[go: up one dir, main page]

CN119854593B - Remote diagnosis system - Google Patents

Remote diagnosis system

Info

Publication number
CN119854593B
CN119854593B CN202411993748.6A CN202411993748A CN119854593B CN 119854593 B CN119854593 B CN 119854593B CN 202411993748 A CN202411993748 A CN 202411993748A CN 119854593 B CN119854593 B CN 119854593B
Authority
CN
China
Prior art keywords
code rate
target code
rate vector
vector
video
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202411993748.6A
Other languages
Chinese (zh)
Other versions
CN119854593A (en
Inventor
苏同金
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Zhongke Yunying Technology Co ltd
Original Assignee
Beijing Zhongke Yunying Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Beijing Zhongke Yunying Technology Co ltd filed Critical Beijing Zhongke Yunying Technology Co ltd
Priority to CN202411993748.6A priority Critical patent/CN119854593B/en
Publication of CN119854593A publication Critical patent/CN119854593A/en
Application granted granted Critical
Publication of CN119854593B publication Critical patent/CN119854593B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/60—Network structure or processes for video distribution between server and client or between remote clients; Control signalling between clients, server and network components; Transmission of management data between server and client, e.g. sending from server to client commands for recording incoming content stream; Communication details between server and client 
    • H04N21/63—Control signaling related to video distribution between client, server and network components; Network processes for video distribution between server and clients or between remote clients, e.g. transmitting basic layer and enhancement layers over different transmission paths, setting up a peer-to-peer communication via Internet between remote STB's; Communication protocols; Addressing
    • H04N21/647—Control signaling between network components and server or clients; Network processes for video distribution between server and clients, e.g. controlling the quality of the video stream, by dropping packets, protecting content from unauthorised alteration within the network, monitoring of network load, bridging between two different networks, e.g. between IP and wireless
    • H04N21/64784—Data processing by the network
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
    • G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
    • G16H40/67—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices for remote operation
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H80/00—ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/47—End-user applications
    • H04N21/478—Supplemental services, e.g. displaying phone caller identification, shopping application
    • H04N21/4788—Supplemental services, e.g. displaying phone caller identification, shopping application communicating with other users, e.g. chatting

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Medical Informatics (AREA)
  • Biomedical Technology (AREA)
  • Public Health (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Pathology (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Business, Economics & Management (AREA)
  • General Business, Economics & Management (AREA)
  • General Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Computer Security & Cryptography (AREA)
  • Medical Treatment And Welfare Office Work (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The invention discloses a remote diagnosis system, which belongs to the technical field of remote diagnosis, and is characterized in that a pre-deployed intelligent optimization algorithm is adopted to carry out code rate self-adaptive adjustment on a video to be diagnosed of a patient, so that a transmission code rate corresponding to the video to be diagnosed is obtained, the video to be diagnosed is transmitted to a doctor remote session terminal according to the transmission code rate, the data transmission rate can be dynamically adjusted according to the use condition of an integral network, the real-time performance and accuracy of remote diagnosis are ensured, and the remote diagnosis system is suitable for a plurality of fields such as medical treatment, education, enterprises and the like.

