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 statement (IDS) submitted on 12/16/2024 has been considered by examiner and made of record in the application file.
Double Patenting
The nonstatutory double patenting rejection is based on a judicially created doctrine grounded in public policy (a policy reflected in the statute) so as to prevent the unjustified or improper timewise extension of the “right to exclude” granted by a patent and to prevent possible harassment by multiple assignees. A nonstatutory double patenting rejection is appropriate where the conflicting claims are not identical, but at least one examined application claim is not patentably distinct from the reference claim(s) because the examined application claim is either anticipated by, or would have been obvious over, the reference claim(s). See, e.g., In re Berg, 140 F.3d 1428, 46 USPQ2d 1226 (Fed. Cir. 1998); In re Goodman, 11 F.3d 1046, 29 USPQ2d 2010 (Fed. Cir. 1993); In re Longi, 759 F.2d 887, 225 USPQ 645 (Fed. Cir. 1985); In re Van Ornum, 686 F.2d 937, 214 USPQ 761 (CCPA 1982); In re Vogel, 422 F.2d 438, 164 USPQ 619 (CCPA 1970); In re Thorington, 418 F.2d 528, 163 USPQ 644 (CCPA 1969).
A timely filed terminal disclaimer in compliance with 37 CFR 1.321(c) or 1.321(d) may be used to overcome an actual or provisional rejection based on nonstatutory double patenting provided the reference application or patent either is shown to be commonly owned with the examined application, or claims an invention made as a result of activities undertaken within the scope of a joint research agreement. See MPEP § 717.02 for applications subject to examination under the first inventor to file provisions of the AIA as explained in MPEP § 2159. See MPEP § 2146 et seq. for applications not subject to examination under the first inventor to file provisions of the AIA . A terminal disclaimer must be signed in compliance with 37 CFR 1.321(b).
The filing of a terminal disclaimer by itself is not a complete reply to a nonstatutory double patenting (NSDP) rejection. A complete reply requires that the terminal disclaimer be accompanied by a reply requesting reconsideration of the prior Office action. Even where the NSDP rejection is provisional the reply must be complete. See MPEP § 804, subsection I.B.1. For a reply to a non-final Office action, see 37 CFR 1.111(a). For a reply to final Office action, see 37 CFR 1.113(c). A request for reconsideration while not provided for in 37 CFR 1.113(c) may be filed after final for consideration. See MPEP §§ 706.07(e) and 714.13.
The USPTO Internet website contains terminal disclaimer forms which may be used. Please visit www.uspto.gov/patent/patents-forms. The actual filing date of the application in which the form is filed determines what form (e.g., PTO/SB/25, PTO/SB/26, PTO/AIA /25, or PTO/AIA /26) should be used. A web-based eTerminal Disclaimer may be filled out completely online using web-screens. An eTerminal Disclaimer that meets all requirements is auto-processed and approved immediately upon submission. For more information about eTerminal Disclaimers, refer to www.uspto.gov/patents/apply/applying-online/eterminal-disclaimer.
Claims 21, and 28-29 are rejected on the ground of nonstatutory double patenting as being unpatentable over claim 1 of U.S. Patent No. 11218584 B2 in view of STAWISZYNSKI (US 20210385638 A1). Although the conflicting claims are not identical, they are not patentable distinct from each other.
Please see the following table for claim 1 analysis.
18/982,938
US-11218584-B2 (Reference)
Claim Interpretation
21. (New) A method for coordinating emergency response, by an emergency management system, the method comprising:
receiving an emergency alert associated with an emergency and with a user;
initiating a communication session with the user through a communication device of the user,
wherein the communication session comprises one or more emergency response questions transmitted to the communication device and one or more user responses to the one or more emergency response questions received from the communication device;
via one or more machine learning algorithms, determining a dispatch recommendation based at least in part on the one or more user responses;
and transmitting the dispatch recommendation to an emergency service provider (ESP).
1. (Currently Amended) A method for facilitating emergency communications by an emergency management system, the method comprising:
a) identifying a user at risk of an emergency; b) presenting an emergency response prompt at a communication device associated with the user; c) receiving confirmation of the emergency;
d) in response to receiving confirmation of the emergency, initiating an autonomous communication session with the user through the communication device,
wherein the autonomous communication session comprises one or more emergency response questions transmitted to the communication device and one or more user responses to the emergency response questions received from the communication device;
e) extracting emergency information from the one or more user responses provided during the autonomous communication session;
and f) transmitting the emergency information to an emergency service provider (ESP).
As can be seen by a side-by-side comparison, the present application is an obvious variation of US-11218584-B2 (Reference), an emergency management system receiving an alert from the user, creating a communication session with the user to ask the user one or more questions, and use the answers provided by the user to send information to Emergency service provide (ESP). The only major difference is the present application has a “via a machine learning” determining a dispatch recommendation based on one ore more user responses and that recommendation is being send to ESP. However, one of ordinary skill in the art clearly can recognize to implement a machine learning to read user data and provide recommendation to ESP. Please see further analysis below in view of STAWISZYNSKI (US 20210385638 A1).
Further analysis for claim 1:
US-11218584-B2 (Reference) substantially discloses the claimed invention but fails to teach via one or more machine learning algorithms, determining a dispatch recommendation based at least in part on the one or more user responses.
However, STAWISZYNSKI discloses via one or more machine learning algorithms, determining a dispatch recommendation (par.67, action) based at least in part on the one or more user responses (paragraph [0038], Fig.1, "the modification of the action associated with the emergency call 107 may be implanted using machine learning and/or deep-learning based algorithms. Hence, the application 223 and/or the virtual assistant application 123 may include machine learning and/or deep-learning based algorithms," and paragraph [0065], "…Similarly, the action 115 may be changed to dispatch two fire engines, one ladder truck, an ambulance, and a police car to the address associated with the incident (e.g. which also changes and/or updates a type of responders dispatched to include EMTs and police officers)." and paragraph [0067], "the virtual assistant application 123 may ask the dispatcher 102 and/or the caller 104 a question on the emergency call 107…based on analysis of the context information prior to determining the modification of the action and/or prior to causing the modification of the action; indeed, the answers to the question may assist the virtual assistant application 123 with determining the modification of the action…The virtual assistant application 123 may determine how to modify an action based on the received answers."(i.e., the action is the dispatch recommendation that is modified by the virtual assistance that is running machine learning by receiving answer to questions sent by the user.));
and transmitting the dispatch recommendation to an emergency service provider (ESP) (paragraph [0012], "Hence, an action 115 is generated based on the incident report which causes one fire engine to be dispatched to the address in the incident report 113; the action 115 may comprise an automatic dispatch command transmitted, for example, to a fire station closest to the address, and may be generated using preconfigured rules at the dispatch device 101." (i.e., the action send to a first station/or ESP such as police to help the caller.)).
US-11218584-B2 (Reference) and STAWISZYNSKI are considered to be analogous to the claimed invention because they are in the same field Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified US-11218584-B2 (Reference) to implement the method of STAWISZYNSKI virtual assistance that is running machine learning in order to have the virtual assistance read source data and update the action in order to provide the best response for the caller (STAWISZYNSKI, paragraph [0021], “the virtual assistant application 143 at the dispatch device 101 is configured to monitor the emergency call 107 and determine a mobile device 121, 131 that includes a respective virtual assistant applications 123, 133 to include on the emergency call 107. For example, the virtual assistant application 143 may monitor the emergency call 107 and/or associated information, such as the address, and determine which of the virtual assistant applications 123, 133 of the mobile devices 121, 131 to include on the emergency call 107. In some examples, such a decision may be based on the location of the mobile devices 121, 131 and/or a role of associated responders 122, 132. For example, as depicted, the virtual assistant application 143 may have determined that while the mobile device 131 is operated by the first responder 132, whose capabilities may be more relevant to the incident associated with the emergency call 107, the mobile device 121 is closer in distance to the incident associated with the emergency call 107; as such, as depicted,” and paragraph [0038], “the virtual assistant application 123 may include machine learning and/or deep-learning based algorithms,”).
Please see the following table for dependent claims
18/982,938
US-11218584-B2 (Reference)
Claim Interpretation
28. (New) The method of claim 21,
further comprising collecting emergency data associated with the emergency from a plurality of sources,
and determining the dispatch recommendation via the one or more machine learning algorithms is based at least in part on the emergency data from the plurality of sources.
