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 .
The present Office Action is in response to the Request for Continued Examination dated 02 September 2025.
Request for Continued Examination
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 02 September 2025has been entered.
DETAILED ACTION
In the amendment filed 02 September 2025:
Claims 39-41 are cancelled
Claims 21,23-24,26,28-30 and 36-37 are amended
Claims 21-30,32-33,35-38 are pending
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 21-30,32-33,35-38 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
Claims 21, 26, 30 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. The claim recites a methods and a server, which are within a statutory category. The limitations of:
Claims 21, 26, 30 (21 is representative)
determining candidate hospitals according to a search radius;
transporting an emergency patient;
record the voice of the emergency patient and to photograph the emergency patient in order to generate status information about the emergency patient during transport, the status information generated;
automatically creating an emergency activity log based on the recorded emergency patient's condition during transport;
transmitting the status information;
determining a severity of the emergency patient based on the status information;
calculating emergency event possibility information based on the status information;
acquiring transport resource availability information about the candidate hospitals, the transport resource availability information acquired from the emergency medical server;
calculating a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and the transport resource availability information;
and determining the optimal transfer hospital based on the fitness of each candidate hospital,
wherein the status information is acquired according to the emergency activity log by recognizing syllables of words spoken by a paramedic and by recognizing photographed images of the emergency patient,
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information with respect to the real-time traffic information and the location information of each candidate hospital,
stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, providing information related to an emergency medical service, the information being stored and provided
calculate the fitness of each candidate hospital during transport of the emergency patient, that are continuously updated, by continuously inputting data acquired throughout the transport of the emergency patient, the data being input and including
first data of the severity of the emergency patient acquired based on the status information, the first data received only during transport of the emergency patient,
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information with respect to the real-time traffic information, the third data received and
configured to:
determine an order of suitability among the candidate hospitals based on the fitness of the optimal transfer hospital compared with a predetermined value;
select one hospital having a highest suitability among the candidate hospitals as the optimal transfer hospital;
transmit information on the order of suitability among the candidate hospitals and the selected one hospital;
transmit, to the selected one hospital, weight information of the emergency patient together with an inquiry as to whether the selected one hospital can accept the emergency patient;
receive, from the selected one hospital, a response to the inquiry, the selected one hospital determining whether to accept the emergency patient based on the weight information of the emergency patient and a number of emergency patients accepted during the transport of the emergency patient, the selected one hospital further transmitting the response;
and update the weight information of the emergency patient and information about the number of accepted emergency patients and the order of suitability among the candidate hospitals in real-time.
as drafted, is a process that, under the broadest reasonable interpretation, covers certain methods of organizing human activity (i.e., managing personal behavior including following rules or instructions) but for recitation of generic computer components. That is, other than reciting an emergency AI server, emergency medical server, cloud server, local server, nationally based server, control unit and storage unit, the claimed invention amounts to managing personal behavior or interaction between people. The Examiner notes that certain “method[s] of organizing human activity” includes a person’s interaction with a computer (see MPEP 2106.04(a)(2)(II)). If a claim limitation, under its broadest reasonable interpretation, covers managing personal behavior or interactions between people but for the recitation of generic computer components, then it falls within the “certain methods of organizing human activity” grouping of abstract ideas. Accordingly, the claims recite an abstract idea.
The claim further recites the additional element of continuously updating a machine learning model to find the best candidate hospital to transport a patient to during an emergency. This represents mere instructions to implement the abstract idea on a generic computer. Implementing an abstract idea using a generic computer or components thereof does not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. See, e.g., Recentive Analytics, Inc. v. Fox Corp., No. 2023-2437 at 10 (Fed. Cir. April 18, 2025) (finding that claims that do no more than apply established methods of machine learning to a new data environment are ineligible). Alternatively, or in addition, the implementation of the trained machine learning model to find the best candidate hospital to transport a patient to during an emergency merely confines the use of the abstract idea (i.e., the trained model) to a particular technological environment or field of use (at least one of supervised learning, support vector machines (SVM), random forest (RF), naive bayes (NB), artificial neural networks (ANN), decision tree, and Bayesian) and thus fails to add an inventive concept to the claims.
This judicial exception is not integrated into a practical application. In particular, the claims recite the additional elements of an emergency AI server, emergency medical server, cloud server, local server, control unit and storage unit, that implement the identified abstract idea. The emergency AI server, emergency medical server, cloud server, local server, nationally based server, control unit and storage unit are not described by the applicant and is recited at a high-level of generality (i.e., generic computer components performing generic computer functions) such that it amounts no more than mere instructions to apply the exception using generic computer components. Accordingly, these additional elements do not integrate the abstract idea into a practical application because it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea.
The claims further recite the additional element of an ambulance device capable of transporting an emergency patient, an ambulance device including a camera capable of audiovisual recording, machine learning models and storage device. The ambulance device capable of transporting an emergency patient, an ambulance device including a camera capable of audiovisual recording, machine learning models and storage device merely generally links the abstract idea to a particular technological environment or field of use. MPEP 2106.04(d)(I) indicates that generally linking an abstract idea to a particular technological environment or field of use cannot provide a practical application. Accordingly, even in combination, this additional element does not integrate the abstract idea into a practical application.
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements of using an emergency AI server, emergency medical server, cloud server, local server, nationally based server, control unit and storage unit to perform the noted steps amounts to no more than mere instructions to apply the exception using a generic computer component. Mere instructions to apply an exception using a generic computer component cannot provide an inventive concept (“significantly more”).
As discussed above with respect to integration of the abstract idea into a practical application, the additional element of using the trained machine learning model to find the best candidate hospital to transport a patient to during an emergency was found to represent mere instructions to implement the abstract idea on a generic computer and/or confine the use of the abstract idea (i.e., the trained model) to a particular technological environment or field of use (at least one of supervised learning, support vector machines (SVM), random forest (RF), naive bayes (NB), artificial neural networks (ANN), decision tree, and Bayesian). This has been re-evaluated under the “significantly more” analysis and determined to be insufficient to provide significantly more. MPEP 2106.05(I) indicates that mere instructions to implement the abstract idea on a generic computer and/or confining the use of the abstract idea to a particular technological environment or field of use cannot provide significantly more. See also Recentive Analytics, Inc. v. Fox Corp., No. 2023-2437 at 17 (Fed. Cir. April 18, 2025) (finding that applying machine learning to an abstract idea does not transform a claim into something significantly more).
Also, as discussed above with respect to integration of the abstract idea into a practical application, the additional elements of an ambulance device capable of transporting an emergency patient, an ambulance device including a camera capable of audiovisual recording, machine learning models and storage device were determined to generally link the abstract idea to a particular technological environment or field of use. This has been re-evaluated under the “significantly more” analysis and has also been found insufficient to provide significantly more. MPEP 2106.05(A) indicates that generally linking an abstract idea to a particular technological environment or field of use cannot provide significantly more. MPEP 2106.05(f) indicates that merely saying “apply it” cannot provide significantly more. Accordingly, even in combination, these additional elements do not provide significantly more. As such the claims are not patent eligible.
Claims 22-25,27-29,32-33,35-38 are similarly rejected because they either further define/narrow the abstract idea and/or do not further limit the claim to a practical application or provide as inventive concept such that the claims are subject matter eligible even when considered individually or as an ordered combination.
Claim(s) 22, 27, 32 merely describe(s) what the status information contains, which further defines the abstract idea.
Claim(s) 23, 28, 36 merely describe(s) expanding search radius to find a candidate hospital, which further defines the abstract idea.
Claim(s) 24, 29, 37 merely describe(s) expanding search radius to find a candidate hospital, which further defines the abstract idea.
Claim(s) 25, 38 merely describe(s) utilization of an air ambulance, which further defines the abstract idea.
Claim Rejections - 35 USC § 103
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The Examiner notes that the rejection will reference the translated documents (attached) corresponding to any foreign documents recited in the rejection.