Description

Remote diagnosis system
Technical Field
The invention belongs to the technical field of remote diagnosis, and particularly relates to a remote diagnosis system.
Background
Remote diagnosis refers to a medical service mode in which medical information of a patient is transmitted to a remote expert or medical institution through a communication network, and diagnosis comments are provided to the patient by the expert or medical institution. The method breaks through geographic limitation, so that medical resources can be distributed more reasonably, and particularly remote diagnosis is important in areas with insufficient medical resources. In the remote diagnosis process, a video to be diagnosed of a patient is often acquired, then the video to be diagnosed is transmitted to a doctor, and then the doctor analyzes and replies the video to be diagnosed, so that a better diagnosis can be made on the condition of the patient. In the prior art, the video to be diagnosed is often transmitted by setting a fixed code rate, so that the overall network utilization efficiency is low, the condition of network blocking in a peak period occurs, and the remote diagnosis quality is reduced.
Disclosure of Invention
The invention provides a remote diagnosis system which is used for solving the technical problems existing in the prior art.
A remote diagnosis system comprises a patient remote session terminal, a doctor remote session terminal and a transmission code rate automatic allocation module;
The patient remote session terminal is used for collecting videos to be diagnosed input by a patient and requesting a network to transmit the videos to be diagnosed to the doctor remote session terminal;
The transmission code rate automatic allocation module is used for carrying out code rate self-adaptive adjustment on the video to be diagnosed of the patient by adopting a pre-deployed intelligent optimization algorithm to obtain a transmission code rate corresponding to the video to be diagnosed, and transmitting the video to be diagnosed to a doctor remote session terminal according to the transmission code rate;
The doctor remote session terminal is used for receiving the video to be diagnosed and playing the video to be diagnosed so as to enable the doctor to remotely diagnose the patient.
In one possible implementation, the method further comprises allowing text information transmission between the patient remote session terminal and the transmission code rate automatic allocation module.
In a possible implementation manner, a pre-deployed intelligent optimization algorithm is adopted to perform code rate self-adaptive adjustment on a video to be diagnosed of a patient, so as to obtain a transmission code rate corresponding to the video to be diagnosed, and the method comprises the following steps:
Aiming at the video to be diagnosed, dividing the video to be diagnosed into a plurality of video blocks, randomly distributing target code rates for each video block, and forming vectors by the target code rates corresponding to the video blocks to obtain code rate vectors of a single video to be diagnosed;
Forming a vector by code rate vectors corresponding to a plurality of patients to obtain a target code rate vector, and repeatedly obtaining a plurality of target code rate vectors;
aiming at any one target code rate vector, acquiring an evaluation function value corresponding to each target code rate vector by adopting a comprehensive video quality evaluation function, and acquiring an optimal target code rate vector according to the evaluation function value corresponding to each target code rate vector;
Aiming at any one target code rate vector, according to the optimal target code rate vector, performing multi-information fusion on the target code rate vector by adopting a multi-vector interaction strategy to obtain a target code rate vector after multi-information fusion;
Aiming at the target code rate vector after multi-information fusion, adopting a multi-information learning strategy to learn more optimal region information of the target code rate vector, and obtaining the target code rate vector after more optimal region information learning;
aiming at the target code rate vector after the better region information is learned, an unknown region searching is carried out on the target code rate vector by adopting a self-adaptive unknown region development strategy, and the target code rate vector after the unknown region searching is obtained;
For the target code rate vector after the unknown region searching, global searching is carried out on the target code rate vector by adopting a global variation development strategy, so as to obtain the target code rate vector after the global searching;
Judging whether the optimization ending condition is met, if so, re-determining an optimal target code rate vector according to the target code rate vector after global search, determining transmission code rates corresponding to videos to be diagnosed of a plurality of patients according to the re-determined optimal target code rate vector, and otherwise, returning to the step of acquiring the evaluation function value.
In one possible implementation manner, for any one target code rate vector, an evaluation function value corresponding to each target code rate vector is obtained by adopting a comprehensive video quality evaluation function, and an optimal target code rate vector is obtained according to the evaluation function value corresponding to each target code rate vector, including:
aiming at any target code rate vector, firstly, acquiring the comprehensive video quality corresponding to the code rate vector of the video to be diagnosed corresponding to each patient by adopting a comprehensive video quality evaluation function, wherein the comprehensive video quality is as follows:
the QoE represents comprehensive video quality, b l represents a code rate corresponding to the first video block in the video to be diagnosed, L represents the total number of video blocks corresponding to the video to be diagnosed, namely the video to be diagnosed is divided into video blocks according to a fixed length in the transmission process to obtain L number of video blocks, T l REBUF represents the blocking time corresponding to the first video block in the video to be diagnosed, b l-1 represents the code rate corresponding to the first-1 video block in the video to be diagnosed, alpha represents a first weighting parameter, and beta represents a second weighting parameter;
weighting and summing the comprehensive video quality corresponding to the code rate vectors corresponding to all patients on the basis of the weight parameters corresponding to each patient to obtain an evaluation function value corresponding to the target code rate vector, wherein the weight parameters corresponding to each patient are preset to be 1, and the staff and doctors are allowed to modify;
And determining the target code rate vector with the maximum evaluation function value as the optimal target code rate vector according to the evaluation function value corresponding to each target code rate vector.
In one possible implementation manner, for the target code rate vector after multi-information fusion, according to the optimal target code rate vector, and adopting a multi-vector interaction strategy to perform multi-information fusion on the target code rate vector, to obtain the target code rate vector after multi-information fusion, the method includes:
Wherein, the Representing the ith target code rate vector in the t-th optimization process,Target code rate vector representing better region information after learningK represents the total number of target code rate vectors, rand 1 represents the random number between (0, 1),Represents the optimal target code rate vector,Representing a first random target code rate vector,Representing a second random target code rate vector,Representing a second random target code rate vector.
In one possible implementation manner, for a target code rate vector after multi-information fusion, performing better region information learning on the target code rate vector by adopting a multi-information learning strategy to obtain a target code rate vector after better region information learning, including:
Wherein, the Represents the jth target code rate vector in the t-th optimization processCorresponding historical optimum values, j=1, 2,..k, K representing the target code rate vector total,A first preferred target code rate vector representing a second largest evaluation function value,A second preferred target code rate vector representing a third largest evaluation function value,Representing an optimal target code rate vector, a 1 representing a first random vector, a 2 representing a second random vector, a 3 representing a third random vector, the dimensions of the first, second, and third random vectors being the same as those of the parameter individual, and each being randomly generated by (2 rand 2-1)*2(itermax-t)/itermax, rand 2 representing a random number between (0, 1), item max representing a preset maximum number of optimizations, b 1 representing a first information learning coefficient, b 2 representing a second information learning coefficient, b 3 representing a third information learning coefficient, the first, second, and third information learning coefficients all being generated by 2rand 3, and rand 3 representing a random number between (0, 1),Representing target code rate vector after unknown region search
In one possible implementation manner, for a target code rate vector after the better region information is learned, an unknown region search is performed on the target code rate vector by adopting an adaptive unknown region development strategy, so as to obtain the target code rate vector after the unknown region search, including:
Wherein, the Representing a target code rate vector after the mth optimal region information is learned in the t-th optimization process,Represents a target code rate vector after the n-th better region information is learned in the t-th optimization process, n=1, 2,..,Representing the average code rate vector corresponding to all target code rate vectors,Representing target code rate vector after unknown region searchΛ represents an information fusion control factor, δ 1 represents a first development coefficient and is set to 0.6, δ 2 represents a second development coefficient and is set to 1.5, e represents a natural constant, and d mn represents a target code rate vectorVector of code rate with targetEuclidean distance between them.
In one possible implementation manner, for a target code rate vector after searching for an unknown region, global mutation development strategy is adopted to perform global search on the target code rate vector to obtain a target code rate vector after global search, including:
Wherein, the Represents the kth target code rate vector in the t-th optimization process,Representing target code rate vectors after global searchK represents the total number of target code rate vectors, rand 4 represents a random number between (0, 1), e represents a natural constant,Representing a fourth random target code rate vector, gamma representing an adaptive global search control factor,Representing a random number between [ -2.5γ,2.5γ ], iter max representing a preset maximum number of optimizations, θ representing an upper limit value of the scaling factor, and ζ representing an adjustment parameter of the scaling factor.
In one possible implementation manner, judging whether the optimization ending condition is met or not includes judging whether the current optimization times reach the preset maximum optimization times, if yes, determining that the optimization ending condition is met, and otherwise, determining that the optimization ending condition is not met.
In one possible implementation manner, determining transmission code rates corresponding to videos to be diagnosed of a plurality of patients according to the redetermined optimal target code rate vector includes:
according to the redetermined optimal target code rate vector, the optimal target code rate vector is redeployed into code rate vectors corresponding to a plurality of patients;
And determining the transmission code rate of each video block in the video to be diagnosed of the patient according to the code rate vector corresponding to each patient.
According to the remote diagnosis system provided by the invention, the code rate of the video to be diagnosed of the patient is adaptively adjusted by adopting the pre-deployed intelligent optimization algorithm, so that the transmission code rate corresponding to the video to be diagnosed is obtained, and the video to be diagnosed is transmitted to the doctor remote session terminal according to the transmission code rate, so that the data transmission rate can be dynamically adjusted according to the use condition of the whole network, the real-time performance and accuracy of remote diagnosis are ensured, and the remote diagnosis system is suitable for a plurality of fields such as medical treatment, education, enterprises and the like.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
Fig. 1 is a schematic structural diagram of a remote diagnosis system according to an embodiment of the present invention.
Specific embodiments of the present invention have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the invention. Rather, they are merely examples of apparatus and methods consistent with aspects of the invention as detailed in the accompanying claims.
Embodiments of the present invention are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, an embodiment of the present invention provides a remote diagnosis system, including a patient remote session terminal 101, a physician remote session terminal 103, and a transmission code rate automatic allocation module 102;
the patient remote session terminal 101 is configured to collect a video to be diagnosed input by a patient, and request network transmission of the video to be diagnosed to a doctor remote session terminal;
It is worth to say that, besides inputting the video to be diagnosed, the patient can also input other information (such as text information and voice information), but the network occupation of other information is low, and even if the network occupation is not optimized, the transmission can be very good, so that the embodiment of the invention is mainly aimed at code rate allocation of the video to be diagnosed.
The automatic transmission code rate distribution module 102 is configured to perform code rate adaptive adjustment on a video to be diagnosed of a patient by adopting a pre-deployed intelligent optimization algorithm, obtain a transmission code rate corresponding to the video to be diagnosed, and transmit the video to be diagnosed to a doctor remote session terminal according to the transmission code rate;
In the prior art, the video to be diagnosed is often transmitted by setting a fixed code rate, so that the overall network utilization efficiency is low, the condition of network blocking in a peak period occurs, and the remote diagnosis quality is reduced. Therefore, the embodiment of the invention adopts the intelligent optimization algorithm to carry out the code rate self-adaptive adjustment, and improves the overall utilization efficiency of the network while ensuring all user experiences as much as possible.