None
The refence application does not disclose the claimed limitation, however, STAWISZYNSKI discloses the said limitation. Please see further analysis below in view of STAWISZYNSKI.
29. (New) The method of claim 21, wherein the dispatch recommendation includes one or more of a specific emergency response unit, a type of emergency response unit, or a number of emergency response units.
None
The refence application does not disclose the claimed limitation, however, STAWISZYNSKI discloses the said limitation. Please see further analysis below in view of STAWISZYNSKI.
Further analysis for claim 28:
STAWISZYNSKI further discloses further comprising collecting emergency data associated with the emergency from a plurality of sources (paragraph [0015], Fig., "The mobile device 131 further comprises one or more sensors, for example a camera 134 and a microphone 135 which may be used by the mobile device 131 to gather data regarding the incident associated with the emergency call 107." (i.e., plurality of sources is reading as plurality of sensors.)),
and determining the dispatch recommendation via the one or more machine learning algorithms is based at least in part on the emergency data from the plurality of sources (paragraph [0012], "Hence, an action 115 is generated based on the incident report which causes one fire engine to be dispatched to the address in the incident report 113; the action 115 may comprise an automatic dispatch command transmitted, for example, to a fire station closest to the address, and may be generated using preconfigured rules at the dispatch device 101." and paragraph [0015], Fig.1, "The mobile device 131 further comprises one or more sensors, for example a camera 134 and a microphone 135 which may be used by the mobile device 131 to gather data regarding the incident associated with the emergency call 107." and paragraph [0022], "The virtual assistant application 123 may monitor the emergency call 107 to determine context information of the emergency call 107, including, but not limited to, context information 150 received in association with the emergency call 107, and correlate such context information with sensor data received from sensors of the mobile device 121 to cause a modification of an action associated with the emergency call 107 including, but not limited to the action 115) based on a correlation between the context information with the sensor data." (i.e., using the sensors to determine the action which is the same as dispatch recommendation.)).
The proposed combination as well as the motivations for combining the references presented in the rejection of the parent claim apply to this claim and are incorporated herein by reference.
Further analysis for claim 29:
STAWISZYNSKI further discloses wherein the dispatch recommendation includes one or more of a specific emergency response unit (paragraph [0012], "Hence, an action 115 is generated based on the incident report which causes one fire engine to be dispatched to the address in the incident report 113; the action 115 may comprise an automatic dispatch command transmitted, for example, to a fire station closest to the address, and may be generated using preconfigured rules at the dispatch device 101." and paragraph [0018], "Furthermore, while present examples are described with respect to the first responders 122, 132 respectively being a police officer and a firefighter, each of the first responders 122, 132 may be any type of first responders including, but not limited to, emergency medical technicians (EMTs), and the like." (i.e., police, firefighter, EMT.)),
a type of emergency response unit (paragraph [0064], “For example, in some examples, the modification of the action associated with the emergency call 107 may comprise causing a change to one or more of:…a type of the emergency responders dispatched in association with the emergency call 107;”),
or a number of emergency response units (paragraph [0064], “For example, in some examples, the modification of the action associated with the emergency call 107 may comprise causing a change to one or more of: a number of emergency responders dispatched in association with the emergency call 107”).
The proposed combination as well as the motivations for combining the references presented in the rejection of the parent claim apply to this claim and are incorporated herein by reference.
Claims 22 are rejected on the ground of nonstatutory double patenting as being unpatentable over U.S. Patent No. 11218584 B2 in view of STAWISZYNSKI (US 20210385638 A1) in further view of Viklund (US 20190272725 A1). Although the conflicting claims are not identical, they are not patentable distinct from each other.
Please see the following table for dependent claim
18/982,938
US-11218584-B2 (Reference)
Claim Interpretation
22. (New) The method of claim 21, wherein at least one of the one or more emergency response questions is generated autonomously via a machine learning model.
None
The refence application in view of STAWISZYNSKI do not disclose the claimed limitation, however, Viklund discloses the said limitation. Please see further analysis below in view of Viklund.
Further analysis for claim 22:
US-11218584-B2 (Reference) in view of STAWISZYNSKI substantially discloses the claimed invention but fails to teach wherein at least one of the one or more emergency response questions is generated autonomously via a machine learning model.
However, Viklund discloses wherein at least one of the one or more emergency response questions is generated autonomously via a machine learning model (paragraph [0133], "In an illustrative example, radar sensor data may indicate that a user regularly lays on her bedroom floor. This data may initially cause Question Logic 195 to generate questions regarding falls." (i.e., Using data to generate questions.)).
US-11218584-B2 (Reference) in view of STAWISZYNSKI and Viklund are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified US-11218584-B2 (Reference) to implement the method of Viklund of generating question in order to obtain more relevant data from the user and to increase accuracy of machine learning (Viklund, paragraph [0122], “The received answers may be used to annotate sensor data and/or detected activities. The received answers may also be used to further train elements of Activity Logic 135 to determine activities from sensor data and/or to further train elements of Activity Logic 135 to determine a health state based on determined activities. The received answers may also be used to train a machine learning system within Question Logic 195 to select more valuable questions. The value of a question being based on how likely an answer to the question will be useful in reaching a goal, e.g., is predicted to improve a statistical accuracy of the machine learning system by the greatest degree.”).
Claims 23-24 are rejected on the ground of nonstatutory double patenting as being unpatentable over U.S. Patent No. 11218584 B2 in view of STAWISZYNSKI (US 20210385638 A1) in further view of LAM (US 20190114321 A1) Although the conflicting claims are not identical, they are not patentable distinct from each other.
Please see the following table for dependent claims
18/982,938
US-11218584-B2 (Reference)
Claim Interpretation
23. (New) The method of claim 22, wherein the machine learning model is trained to evaluate user responses and messages from the user in the communication session and generate an emergency response question or other response based on the user responses and message from the user.
None
The refence application in view of STAWISZYNSKI do not disclose the claimed limitation, however, Viklund discloses the said limitation. Please see further analysis below in view of LAM.
24. (New) The method of claim 21, wherein the one or more emergency response questions are part of a predetermined script of messages generated via a machine learning algorithm.
5. (Currently Amended) The method of claim 1, wherein initiating the autonomous communication session comprises transmitting one or more messages comprising the one or more emergency response questions to the communication device according to a predetermined script.
The refence application in view of STAWISZYNSKI do not disclose the claimed limitation wherein the predetermined script of messages generated via a machine learning algorithm, however, Viklund discloses the said limitation. Please see further analysis below in view of LAM.
Further analysis for claim 23:
STAWISZYNSKI further discloses wherein the machine learning model is trained to evaluate user responses and messages from the user in the communication session (paragraph [0067], Fig., "the virtual assistant application 123 may ask the dispatcher 102 and/or the caller 104 a question on the emergency call 107…based on analysis of the context information prior to determining the modification of the action and/or prior to causing the modification of the action; indeed, the answers to the question may assist the virtual assistant application 123 with determining the modification of the action." (i.e., Evaluating the answers from the caller.)).
US-11218584-B2 (Reference) in view of STAWISZYNSKI substantially discloses the claimed invention but fails to teach wherein at least one of the one or more emergency response questions is generated autonomously via a machine learning model.
However, LAM discloses and generate (paragraph [0060], Fig.9, "A potential advantage of this system is that there is a reduced need to establish manual conditional logic between questions and answers for a question pathway. The system can be provided with a repository of questions and corresponding answers, and required information for one or more forms, and either through pre-training or reinforcement training of the neural network, the neural network automatically establishes next best questions based on generated suitability scores. Accordingly, especially where there are a large number of forms being provisioned into auto-teleinterview forms, the repositories may be simply linked to the neural network to dynamically generate improved decisions for traversing the question decision trees." (i.e., determining other question based on the user answers.)).
US-11218584-B2 (Reference) in view of STAWISZYNSKI and LAM are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified US-11218584-B2 (Reference) to implement the method of LAM in order to improve relevancy and engagement without the need of a human operator (LAM, abstract, “The computing device is configured to automatically tailor a flow of a conversation to an effort to improve relevancy and engagement without the need of a human operator to manually tailor the conversation, which, for example, could be impractically expensive.”).