Claims 21-22 is/are rejected under 35 U.S.C. 103(a) as being unpatentable over AOKI et al (Foreign Publication WO-2012098613-A1) in view of BAE et al (Foreign Publication KR-20060037684-A) in view of Kim et al (US Publication No. 20180322961) in view of MARUYAMA et al (Foreign Publication JP-2011048775-A) in view of PEETERS et al (US Publication No. 20160157739) in view of Gounares et al (US Publication No. 20090198733) in view of Simoudis et al (US Publication No. 20200363220).
Regarding Claim 21
AOKI teaches a method for determining an optimal transfer hospital, the method comprising:
determining candidate hospitals according to a search radius [AOKI at Page 10 Para 8 teaches the server sorts the list of medical institutions that can be transported based on the judgment of severity and urgency and the characteristics and list of pre-registered medical institutions according to the distance from the site and the busyness of each medical institution];
automatically creating, by the ambulance device, an emergency activity log based on the recorded emergency patient's condition during transport [AOKI at Page 10 Para 7 teaches the ambulance team records data necessary for the determination of “severity / emergency” in the patient's past history, current medical history, and physical findings (S7). Based on this recorded data, the server uses a severity / emergency determination algorithm incorporated internally based on the “Employment Standards for Transporting and Accepting Victims” determined by each local government. A determination is made (S8)];
determining, in the emergency Al server, a severity of the emergency patient based on the status information [AOKI at Page 10 Para 7];
acquiring, in the emergency Al server, transport resource availability information about the candidate hospitals, the transport resource availability information acquired from the emergency medical server [AOKI at Page 10 Para 8];
first data of the severity of the emergency patient acquired from the ambulance device based on the status information, the first data received only during transport of the emergency patient [AOKI at Page 16 Para 3 teaches the severity determination unit 251c calculates the severity of the patient based on the registered information and various indexes. For example, when the consciousness state, blood pressure, pulse rate, respiration, body temperature, SpO2, etc. are input by the ambulance team on the screen 502 as shown in FIG. 25, the severity determination unit 201e, based on the input information, It is possible to determine the urgency level of the disease state and display it on the screen],
wherein the emergency Al server is further configured to:
determine an order of suitability among the candidate hospitals based on the fitness of the optimal transfer hospital compared with a predetermined value [AOKI at Page 10 Para 8];
select one hospital having a highest suitability among the candidate hospitals as the optimal transfer hospital [AOKI at Page 14 Para 7 teaches in addition to this, the transport destination candidate is selected in consideration of the suspected disease and its severity];
transmit, to the ambulance device, information on the order of suitability among the candidate hospitals and the selected one hospital [AOKI at Page 4 Para 5 teaches Hereinafter, an example of screen transition in the terminal will be described with reference to FIGS. Screen data on the terminal is generated under the control of the display control unit 301b of the server. Information input by the terminal is registered in the information registration unit 301d of the server. The list displayed on the terminal is created by the server list creation unit 301f];
transmit, to the selected one hospital, weight information of the emergency patient together with an inquiry as to whether the selected one hospital can accept the emergency patient [AOKI at Page 14 Para 4 teaches in the initial branch screen 502, when one of endogenous adult CPA, endogenous child CPA, extrinsic CPA, and DNR-compatible CPA is designated in the input designation area of a highly urgent disease displayed on the upper left, FIG. As shown in FIG. 32, the screen transits to an acceptability status screen 509 regarding CPA. On this screen 509, the occurrence status (map), the activity status of today's list hospital, and current patient information are displayed (patient information interpreted as weight information of the emergency patient); AOKI at Page 14 Para 5 teaches when the hospital is selected from the list of activity status of today's list hospital on the acceptability screen 509, the screen changes to an acceptability input screen 511 as shown in FIG. In this screen 511, the name of the medical institution to be inquired, the telephone number, and the name of the on-duty doctor are displayed on the upper side, and the telephone, background / transport source, acceptable, and difficult to accept buttons are displayed in the middle];
receive, from the selected one hospital, a response to the inquiry, the selected one hospital determining whether to accept the emergency patient based on the weight information of the emergency patient [AOKI at Page 14 Para 5 teaches when the terminal is operated at a medical institution or the like and the difficult to accept button is pressed, a difficult to accept reason input panel 513 as shown in FIG. 36 is displayed. On this panel 513, it is possible to select a reason for difficulty in acceptance.] and a number of emergency patients accepted during the transport of the emergency patient, the selected one hospital further transmitting the response to the ambulance device [AOKI at Page 6 Para 9 teaches by the way, the medical institution displays the availability of beds and resources for each department or specialty by “○”, “×”, etc., and the emergency team determines the transport destination based on the signature (emergency team transport destination interpreted to be determined on the ambulance device)];
and update the weight information of the emergency patient and information about the number of accepted emergency patients and the order of suitability among the candidate hospitals in real-time [AOKI at Page 10 Para 8 teaches the server updates the list based on this notification (S13). In this way, the medical institution and the emergency team make the best decision while sharing the same information (patient outbreak status, busyness of each medical institution, patient status, etc.). In addition, when the ambulance team makes an inquiry, if it is difficult to accept due to the situation of the medical institution, the information can be shared by touching the ambulance team].
AOKI does not teach transporting an emergency patient in an ambulance device including a camera capable of audiovisual recording;
automatically operating the camera to record the voice of the emergency patient and to photograph the emergency patient in order to generate status information about the emergency patient during transport, the status information generated by the camera being stored in a storage device provided in the ambulance device;
transmitting the status information from the ambulance device to an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server;
calculating, in the emergency medical server, emergency event possibility information based on the status information;
calculating, in the emergency Al server, a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and the transport resource availability information;
and determining, in the emergency Al server, the optimal transfer hospital based on the fitness of each candidate hospital,
wherein the status information is acquired according to the emergency activity log by recognizing syllables of words spoken by a paramedic of the ambulance device and by recognizing photographed images of the emergency patient,
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server,
wherein the emergency Al server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server, and
BAE teaches transporting an emergency patient in an ambulance device including a camera capable of audiovisual recording [BAE at Page 2 Para 1 teaches inside the ambulance, at least a camera for photographing a patient's condition, a microphone for receiving an audio signal inside the vehicle and sending it to an emergency center, a speaker for outputting an audio signal transmitted from the emergency center, and an ambulance; BAE at Page 8 Para 8 teaches as described above, the present invention has an advantage in that an emergency center in a hospital or the like can identify a patient's condition in an ambulance vehicle through video and audio, thereby enabling a first-aid for a specialist];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine patient severity of AOKI with the camera of BAE with the motivation to improve monitoring of a patient in an ambulance car.
AOKI/BAE do not teach automatically operating the camera to record the voice of the emergency patient and to photograph the emergency patient in order to generate status information about the emergency patient during transport, the status information generated by the camera being stored in a storage device provided in the ambulance device;
transmitting the status information from the ambulance device to an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server;
calculating, in the emergency medical server, emergency event possibility information based on the status information;
calculating, in the emergency Al server, a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and the transport resource availability information;
and determining, in the emergency Al server, the optimal transfer hospital based on the fitness of each candidate hospital,
wherein the status information is acquired according to the emergency activity log by recognizing syllables of words spoken by a paramedic of the ambulance device and by recognizing photographed images of the emergency patient,
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server,
wherein the emergency Al server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server, and
KIM teaches operating the camera to record the voice of the emergency patient and to photograph the emergency patient in order to generate status information about the emergency patient during transport, the status information generated by the camera being stored in a storage device provided in the ambulance device [KIM at Para 0042 teaches in general, a voice module 104, in various embodiments, is configured to receive and/or record voice audio data from a user (e.g., a patient, an athlete, another user, or the like) and/or to assess and/or diagnose the presence and/or severity of one or more medical conditions (e.g., injuries, illnesses, diseases, or the like) based on collected voice audio data (interpret to combine with ambulance device of AOKI)];
wherein the status information is acquired according to the emergency activity log by recognizing syllables of words spoken by a paramedic of the ambulance device and by recognizing photographed images of the emergency patient [KIM at Para. 0067 teaches the speech recognition results may be in any appropriate format and include any appropriate information. For example, the speech recognition results may include a word lattice that includes multiple possible sequences of words, information about pause fillers, and the timings of words, syllables, vowels, pause fillers, or any other unit of speech; KIM at Para. 0153 teaches in one embodiment, the detection module 1106 may extract one or more image features from image data (e.g., one or more images, video, or the like of the user, of the user's face, of another body part of the user associated with a medical condition, or the like) from an image sensor such as a camera of a computing device 102, and may input the one or more image features into a model (e.g., with extracted voice features or the like)],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE with the speech recognition of KIM with the motivation to improve the performance of a medical condition diagnosis system.