The doctor remote session terminal 103 is configured to receive the video to be diagnosed and play the video to be diagnosed, so that the doctor can remotely diagnose the patient.
Optionally, the physician remote session terminal 103 may also transmit data back to the patient remote session terminal 101 to effect diagnosis.
According to the remote diagnosis system provided by the invention, the code rate of the video to be diagnosed of the patient is adaptively adjusted by adopting the pre-deployed intelligent optimization algorithm, so that the transmission code rate corresponding to the video to be diagnosed is obtained, and the video to be diagnosed is transmitted to the doctor remote session terminal according to the transmission code rate, so that the data transmission rate can be dynamically adjusted according to the use condition of the whole network, the real-time performance and accuracy of remote diagnosis are ensured, and the remote diagnosis system is suitable for a plurality of fields such as medical treatment, education, enterprises and the like.
In one possible implementation, the method further comprises allowing text information transmission between the patient remote session terminal and the transmission code rate automatic allocation module. It should be noted that, in addition to the data illustrated in the embodiment of the present invention, other information may be used as the interactive information in the diagnosis process, so as to achieve a more comprehensive diagnosis.
In a possible implementation manner, a pre-deployed intelligent optimization algorithm is adopted to perform code rate self-adaptive adjustment on a video to be diagnosed of a patient, so as to obtain a transmission code rate corresponding to the video to be diagnosed, and the method comprises the following steps:
Aiming at the video to be diagnosed, dividing the video to be diagnosed into a plurality of video blocks, randomly distributing target code rates for each video block, and forming vectors by the target code rates corresponding to the video blocks to obtain code rate vectors of a single video to be diagnosed;
Optionally, the general code rate is set to be a plurality of gears and is not continuous interval data, so that in the embodiment of the invention, each gear can be mapped to a subinterval between (0 and 1) (for example, the subinterval corresponding to the first gear is (0,0.1), then the target code rate is randomly allocated to each video block and should be the first gear), after the subintervals corresponding to all gears are combined, the intervals (0 and 1) are obtained, so that continuous optimization can be realized, and in the subsequent use and calculation process, the code rate corresponding to each dimension data is determined, so that optimization is realized. Forming a vector by code rate vectors corresponding to a plurality of patients to obtain a target code rate vector, and repeatedly obtaining a plurality of target code rate vectors;
aiming at any one target code rate vector, acquiring an evaluation function value corresponding to each target code rate vector by adopting a comprehensive video quality evaluation function, and acquiring an optimal target code rate vector according to the evaluation function value corresponding to each target code rate vector;
Aiming at any one target code rate vector, according to the optimal target code rate vector, performing multi-information fusion on the target code rate vector by adopting a multi-vector interaction strategy to obtain a target code rate vector after multi-information fusion;
Aiming at the target code rate vector after multi-information fusion, adopting a multi-information learning strategy to learn more optimal region information of the target code rate vector, and obtaining the target code rate vector after more optimal region information learning;
aiming at the target code rate vector after the better region information is learned, an unknown region searching is carried out on the target code rate vector by adopting a self-adaptive unknown region development strategy, and the target code rate vector after the unknown region searching is obtained;
For the target code rate vector after the unknown region searching, global searching is carried out on the target code rate vector by adopting a global variation development strategy, so as to obtain the target code rate vector after the global searching;
Judging whether the optimization ending condition is met, if so, re-determining an optimal target code rate vector according to the target code rate vector after global search, determining transmission code rates corresponding to videos to be diagnosed of a plurality of patients according to the re-determined optimal target code rate vector, and otherwise, returning to the step of acquiring the evaluation function value.
In the existing intelligent optimization algorithm, the problem that local optimization is easily involved often exists, so that code rate allocation is not in an optimal state, and network resources cannot be utilized to the maximum extent to ensure patient treatment experience. Therefore, the embodiment of the invention provides an intelligent optimization algorithm which can optimize the utilization rate of the whole network based on the evaluation function value.
In one possible implementation manner, for any one target code rate vector, an evaluation function value corresponding to each target code rate vector is obtained by adopting a comprehensive video quality evaluation function, and an optimal target code rate vector is obtained according to the evaluation function value corresponding to each target code rate vector, including:
aiming at any target code rate vector, firstly, acquiring the comprehensive video quality corresponding to the code rate vector of the video to be diagnosed corresponding to each patient by adopting a comprehensive video quality evaluation function, wherein the comprehensive video quality is as follows:
The QoE represents comprehensive video quality, b l represents a code rate corresponding to the first video block in the video to be diagnosed, L represents the total number of video blocks corresponding to the video to be diagnosed, namely the video to be diagnosed is divided into video blocks according to a fixed length in the transmission process, L number of video blocks are obtained, T l REBUF represents the blocking time corresponding to the first video block in the video to be diagnosed, b l-1 represents the code rate corresponding to the first-1 video block in the video to be diagnosed, alpha represents a first weighting parameter, beta represents a second weighting parameter, and the blocking time can be obtained through a deep learning technology or other prior technologies;
And carrying out weighted summation on the comprehensive video quality corresponding to the code rate vectors corresponding to all patients on the basis of the weight parameters corresponding to each patient to obtain an evaluation function value corresponding to the target code rate vector, wherein the weight parameters corresponding to each patient are preset to be 1, and workers and doctors are allowed to modify, for example, when the patients visit different departments, different weights can be set, so that the sick patients can have better experience of visiting.
And determining the target code rate vector with the maximum evaluation function value as the optimal target code rate vector according to the evaluation function value corresponding to each target code rate vector.