Further analysis for claim 24:
LAM further discloses wherein the one or more emergency response questions are part of a predetermined script of messages generated via a machine learning algorithm (paragraph [0060], Fig.9, "A potential advantage of this system is that there is a reduced need to establish manual conditional logic between questions and answers for a question pathway. The system can be provided with a repository of questions and corresponding answers, and required information for one or more forms, and either through pre-training or reinforcement training of the neural network, the neural network automatically establishes next best questions based on generated suitability scores. Accordingly, especially where there are a large number of forms being provisioned into auto-teleinterview forms, the repositories may be simply linked to the neural network to dynamically generate improved decisions for traversing the question decision trees." (i.e., repository of questions reading as predetermined scripts the machine learning uses to traversing the question decision tree.)).
The proposed combination as well as the motivations for combining the references presented in the rejection of the parent claim apply to this claim and are incorporated herein by reference.
Claims 25 is rejected on the ground of nonstatutory double patenting as being unpatentable over U.S. Patent No. 11218584 B2 in view of STAWISZYNSKI (US 20210385638 A1) in further view of DIZENGOF (US 20180301017 A1) Although the conflicting claims are not identical, they are not patentable distinct from each other.
Please see the following table for dependent claims
18/982,938
US-11218584-B2 (Reference)
Claim Interpretation
25. (New) The method of claim 21, wherein the one or more machine learning algorithms comprise two or more feature spaces comprising emergency alert attribute types.
None
The refence application in view of STAWISZYNSKI do not disclose the claimed limitation, however, Viklund discloses the said limitation. Please see further analysis below in view of DIZENGOF.
For analysis for claim 25:
US-11218584-B2 (Reference) in view of STAWISZYNSKI substantially discloses the claimed invention but fails to teach wherein the one or more machine learning algorithms comprise two or more feature spaces comprising emergency alert attribute types.
However, DIZENGOF discloses wherein the one or more machine learning algorithms comprise two or more feature spaces comprising emergency alert attribute types (paragraph [0049], "The sensors may monitor and/or depict an environment of the originating client device. The sensors may be integrated in the originating client device and/or included in one or more peripheral devices which are operatively communicating with the originating client device, for example, a wearable device and/or the like. The sensory data may relate to the originating client device itself, to the user of the client device (reporter) and/or to the surroundings of the client device. The sensory data may include, for example, imagery data (images, video, etc.), audio data (sound, voice, speech, noise, etc.), motion data, geolocation data, physical condition data of the reporter (e.g. heartbeat rate, blood pressure, respiration rate, temperature, perspiration level, etc.), interaction data reflecting interaction between the reporter and the originating client device and/or the like." and paragraph [0051], "Based on the environment parameter(s) and optionally on the identification data, the incoming emergency calls routing system may estimate the type of the potential emergency event and optionally estimate one or more characteristics of the potential emergency event, for example, location, severity, urgency and/or the like. The incoming emergency calls routing system may further apply one or more machine learning algorithms trained to classify the identified environment parameter(s) to a certain type of the potential emergency event." (i.e., machine learning using the environment information to determine response to the emergency such as audio data, geolocation data, physical condition data.)).
US-11218584-B2 (Reference) in view of STAWISZYNSKI and DIZENGOF are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified US-11218584-B2 (Reference) to implement the method of DIZENGOF in order to enable the machine learning of adjusting to the environment and learning of the environment can lead to determining a priority score that can help reduce the response time to incoming emergency calls associated with high severity (DIZENGOF, paragraph [0025], “Applying the trained machine learning algorithm(s) to estimate the potential emergency event may allow for constant evolution of the routing system in adjusting to new and/or varying environment parameters to accurately classify the potential emergency events according to the identified environment parameters.” And paragraph [0032], “the event report record comprises a priority score calculated for the one or more incoming emergency calls based on the one or more environment parameters. The priority score calculated for one or more of the incoming emergency calls may be used by the selected emergency dispatch center to prioritize the incoming emergency calls routed to the selected emergency dispatch center and hence reduce the response time to incoming emergency calls associated with high severity and/or high urgency potential emergency events.”).
Claims 27 is rejected on the ground of nonstatutory double patenting as being unpatentable over U.S. Patent No. 11218584 B2 in view of STAWISZYNSKI (US 20210385638 A1) in further view of MacGabann (US 20190313230 A1). Although the conflicting claims are not identical, they are not patentable distinct from each other.
Please see the following table for dependent claims
18/982,938
US-11218584-B2 (Reference)
Claim Interpretation
27. (New) The method of claim 21, wherein the one or more machine learning algorithms parses text of the one or more user responses to determine the dispatch recommendation.
None
The refence application in view of STAWISZYNSKI do not disclose the claimed limitation, however, Viklund discloses the said limitation. Please see further analysis below in view of MacGabann.
For analysis for claim 27:
US-11218584-B2 (Reference) in view of STAWISZYNSKI substantially discloses the claimed invention but fails to teach wherein the one or more machine learning algorithms comprise two or more feature spaces comprising emergency alert attribute types.
However, MacGabann discloses wherein the one or more machine learning algorithms parses text of the one or more user responses to determine the dispatch recommendation (paragraph [0054], Fig.1B, "The collected information may be parsed using natural language with confidence intervals or levels, similar to the discussion herein. When the confidence interval in the natural language processing of the scraped social media meets a predetermined level, the scraped social media may be used to determine an EMS or similar code." and paragraph [0204], "The rescue request manager 125 may parse any text provided in free-form input fields for use in assessing emergency severity and/or suitable emergency responders, for example using natural language processing, and/or may pass on the text to the dispatched emergency responder." (i.e., using natural language processing to parse user text. Fig.1B discloses to determine dispatch recommendation.)).
US-11218584-B2 (Reference) in view of STAWISZYNSKI and MacGabann are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified US-11218584-B2 (Reference) to implement the method of MacGabann parse text from a machine learning to obtain additional information the user may have or not have provided or found elsewhere that can help with increasing in triaging users by determining an appropriate EMS (DIZENGOF, paragraph [0053], “In some embodiments, the rescue request manager 125 and/or the rescue management servers 120 collects information about events and/or victims not available through communications from victims, etc., by scraping or otherwise analyzing social media posts and communications. In some embodiments, the scraping process collects victim and/or event location severity data, and/or similar information based on detected or identified social media posts and communications. The information collected by the scraping process may be used to determine victim density during an event. Such processing may allow automatic triaging of victims that did not affirmatively generate a request via the emergency response system 100 or other PSAP communication.”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 21, 27-36, 38, and 40 are rejected under 35 U.S.C. 103 as being unpatentable over MacGabann (US 20190313230 A1) in view of STAWISZYNSKI (US 20210385638 A1).
Regarding Claim 21, MacGabann discloses A method for coordinating emergency response, by an emergency management system, the method comprising:
receiving an emergency alert associated with an emergency and with a user (paragraph [0058], Fig.1B, "At interaction (1), the user initiates and completes the rescue request using the dynamic user interface of the rescue application 105. As described herein, the rescue application 105 can present a first user interface that allows the user to specify which type of emergency the user is experiencing." (i.e., user initiates an alert.));
initiating a communication session with the user through a communication device of the user (paragraph [0060], Fig.1B, "At interaction (2), the rescue application 105 causes the user device 110 to transmit the rescue request to the rescue request manager 125 implemented on the rescue management servers 120. As described herein, this may involve determining a suitable network over which to transmit the rescue request." and paragraph [0063], "At interaction (5), the responder application 135 may send a dispatch confirmation to the rescue application 105. The dispatch confirmation can alert the user that an emergency responder is on the way, and may provide information such as estimated time of arrival, route tracking, and identification of the emergency responder." and paragraph [0065], "Interactions (5) and (6) are depicted as taking place directly between the responder application 135 and the rescue application 105." and paragraph [0067], "while the description above utilizes interactions between the rescue request application 105 and the rescue request manager 125, in some embodiments, the rescue request manager 125 is able to receive details regarding rescue requests from other communications, such as SMS messages, social media scrapping, and audio/video communications. For example, the rescue request of interaction (2) may be received via an SMS message from the user's computing device 110" (i.e., The rescue application is the established communication between user and person who will help coordinate rescue.)),
However, MacGabann does not disclose or was not relied upon wherein the communication session comprises one or more emergency response questions transmitted to the communication device and one or more user responses to the one or more emergency response questions received from the communication device; via one or more machine learning algorithms, determining a dispatch recommendation based at least in part on the one or more user responses; and transmitting the dispatch recommendation to an emergency service provider (ESP).