AOKI/BAE/KIM do not teach transmitting the status information from the ambulance device to an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server;
calculating, in the emergency medical server, emergency event possibility information based on the status information;
calculating, in the emergency Al server, a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and the transport resource availability information;
and determining, in the emergency Al server, the optimal transfer hospital based on the fitness of each candidate hospital,
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server,
wherein the emergency Al server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server, and
MARUYAMA teaches transmitting the status information from the ambulance device to an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server [MARUYAMA at Page 3 Para 5 teaches the vehicle terminal 2 is mounted on an emergency vehicle such as an ambulance and wirelessly communicates with the management server 3 to acquire and display identification information of a medical institution such as a hospital that should go from the emergency site that is the current location. As a result, the ambulance crew can transport the emergency patient and the injured person to an appropriate medical institution without hesitation on site. The management server 3 is installed in a general center having jurisdiction over a predetermined area, and communicates with the vehicle terminal 2 and the hospital server 4 so that when there is an inquiry about an accepted hospital from the vehicle terminal 2, each hospital server 4 receives each hospital.];
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server [MARUYAMA at Page 3 Para 1 teaches however, when receiving the inquiry of the receiving hospital from the terminal and means for storing the hospital location information in advance for each hospital, the inquiry of the corresponding time is transmitted to the hospital server for each hospital, As a response, the means for receiving and storing the corresponding time from the hospital server, the location information of the terminal included in the inquiry of the accepting hospital, and the prestored information of each hospital Based on the location information, for each hospital, a means for calculating and storing the travel time from the current position of the emergency vehicle to the hospital and the larger of the corresponding time and the travel time for each hospital Means for storing the time until the hospital can accept the patient and the minimum of the reception times of each hospital, and the hospital associated with the minimum value is selected as the receiving hospital. And means for transmitting information related to the hospital to the terminal],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM with the servers of MARUYAMA with the motivation to pick the most qualified hospital for the patient.
AOKI/BAE/KIM/MARUYAMA do not teach calculating, in the emergency medical server, emergency event possibility information based on the status information;
calculating, in the emergency Al server, a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and the transport resource availability information;
and determining, in the emergency Al server, the optimal transfer hospital based on the fitness of each candidate hospital,
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the emergency Al server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server, and
PEETERS teaches calculating, in the emergency medical server, emergency event possibility information based on the status information [PEETERS at Para. 0033 teaches by ‘one or more parameters indicative of a probability of Return of Spontaneous Circulation’ may be understood a number which is indicative of a probability of Return of Spontaneous Circulation];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA with the emergency event possibility of PEETERS with the motivation to better understand the patient’s condition to better match to a candidate hospital.
AOKI/BAE/KIM/MARUYAMA/PEETERS do not teach calculating, in the emergency Al server, a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and the transport resource availability information;
and determining, in the emergency Al server, the optimal transfer hospital based on the fitness of each candidate hospital,
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the emergency Al server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server, and
PEETERS teaches calculating, in the emergency medical server, emergency event possibility information based on the status information [PEETERS at Para. 0033 teaches by ‘one or more parameters indicative of a probability of Return of Spontaneous Circulation’ may be understood a number which is indicative of a probability of Return of Spontaneous Circulation (interpreted as emergency event possibility information)];
Gounares teaches the emergency Al server, a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and the transport resource availability information [Gounares at Para. 0004 teaches the subject innovation relates to systems and/or methods that facilitate identifying an optimal medical facility to transport a patient involved in an emergency medical incident. Moreover, the subject innovation relates to systems and/or methods that facilitate routing a patent to medical care and/or routing medical care to a patient. A match component can be utilized in order to identify an optimal selection of a medical facility to transport a patient based on evaluating a portion of data related to at least one of a patient in need of emergency medical attention, a medical facility, and/or a route and respective traffic between the medical facility and the patient. In general, the match component can examine the portion of data to select a medical facility, a route or set of directions, and/or a patient needs (e.g., medical assets, specialists, etc.) based upon a patient location, traffic evaluation, a patient health condition, available medical support (e.g., devices, medicine, personnel, etc.), predicted traffic, patient authorized medical data, and/or patient status (e.g., vital signs, injury, etc.) (interpret to combine with emergency event possibility information of PEETERS)];
and determining, in the emergency Al server, the optimal transfer hospital based on the fitness of each candidate hospital [Gounares at Para. 0004],
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital [Gounares at Para. 0037 teaches in general, the contingency component 402 can provide online adaptive flows based on real time monitoring of at least one of a patient, traffic, prediction of traffic, etc. to make decisions and updates based on information (e.g., stuck in traffic, construction, detours, etc.); Gounares at Para. 0047 teaches moreover, travel time can be analyzed based on predicting traffic along the route from the patient's location to the medical facility's location. For instance, characteristics such as personnel, staffing, assets (e.g., devices in a vehicle/facility, drugs, equipment, needles, oxygen, scanning devices, etc.), resources, patient flow, modes of transportation, and the like can be considered in determining if a medical facility suites a particular patient],
[ … ] … calculate the fitness of each candidate hospital during transport of the emergency patient [Gounares at Para. 0035 teaches the system 300 can further include a data store 310 that can include any suitable data related to a patient, an incident that requires medical assistance, an accident, a medical facility, traffic on a route between an accident and a medical facility, etc. It is to be appreciated that such information or data can be at least one of dynamically gathered, collected and periodically updated, and/or any suitable combination thereof. For example, a periodic update can be requested or retrieved from medical facilities based on duration of time. In general, the data store 310 can include, but not limited to including, patient data, accident or incident data, transportation/traffic data, medical facility information, and/or any suitable combination thereof.], … [ … ] … the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including [Gounares at Para. 0035]
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient [Gounares at Para. 0022 teaches the match component 102 can evaluate the portion of data (e.g., patient data, medical facility data, and/or traffic data) such as, but not limited to, traffic patterns, previous traffic flows, databases of ambulance flows, medical facility assets (e.g., devices in a vehicle/facility, drugs, equipment, needles, oxygen, scanning devices, etc.), medical professional staffing (e.g., employees on staff, specialists, experts, surgeons, credentials of employees, etc.), patient status during transport, severity of injuries, a location of patient, a location of the emergency situation, received medical data (e.g., EMT report, initial prognosis, blood pressure, vital stats, heart rate, historic medical data, etc.), history of traffic patterns, emergency vehicle routes, directions, travel distance, and/or any other suitable data associated with transporting a patient to a medical facility 104 in an emergency situation],
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server [Gounares at Para. 0037 teaches the system 400 can employ a contingency component 402 that enables a pre-calculated or dynamically generated contingency plan for a patient being transported in an emergency situation. In general, the contingency component 402 can provide online adaptive flows based on real time monitoring of at least one of a patient, traffic, prediction of traffic, etc. to make decisions and updates based on information (e.g., stuck in traffic, construction, detours, etc.). In other words, the contingency component 402 can re-assess a transport for a patient based on a circumstance or event that may have been unexpected in a match initiated by the match component 108], and
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA, PEETERS with the fitness calculation of Gounares with the motivation to provide increased efficiency, decrease errors and costs, and more importantly save lives.