In one possible implementation manner, for the target code rate vector after multi-information fusion, according to the optimal target code rate vector, and adopting a multi-vector interaction strategy to perform multi-information fusion on the target code rate vector, to obtain the target code rate vector after multi-information fusion, the method includes:
Wherein, the Representing the ith target code rate vector in the t-th optimization process,Target code rate vector representing better region information after learningK represents the total number of target code rate vectors, rand 1 represents the random number between (0, 1),Represents the optimal target code rate vector,Representing a first random target code rate vector,Representing a second random target code rate vector,Representing a second random target code rate vector.
The multi-vector interaction strategy provided by the embodiment of the invention can effectively learn the information of the optimal position and other random position information, so that the target code rate vector is ensured to advance to the optimal position while being locally searched, and then the information of other vectors is simultaneously learned, and the diversification of vector information is ensured.
In one possible implementation manner, for a target code rate vector after multi-information fusion, performing better region information learning on the target code rate vector by adopting a multi-information learning strategy to obtain a target code rate vector after better region information learning, including:
Wherein, the Represents the jth target code rate vector in the t-th optimization processCorresponding historical optimum values, j=1, 2,..k, K representing the target code rate vector total,A first preferred target code rate vector representing a second largest evaluation function value,A second preferred target code rate vector representing a third largest evaluation function value,Representing an optimal target code rate vector, a 1 representing a first random vector, a 2 representing a second random vector, a 3 representing a third random vector, the dimensions of the first, second, and third random vectors being the same as those of the parameter individual, and each being randomly generated by (2 rand 2-1)*2(itermax-t)/itermax, rand 2 representing a random number between (0, 1), item max representing a preset maximum number of optimizations, b 1 representing a first information learning coefficient, b 2 representing a second information learning coefficient, b 3 representing a third information learning coefficient, the first, second, and third information learning coefficients all being generated by 2rand 3, and rand 3 representing a random number between (0, 1),Representing target code rate vector after unknown region search
The multi-information learning strategy provided by the embodiment of the invention can learn the information of a plurality of better areas and can effectively improve the searching precision and searching efficiency of the algorithm.
In one possible implementation manner, for a target code rate vector after the better region information is learned, an unknown region search is performed on the target code rate vector by adopting an adaptive unknown region development strategy, so as to obtain the target code rate vector after the unknown region search, including:
Wherein, the Representing a target code rate vector after the mth optimal region information is learned in the t-th optimization process,Represents a target code rate vector after the n-th better region information is learned in the t-th optimization process, n=1, 2,..,Representing the average code rate vector corresponding to all the target code rate vectors, namely, each dimension parameter of the average code rate vector is the average value of all the target code rate vectors in the dimension parameter,Representing target code rate vector after unknown region searchΛ represents an information fusion control factor, δ 1 represents a first development coefficient and is set to 0.6, δ 2 represents a second development coefficient and is set to 1.5, e represents a natural constant, and d mn represents a target code rate vectorVector of code rate with targetEuclidean distance between them.
The self-adaptive unknown region development strategy provided by the embodiment of the invention can search based on the centers of all vectors no matter in the early stage or the later stage of the algorithm, can effectively realize the search of the unknown region, and can ensure the search precision of the algorithm when the algorithm starts to converge in the later stage of the algorithm.
In one possible implementation manner, for a target code rate vector after searching for an unknown region, global mutation development strategy is adopted to perform global search on the target code rate vector to obtain a target code rate vector after global search, including:
Wherein, the Represents the kth target code rate vector in the t-th optimization process,Representing target code rate vectors after global searchK represents the total number of target code rate vectors, rand 4 represents a random number between (0, 1), e represents a natural constant,Representing a fourth random target code rate vector, gamma representing an adaptive global search control factor,Representing a random number between [ -2.5γ,2.5γ ], iter max representing a preset maximum number of optimizations, θ representing an upper limit value of the scaling factor, and ζ representing an adjustment parameter of the scaling factor.
The global variation development strategy provided by the embodiment of the invention can effectively improve the global searching capability of the algorithm, thereby ensuring that the algorithm cannot sink into the local optimum, gradually increasing the searching precision along with the increase of the optimization times t of the algorithm, ensuring that the algorithm is successfully converged, and finally improving the code rate allocation rationality and efficiency and improving the network resource utilization efficiency.
Optionally, the target code rate vector can be subjected to out-of-range processing after each search, so that the code rate allocation is ensured to be effective.
In one possible implementation manner, judging whether the optimization ending condition is met or not includes judging whether the current optimization times reach the preset maximum optimization times, if yes, determining that the optimization ending condition is met, and otherwise, determining that the optimization ending condition is not met.
In one possible implementation manner, determining transmission code rates corresponding to videos to be diagnosed of a plurality of patients according to the redetermined optimal target code rate vector includes:
according to the redetermined optimal target code rate vector, the optimal target code rate vector is redeployed into code rate vectors corresponding to a plurality of patients;
And determining the transmission code rate of each video block in the video to be diagnosed of the patient according to the code rate vector corresponding to each patient.
Other embodiments of the invention will be apparent to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. This invention is intended to cover any variations, uses, or adaptations of the invention following, in general, the principles of the invention and including such departures from the present disclosure as come within known or customary practice within the art to which the invention pertains. It is to be understood that the invention is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the invention is limited only by the appended claims.