STAWISZYNSKI discloses wherein the communication session comprises one or more emergency response questions transmitted to the communication device and one or more user responses to the one or more emergency response questions received from the communication device (paragraph [0067], Fig., "the virtual assistant application 123 may ask the dispatcher 102 and/or the caller 104 a question on the emergency call 107…based on analysis of the context information prior to determining the modification of the action and/or prior to causing the modification of the action; indeed, the answers to the question may assist the virtual assistant application 123 with determining the modification of the action." (i.e., questions are being send to the caller 104.));
via one or more machine learning algorithms, determining a dispatch recommendation (par.67, action) based at least in part on the one or more user responses (paragraph [0038], Fig.1, "the modification of the action associated with the emergency call 107 may be implanted using machine learning and/or deep-learning based algorithms. Hence, the application 223 and/or the virtual assistant application 123 may include machine learning and/or deep-learning based algorithms," and paragraph [0065], "…Similarly, the action 115 may be changed to dispatch two fire engines, one ladder truck, an ambulance, and a police car to the address associated with the incident (e.g. which also changes and/or updates a type of responders dispatched to include EMTs and police officers)." and paragraph [0067], "the virtual assistant application 123 may ask the dispatcher 102 and/or the caller 104 a question on the emergency call 107…based on analysis of the context information prior to determining the modification of the action and/or prior to causing the modification of the action; indeed, the answers to the question may assist the virtual assistant application 123 with determining the modification of the action…The virtual assistant application 123 may determine how to modify an action based on the received answers."(i.e., the action is the dispatch recommendation that is modified by the virtual assistance that is running machine learning by receiving answer to questions sent by the user.));
and transmitting the dispatch recommendation to an emergency service provider (ESP) (paragraph [0012], Fig.1, "Hence, an action 115 is generated based on the incident report which causes one fire engine to be dispatched to the address in the incident report 113; the action 115 may comprise an automatic dispatch command transmitted, for example, to a fire station closest to the address, and may be generated using preconfigured rules at the dispatch device 101." (i.e., the action sends to a first station/or ESP such as police to help the caller.)).
MacGabann and STAWISZYNSKI are considered to be analogous to the claimed invention because they are in the same field Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified MacGabann to implement the method of STAWISZYNSKI virtual assistance that is running machine learning in order to have the virtual assistance read source data and update the action in order to provide the best response for the caller (STAWISZYNSKI, paragraph [0021], “the virtual assistant application 143 at the dispatch device 101 is configured to monitor the emergency call 107 and determine a mobile device 121, 131 that includes a respective virtual assistant applications 123, 133 to include on the emergency call 107. For example, the virtual assistant application 143 may monitor the emergency call 107 and/or associated information, such as the address, and determine which of the virtual assistant applications 123, 133 of the mobile devices 121, 131 to include on the emergency call 107. In some examples, such a decision may be based on the location of the mobile devices 121, 131 and/or a role of associated responders 122, 132. For example, as depicted, the virtual assistant application 143 may have determined that while the mobile device 131 is operated by the first responder 132, whose capabilities may be more relevant to the incident associated with the emergency call 107, the mobile device 121 is closer in distance to the incident associated with the emergency call 107; as such, as depicted,” and paragraph [0038], “the virtual assistant application 123 may include machine learning and/or deep-learning based algorithms,”).
Regarding Claim 27, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 21.
MacGabann further discloses wherein the one or more machine learning algorithms parses text of the one or more user responses to determine the dispatch recommendation (paragraph [0054], Fig.1B, "The collected information may be parsed using natural language with confidence intervals or levels, similar to the discussion herein. When the confidence interval in the natural language processing of the scraped social media meets a predetermined level, the scraped social media may be used to determine an EMS or similar code." and paragraph [0204], "The rescue request manager 125 may parse any text provided in free-form input fields for use in assessing emergency severity and/or suitable emergency responders, for example using natural language processing, and/or may pass on the text to the dispatched emergency responder." (i.e., using natural language processing to parse user text. Fig.1B discloses to determine dispatch recommendation.)).
Regarding Claim 28, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 21.
STAWISZYNSKI further discloses further comprising collecting emergency data associated with the emergency from a plurality of sources (paragraph [0015], Fig.1, "The mobile device 131 further comprises one or more sensors, for example a camera 134 and a microphone 135 which may be used by the mobile device 131 to gather data regarding the incident associated with the emergency call 107." (i.e., plurality of sources is reading as plurality of sensors.)),
and determining the dispatch recommendation via the one or more machine learning algorithms is based at least in part on the emergency data from the plurality of sources (paragraph [0012], "Hence, an action 115 is generated based on the incident report which causes one fire engine to be dispatched to the address in the incident report 113; the action 115 may comprise an automatic dispatch command transmitted, for example, to a fire station closest to the address, and may be generated using preconfigured rules at the dispatch device 101." and paragraph [0015], Fig., "The mobile device 131 further comprises one or more sensors, for example a camera 134 and a microphone 135 which may be used by the mobile device 131 to gather data regarding the incident associated with the emergency call 107." and paragraph [0022], "The virtual assistant application 123 may monitor the emergency call 107 to determine context information of the emergency call 107, including, but not limited to, context information 150 received in association with the emergency call 107, and correlate such context information with sensor data received from sensors of the mobile device 121 to cause a modification of an action associated with the emergency call 107 including, but not limited to the action 115) based on a correlation between the context information with the sensor data." (i.e., using the sensors to determine.)).
The proposed combination as well as the motivations for combining the references presented in the rejection of the parent claim apply to this claim and are incorporated herein by reference.
Regarding Claim 29, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 21.
STAWISZYNSKI further discloses wherein the dispatch recommendation includes one or more of a specific emergency response unit (paragraph [0012], "Hence, an action 115 is generated based on the incident report which causes one fire engine to be dispatched to the address in the incident report 113; the action 115 may comprise an automatic dispatch command transmitted, for example, to a fire station closest to the address, and may be generated using preconfigured rules at the dispatch device 101." and paragraph [0018], "Furthermore, while present examples are described with respect to the first responders 122, 132 respectively being a police officer and a firefighter, each of the first responders 122, 132 may be any type of first responders including, but not limited to, emergency medical technicians (EMTs), and the like." (i.e., police, firefighter, EMT.)),
a type of emergency response unit (paragraph [0064], “For example, in some examples, the modification of the action associated with the emergency call 107 may comprise causing a change to one or more of:…a type of the emergency responders dispatched in association with the emergency call 107;”),
or a number of emergency response units (paragraph [0064], “For example, in some examples, the modification of the action associated with the emergency call 107 may comprise causing a change to one or more of: a number of emergency responders dispatched in association with the emergency call 107”).
The proposed combination as well as the motivations for combining the references presented in the rejection of the parent claim apply to this claim and are incorporated herein by reference.
Regarding Claim 30, MacGabann discloses A method for coordinating emergency response, by an emergency management system, the method comprising: receiving an emergency alert associated with an emergency and with a user (paragraph [0058], Fig.1B, "At interaction (1), the user initiates and completes the rescue request using the dynamic user interface of the rescue application 105. As described herein, the rescue application 105 can present a first user interface that allows the user to specify which type of emergency the user is experiencing." (i.e., the user sending a rescue request.));
collecting emergency data associated with the emergency from a plurality of sources (paragraph [0051], Fig.1B, "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." (i.e., receive SMS, video, image.)),
at least one of the plurality of sources being a sensor associated with the user or a sensor at a location of the emergency (paragraph [0051], "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." (i.e., receive SMS, video, and image data.)).
However, MacGabann does not disclose or was not relied upon via one or more machine learning algorithms, analyzing the emergency data to determine a category and a severity of the emergency and to generate a text summary of the emergency based on the emergency data; providing the text summary to an emergency service provider (ESP).