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares do not teach wherein the emergency Al server is configured to perform machine learning to … [ … ] … includes a cloud server, and stores a plurality of machine learning models that are continuously updated,
Simoudis teaches wherein the emergency Al server is configured to perform machine learning to [Simoudis at Para. 0056 teaches the platform may be capable of generating a personalized transportation plan for a user, to process, recommend, and/or present personalized mobility data, routing data, scheduling data, traffic data, and many other forms of data. In some instances, machine learning techniques can be utilized to create a personalized transportation plan that includes predicted destinations, travel schedules (e.g., begin time, end time), options for transaction-based purchase of goods, services, and content during transportation, types of vehicles (e.g., types of autonomous vehicles such as sedans or vans, brands), types of transportation modes (e.g., autonomous vehicle, public transportation (such as train, light rail, or city bus), shuttle, ride-sharing, ride-hailing, shared trip or private trip, walking, bicycle, e-scooter, taxi, etc.), and others.] … [ … ] … includes a cloud server, and stores a plurality of machine learning models that are continuously updated [Simoudis at Para. 0058 teaches the one or more databases 107, 109 may utilize any suitable database techniques. For instance, structured query language (SQL) or “NoSQL” database may be utilized for storing the user profile data, historical data, predictive model or algorithms used for generating a personalized transportation plan, map or other data; Simoudis at Para. 0070 teaches FIG. 13 shows examples of data processed or used by the transportation plan generator 1107. The transportation plan generator may be configured to analyze user data, vehicle data (e.g., data stored in the vehicle database or real-time vehicle data), and third-party data, and use machine learning, planning, and reasoning algorithms to create a transportation plan that is tailored to each user on a day-by-day basis, and updated as-necessary in near real-time during the day],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA, PEETERS, Gounares with the machine learning models of Simoudis with the motivation to improve local transportation.
Regarding Claim 22
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis teach the method of claim 21,
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis further teach wherein the status information of the emergency patient includes at least one of biosignal information, age information, complained symptom information, existing medical history information, consciousness information, and electrocardiogram information [AOKI at Page 14 Para 4 teaches as the current patient, the age, sex, chief complaint, awareness, current arrival time, etc. of the patient are displayed. In such a screen 509, when the center “transmission screen” button is pressed, a transmission item panel 510 as shown in FIG. 33 is displayed. In this panel 510, the estimated cardiopulmonary arrest time, age, sex, presence / absence of DNR correspondence are input as basic items, and CPA-specific information is presence / absence of eyewitness, presence / absence of bystander, initial electrocardiogram, AED, medical history, family The clinic, pass ID, transport history, disease name, transport destination, ETA, etc. are input], the emergency event possibility information includes at least one of intensive careunit hospitalization possibility information, STEMI possibility information, UA+NSTEM possibility information, LVO possibility information, cerebral infarction and cerebral hemorrhage possibility information, return of spontaneous circulation possibility information, and cardiac arrest recurrence possibility information [PEETERS at Para. 0033 (see Claim 21 for explanation)], and the transport resource availability information further includes at least one of available sickbed information of each candidate hospital, duty doctor information of each candidate hospital, and facility information of each candidate hospital [AOKI at Page 14 Para 5 teaches in this screen 511, the name of the medical institution to be inquired, the telephone number, and the name of the on-duty doctor are displayed on the upper side, and the telephone, background / transport source, acceptable, and difficult to accept buttons are displayed in the middle].
Claims 23-24 rejected under 35 U.S.C. 103(a) as being unpatentable over AOKI, BAE, KIM, MARUYAMA, PEETERS, Gounares, Simoudis as applied to claim 21 above, and further in view of TANAKA et al (Foreign Publication JP-2005071092-A).
Regarding Claim 23
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis teach the method of claim 22,
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis teach further comprising:
re-determining candidate hospitals by expanding the search radius [MARUYAMA at Page 3 Para. 9 teaches if there is no hospital whose acceptance time is less than or equal to a predetermined value, the possibility of finding a hospital that can be immediately responded or has a short response time can be found by expanding the range and searching for a hospital (interpret to correspond with evaluation of TANAKA)] … [ … ]
calculating a fitness of each re-determined candidate hospital [Gounares at Para. 0004 (see Claim 1 for explanation)];
and re-determining the optimal transfer hospital based on the fitness of each re- determined candidate hospital [Gounares at Para. 0004 (see Claim 1 for explanation)].
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis do not teach [ … ] … when the fitness of the optimal transfer hospital is lower than the predetermined value;
TANAKA teaches […] … when the fitness of the optimal transfer hospital is lower than a predetermined value [TANAKA at Page 7 Para. 8-9 teaches as a result of the foregoing, the evaluation of hospital A is 15 points as shown by evaluation formula 1600 in FIG. 11, and the evaluation of hospital D is 17 points as shown by evaluation formula 1700. As a result, the first hospital candidate that issues an emergency patient acceptance instruction is D hospital with the highest acquisition points, and second hospital A. This result is registered in the designated hospital list table 128 as shown in FIG. In the example described above, the evaluation value of Hospital A is 15 points and Hospital D is 17 points. However, if the evaluation value calculated by the evaluation formula is 10 points or less, such a hospital is used for emergency patients. The designated hospital that is most suitable for the emergency patient is calculated such that the designated hospital is not included as an unfavorable hospital(interpreted to correspond with expanded search of MARUYAMA, evaluations interpreted to be given better priority above a threshold and considered more suitable)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA, PEETERS, Gounares, Simoudis with the predetermined value of TANAKA with the motivation to pick the most qualified hospital for the patient.
Regarding Claim 24
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis teach the method of claim 22,
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis teach further comprising:
(1) re-determining candidate hospitals by expanding the search radius [MARUYAMA at Page 3 Para. 9 (see Claim 23 for explanation)] … [ … ]
(2) calculating a fitness of each re-determined candidate hospital [Gounares at Para. 0004 (see Claim 1 for explanation)];
(3) re-determining an optimal transfer hospital based on the fitness of each re- determined candidate hospital [Gounares at Para. 0004 (see Claim 1 for explanation)]; and
(4) continuously repeating steps (1) to (3) until the re-determined fitness of the optimal transfer hospital becomes greater than or equal to the predetermined value [MARUYAMA at Page 5 Para. 7 teaches When the minimum value is equal to or smaller than a predetermined value, the hospital related to the minimum value is selected as an accepting hospital, information on the hospital is transmitted to the terminal, and the minimum value is larger than the predetermined value; MARUYAMA at Page 3 Para. 9 (interpreted as repeating steps until a hospital meets a predetermined value)].
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis do not teach [ … ] … when the re-determined fitness of the optimal transfer hospital is lower than the predetermined value;
TANAKA teaches […] … when the re-determined fitness of the optimal transfer hospital is lower than a predetermined value [TANAKA at Page 7 Para. 8-9 teaches as a result of the foregoing, the evaluation of hospital A is 15 points as shown by evaluation formula 1600 in FIG. 11, and the evaluation of hospital D is 17 points as shown by evaluation formula 1700. As a result, the first hospital candidate that issues an emergency patient acceptance instruction is D hospital with the highest acquisition points, and second hospital A. This result is registered in the designated hospital list table 128 as shown in FIG. In the example described above, the evaluation value of Hospital A is 15 points and Hospital D is 17 points. However, if the evaluation value calculated by the evaluation formula is 10 points or less, such a hospital is used for emergency patients. The designated hospital that is most suitable for the emergency patient is calculated such that the designated hospital is not included as an unfavorable hospital(interpreted to correspond with expanded search of MARUYAMA, evaluations interpreted to be given better priority above a threshold and considered more suitable)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA, PEETERS, Gounares, Simoudis with the predetermined value of TANAKA with the motivation to pick the most qualified hospital for the patient.
Claims 25 rejected under 35 U.S.C. 103(a) as being unpatentable over AOKI, BAE, KIM, MARUYAMA, PEETERS, Gounares, Simoudis as applied to claim 21 above, and further in view of Groden et al (US Publication 20180217599).
Regarding Claim 25
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis teach the method of claim 21,
AOKI/BAE/KIM/MARUYAMA/PEETERS/Gounares/Simoudis do not teach further comprising:
determining whether to utilize an air ambulance to transport the emergency patient based on at least one of location information of the optimal transfer hospital, real-time traffic information, and air ambulance operation information,
and determining an optimal handover point based on at least one of the location information of the optimal transfer hospital, the real-time traffic information, and the air ambulance operation information when the air ambulance is utilized to transport the emergency patient.