Claims (9)

1. The remote diagnosis system is characterized by comprising a patient remote session terminal, a doctor remote session terminal and a transmission code rate automatic allocation module;
The patient remote session terminal is used for collecting videos to be diagnosed input by a patient and requesting a network to transmit the videos to be diagnosed to the doctor remote session terminal;
The transmission code rate automatic allocation module is used for carrying out code rate self-adaptive adjustment on the video to be diagnosed of the patient by adopting a pre-deployed intelligent optimization algorithm to obtain a transmission code rate corresponding to the video to be diagnosed, and transmitting the video to be diagnosed to a doctor remote session terminal according to the transmission code rate;
The doctor remote session terminal is used for receiving the video to be diagnosed and playing the video to be diagnosed so as to enable a doctor to remotely diagnose a patient;
Performing code rate self-adaptive adjustment on the video to be diagnosed of the patient by adopting a pre-deployed intelligent optimization algorithm to obtain a transmission code rate corresponding to the video to be diagnosed, wherein the method comprises the following steps:
Aiming at the video to be diagnosed, dividing the video to be diagnosed into a plurality of video blocks, randomly distributing target code rates for each video block, and forming vectors by the target code rates corresponding to the video blocks to obtain code rate vectors of a single video to be diagnosed;
Forming a vector by code rate vectors corresponding to a plurality of patients to obtain a target code rate vector, and repeatedly obtaining a plurality of target code rate vectors;
aiming at any one target code rate vector, acquiring an evaluation function value corresponding to each target code rate vector by adopting a comprehensive video quality evaluation function, and acquiring an optimal target code rate vector according to the evaluation function value corresponding to each target code rate vector;
Aiming at any one target code rate vector, according to the optimal target code rate vector, performing multi-information fusion on the target code rate vector by adopting a multi-vector interaction strategy to obtain a target code rate vector after multi-information fusion;
Aiming at the target code rate vector after multi-information fusion, adopting a multi-information learning strategy to learn more optimal region information of the target code rate vector, and obtaining the target code rate vector after more optimal region information learning;
aiming at the target code rate vector after the better region information is learned, an unknown region searching is carried out on the target code rate vector by adopting a self-adaptive unknown region development strategy, and the target code rate vector after the unknown region searching is obtained;
For the target code rate vector after the unknown region searching, global searching is carried out on the target code rate vector by adopting a global variation development strategy, so as to obtain the target code rate vector after the global searching;
And judging whether the optimization ending condition is met, if so, re-determining an optimal target code rate vector according to the target code rate vector after global search, determining transmission code rates corresponding to videos to be diagnosed of a plurality of patients according to the re-determined optimal target code rate vector, and otherwise, returning to acquire the evaluation function value.
2. The remote diagnostic system of claim 1, further comprising allowing text messaging between the patient remote session terminal and the automatic transmission rate allocation module.
3. The remote diagnosis system according to claim 1, wherein for any one target code rate vector, the comprehensive video quality evaluation function is used to obtain an evaluation function value corresponding to each target code rate vector, and the optimal target code rate vector is obtained according to the evaluation function value corresponding to each target code rate vector, including:
aiming at any target code rate vector, firstly, acquiring the comprehensive video quality corresponding to the code rate vector of the video to be diagnosed corresponding to each patient by adopting a comprehensive video quality evaluation function, wherein the comprehensive video quality is as follows:
Wherein, the Representing the quality of the integrated video,Representing the code rate corresponding to the first video block in the video to be diagnosed, L representing the total number of video blocks corresponding to the video to be diagnosed, namely dividing the video to be diagnosed into video blocks according to a fixed length in the transmission process to obtain L number of video blocks,Representing the corresponding clamping time of the first video block in the video to be diagnosed,Representing the code rate corresponding to the first-1 video block in the video to be diagnosed,A first weighting parameter is indicated and a first weighting parameter is indicated,Representing a second weighting parameter;
weighting and summing the comprehensive video quality corresponding to the code rate vectors corresponding to all patients on the basis of the weight parameters corresponding to each patient to obtain an evaluation function value corresponding to the target code rate vector, wherein the weight parameters corresponding to each patient are preset to be 1, and the staff and doctors are allowed to modify;
And determining the target code rate vector with the maximum evaluation function value as the optimal target code rate vector according to the evaluation function value corresponding to each target code rate vector.