STAWISZYNSKI discloses via one or more machine learning algorithms, analyzing the emergency data to determine a category and a severity of the emergency (paragraph [0018], "Furthermore, while present examples are described with respect to the first responders 122, 132 respectively being a police officer and a firefighter, each of the first responders 122, 132 may be any type of first responders including, but not limited to, emergency medical technicians (EMTs), and the like." and paragraph [0021], "For example, as depicted, the virtual assistant application 143 may have determined that while the mobile device 131 is operated by the first responder 132, whose capabilities may be more relevant to the incident associated with the emergency call 107," and paragraph [0022], Fig.1, "The virtual assistant application 123 may monitor the emergency call 107 to determine context information of the emergency call 107, including, but not limited to, context information 150 received in association with the emergency call 107, and correlate such context information with sensor data received from sensors of the mobile device 121 to cause a modification of an action associated with the emergency call 107 including, but not limited to the action 115) based on a correlation between the context information with the sensor data." and paragraph [0065], "For example, the virtual assistant application 123 may communicate with the dispatch device 101 and/or the virtual assistant application 143 at the dispatch device 101 to change and/or update information at the incident report 113 and/or the action 115. In the example depicted in FIG. 1, the incident report may be updated to change the modifying circumstances from “DUMPSTER” to “BUILDING” and the alarm level (e.g. a priority) from “5” to “3” (e.g. a higher priority)." (i.e., also discloses receiving data from multiple sources and using virtual assistance that is running machine learning uses sensor data to determine alarm level or severity of the emergency and category as needing police or firefighter for the emergency call.))
and to generate a text summary (par.65, Fig.1, incident report) of the emergency based on the emergency data (paragraph [0012], "…the dispatcher 102 operates the dispatch device 101 to generate an incident report 113…" and paragraph [0065], "For example, the virtual assistant application 123 may communicate with the dispatch device 101 and/or the virtual assistant application 143 at the dispatch device 101 to change and/or update information at the incident report 113 and/or the action 115. In the example depicted in FIG. 1, the incident report may be updated to change the modifying circumstances from “DUMPSTER” to “BUILDING” and the alarm level (e.g. a priority) from “5” to “3” (e.g. a higher priority)."and paragraph [0074], "the virtual assistant application 123 transmits a command 470 to modify the incident report 113 and/or the action 115. In some examples, as depicted, the virtual assistant application 123 may request 480 confirmation for modifying the incident report 113…" and paragraph [0075], "The command 470 is received at the dispatch device 101, the incident report 113 and/or the action 115 are modified accordingly. For example, as depicted, the incident report 113 is modified to change the incident type to include “ARSON”, the modifying circumstance is changed from “DUMPSTER” to “STRUCTURE” and the alarm level (e.g. the priority) is increased from “5” to “3”." (i.e., virtual assistant helping generate summary of the incident.));
providing the text summary to an emergency service provider (ESP) (paragraph [0014], Fig., "the system 100 further comprises a mobile device 121, associated with (and/or carried by) a first responder 122 (as depicted a patrol officer and/or a police officer), the mobile device 121 further operating a virtual assistant application 123." and paragraph [0049], "the incident report 113 may be transmitted to the mobile device 121 in the context information 150 (on the emergency call 107 and/or using a data connection) received in association with the emergency call 107," (i.e., sending the summary to ESP.)).
MacGabann and STAWISZYNSKI are considered to be analogous to the claimed invention because they are in the same field Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified MacGabann to implement the method of STAWISZYNSKI virtual assistance that is running machine learning in order to have the virtual assitance read source data and update the action in order to provide the be response for the caller (STAWISZYNSKI, paragraph [0021], “the virtual assistant application 143 at the dispatch device 101 is configured to monitor the emergency call 107 and determine a mobile device 121, 131 that includes a respective virtual assistant applications 123, 133 to include on the emergency call 107. For example, the virtual assistant application 143 may monitor the emergency call 107 and/or associated information, such as the address, and determine which of the virtual assistant applications 123, 133 of the mobile devices 121, 131 to include on the emergency call 107. In some examples, such a decision may be based on the location of the mobile devices 121, 131 and/or a role of associated responders 122, 132. For example, as depicted, the virtual assistant application 143 may have determined that while the mobile device 131 is operated by the first responder 132, whose capabilities may be more relevant to the incident associated with the emergency call 107, the mobile device 121 is closer in distance to the incident associated with the emergency call 107; as such, as depicted,” and paragraph [0038], “the virtual assistant application 123 may include machine learning and/or deep-learning based algorithms,”).
Regarding Claim 31, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 30.
STAWISZYNSKI further discloses wherein the one or more machine learning algorithms are trained on a data set comprising emergency data sets and corresponding categories associated with the emergency data sets (paragraph [0038], Fig.1, "The correlation between the context information with the sensor data, and the modification of the action associated with the emergency call 107 may be implanted using machine learning and/or deep-learning based algorithms. Hence, the application 223 and/or the virtual assistant application 123 may include machine learning and/or deep-learning based algorithms, and the like, which have been trained and/or configured to correlate context information with sensor data, and modify actions associated with emergency calls. Indeed, such training may occur by implementing the application 223 and providing feedback to the application 223 based on past implementations of the application 223. Furthermore, the application 223 may initially be operated by the controller 220 in a training mode to train the application 223 to correlate context information with sensor data, and modify actions associated with emergency calls." and paragraph [0075], "The command 470 is received at the dispatch device 101, the incident report 113 and/or the action 115 are modified accordingly. For example, as depicted, the incident report 113 is modified to change the incident type to include “ARSON”, the modifying circumstance is changed from “DUMPSTER” to “STRUCTURE” and the alarm level (e.g. the priority) is increased from “5” to “3”." (i.e., discloses the virtual assistance was trained on emergency data sets and corresponding categories as the virtual assistance is modifying action and reports based on data received from the caller.)).
The proposed combination as well as the motivations for combining the references presented in the rejection of the parent claim apply to this claim and are incorporated herein by reference.
Regarding Claim 32, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 30.
MacGabann further discloses wherein at least one of the plurality of sources is social media and the method includes filtering the social media to obtain relevant social media data associated with the emergency (paragraph [0051], "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." and paragraph [0053], "the rescue request manager 125 and/or the rescue management servers 120 collects information about events and/or victims not available through communications from victims, etc., by scraping or otherwise analyzing social media posts and communications. In some embodiments, the scraping process collects victim and/or event location severity data, and/or similar information based on detected or identified social media posts and communications. The information collected by the scraping process may be used to determine victim density during an event. Such processing may allow automatic triaging of victims that did not affirmatively generate a request via the emergency response system 100 or other PSAP communication." (i.e., discloses social media as a source.)).
Regarding Claim 33, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 30.
STAWISZYNSKI further discloses wherein at least one of the plurality of sources is an emergency data database and the emergency data comprises at least one of environmental data (paragraph [0015], "The mobile device 131 further comprises one or more sensors, for example a camera 134 and a microphone 135 which may be used by the mobile device 131 to gather data regarding the incident associated with the emergency call 107." and paragraph [0065], Fig., "For example, the virtual assistant application 123 may communicate with the dispatch device 101 and/or the virtual assistant application 143 at the dispatch device 101 to change and/or update information at the incident report 113 and/or the action 115. In the example depicted in FIG. 1, the incident report may be updated to change the modifying circumstances from “DUMPSTER” to “BUILDING” and the alarm level (e.g. a priority) from “5” to “3” (e.g. a higher priority)." (i.e., camera to collect environmental data like building.)),
The proposed combination as well as the motivations for combining the references presented in the rejection of the parent claim apply to this claim and are incorporated herein by reference.
Regarding Claim 34, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 30.
MacGabann further discloses wherein the emergency data includes one or more messages from the user via a communication device of the user (paragraph [0051], "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." (i.e., SMS messages.)),
and the one or more machine learning algorithms are trained to parse text from the one or more messages (paragraph [0204], "The rescue request manager 125 may parse any text provided in free-form input fields for use in assessing emergency severity and/or suitable emergency responders, for example using natural language processing, and/or may pass on the text to the dispatched emergency responder." (i.e., natural language used to parse text.)).
Regarding Claim 35, MacGabann discloses A method for coordinating emergency response, by an emergency management system, the method comprising:
receiving an emergency alert associated with an emergency and with a user, the emergency alert including a location of the emergency (paragraph [0030], "Further, the rescue application can provide for automated emergency dispatch and location tracking even during internet or landline failure by adaptively determining whether to send rescue request packets over Internet, Short Message Service (“SMS”), or other communications medium. SMS is a text messaging service component of mobile device systems that uses standardized communication protocols to enable mobile devices to exchange short text messages." and paragraph [0051], " In some embodiments, the rescue management servers 120 and/or the rescue request manager 125 parses the image and video files and analyzes them using one or more computer vision applications and/or algorithms. In some embodiments, these applications and/or algorithms may determine location data…" and paragraph [0055], "In some embodiments, the social media scraping may determine a value for victim density during an event, location data," and paragraph [0058], Fig., "At interaction (1), the user initiates and completes the rescue request using the dynamic user interface of the rescue application 105. As described herein, the rescue application 105 can present a first user interface that allows the user to specify which type of emergency the user is experiencing." (i.e., receiving an alert from the user associated with an emergency and can include location data.));
collecting emergency data associated with the emergency from a plurality of sources (paragraph [0051], Fig.1B, "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." (i.e., collecting from SMS, image, video, social media.));
However, MacGabann does not disclose or was not relied upon via one or more machine learning models, determining a dispatch category based at least in part on the emergency data; via the one or more machine learning models, determining an emergency dispatch center to respond to the emergency based at least in part on the emergency data and the location of the emergency.
STAWISZYNSKI discloses via one or more machine learning models, determining a dispatch category based at least in part on the emergency data (paragraph [0018], "Furthermore, while present examples are described with respect to the first responders 122, 132 respectively being a police officer and a firefighter, each of the first responders 122, 132 may be any type of first responders including, but not limited to, emergency medical technicians (EMTs), and the like." and paragraph [0021], "For example, as depicted, the virtual assistant application 143 may have determined that while the mobile device 131 is operated by the first responder 132, whose capabilities may be more relevant to the incident associated with the emergency call 107," and paragraph [0022], "correlate such context information with sensor data received from sensors of the mobile device 121 to cause a modification of an action associated with the emergency call 107 including, but not limited to the action 115) based on a correlation between the context information with the sensor data." and paragraph [0048], "The context information may include, but is not limited to, one or more of a location associated with the emergency call 107;" and paragraph [0065], "the modifying circumstances from “DUMPSTER” to “BUILDING” and the alarm level (e.g. a priority) from “5” to “3” (e.g. a higher priority). The incident report 113 may further be updated to include an incident type of “ARSON”. Similarly, the action 115 may be changed to dispatch two fire engines, one ladder truck, an ambulance, and a police car to the address associated with the incident (e.g. which also changes and/or updates a type of responders dispatched to include EMTs and police officers)." (i.e., virtual assistance changing the dispatch categories such as adding EMT because the incident report has an "ARSON" therefore the machine learning is determining a dispatch category based on data received from user. Also determining to determining a police or firefighter.));
via the one or more machine learning models, determining an emergency dispatch center to respond to the emergency based at least in part on the emergency data and the location of the emergency (paragraph [0021], "the virtual assistant application 143 may monitor the emergency call 107 and/or associated information, such as the address, and determine which of the virtual assistant applications 123, 133 of the mobile devices 121, 131 to include on the emergency call 107. In some examples, such a decision may be based on the location of the mobile devices 121, 131 and/or a role of associated responders 122, 132. For example, as depicted, the virtual assistant application 143 may have determined that while the mobile device 131 is operated by the first responder 132, whose capabilities may be more relevant to the incident associated with the emergency call 107, the mobile device 121 is closer in distance to the incident associated with the emergency call 107; as such, as depicted, the virtual assistant application 143 has connected the virtual assistant application 123 of the mobile device 121 to the emergency call 107." and paragraph [0048], "The context information may include, but is not limited to, one or more of a location associated with the emergency call 107;" and paragraph [0065], "Similarly, the action 115 may be changed to dispatch two fire engines, one ladder truck, an ambulance, and a police car to the address associated with the incident (e.g. which also changes and/or updates a type of responders dispatched to include EMTs and police officers)." (i.e., dispatching police or firefighter depending on the location or distance from the emergency call and the type of emergency that is needed.)).
MacGabann and STAWISZYNSKI are considered to be analogous to the claimed invention because they are in the same field Services for handling of emergency or hazardous situations, e.g. earthquake and tsunami warning systems [ETWS]. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have modified MacGabann to implement the method of STAWISZYNSKI virtual assistance that is running machine learning in order to have the virtual assitance read source data and update the action in order to provide the be response for the caller (STAWISZYNSKI, paragraph [0021], “the virtual assistant application 143 at the dispatch device 101 is configured to monitor the emergency call 107 and determine a mobile device 121, 131 that includes a respective virtual assistant applications 123, 133 to include on the emergency call 107. For example, the virtual assistant application 143 may monitor the emergency call 107 and/or associated information, such as the address, and determine which of the virtual assistant applications 123, 133 of the mobile devices 121, 131 to include on the emergency call 107. In some examples, such a decision may be based on the location of the mobile devices 121, 131 and/or a role of associated responders 122, 132. For example, as depicted, the virtual assistant application 143 may have determined that while the mobile device 131 is operated by the first responder 132, whose capabilities may be more relevant to the incident associated with the emergency call 107, the mobile device 121 is closer in distance to the incident associated with the emergency call 107; as such, as depicted,” and paragraph [0038], “the virtual assistant application 123 may include machine learning and/or deep-learning based algorithms,”).
Regarding Claim 36, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 35.
MacGabann further discloses wherein the emergency alert includes at least one message from a user via a communication device (paragraph [0051], "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." and paragraph [0058], "At interaction (1), the user initiates and completes the rescue request using the dynamic user interface of the rescue application 105. As described herein, the rescue application 105 can present a first user interface that allows the user to specify which type of emergency the user is experiencing…Optionally, the user interfaces can be supplemented with free-form text input that enables users to provide additional information." (i.e., SMS message.))
and determining a dispatch category is based at least in part on the at least one message from the user (paragraph [0051], Fig.1B, "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." and paragraph [0061], "At interaction (3), the rescue request manager 125 performs automated triaging of the rescue request with other incoming rescue requests and identifies a suitable responder to dispatch to the user…Identification of a suitable responder can include matching any injury or emergency situations with one or more of police, firefighters, emergency medical personnel, and other types of emergency responders."(i.e., using the information from SMS to match with the dispatch category.)).
Regarding Claim 38, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 35.
MacGabann further discloses wherein at least one of the plurality of sources is a sensor providing data about the emergency (paragraph [0051], "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." (i.e., image, and video providing data about the emergency.)).
Regarding Claim 40, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 35.
MacGabann further discloses wherein at least one of the plurality of sources is social media (paragraph [0051], "the rescue management servers 120, the PSAP, and/or the rescue request manager 125 may receive image and/or video files, for example via an SMS message, social media, via the rescue application 105, or other submission." (i.e., source is social media.))
and the method includes filtering the social media to obtain relevant social media data associated with the emergency (paragraph [0053], "the rescue request manager 125 and/or the rescue management servers 120 collects information about events and/or victims not available through communications from victims, etc., by scraping or otherwise analyzing social media posts and communications. In some embodiments, the scraping process collects victim and/or event location severity data, and/or similar information based on detected or identified social media posts and communications. The information collected by the scraping process may be used to determine victim density during an event. Such processing may allow automatic triaging of victims that did not affirmatively generate a request via the emergency response system 100 or other PSAP communication." (i.e., scraping process is reading as filtering social media to identify social media data associated with the emergency.)).
Claim(s) 22 is rejected under 35 U.S.C. 103 as being unpatentable over MacGabann (US 20190313230 A1) in view of STAWISZYNSKI (US 20210385638 A1) in further view of Viklund (US 20190272725 A1).
Regarding Claim 22, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 21.
However, MacGabann in view of STAWISZYNSKI do not disclose or were not relied upon wherein at least one of the one or more emergency response questions is generated autonomously via a machine learning model.
Viklund discloses wherein at least one of the one or more emergency response questions is generated autonomously via a machine learning model (paragraph [0133], Fig., "In an illustrative example, radar sensor data may indicate that a user regularly lays on her bedroom floor. This data may initially cause Question Logic 195 to generate questions regarding falls." (i.e., Using data to generate questions.)).
MacGabann in view of STAWISZYNSKI and Viklund are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified MacGabann to implement the method of Viklund of generating question in order to obtain more relevant data from the user and to increase accuracy of machine learning (Viklund, paragraph [0122], “The received answers may be used to annotate sensor data and/or detected activities. The received answers may also be used to further train elements of Activity Logic 135 to determine activities from sensor data and/or to further train elements of Activity Logic 135 to determine a health state based on determined activities. The received answers may also be used to train a machine learning system within Question Logic 195 to select more valuable questions. The value of a question being based on how likely an answer to the question will be useful in reaching a goal, e.g., is predicted to improve a statistical accuracy of the machine learning system by the greatest degree.”).