Groden teaches determining whether to utilize an air ambulance to transport the emergency patient based on at least one of location information of the determined optimal transfer hospital, real-time traffic information, and air ambulance operation information [Groden at Para. 0018 teaches feasibility parameters can additionally or alternatively include route-related parameters (e.g., travel time, fuel and/or battery charge requirements, other aircraft performance factors, airspace-related parameters, traffic-related parameters, etc.), patient condition-related parameters (e.g.; required, estimated, and/or ideal response time to reach a patient],
and determining an optimal handover point based on at least one of the location information of the optimal transfer hospital, the real-time traffic information, and the air ambulance operation information when the air ambulance is utilized to transport the emergency patient [Groden at Para. 0026 teaches in a first variation, the closest aircraft (e.g., of the set of aircraft with appropriate resources to perform the mission) is selected. In this variation, aircraft distance can be determined based on geographical distance to the first waypoint (e.g., pickup location), estimated response time (e.g., response time to the first waypoint, response time to a subsequent time-sensitive waypoint, etc.), and/or any other suitable metric].
It would be prima facie obvious to one skilled in the art of optimal transport to modify the references of AOKI, BAE, KIM, MARUYAMA, PEETERS, Gounares, Simoudis with the air ambulance of Groden with the motivation to get the patient to a candidate hospital in the most optimal way.
Claims 26-27 is/are rejected under 35 U.S.C. 103(a) as being unpatentable over AOKI et al (Foreign Publication WO-2012098613-A1) in view of Gounares et al (US Publication No. 20090198733) in view of Kim et al (US Publication No. 20180322961) in view of BAE et al (Foreign Publication KR-20060037684-A) in view of PEETERS et al (US Publication No. 20160157739) in view of MARUYAMA et al (Foreign Publication JP-2011048775-A) in view of Simoudis et al (US Publication No. 20200363220).
Regarding Claim 26
AOKI teaches a server for determining an optimal transfer hospital, the server comprising:
a control unit which determines candidate hospitals according to a search radius [AOKI at Page 10 Para 8 (see Claim 21 for explanation)],
determines a severity of the emergency patient based on the status information [AOKI at Page 10 Para 7 (see Claim 21 for explanation)],
first data of the severity of the emergency patient acquired from the ambulance device based on the status information, the first data received only during transport of the emergency patient [AOKI at Page 16 Para 3 (see Claim 21 for explanation)],
and wherein the emergency Al server is further configured to:
determine an order of suitability among the candidate hospitals based on the fitness of the optimal transfer hospital compared with a predetermined value [AOKI at Page 10 Para 8 (see Claim 21 for explanation)];
select one hospital having a highest suitability among the candidate hospitals as the optimal transfer hospital [AOKI at Page 14 Para 7 (see Claim 21 for explanation)]l;
transmit, to the ambulance device, information on the order of suitability among the candidate hospitals and the selected one hospital [AOKI at Page 4 Para 5 (see Claim 21 for explanation)];
transmit, to the selected one hospital, weight information of the emergency patient together with an inquiry as to whether the selected one hospital can accept the emergency patient [AOKI at Page 14 Para 4-5 (see Claim 21 for explanation)];
receive, from the selected one hospital, a response to the inquiry, the selected one hospital determining whether to accept the emergency patient based on the weight information of the emergency patient and a number of emergency patients accepted during the transport of the emergency patient, the selected one hospital further transmitting the response to the ambulance device [AOKI at Page 6 Para 9, Page 14 Para 5 (see Claim 21 for explanation)];
and update the weight information of the emergency patient and information about the number of accepted emergency patients and the order of suitability among the candidate hospitals in real-time [AOKI at Page 10 Para 8 (see Claim 21 for explanation)].
AOKI does not teach an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server and is configured to receive status information about an emergency patient being transported in an ambulance device including a camera capable of audiovisual recording for automatically creating an emergency activity log, the camera being automatically operated to record the voice of the emergency patient and to photograph the emergency patient in order to generate the status information about the emergency patient during transport, the status information generated by the camera being stored in a storage device provided in the ambulance device;
acquires emergency event possibility information from the emergency medical server,
calculates a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and transport resource availability information acquired from the emergency medical server, and determines an optimal transfer hospital based on the fitness of each candidate hospital;
and a storage unit which stores the status information about the emergency patient, the emergency event possibility information, and the transport resource availability information,
wherein the status information is acquired in the ambulance device according to the emergency activity log by recognizing syllables of words spoken by a paramedic of the ambulance device and by recognizing photographed images of the emergency patient,
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server,
wherein the emergency Al server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient, and
third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server,
Gounares teaches emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server and is configured to [Gounares at Para. 0054 teaches one possible communication between a client 910 and a server 920 can be in the form of a data packet adapted to be transmitted between two or more computer processes. The system 900 includes a communication framework 940 that can be employed to facilitate communications between the client(s) 910 and the server(s) 920. The client(s) 910 are operably connected to one or more client data store(s) 950 that can be employed to store information local to the client(s) 910. Similarly, the server(s) 920 are operably connected to one or more server data store(s) 930 that can be employed to store information local to the servers 920]… [ … ]
calculates a fitness of each candidate hospital based on the severity of the emergency patient, the emergency event possibility information, and transport resource availability information acquired from the emergency medical server, and determines an optimal transfer hospital based on the fitness of each candidate hospital [Gounares at Para. 0004 (see Claim 21 for explanation)];
and a storage unit which stores the status information about the emergency patient, the emergency event possibility information, and the transport resource availability information [Gounares at Para. 0022 (interpreted to combine with emergency event possibility information of PEETERS; see Claim 21 for explanation)],
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital [Gounares at Para. 0037 (see Claim 21 for explanation)],
wherein the emergency Al … [ …] … to calculate the fitness of each candidate hospital during transport of the emergency patient [Gounares at Para. 0004 (see Claim 21 for explanation)], includes a cloud server, and [ … ] … continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including [Gounares at Para. 0022 (see Claim 21 for explanation)]
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the emergency patient [Gounares at Para. 0022 (see Claim 21 for explanation)], and
third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server [Gounares at Para. 0037 (see Claim 21 for explanation)],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine patient severity of AOKI with the transport resource availability of GOUNARES with the motivation to provide increased efficiency, decrease errors and costs, and more importantly save lives.
AOKI/GOUNARES do not teach [ … ] … and is configured to receive status information about an emergency patient being transported in an ambulance device including a camera capable of audiovisual recording for automatically creating an emergency activity log, the camera being automatically operated to record the voice of the emergency patient and to photograph the emergency patient in order to generate the status information about the emergency patient during transport, the status information generated by the camera being stored in a storage device provided in the ambulance device;
acquires emergency event possibility information from the emergency medical server,
wherein the status information is acquired in the ambulance device according to the emergency activity log by recognizing syllables of words spoken by a paramedic of the ambulance device and by recognizing photographed images of the emergency patient,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server,
[ … ] … configured to perform machine learning to … [ … ] …, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by … [ … ]
KIM teaches and is configured to receive status information about an emergency patient [KIM at Para 0042 (see Claim 21 for explanation)] … [ … ] … for automatically creating an emergency activity log, the camera being automatically operated to record the voice of the emergency patient and to photograph the emergency patient in order to generate the status information about the emergency patient during transport, the status information generated by the camera being stored in a storage device provided in the ambulance device [KIM at Para 0042 (see Claim 21 for explanation)];
wherein the status information is acquired in the ambulance device according to the emergency activity log by recognizing syllables of words spoken by a paramedic of the ambulance device and by recognizing photographed images of the emergency patient [KIM at Para 0067, 0153 (see Claim 21 for explanation)],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, GOUNARES with the speech recognition of KIM with the motivation to improve the performance of a medical condition diagnosis system.
AOKI/GOUNARES/KIM do not teach [ … ] … being transported in an ambulance device including a camera capable of audiovisual recording … [ … ]
acquires emergency event possibility information from the emergency medical server,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server,
[ … ] … configured to perform machine learning to … [ … ] …, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by … [ … ]
BAE teaches [ … ] … being transported in an ambulance device including a camera capable of audiovisual recording [BAE at Page 2 Para 1 (see Claim 21 for explanation)]… [ … ]
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, GOUNARES with the camera of BAE with the motivation to improve monitoring of a patient in an ambulance car.