4. The remote diagnosis system according to claim 3, wherein for the target code rate vector after the multi-information fusion, according to the optimal target code rate vector, and adopting a multi-vector interaction strategy to perform multi-information fusion on the target code rate vector, to obtain the target code rate vector after the multi-information fusion, the remote diagnosis system comprises:
Wherein, the Representing the ith target code rate vector in the t-th optimization process,Target code rate vector representing better region information after learningI=1, 2,..k, K represents the target code rate vector total,Representing the random number between (0, 1),Represents the optimal target code rate vector,Representing a first random target code rate vector,Representing a second random target code rate vector,Representing a second random target code rate vector.
5. The remote diagnosis system of claim 4, wherein for the target code rate vector after multi-information fusion, performing better regional information learning on the target code rate vector by adopting a multi-information learning strategy to obtain the target code rate vector after better regional information learning, comprising:
Wherein, the Represents the jth target code rate vector in the t-th optimization processCorresponding historical optimum values, j=1, 2,..k, K representing the target code rate vector total,A first preferred target code rate vector representing a second largest evaluation function value,A second preferred target code rate vector representing a third largest evaluation function value,Represents the optimal target code rate vector,A first random vector is represented and is used to represent,A second random vector is represented and is used to represent,Representing a third random vector, the dimensions of the first random vector, the second random vector and the third random vector being the same as the dimensions of the parameter individual, and each dimension passing throughThe random generation is performed such that,Representing the random number between (0, 1),Indicating a preset maximum number of optimizations,A first information learning coefficient is represented and,Represents the second information learning coefficient,Represents a third information learning coefficient, the first information learning coefficient, the second information learning coefficient and the third information learning coefficient are all 2Generated and is provided withRepresenting the random number between (0, 1),Representing target code rate vector after unknown region search。
6. The remote diagnosis system according to claim 5, wherein for the target code rate vector after the better region information learning, the unknown region search is performed on the target code rate vector by adopting the adaptive unknown region development strategy, so as to obtain the target code rate vector after the unknown region search, comprising:
Wherein, the Representing a target code rate vector after the mth optimal region information is learned in the t-th optimization process,Represents a target code rate vector after the n-th better region information is learned in the t-th optimization process, n=1, 2,..,Representing the average code rate vector corresponding to all the target code rate vectors, namely, each dimension parameter of the average code rate vector is the average value of all the target code rate vectors in the dimension parameter,Representing target code rate vector after unknown region search,The information fusion control factor is represented by a set of information fusion control factors,Represents a first development factor and is set to 0.6; Represents a second development coefficient, and is set to 1.5, e represents a natural constant, Representing a target code rate vectorVector of code rate with targetEuclidean distance between them.
7. The remote diagnosis system of claim 6, wherein for the target code rate vector after the unknown region search, global search is performed on the target code rate vector using a global variation development strategy to obtain the target code rate vector after the global search, comprising:
Wherein, the Represents the kth target code rate vector in the t-th optimization process,Representing target code rate vectors after global searchK=1, 2,..k, K represents the target code rate vector total,Representing the random number between (0, 1),Represents a natural constant of the natural product,A fourth random target code rate vector is represented,Representing the adaptive global search control factor,Representation [ -2.5,2.5A random number between ],Indicating a preset maximum number of optimizations,Representing the upper limit value of the scaling factor,Representing the adjustment parameters of the scaling factor.
8. The remote diagnosis system according to claim 7, wherein the determining whether the optimization end condition is satisfied comprises determining whether the current optimization number reaches a preset maximum optimization number, if so, determining that the optimization end condition is satisfied, and otherwise, determining that the optimization end condition is not satisfied.
9. The remote diagnosis system according to claim 1, wherein determining the transmission code rate corresponding to the video to be diagnosed for the plurality of patients based on the redetermined optimal target code rate vector comprises:
according to the redetermined optimal target code rate vector, the optimal target code rate vector is redeployed into code rate vectors corresponding to a plurality of patients;
And determining the transmission code rate of each video block in the video to be diagnosed of the patient according to the code rate vector corresponding to each patient.
CN202411993748.6A 2024-12-31 2024-12-31 Remote diagnosis system Active CN119854593B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202411993748.6A CN119854593B (en) 2024-12-31 2024-12-31 Remote diagnosis system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202411993748.6A CN119854593B (en) 2024-12-31 2024-12-31 Remote diagnosis system