Claim(s) 23-24 are rejected under 35 U.S.C. 103 as being unpatentable over MacGabann (US 20190313230 A1) in view of STAWISZYNSKI (US 20210385638 A1) in further view of LAM (US 20190114321 A1).
Regarding Claim 23, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 22.
STAWISZYNSKI further discloses wherein the machine learning model is trained to evaluate user responses and messages from the user in the communication session (paragraph [0067], Fig.1, "the virtual assistant application 123 may ask the dispatcher 102 and/or the caller 104 a question on the emergency call 107…based on analysis of the context information prior to determining the modification of the action and/or prior to causing the modification of the action; indeed, the answers to the question may assist the virtual assistant application 123 with determining the modification of the action." (i.e., Evaluating the answers from the caller.)).
However, MacGabann in view of STAWISZYNSKI do not disclose or were not relied upon and generate an emergency response question or other response based on the user responses and message from the user.
LAM discloses and generate (paragraph [0060], Fig.9, "A potential advantage of this system is that there is a reduced need to establish manual conditional logic between questions and answers for a question pathway. The system can be provided with a repository of questions and corresponding answers, and required information for one or more forms, and either through pre-training or reinforcement training of the neural network, the neural network automatically establishes next best questions based on generated suitability scores. Accordingly, especially where there are a large number of forms being provisioned into auto-teleinterview forms, the repositories may be simply linked to the neural network to dynamically generate improved decisions for traversing the question decision trees." (i.e., determining other questions to ask the user based on the user answers.))
MacGabann in view of STAWISZYNSKI and LAM are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified MacGabann to implement the method of LAM in order to improve relevancy and engagement without the need of a human operator (LAM, abstract, “The computing device is configured to automatically tailor a flow of a conversation to an effort to improve relevancy and engagement without the need of a human operator to manually tailor the conversation, which, for example, could be impractically expensive.”).
Regarding Claim 24, MacGabann in view of STAWISZYNSKI in further view of LAM discloses all the limitation of claim 23.
LAM further discloses wherein the one or more emergency response questions are part of a predetermined script of messages generated via a machine learning algorithm (paragraph [0060], Fig.9, "A potential advantage of this system is that there is a reduced need to establish manual conditional logic between questions and answers for a question pathway. The system can be provided with a repository of questions and corresponding answers, and required information for one or more forms, and either through pre-training or reinforcement training of the neural network, the neural network automatically establishes next best questions based on generated suitability scores. Accordingly, especially where there are a large number of forms being provisioned into auto-teleinterview forms, the repositories may be simply linked to the neural network to dynamically generate improved decisions for traversing the question decision trees." (i.e., repository of questions reading as predetermined scripts the machine learning uses to traversing the question decision tree.)).
The proposed combination as well as the motivations for combining the references presented in the rejection of the parent claim apply to this claim and are incorporated herein by reference.
Claim(s) 25 is rejected under 35 U.S.C. 103 as being unpatentable over MacGabann (US 20190313230 A1) in view of STAWISZYNSKI (US 20210385638 A1) in further view of DIZENGOF (US 20180301017 A1).
Regarding Claim 25, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 21.
However, MacGabann in view of STAWISZYNSKI do not disclose or were not relied upon wherein the one or more machine learning algorithms comprise two or more feature spaces comprising emergency alert attribute types.
DIZENGOF discloses wherein the one or more machine learning algorithms comprise two or more feature spaces comprising emergency alert attribute types (paragraph [0049], "The sensors may monitor and/or depict an environment of the originating client device. The sensors may be integrated in the originating client device and/or included in one or more peripheral devices which are operatively communicating with the originating client device, for example, a wearable device and/or the like. The sensory data may relate to the originating client device itself, to the user of the client device (reporter) and/or to the surroundings of the client device. The sensory data may include, for example, imagery data (images, video, etc.), audio data (sound, voice, speech, noise, etc.), motion data, geolocation data, physical condition data of the reporter (e.g. heartbeat rate, blood pressure, respiration rate, temperature, perspiration level, etc.), interaction data reflecting interaction between the reporter and the originating client device and/or the like." and paragraph [0051], "Based on the environment parameter(s) and optionally on the identification data, the incoming emergency calls routing system may estimate the type of the potential emergency event and optionally estimate one or more characteristics of the potential emergency event, for example, location, severity, urgency and/or the like. The incoming emergency calls routing system may further apply one or more machine learning algorithms trained to classify the identified environment parameter(s) to a certain type of the potential emergency event." (i.e., machine learning using the environment information to determine response to the emergency such as audio data, geolocation data, physical condition data.)).
MacGabann in view of STAWISZYNSKI and DIZENGOF are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified MacGabann to implement the method of DIZENGOF in order to enable the machine learning of adjusting to the environment and learning of the environment can lead to determining a priority score that can help reduce the response time to incoming emergency calls associated with high severity (DIZENGOF, paragraph [0025], “Applying the trained machine learning algorithm(s) to estimate the potential emergency event may allow for constant evolution of the routing system in adjusting to new and/or varying environment parameters to accurately classify the potential emergency events according to the identified environment parameters.” And paragraph [0032], “the event report record comprises a priority score calculated for the one or more incoming emergency calls based on the one or more environment parameters. The priority score calculated for one or more of the incoming emergency calls may be used by the selected emergency dispatch center to prioritize the incoming emergency calls routed to the selected emergency dispatch center and hence reduce the response time to incoming emergency calls associated with high severity and/or high urgency potential emergency events.”).
Claim(s) 37 is rejected under 35 U.S.C. 103 as being unpatentable over MacGabann (US 20190313230 A1) in view of STAWISZYNSKI (US 20210385638 A1) in further view of Patton (US 20190251139 A1).
Regarding Claim 37, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 35.
However, MacGabann in view of STAWISZYNSKI do not disclose or were not relied upon wherein the one or more machine learning models are trained on a data set comprising emergency data sets and corresponding dispatch categories.
Patton discloses wherein the one or more machine learning models are trained on a data set comprising emergency data sets and corresponding dispatch categories (paragraph [0048], "The multi-source probability can reflect a mathematical probability or approximation of a mathematical probability of an event (e.g., fire, accident, weather, police presence, etc.) actually occurring based on multiple normalized signals (e.g., the signal sequence)." and paragraph [0078], "Normalization modules for extracting/deriving/inferring time, location, and context can include text processing modules, NLP modules, image processing modules, video processing modules, etc. The modules can be used to extract/derive/infer data representative of time, location, and context for a signal. Time, Location, and Context for a signal can be extracted/derived/inferred from metadata and/or content of the signal. For example, NLP modules can analyze metadata and content of a sound clip to identify a time, location, and keywords (e.g., fire, shooter, etc.). An acoustic listener can also interpret the meaning of sounds in a sound clip (e.g., a gunshot, vehicle collision, etc.) and convert to relevant context." and paragraph [0084], "A database maintains mappings between different combinations of signal properties and ratios of signals turning into events (a probability) for that combination of signal properties. The database is queried with the combination of signal properties. The database returns a ratio of signals having the signal properties turning into events. The ratio is assigned to the signal. A combination of signal properties can include: (1) event class (e.g., fire, accident, weather, etc.), (2) media type (e.g., text, image, audio, etc.), (3) source (e.g., twitter, traffic camera, first responder radio traffic, etc.), and (4) geo type (e.g., geo cell, region, or non-geo)." and paragraph [0085], " a single source probability is calculated by single source classifiers (e.g., machine learning models, artificial intelligence, neural networks, etc.) that consider hundreds, thousands, or even more signal features of a signal. Single source classifiers can be based on binary models and/or multi-class models." and paragraph [0091], "…Each single source probability is a probability of the ingested signal being a particular category of event (e.g., fire, weather, medical, accident, police presence, etc.)…"and paragraph [0147], “As descried, in general, on an ongoing basis, concurrently with signal ingestion (and also essentially in real-time), event detection infrastructure 103 detects different categories of (planned and unplanned) events (e.g., fire, police response, mass shooting, traffic accident, natural disaster, storm, active shooter, concerts, protests, etc.) in different locations (e.g., anywhere across a geographic area, such as, the United States, a State, a defined area, an impacted area, an area defined by a geo cell, an address, etc.), at different times from time, location, and context included in normalized signals.” (i.e., par.85 indicate the machine learning were trained on a data set comprising emergency data sets and corresponding dispatch categories as disclosed in par.84, 91, 147.)).
MacGabann in view of STAWISZYNSKI and Patton are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified MacGabann to implement the method of Patton in order to increase the efficiency of determining truthfulness, severity, and an associated geo cell and thus saving resources when false calls are made (Patton, paragraph [0148], “can also determine an event truthfulness, event severity, and an associated geo cell. In one aspect, context information in a normalized signal increases the efficiency of determining truthfulness, severity, and an associated geo cell.”).
Claim(s) 39 is rejected under 35 U.S.C. 103 as being unpatentable over MacGabann (US 20190313230 A1) in view of STAWISZYNSKI (US 20210385638 A1) in further view of Pecoraro (NPL "Using Data Science to Predict Response Times of Firefighters" by Cyril Pecoraro).
Regarding Claim 39, MacGabann in view of STAWISZYNSKI discloses all the limitation of claim 35.
However, MacGabann in view of STAWISZYNSKI do not disclose wherein the one or more machine learning models are trained on a data set comprising actual emergency response times for specific emergency dispatch centers and emergency locations.
Pecoraro discloses wherein the one or more machine learning models are trained on a data set comprising actual emergency response times for specific emergency dispatch centers and emergency locations (page 2, paragraph 3, Fig.1, "Fire departments usually divide the response times of their firefighters in two main parts: turnout time, which corresponds to the seconds elapsed while firefighters prepare themselves at the station, and travel time, which refers to the time taken by the vehicle to arrive at the location of the incident." and page 3 paragraph 2, "To predict the response time, the prediction of the turnout time is added to the prediction of the travel time; both require the use of a regression algorithm." and page 7, paragraph 1, "Features such as the time of day, season, type of units, type of incidents (5 types) and information about the fire station of origin were provided to the algorithm. The training set was composed of around 800,000 interventions that happened between 2009 and 2016. Interventions posterior to 2016 were used in the test set." And page 7 paragraph 2, “This shows the improvement brought by using machine learning to predict a turnout time that may vary based on several factors.” and page 11, lines 6-8, "…A complete simulation engine could be built combining several predictive tools. An engine predicting the risks of fire in a building similar to Firebird could be associated with another engine predicting the medical emergencies..." (i.e., A machine learning that is trained on response time to predict response time. The specific emergency dispatch center such as Firebird for fire and medical emergencies is another dispatch center.)).
MacGabann in view of STAWISZYNSKI and Pecoraro are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified MacGabann to implement the method of Patton of machine learning determining or predicting response time as machine learning provides a more accurate response time as the machine learning model takes into account external dynamic factors such as weather and traffic (Patton, page 7, paragraph 3, “A lot of fire departments and emergency services rely on geographic information systems tools, such as ESRI ARCGis or Network Analyst, to obtain estimations about the response time. These tools rely on computing the shortest route using a graphical representation of the road network, which usually gives an accurate estimate of the travel time. Their drawback is that they cannot always take into consideration external dynamic factors such as the weather, traffic or type of units or intervention. Hence, there is an opportunity for machine learning tools to be used here.”).
Claim(s) 26 is rejected under 35 U.S.C. 103 as being unpatentable over MacGabann (US 20190313230 A1) in view of STAWISZYNSKI (US 20210385638 A1) in view of DIZENGOF (US 20180301017 A1) in further view of Viklund (US 20190272725 A1).
Regarding Claim 26, MacGabann in view of STAWISZYNSKI in view of DIZENGOF discloses all the limitation of claim 25.
DIZENGOF further discloses wherein the emergency alert attribute types include one or more of location, (paragraph [0049], "The sensors may monitor and/or depict an environment of the originating client device. The sensors may be integrated in the originating client device and/or included in one or more peripheral devices which are operatively communicating with the originating client device, for example, a wearable device and/or the like. The sensory data may relate to the originating client device itself, to the user of the client device (reporter) and/or to the surroundings of the client device. The sensory data may include, for example, imagery data (images, video, etc.), audio data (sound, voice, speech, noise, etc.), motion data, geolocation data, physical condition data of the reporter (e.g. heartbeat rate, blood pressure, respiration rate, temperature, perspiration level, etc.), interaction data reflecting interaction between the reporter and the originating client device and/or the like." and paragraph [0051], "Based on the environment parameter(s) and optionally on the identification data, the incoming emergency calls routing system may estimate the type of the potential emergency event and optionally estimate one or more characteristics of the potential emergency event, for example, location, severity, urgency and/or the like. The incoming emergency calls routing system may further apply one or more machine learning algorithms trained to classify the identified environment parameter(s) to a certain type of the potential emergency event." (i.e., machine learning using the environment information to determine response to the emergency that includes location)).
However, MacGabann in view of STAWISZYNSKI in view of DIZENGOF do not disclose or were not relied upon wherein the emergency alert attribute types include demographic information.
Viklund discloses wherein the emergency alert attribute types include demographic information (paragraph [0186], "Activity Analysis Logic 730 can include a first Machine Learning System 735, a second Machine Learning System 745, and/or Rule Logic 747." and paragraph [0225], "Activity Expectation Logic Activity Logic 135 or Activity Analysis Logic 730 is configured to first determine an expected activity of the user based on demographics of the user, and then to further refine the expected activity based on actual activity of the user as determined by Activity Analysis Logic 1730 based on data from Sensors 715, and/or answers to selected questions. In these cases, the expected activity is based on both demographics and measured activity." and paragraph [0238], "…Alert Logic 755 is optionally an embodiment of Alert Logic 186. As discussed elsewhere herein, an alert is sent if one or more dimensions of the (measured) activity level of the user are sufficiently different than the expected activity level.…" and paragraph [0279], " A dynamic threshold is one that may vary depending on different criteria. In various embodiments, the threshold varies as a function of time, as a function of an expected confidence (accuracy) of the expected activity level, as a function of an expected accuracy of the received activity level, as a function of an amount of activity data received for the user, as a function of the demographics of the user…an alert be sent. Thresholds determined in Determine Threshold Step 1125 may, therefore, be based on responses to selected questions."(i.e., machine learning using demographic information to predict expected activity level, see DIZENGOF wherein discloses measuring blood pressure, respiration rate, and its an emergency alert attribute as if the user activity is under performance and alert needs to be sent out.)).
MacGabann in view of STAWISZYNSKI in further view of DIZENGOF and Viklund are considered to be analogous to the claimed invention because they are in the same field Machine learning. Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention to have further modified MacGabann to implement the method of Viklund of having a machine learning trained on demographic information in order to obtain more relevant data from the user and to increase accuracy of machine learning (Viklund, paragraph [0122], “The received answers may be used to annotate sensor data and/or detected activities. The received answers may also be used to further train elements of Activity Logic 135 to determine activities from sensor data and/or to further train elements of Activity Logic 135 to determine a health state based on determined activities. The received answers may also be used to train a machine learning system within Question Logic 195 to select more valuable questions. The value of a question being based on how likely an answer to the question will be useful in reaching a goal, e.g., is predicted to improve a statistical accuracy of the machine learning system by the greatest degree.”).
Other Pertinent References
Pal; Jayanta et al. "METHOD FOR SMARTPHONE-BASED ACCIDENT DETECTION." (US 20170053461 A1), Filed 2016-08-22.
Phillipps; Kelly D. et al. "INTEGRATED MACHINE LEARNING FOR A DATA MANAGEMENT PRODUCT." (US 20140195466 A1), Filed 2014-01-08.
Jayavelu; Arumugam et al. "SYSTEMS AND METHODS FOR IDENTIFYING INCIDENTS USING SOCIAL MEDIA." (US 20190361951 A1), Filed 2019-02-15, provisional dates 2018-12-19 and 2018-02-16.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Erkin S. Abdullaev whose telephone number is (571)272-4135. The examiner can normally be reached Monday - Friday - 8:00 am - 5:00 pm.
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, Wesley Kim can be reached at (571)272-7867. 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.
ERKIN S. ABDULLAEV
Examiner
Art Unit 2648
/ERKIN ABDULLAEV/Examiner, Art Unit 2648
/WESLEY L KIM/Supervisory Patent Examiner, Art Unit 2648
Prosecution Insights