AOKI/GOUNARES/KIM/BAE do not teach acquires emergency event possibility information from the emergency medical server,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server,
[ … ] … configured to perform machine learning to … [ … ] …, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by … [ … ]
PEETERS teaches acquires emergency event possibility information from the emergency medical server [PEETERS at Para. 0033 (see Claim 21 for explanation)],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, GOUNARES, KIM, BAE with the emergency event possibilitysimoudis of PEETERS with the motivation to better understand the patient’s condition to better match to a candidate hospital.
AOKI/GOUNARES/KIM/BAE/PEETERS do not teach wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server,
[ … ] … configured to perform machine learning to … [ … ] …, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by … [ … ]
MARUYAMA teaches wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency Al server [MARUYAMA at Page 3 Para 1 (see Claim 21 for explanation)],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, GOUNARES, KIM, BAE, PEETERS with the servers of MARUYAMA with the motivation to pick the most qualified hospital for the patient.
AOKI/GOUNARES/KIM/BAE/PEETERS/MARUYAMA do not teach [ … ] … configured to perform machine learning to … [ … ] …, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by … [ … ]
Simoudis teaches [ … ] … configured to perform machine learning to [Simoudis at Para. 0056 (see Claim 21 for explanation)]… [ … ] …, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by [Simoudis at Para. 0058 (see Claim 21 for explanation)]… [ … ]
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, GOUNARES, KIM, BAE, PEETERS, MARUYAMA with the machine learning models of Simoudis with the motivation to improve local transportation.
Regarding Claim 27
Claim(s) 27 is/are analogous to Claim(s) 22, thus Claim(s) 27 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 22.
Claims 28-29 rejected under 35 U.S.C. 103(a) as being unpatentable over AOKI, GOUNARES, KIM, BAE, PEETERS, MARUYAMA, Simoudis as applied to claim 26 above, and further in view of TANAKA et al (Foreign Publication JP-2005071092-A).
Regarding Claim 28
Claim(s) 28 is/are analogous to Claim(s) 23, thus Claim(s) 28 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 23.
Regarding Claim 29
Claim(s) 29 is/are analogous to Claim(s) 24, thus Claim(s) 29 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 24.
Claims 30,32-33,35 is/are rejected under 35 U.S.C. 103(a) as being unpatentable over AOKI et al (Foreign Publication WO-2012098613-A1) in view of BAE et al (Foreign Publication KR-20060037684-A) in view of Kim et al (US Publication No. 20180322961) in view of MARUYAMA et al (Foreign Publication JP-2011048775-A) in view of PEETERS et al (US Publication No. 20160157739) in view of Gounares et al (US Publication No. 20090198733) in view of ITOU et al (US Publication No. 20190125287) in view of Simoudis et al (US Publication No. 20200363220).
Regarding Claim 30
AOKI teaches a method for determining a hospital to which each of a plurality of emergency patients is transported, the method comprising:
determining candidate hospitals [AOKI at Page 10 Para 8 (see Claim 21 for explanation)];
determining, in the emergency Al server, a severity of the specific emergency patient based on the status information [AOKI at Page 10 Para 7 (see Claim 21 for explanation)],
acquiring, in the emergency AI server, transport resource availability information about the candidate hospitals, the transport resource availability information acquired from the emergency medical server [AOKI at Page 10 Para 8 (see Claim 21 for explanation)], and
and transmitting, from the emergency AI server to the optimal transfer hospital, the weight information together with an inquiry about whether to accept the emergency patient [AOKI at Page 14 Para 4-5 (see Claim 21 for explanation)],
wherein the distance-based hospital modeling is configured to calculate the weight for each candidate hospital based on transport distance information using [AOKI at Page 10 Para 8 (see Claim 21 for explanation)] … [ … ]
first data of the severity of the specific emergency patient acquired from the ambulance device based on the status information, the first data received only during transport of the specific emergency patient [AOKI at Page 16 Para 3 (see Claim 21 for explanation)],
and wherein the emergency AI server is further configured to:
determine an order of suitability among the candidate hospitals based on the fitness of the optimal transfer hospital compared with a predetermined value [AOKI at Page 10 Para 8 (see Claim 21 for explanation)];
select one hospital having a highest suitability among the candidate hospitals as the optimal transfer hospital [AOKI at Page 14 Para 7 (see Claim 21 for explanation)];
transmit, to the ambulance device, information on the order of suitability among the candidate hospitals and the selected one hospital [AOKI at Page 4 Para 5 (see Claim 21 for explanation)] ;
transmit, to the selected one hospital, the weight information of each of the plurality of emergency patients together with an inquiry as to whether the selected one hospital can accept an emergency patient of the plurality of emergency patients [AOKI at Page 14 Para 4-5 (see Claim 21 for explanation)];
receive, from the selected one hospital, a response to the inquiry, the selected one hospital determining whether to accept the emergency patient based on the weight information of the plurality of emergency patients and a number of emergency patients accepted during the transport of the specific emergency patient, the selected one hospital further transmitting the response to the ambulance device [AOKI at Page 6 Para 9, Page 14 Para 5 (see Claim 21 for explanation)];
and update the weight information of the plurality of emergency patients and information about the number of accepted emergency patients and the order of suitability among the candidate hospitals in real-time [AOKI at Page 10 Para 8 (see Claim 21 for explanation)].
AOKI does not teach acquiring status information about a specific emergency patient among the plurality of emergency patients, the specific emergency patient being transported in an ambulance device including a camera capable of audiovisual recording;
automatically operating the camera to record the voice of the specific emergency patient and to photograph the specific emergency patient in order to generate the status information, the status information generated by the camera being stored in a storage device provided in the ambulance device;
transmitting the status information from the ambulance device to an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server;
generating, in the emergency Al server, weight information about each candidate hospital of each of the plurality of emergency patients;
determining, in the emergency Al server, an optimal transfer hospital of each of the plurality of emergency patients by
calculating, in the emergency medical server, emergency event possibility information based on the status information,
calculating, in the emergency AI server, a fitness of each candidate hospital based on the severity of the specific emergency patient, the emergency event possibility information, and the transport resource availability information;
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the weight information is generated by calculating a weight for each candidate hospital of each emergency patient according to transport distance-based hospital modeling and patient information-based hospital modeling,
[ … ] using hospital and lesion factor information, the hospital and lesion factor information including a hospital index indicating each candidate hospital and a lesion index indicating a lesion of each emergency patient,
wherein the patient information-based hospital modeling is configured to calculate the weight for each candidate hospital based on
patient information that includes the lesion index and
candidate hospital information that includes the hospital index and at least one of cardiac arrest hospitalization survival rate, major trauma, STEMI acceptance rate and stroke acceptance rate, and whether to be hospitalized in an intensive care unit,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency AI server,
wherein the emergency AI server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the specific emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the specific emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the specific emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server,
BAE teaches acquiring status information about a specific emergency patient among the plurality of emergency patients, the specific emergency patient being transported in an ambulance device including a camera capable of audiovisual recording [BAE at Page 2 Para 1 (see Claim 21 for explanation)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine patient severity of AOKI with the camera of BAE with the motivation to improve monitoring of a patient in an ambulance car.
AOKI/BAE do not teach automatically operating the camera to record the voice of the specific emergency patient and to photograph the specific emergency patient in order to generate the status information, the status information generated by the camera being stored in a storage device provided in the ambulance device;
transmitting the status information from the ambulance device to an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server;
generating, in the emergency Al server, weight information about each candidate hospital of each of the plurality of emergency patients;
determining, in the emergency Al server, an optimal transfer hospital of each of the plurality of emergency patients by
calculating, in the emergency medical server, emergency event possibility information based on the status information,
calculating, in the emergency AI server, a fitness of each candidate hospital based on the severity of the specific emergency patient, the emergency event possibility information, and the transport resource availability information;
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the weight information is generated by calculating a weight for each candidate hospital of each emergency patient according to transport distance-based hospital modeling and patient information-based hospital modeling,
[ … ] using hospital and lesion factor information, the hospital and lesion factor information including a hospital index indicating each candidate hospital and a lesion index indicating a lesion of each emergency patient,
wherein the patient information-based hospital modeling is configured to calculate the weight for each candidate hospital based on
patient information that includes the lesion index and
candidate hospital information that includes the hospital index and at least one of cardiac arrest hospitalization survival rate, major trauma, STEMI acceptance rate and stroke acceptance rate, and whether to be hospitalized in an intensive care unit,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency AI server,
wherein the emergency AI server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the specific emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the specific emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the specific emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server,
KIM teaches automatically operating the camera to record the voice of the specific emergency patient and to photograph the specific emergency patient in order to generate the status information, the status information generated by the camera being stored in a storage device provided in the ambulance device [KIM at Para. 0042 (see Claim 21 for explanation)];
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE with the speech recognition of KIM with the motivation to improve the performance of a medical condition diagnosis system.
AOKI/BAE/KIM do not teach transmitting the status information from the ambulance device to an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server;
generating, in the emergency Al server, weight information about each candidate hospital of each of the plurality of emergency patients;
determining, in the emergency Al server, an optimal transfer hospital of each of the plurality of emergency patients by
calculating, in the emergency medical server, emergency event possibility information based on the status information,
calculating, in the emergency AI server, a fitness of each candidate hospital based on the severity of the specific emergency patient, the emergency event possibility information, and the transport resource availability information;
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the weight information is generated by calculating a weight for each candidate hospital of each emergency patient according to transport distance-based hospital modeling and patient information-based hospital modeling,
[ … ] using hospital and lesion factor information, the hospital and lesion factor information including a hospital index indicating each candidate hospital and a lesion index indicating a lesion of each emergency patient,
wherein the patient information-based hospital modeling is configured to calculate the weight for each candidate hospital based on
patient information that includes the lesion index and
candidate hospital information that includes the hospital index and at least one of cardiac arrest hospitalization survival rate, major trauma, STEMI acceptance rate and stroke acceptance rate, and whether to be hospitalized in an intensive care unit,
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency AI server,
wherein the emergency AI server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the specific emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the specific emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
first data of the severity of the specific emergency patient acquired from the ambulance device based on the status information, the first data received only during transport of the specific emergency patient,
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the specific emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server,
MARUYAMA teaches transmitting the status information from the ambulance device to an emergency artificial intelligence (AI) server that communicates with an emergency medical server provided separately from the emergency Al server [MARUYAMA at Page 3 Para 5 (see Claim 21 for explanation)];
wherein the emergency medical server includes a local server and stores the transport resource availability information and real-time resource information related to the candidate hospitals and the search radius, the local server including a nationally based server providing information related to an emergency medical service to the ambulance device, the information stored in the emergency medical server being provided to the ambulance device and the emergency AI server [MARUYAMA at Page 3 Para 1 (see Claim 21 for explanation)],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM with the servers of MARUYAMA with the motivation to pick the most qualified hospital for the patient.
AOKI/BAE/KIM/MARUYAMA do not teach generating, in the emergency Al server, weight information about each candidate hospital of each of the plurality of emergency patients;
determining, in the emergency Al server, an optimal transfer hospital of each of the plurality of emergency patients by
calculating, in the emergency medical server, emergency event possibility information based on the status information,
calculating, in the emergency AI server, a fitness of each candidate hospital based on the severity of the specific emergency patient, the emergency event possibility information, and the transport resource availability information;
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital,
wherein the weight information is generated by calculating a weight for each candidate hospital of each emergency patient according to transport distance-based hospital modeling and patient information-based hospital modeling,
[ … ] using hospital and lesion factor information, the hospital and lesion factor information including a hospital index indicating each candidate hospital and a lesion index indicating a lesion of each emergency patient,
wherein the patient information-based hospital modeling is configured to calculate the weight for each candidate hospital based on
patient information that includes the lesion index and
candidate hospital information that includes the hospital index and at least one of cardiac arrest hospitalization survival rate, major trauma, STEMI acceptance rate and stroke acceptance rate, and whether to be hospitalized in an intensive care unit,
wherein the emergency AI server is configured to perform machine learning to calculate the fitness of each candidate hospital during transport of the specific emergency patient, includes a cloud server, and stores a plurality of machine learning models that are continuously updated, the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the specific emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including
first data of the severity of the specific emergency patient acquired from the ambulance device based on the status information, the first data received only during transport of the specific emergency patient,
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the specific emergency patient,
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server,
Gounares teaches generating, in the emergency Al server, weight information about each candidate hospital of each of the plurality of emergency patients[Gounares at Para. 0004 (see Claim 21 for explanation)];
determining, in the emergency Al server, an optimal transfer hospital of each of the plurality of emergency patients [Gounares at Para. 0004 (see Claim 1 for explanation)] by
calculating, in the emergency AI server, a fitness of each candidate hospital based on the severity of the specific emergency patient, the emergency event possibility information, and the transport resource availability information [Gounares at Para. 0004 (see Claim 21 for explanation)];
wherein the transport resource availability information includes location information of each candidate hospital and further includes real-time traffic information and current position information of the ambulance device with respect to the real-time traffic information and the location information of each candidate hospital [Gounares at Para. 0037 (see Claim 21 for explanation)],
wherein the weight information is generated by calculating a weight for each candidate hospital of each emergency patient according to transport distance-based hospital modeling and patient information-based hospital modeling [Gounares at Para. 0021 teaches in general, the match component 102 can consider data related to the patient (e.g., patient data such as patient location, status, urgency, insurance coverage, patient preference, patient authorized medical data, etc.), information related to potential or available medical facilities (e.g., medical facility data such as, travel distance, routes from the patient location to the medical facility location, staffing, available resources, etc.) as well as data related to traffic (e.g., traffic data such as traffic predictions, traffic flow, emergency vehicle patterns, etc.)],
[ … ] … calculate the fitness of each candidate hospital during transport of the specific emergency patient [Gounares at Para. 0035 (see Claim 21 for explanation)], … [ … ] … the machine learning performed in the plurality of machine learning models by continuously inputting data acquired from the emergency medical server and the ambulance device throughout the transport of the specific emergency patient, the data being input to an optimal hospital selection model of the plurality of machine learning models and including [Gounares at Para. 0035 (see Claim 21 for explanation)]
second data of the emergency event possibility information acquired from the ambulance device based on the status information, the second data received only during the transport of the specific emergency patient [Gounares at Para. 0022 (see Claim 21 for explanation)],
and third data of the transport resource availability information acquired from the emergency medical server based on the location information of each candidate hospital, the real-time traffic information, and the current position information of the ambulance device with respect to the real-time traffic information, the third data received only from the emergency medical server [Gounares at Para. 0037 (see Claim 21 for explanation)],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA, PEETERS with the fitness calculation of Gounares with the motivation to provide increased efficiency, decrease errors and costs, and more importantly save lives.
AOKI/BAE/KIM/MARUYAMA/Gounares do not teach calculating, in the emergency medical server, emergency event possibility information based on the status information,
[ … ] using hospital and lesion factor information, the hospital and lesion factor information including a hospital index indicating each candidate hospital and a lesion index indicating a lesion of each emergency patient,
wherein the patient information-based hospital modeling is configured to calculate the weight for each candidate hospital based on
patient information that includes the lesion index and
candidate hospital information that includes the hospital index and at least one of cardiac arrest hospitalization survival rate, major trauma, STEMI acceptance rate and stroke acceptance rate, and whether to be hospitalized in an intensive care unit,
perform machine learning to … [ … ] …, and stores a plurality of machine learning models that are continuously updated, … [ … ]
PEETERS teaches calculating, in the emergency medical server, emergency event possibility information based on the status information [PEETERS at Para. 0033 (see Claim 21 for explanation)],
candidate hospital information that includes the hospital index and at least one of cardiac arrest hospitalization survival rate, major trauma, STEMI acceptance rate and stroke acceptance rate, and whether to be hospitalized in an intensive care unit [PEETERS at Para. 0033 (see Claim 21 for explanation)],
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA, Gounares with the emergency event possibility of PEETERS with the motivation to better understand the patient’s condition to better match to a candidate hospital.
AOKI/BAE/KIM/MARUYAMA/Gounares/PEETERS do not teach [ … ] using hospital and lesion factor information, the hospital and lesion factor information including a hospital index indicating each candidate hospital and a lesion index indicating a lesion of each emergency patient,
wherein the patient information-based hospital modeling is configured to calculate the weight for each candidate hospital based on
patient information that includes the lesion index and
wherein the emergency AI server is configured to perform machine learning to … [ … ] …, and stores a plurality of machine learning models that are continuously updated, … [ … ]
ITOU teaches [ … ] using hospital and lesion factor information, the hospital and lesion factor information including a hospital index indicating each candidate hospital and a lesion index indicating a lesion of each emergency patient [ITOU at Para. 0087 teaches to identify the lesions of the biological lumens, in accordance with an exemplary embodiment patient information is acquired. The patient information can include electromagnetic wave information, medical record information, other nonclinical periodical information, big data, etc., of patients' lesions],
wherein the patient information-based hospital modeling is configured to calculate the weight for each candidate hospital based on patient information that includes the lesion index [ITOU at Para. 0051 teaches FIG. 9 is a conceptual illustration of the diagnostic method according to the embodiment performing image information based on a convolutional neural network (CNN) and diagnosing a lesion to be treated first by deep-learning using information from a lesion of a patient including extracted the lesion curvature information]
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA, Gounares, PEETERS with the lesion data of ITOU with the motivation to improving the diagnostic accuracy of lesions.
AOKI/BAE/KIM/MARUYAMA/Gounares/PEETERS/ITOU do not teach wherein the emergency AI server is configured to perform machine learning to … [ … ] …, and stores a plurality of machine learning models that are continuously updated, … [ … ]
Simoudis teaches wherein the emergency AI server is configured to perform machine learning to [Simoudis at Para. 0056 (see Claim 21 for explanation)]… [ … ] …, and stores a plurality of machine learning models that are continuously updated [Simoudis at Para. 0058, 0070 (see Claim 21 for explanation)], … [ … ]
It would have been prima facie obvious skill in the art, at the time of effective filing, to combine the references of AOKI, BAE, KIM, MARUYAMA, Gounares, PEETERS, ITOU with the machine learning models of Simoudis with the motivation to improve local transportation.
Regarding Claim 32
AOKI/BAE/KIM/MARUYAMA/Gounares/PEETERS/ITOU/Simoudis teach the method of claim 30,
AOKI/BAE/KIM/MARUYAMA/Gounares/PEETERS/ITOU/Simoudis further teach wherein, if the optimal transfer hospital does not accept the specific emergency patient, the method further comprises:
updating the status information about the specific emergency patient and each candidate hospital in real-time [Gounares at Para. 0035 (see Claim 21 for explanation)];
and re-generating the weight information after the updating [Gounares at Para. 0004 (see Claim 1 for explanation)].
Regarding Claim 33
AOKI/BAE/KIM/MARUYAMA/Gounares/PEETERS/ITOU/Simoudis teach the method of claim 30,
AOKI/BAE/KIM/MARUYAMA/Gounares/PEETERS/ITOU/Simoudis further teach further comprising:
determining the optimal transfer hospital for each emergency patient [Gounares at Para. 0004 (see Claim 1 for explanation)];
and generating weight information about the optimal transfer hospital [Gounares at Para. 0004 (see Claim 1 for explanation)].
Regarding Claim 35
Claim(s) 16-20 is/are analogous to Claim(s) 1-XX, thus Claim(s) 16-20 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 1-XX.
Claims 36-37 rejected under 35 U.S.C. 103(a) as being unpatentable over AOKI, BAE, KIM , MARUYAMA, Gounares, PEETERS, ITOU, Simoudis as applied to claim 30 above, and further in view of TANAKA et al (Foreign Publication JP-2005071092-A).
Regarding Claim 36
Claim(s) 16-20 is/are analogous to Claim(s) 1-XX, thus Claim(s) 16-20 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 1-XX.
Regarding Claim 37
Claim(s) 37 is/are analogous to Claim(s) 24, thus Claim(s) 37 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 24.
Claim 38 rejected under 35 U.S.C. 103(a) as being unpatentable over AOKI, BAE, KIM , MARUYAMA, Gounares, PEETERS, ITOU, Simoudis as applied to claim 30 above, and further in view of Groden et al (US Publication 20180217599).
Regarding Claim 38
Claim(s) 38 is/are analogous to Claim(s) 25, thus Claim(s) 38 is/are similarly analyzed and rejected in a manner consistent with the rejection of Claim(s) 25.
Response to Arguments
Rejection under 35 U.S.C. § 101
Regarding the rejection of Claims 21-30,32-33,35-38, the Examiner has considered the Applicant’s arguments; however, the arguments are not persuasive. Any arguments inadvertently not addressed are unpersuasive for at least the following reasons. Applicant argues:
Applicant wishes to clarify an earlier argument regarding a solution to the technical problem. Essentially, the solution is adopting the configuration of FIG. 1, by which a contemporary configuration - namely, an ambulance device 1000 communicating with a contemporary server (server 2000) - is reimagined. In other words, the configuration of the device 1000 communicating with server 2000 is being improved upon.
The improvement is linked to specific claim text, to include limitations respectively describing the makeup of the emergency medical server 2000 (see pub. paras. 0052- 0053) and emergency AI server 3000 (see pub. para. 0066), and particularly the function of the server 3000 (see pub. paras. 0007, 0075, 0159-0161). Support for the recited data that is continuously input to the optimal hospital selection model can be found at pub. paras. 0058, 0148 (first data), pub. paras. 0049, 0149 (second data), and pub. paras. 0071-0072 (third data).
Applicant therefore argues that Recentive does not apply in the instant application. That is, Applicant argues that the independent claims as amended do describe how the improvement is accomplished and do delineate steps to achieve the improvement. Furthermore, Applicant argues that this improvement is achieved through specific steps relative to the server 3000. For example, through the utilization of the configuration of FIG. 1, the claim description of the emergency AI server 3000 specifies where the inputs are coming from and when the inputs are acquired and further specifies functions of the server 3000 executed with respect to a hospital selected as the optimal transfer hospital.
Regarding (a), the Examiner respectfully disagrees. Initially, the claims do not recite a contemporary server. The Examiner assumes that Applicant is referring to the emergency medical server. In any event, there is no improvement present within the meaning of MPEP 2106.04(d)(1). An ambulance device communicating with an external server is in no way an improvement.
Regarding (b), the Examiner respectfully disagrees. The servers are not performing actions outside of their normal function. Therefore, the servers do not provide a practical application and significantly more. See response to arguments (a).
Regarding (c), the Examiner respectfully disagrees. Recentive is directly on point with regard to the training and use of AI aspects of the claim. The source of data inputs as well as when to transmit them equate to mere data gathering and transmission, which cannot recite a practical application and significantly more. Recentive is pertinent because the claims include the additional elements of AI (machine learning) models that are trained using specific data and are then used in the claim. As with Recentive, there is no indication that the training or use of AI is improved upon in any way; the mere application of specific data to an AI model to train it and then use of the trained AI model is not an improvement.
Rejection under 35 U.S.C. § 102/103
Regarding the rejection of Claims 21-30,32-33,35-38, the Examiner has considered the Applicant’s arguments; however, these arguments are moot given the new grounds of afforded by the present RCE.
Conclusion
The prior art made of record and not relied upon in the present basis of rejection are noted in the attached PTO 892 and include:
KAWABATA et al (Foreign Publication JP-2019096003-A) discloses device and program capable of selecting a medical institution of a transportation destination when transporting a sick and injured person in an emergency.
LA PARKA et al (Foreign Publication CN-108784655-A) discloses method for rapid evaluation of a medical patient.
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JONATHAN C EDOUARD whose telephone number is (571)270-0107. The examiner can normally be reached M-F 730 - 430.
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, Robert Morgan can be reached on (571) 272 - 6773. 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.
/JONATHAN C EDOUARD/Examiner, Art Unit 3683
/JASON S TIEDEMAN/Primary Examiner, Art Unit 3683
Prosecution Insights