Publications (2)

Publication Number Publication Date
CN119854593A CN119854593A (en) 2025-04-18
CN119854593B true CN119854593B (en) 2025-09-12

Family

ID=95357489

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202411993748.6A Active CN119854593B (en) 2024-12-31 2024-12-31 Remote diagnosis system

Country Status (1)

Country Link
CN (1) CN119854593B (en)

Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119128930A (en) * 2024-08-16 2024-12-13 山西智杰软件工程有限公司 A remote transmission method for diagnostic data based on regional remote diagnosis and treatment platform

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105306960B (en) * 2015-10-18 2018-05-04 北京航空航天大学 A kind of dynamic self-adapting streaming system for being used for transmission high quality online course video
US10861604B2 (en) * 2016-05-05 2020-12-08 Advinow, Inc. Systems and methods for automated medical diagnostics
CN113852817B (en) * 2020-06-28 2024-04-05 上海交通大学 Adaptive bit rate transmission server, bit rate determination method, transmission system and method
CN118075553A (en) * 2024-01-12 2024-05-24 北京邮电大学 Video semantic communication method and related equipment based on network adaptive transmission

Patent Citations (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN119128930A (en) * 2024-08-16 2024-12-13 山西智杰软件工程有限公司 A remote transmission method for diagnostic data based on regional remote diagnosis and treatment platform

Also Published As

Publication number Publication date
CN119854593A (en) 2025-04-18

Similar Documents

Publication Publication Date Title
CN113568727B (en) Mobile edge computing task allocation method based on deep reinforcement learning
US20220116281A1 (en) Method and apparatus for predicting bandwidth
WO2021128805A1 (en) Wireless network resource allocation method employing generative adversarial reinforcement learning
CN112954736A (en) Policy-based computation offload of wireless energy-carrying internet-of-things equipment
CN112153702B (en) Local area network bandwidth resource allocation method, storage device and equipment
CN107094060A (en) Distributed super-intensive heterogeneous network disturbance coordination method based on non-cooperative game
CN112017785A (en) Disease risk prediction system, method, device, equipment and medium
CN108958939A (en) Distribution method, device and the server of Service Source
CN116825331A (en) Microwave physiotherapy self-learning self-diagnosis system and device based on outpatient big data
CN119358708B (en) Self-adaptive bilateral distillation personalized federal learning method based on diffusion model
CN113543160A (en) 5G slice resource allocation method and device, computing equipment and computer storage medium
CN117010534B (en) Dynamic model training method, system and equipment based on annular knowledge distillation and meta federal learning
CN110996365B (en) A Heterogeneous Network Vertical Handoff Algorithm and System Based on Multi-objective Optimization Model
CN111866187A (en) Task scheduling method of distributed deep learning reasoning cloud platform
CN116959665A (en) Motion monitoring method, device, equipment and storage medium
CN114492841B (en) A model gradient updating method and device
Wang et al. DeepNetQoE: Self-adaptive QoE optimization framework of deep networks
CN119854593B (en) Remote diagnosis system
CN116994733A (en) Reinforced learning prediction sorting physical examination queuing system based on data flow
CN101321388B (en) Cognition radio network FDM channel selection method based on game theory
CN103284690A (en) Transmission method and device of physiological parameters and mobile health system
CN118506995B (en) Medical image high-speed retrieval method and system using artificial intelligence
CN114449536A (en) 5G ultra-dense network multi-user access selection method based on deep reinforcement learning
CN119946329A (en) Video streaming media dual time scale wireless transmission method, system and storage medium
CN116302569B (en) Resource partition intelligent scheduling method based on user request information

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant