or more tasks, and third data representing the one or more trigger events (In particular embodiments, the dialog state tracker 337 may suggest candidate tasks based on available knowledge including a knowledge graph 510, user memory 515, and user task history 520. In particular embodiments, user memory 515 may be the source of truth to store all the possible proactive tasks that may be triggered for a user) (page 19, paragraph [0102]);
after storing the first proactive task plan data, receiving event data indicating the one or more trigger events has occurred (Both user state (e.g., user's current activity) and task state (e.g., triggering conditions) may be tracked) (page 19, paragraph [0102]) and ((The candidate tasks may be sent to the action selector 341, which may communicate with other modules to present proactive content to the user) (page 19, paragraph [0102]);
based on the event data (Both user state (e.g., user's current activity) and task state (e.g., triggering conditions) may be tracked) (page 19, paragraph [0102]) corresponding to the one or more trigger events, identifying the first proactive task plan data in a storage component (In particular embodiments, the dialog state tracker 337 may suggest candidate tasks based on available knowledge including a knowledge graph 510, user memory 515, and user task history 520. In particular embodiments, user memory 515 may be the source of truth to store all the possible proactive tasks that may be triggered for a user) (page 19, paragraph [0102]);
after identifying the first proactive task plan data in the storage component, causing the one or more tasks to be performed to generate first proactive output data (The audio signal captured by the smart dock may trigger the proactive suggestions. Accordingly, the assistant system 140 may first perform music retrieval based on the received audio signals and determine what song it is and which artist it belongs to) (page 22, paragraph [0118]); and
outputting the first proactive output data using one or more devices associated with the user identifier (The audio signal captured by the smart dock may trigger the proactive suggestions. Accordingly, the assistant system 140 may first perform music retrieval based on the received audio signals and determine what song it is and which artist it belongs to. The assistant system 140 may generate a response 902 as “it's the new billboard hit by artist A. Artists B and C have similar songs. Would you like to listen?” The response 902 may comprise information of the music the user heard and also a proactive suggestion suggesting the user to listen to some similar songs) (page 22, paragraph [0118]).
Regarding Claim 2, Presant et al discloses the computer-implemented method, further comprising;
determining, by the language model (When a user requests assistance, the assistant system 140 may then swap these pre-computed language models quickly so that the personalized language model may be optimized locally by the assistant system 140 at run time based on user activities (page 9, paragraph [0059]) during a dialog with the user, that a dialog with the user has ended and proactive content is to be presented to the user (The method may begin at step 1110, where the assistant system 140 may receive one or more inputs associated with proactive triggers associated with a first user, wherein the one or more inputs comprise one or more of an indication of a completion of a first task or a multimodal signal being based on one or more of a date, a time, a location, a visual signal, a sound signal, an entity update, or a user context) (page 23, paragraph [0120]);
based on the language model (the assistant system 140 may determine, based on a machine-learning model) (page 23, paragraph [0120]) determining proactive content is to be presented to the user, identifying a plurality of stored proactive task plan data associated with the user identifier of the user (At step 1120, the assistant system 140 may determine whether the first user is eligible to receive proactive suggestions based on one or more of a proactive policy, user context data associated with the first user, task history data associated with the first user, or user memory associated with the first user) (page 23, paragraph [0120]);
determining proactive content data corresponding to at least one instance of proactive content capable of being presented to the user (user context data associated with the first user, task history data associated with the first user, or user memory associated with the first user. At step 1130, the assistant system 140 may generate one or more proactive suggestions based on the one or more inputs) (page 23, paragraph [0120]);
processing the plurality of stored proactive task plan data and the proactive content data to determine, from among the plurality of stored proactive task plan data, that one or more tasks, in second proactive task plan data (At step 1150, the assistant system 140 may determine, based on a machine-learning model, a subsequent intent associated with the first user based on the initial intent) (page 23, paragraph [0120])of the plurality of stored proactive task plan data, are to be performed (At step 1160, the assistant system 140 may select one or more of the proactive suggestions based on one or more of the task history data associated with the first user, the user context data associated with the first user, the user memory associated with the first user, or the knowledge graph) (page 23, paragraph [0120]);
causing the one or more tasks of the second proactive task plan data to be performed to generate second proactive output data (At step 1170, the assistant system 140 may determine a delivery schedule of the proactive content, wherein the delivery schedule is determined based on one or more of the user context data associated with the first user, user memory associated with the first user, or a knowledge graph) (page 23, paragraph [0120]); and
indicating the second proactive output data using one or more devices associated with the user identifier (At step 1180, the assistant system 140 may send, to a client system 130 associated the first user, instructions for presenting proactive content to the first user based on the delivery schedule, wherein the proactive content comprises the selected proactive suggestions (page 23, paragraph [0120]).
Regarding Claim 3, Presant et al discloses a computer-implemented method comprising:
receiving first data indicating one or more interests of a user (At step 1140, the assistant system 140 may determine an initial intent associated with the first user based on the one or more inputs) (page 23, paragraph [0120]);
generating first prompt data requesting a generative model determine a predicted action of the user based on the first data (At step 1150, the assistant system 140 may determine, based on a machine-learning model, a subsequent intent associated with the first user based on the initial intent, wherein the machine-learning model is trained based on data associated with a plurality of intent-pairs, and wherein the data associated with the plurality of intent-pairs comprises data associated with an intent-pair between the initial intent and the subsequent intent) (page 23, paragraph [0120]);
using the generative model to process the first prompt data and determine the predicted action (In particular embodiments, the task completion component 340 of the action execution module 226 may communicate with dialog policies 345 comprised in the dialog arbitrator 216 to obtain the guidance of the next system action) (page 16, paragraph [0089]);
determining one or more tasks to be performed to execute the predicted action (In particular embodiments, the action selection component 341 may therefore select an action based on the dialog intent, the associated content objects, and the guidance from dialog policies 345) (page 16, paragraph [0089]);
determining one or more trigger events for triggering performance (In particular embodiments, the assistant system 140 may receive one or more inputs associated with proactive triggers associated with a first user. The assistant system 140 may determine whether the first user is eligible to receive proactive suggestions based on one or more proactive policies) (page 18, paragraph [0099]) of the one or more tasks (Proactive content may comprise suggested queries, suggested follow-up actions, supplemental information, surveys, or any other suitable content) (page 18, paragraph [0098]);
after determining the one or more trigger events, determining the one or more trigger events has occurred (Both user state (e.g., user's current activity) and task state (e.g., triggering conditions) may be tracked) (page 19, paragraph [0102]);
based on the one or more trigger events occurring, causing the one or more tasks to be performed to generate first proactive output data (At step 1180, the assistant system 140 may send, to a client system 130 associated the first user, instructions for presenting proactive content to the first user based on the delivery schedule, wherein the proactive content comprises the selected proactive suggestions) (page 23, paragraph [0120]); and
outputting the first proactive output data using one or more devices of the user (The assistant system 140 may generate a response 902 as “it's the new billboard hit by artist A. Artists B and C have similar songs. Would you like to listen?” The response 902 may comprise information of the music the user heard and also a proactive suggestion suggesting the user to listen to some similar songs) (page 22, paragraph [0118]).
Claims 4 and 13 are rejected for the same reason as claim 2.
Regarding Claim 5, Presant et al discloses the computer-implemented method, further comprising:
performing a search of a storage component, including data related to trigger events, to identify two or more trigger events relating to the predicted action as determined by the generative model (As an example and not by way of limitation, for the utterance “who is John?” no clear category is implied in the utterance. Therefore, the entity resolution component 330 may resolve “John” against everything. As another example and not by way of limitation, for the utterance “send a message to John”, the entity resolution component 330 may easily determine “John” refers to a person that one can message. As a result, the entity resolution component 330 may bias the resolution to a friend. As another example and not by way of limitation, for the utterance “what is John's most famous album?” To resolve “John”, the entity resolution component 330 may first determine the task corresponding to the utterance, which is finding a music album. The entity resolution component 330 may determine that entities related to music albums include singers, producers, and recording studios) (page 11, paragraph [0084]); and
using the generative model to determine the one or more trigger events from among the two or more trigger events (Therefore, the entity resolution component 330 may search among these types of entities in a music domain to resolve “John.”) (page 15, paragraph [0084]).
Regarding Claim 6, Presant et al discloses the computer-implemented method, further comprising: receiving at least one of:
second data indicating one or more system functionality subscriptions of the user (The user profile of the user may comprise user profile data including demographic information, social information, and contextual information associated with the user. The user profile data may also include user interests and preferences on a plurality of topics, aggregated through conversations on news feed, search logs, messaging platforms, etc.) (page 9, paragraph [0058]) (Since only one of the limitations need to be addressed, the other two limitations will not be addressed at this time.),
third data indicating one or more instances of feedback provided by the user in response to one or more system outputs (Since only one of the limitations need to be addressed, this limitation will not be addressed at this time.), and
fourth data indicating one or more actions configured by the user to be performed in response to one or more corresponding trigger events (Since only one of the limitations need to be addressed, this limitation will not be addressed at this time.); and
generating the first prompt data (The assistant application 136 may communicate the user input to the assistant system 140. Based on the user input, the assistant system 140 may generate responses) (page 4, paragraph [0036]) to request the generative model (When a user requests assistance, the assistant system 140 may then swap these pre-computed language models quickly so that the personalized language model may be optimized locally by the assistant system 140 at run time based on user activities (page 9, paragraph [0059]) determine the predicted action (At step 1120, the assistant system 140 may determine whether the first user is eligible to receive proactive suggestions based on one or more of a proactive policy, user context data associated with the first user, task history data associated with the first user, or user memory associated with the first user) (page 23, paragraph [0120])further based on at least one of the second data (In particular embodiments, the response execution module 232 may perform different tasks based on the output of the CU composer 355. These tasks may include writing (i.e., storing/updating) the dialog state 361 retrieved from data store 212 and generating responses 362) (page 1, paragraph [0091]),
the third data, and the fourth data ((Since only one of the limitations need to be addressed, these limitations will not be addressed at this time.)
Regarding Claim 7, Presant et al discloses the computer-implemented method, further comprising:
receiving second data indicating the user has updated a stored preference in user profile data (The completion of a task, a change in the user context, or a relevant multimodal signal, may trigger a proactive policy) (page 18, paragraph [0098]) (Since only one of the limitations need to be addressed, the other two limitations will not be addressed at this time.) ; and
using the generative model to process the first prompt data and determine the predicted action in response to receiving the second data (Based on the proactive policy, the assistant system 140 may determine what kind of proactive content to execute) (page 18, paragraph [0098]).
Regarding Claim 8, Presant et al discloses the computer-implemented method, further comprising: receiving second data indicating one or more of:
a first user input subscribing to receiving updates regarding an entity or topic over time, and
a second user input indicating information about an entity or topic is to be prevented from being presented to the user (The assistant system 140 may determine whether the first user is eligible to receive proactive suggestions based on one or more proactive policies) (page 18, paragraph [0099]); and
using the generative model (When a user requests assistance, the assistant system 140 may then swap these pre-computed language models quickly so that the personalized language model may be optimized locally by the assistant system 140 at run time based on user activities) (page 9, paragraph [0059]) to process the first prompt data and determine the predicted action in response to receiving the second data (The assistant system 140 may then generate one or more proactive suggestions based on the one or more inputs and user context data associated with the first user. In particular embodiments, the assistant system 140 may select one or more of the proactive suggestions based on task history data associated with the first user. The assistant system 140 may further send, to a client system 130 associated the first user, instructions for presenting proactive content to the first user. The proactive content may comprise the selected proactive suggestions) (page 18, paragraph [0099]).
Regarding Claim 9, Presant et al discloses the computer-implemented method, further comprising:
determining a system-performable action corresponding to the predicted action (In particular embodiments, for the second and third scenarios mentioned above, the dialog arbitrator 216 may determine that the agents on the client-side are capable of executing tasks responsive to the user input but additional information is needed (e.g., response templates) or that the tasks can be only handled by the agents on the server-side. If the dialog arbitrator 216 determines that the tasks can be only handled by the agents on the server-side) (pages 10 and 11, paragraph [0065]) as determined by the generative model (The models may include one or more of hidden Markov models, neural networks, deep learning models, or any combination thereof) (page 7, paragraph [0050]); and
determining application programming interface (API) data (As an example and not by way of limitation, the social-networking system 160 may enable users to interact with each other as well as receive content from third-party systems 170 or other entities, or to allow users to interact with these entities through an application programming interfaces (API) or other communication channels) (page 5, paragraph [0041]) for executing the system- performable action (The set of executable dialog actions may interact with agents, users and the assistant system 140 itself) (page 11, paragraph [0066]).
Regarding Claim 10, Presant et al discloses the computer-implemented method, further comprising:
processing the first prompt data to determine natural language data corresponding to the predicted action (The NLU module 210 may additionally consider contextual information when analyzing the user input) (page 7, paragraph [0052]); and
determining the system-performable action has a description that is semantically similar to the natural language data (In particular embodiments, an intent and/or a slot may be an output of the NLU module 210. An intent may be an element in a pre-defined taxonomy of semantic intentions, which may indicate a purpose of a user interacting with the assistant system 140) (page 7, paragraph [0052]).
Regarding Claim 11, Presant et al discloses the computer-implemented method, further comprising:
after determining the predicted action using the generative model, sending, to an events component (Both user state (e.g., user's current activity) and task state (e.g., triggering conditions) may be tracked) (page 19, paragraph [0102]), event data indicating the predicted action has been determined (At step 1170, the assistant system 140 may determine a delivery schedule of the proactive content, wherein the delivery schedule is determined based on one or more of the user context data associated with the first user, user memory associated with the first user, or a knowledge graph( (page 23, paragraph [0120]); and
determining the one or more tasks based on the event data being sent to the events component (At step 1180, the assistant system 140 may send, to a client system 130 associated the first user, instructions for presenting proactive content to the first user based on the delivery schedule, wherein the proactive content comprises the selected proactive suggestions) (page 23, paragraph [0120]).
Regarding Claim 12, Presant et al discloses a computing system comprising:
at least one processor (processor 1502) (page 30, paragraph [0153]); and
at least one memory (memory 1504) comprising instructions that, when executed by the at least one processor (As an example and not by way of limitation, to execute instructions, processor 1502 may retrieve (or fetch) the instructions from an internal register, an internal cache, memory 1504, or storage 1506) (page 30, paragraph [0153]), cause the computing system to:
receive first data indicating one or more interests of a user (At step 1140, the assistant system 140 may determine an initial intent associated with the first user based on the one or more inputs) (page 23, paragraph [0120]);
generate first prompt data requesting a generative model determine a predicted action of the user based on one or more of the first data (At step 1150, the assistant system 140 may determine, based on a machine-learning model, a subsequent intent associated with the first user based on the initial intent, wherein the machine-learning model is trained based on data associated with a plurality of intent-pairs, and wherein the data associated with the plurality of intent-pairs comprises data associated with an intent-pair between the initial intent and the subsequent intent) (page 23, paragraph [0120]);
use the generative model to process the first prompt data and determine the predicted action (In particular embodiments, the task completion component 340 of the action execution module 226 may communicate with dialog policies 345 comprised in the dialog arbitrator 216 to obtain the guidance of the next system action) (page 16, paragraph [0089]);
determine one or more tasks to be performed to execute the predicted action (In particular embodiments, the action selection component 341 may therefore select an action based on the dialog intent, the associated content objects, and the guidance from dialog policies 345) (page 16, paragraph [0089]);
determine one or more trigger events for triggering performance (In particular embodiments, the assistant system 140 may receive one or more inputs associated with proactive triggers associated with a first user. The assistant system 140 may determine whether the first user is eligible to receive proactive suggestions based on one or more proactive policies) (page 18, paragraph [0099]) of the one or more tasks (Proactive content may comprise suggested queries, suggested follow-up actions, supplemental information, surveys, or any other suitable content) (page 18, paragraph [0098]);
after determine the one or more trigger events, determining the one or more trigger events has occurred ((Both user state (e.g., user's current activity) and task state (e.g., triggering conditions) may be tracked) (page 19, paragraph [0102]);
based on the one or more trigger events occurring, cause the one or more tasks to be performed to generate first proactive output data (At step 1180, the assistant system 140 may send, to a client system 130 associated the first user, instructions for presenting proactive content to the first user based on the delivery schedule, wherein the proactive content comprises the selected proactive suggestions) (page 23, paragraph [0120]); and
output the first proactive output data using one or more devices of the user (The assistant system 140 may generate a response 902 as “it's the new billboard hit by artist A. Artists B and C have similar songs. Would you like to listen?” The response 902 may comprise information of the music the user heard and also a proactive suggestion suggesting the user to listen to some similar songs) (page 22, paragraph [0118]).
Claim 14 is rejected for the same reason as claim 5.
Claim 15 is rejected for the same reason as claim 6.
Claim 16 is rejected for the same reason as claim 7.
Claim 17 is rejected for the same reason as claim 8.
Claim 18 is rejected for the same reason as claim 9.
Claim 19 is rejected for the same reason as claim 10.
Claim 20 is rejected for the same reason as claim 11.
Cited Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Poddar (US 11,443,120) discloses multimodal entity and coreference resolution for assistant systems.
Poddar (US 11,704,745) discloses multimodal dialog state tracking and action prediction for assistant systems.
Poddar (US 11,443,120) discloses multimodal entity and coreference resolution for assistant systems.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SATWANT K SINGH whose telephone number is (571)272-7468. The examiner can normally be reached Monday thru Friday 9:00 AM to 6:00 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Paras D Shah can be reached at (571}270-1650. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/SATWANT K SINGH/Primary Examiner, Art Unit 2653
Prosecution Insights