CN114496094A - Metric learning method, system, equipment and medium for intestinal flora transplantation matching - Google Patents

Metric learning method, system, equipment and medium for intestinal flora transplantation matching Download PDF

Info

Publication number
CN114496094A
CN114496094A CN202111559769.3A CN202111559769A CN114496094A CN 114496094 A CN114496094 A CN 114496094A CN 202111559769 A CN202111559769 A CN 202111559769A CN 114496094 A CN114496094 A CN 114496094A
Authority
CN
China
Prior art keywords
donor
metric
data
neural network
learning
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.)
Pending
Application number
CN202111559769.3A
Other languages
Chinese (zh)
Inventor
黄伟斌
王科
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.)
Guangzhou Baoliang Medical Technology Co ltd
Original Assignee
Guangzhou Baoliang Medical 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 Guangzhou Baoliang Medical Technology Co ltd filed Critical Guangzhou Baoliang Medical Technology Co ltd
Priority to CN202111559769.3A priority Critical patent/CN114496094A/en
Publication of CN114496094A publication Critical patent/CN114496094A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16B—BIOINFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR GENETIC OR PROTEIN-RELATED DATA PROCESSING IN COMPUTATIONAL MOLECULAR BIOLOGY
    • G16B40/00—ICT specially adapted for biostatistics; ICT specially adapted for bioinformatics-related machine learning or data mining, e.g. knowledge discovery or pattern finding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Medical Informatics (AREA)
  • Mathematical Physics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Epidemiology (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Biology (AREA)
  • Biotechnology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Bioethics (AREA)
  • Public Health (AREA)
  • Prostheses (AREA)

Abstract

The invention relates to the technical field of intestinal flora transplantation, and discloses a measurement learning method, a system, equipment and a medium for intestinal flora transplantation matching, wherein the method comprises the following steps: constructing a twin neural network; inputting donor data and acceptor data into the twin neural network for training to obtain donor metric characteristics and acceptor metric characteristics; and performing learning training on the donor metric characteristics and the receptor metric characteristics through a loss function, and outputting a training result. According to the method, the system, the equipment and the medium for metric learning of the intestinal flora transplantation match, the twin neural Network (Simase Network) is utilized to perform matching metric learning on the receipt of the donor and the recipient of the intestinal flora transplantation, and a more accurate matching metric calculation model can be generated. And the similarity calculation model of the receptor and the donor is more reasonable by using the contextual Loss function to train the matching data.

Description

Metric learning method, system, equipment and medium for intestinal flora transplantation matching
Technical Field
The invention relates to the technical field of intestinal flora transplantation, in particular to a measurement learning method, a system, computer equipment and a readable storage medium for accurate matching of intestinal flora transplantation.
Background
Metric learning (metric learning) is a method of learning from data a metric of distance between data objects. The goal is to make the distance between similar objects small and the distance between dissimilar objects large under the learned distance metric.
In the case of intestinal flora transplantation, it is necessary to precisely match the donor and recipient data. At present, the euclidean distances between features are directly calculated, but the euclidean distances are obviously unreasonable assuming that importance weights of all features are completely consistent, so that an accurate measurement model for matching between a receptor and a common object needs to be found based on supervised learning and a measurement learning method.
Therefore, the prior art needs to be further improved and improved.
Disclosure of Invention
The purpose of the invention is: matching metric learning is performed on the donor and recipient receipts of intestinal flora transplantation by using a twin neural Network (Siamese Network) to generate a more accurate matching metric calculation model.
In order to achieve the above object, in a first aspect, the present invention provides a metric learning method for intestinal flora transplantation matching, the method comprising:
constructing a twin neural network;
inputting donor data and acceptor data into the twin neural network for training to obtain donor metric characteristics and acceptor metric characteristics;
and performing learning training on the donor metric characteristics and the receptor metric characteristics through a loss function, and outputting a training result.
Further, the step of inputting the donor data and the receptor data into the twin neural network for training to obtain the donor metric characteristic and the receptor metric characteristic includes:
the twin neural network extracts donor data characteristics and acceptor data characteristics from the donor data and the acceptor data respectively;
and mapping the donor data features and the acceptor data features to a new space respectively to form donor metric features and acceptor metric features represented in the new space.
Further, the donor and recipient metric features are learning trained by the following loss function:
Figure BDA0003417537340000021
wherein W is the network weight, Y is the pair tag,
Figure BDA0003417537340000022
the characteristics are measured for the donor and,
Figure BDA0003417537340000023
measuring characteristics for receptors, DWIs composed of
Figure BDA0003417537340000024
And
Figure BDA0003417537340000025
the euler distance in the latent variable space, m, is a predetermined threshold.
Further, if
Figure BDA0003417537340000026
And
Figure BDA0003417537340000027
belong to the same class, if the sample is positive, Y is 0, and D is adjustedWIs the minimum value; if it is not
Figure BDA0003417537340000028
And
Figure BDA0003417537340000029
not as a negative sample, Y is 1, and if DWLess than a predetermined threshold, DWIncreasing to the predetermined threshold.
Further, the step of inputting the donor data and the recipient data into the twin neural network for training further comprises:
the donor and recipient data were normalized.
Further, both neural networks of the twin neural network are LSTM neural networks or CNN neural networks.
In a second aspect, an embodiment of the present invention provides a metric learning system for intestinal flora transplantation, the system including:
the network construction module is used for constructing a twin neural network;
the characteristic processing module is used for inputting donor data and acceptor data into the twin neural network for training to obtain donor measurement characteristics and acceptor measurement characteristics;
and the matching learning module is used for performing matching learning training on the donor metric characteristic and the receptor metric characteristic through a loss function and outputting a training result.
Further, the system further comprises:
and the standardization module is used for carrying out standardization processing on the donor data and the receptor data.
In a third aspect, the present invention provides a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the above method when executing the computer program.
In a fourth aspect, the invention provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of the above-described method.
The embodiment of the invention provides a metric learning method, a metric learning system, a metric learning device and a metric learning medium for intestinal flora transplantation matching, wherein a twin neural Network (Simase Network) is used for matching metric learning of a donor receipt and a receptor receipt of intestinal flora transplantation, so that a more accurate matching metric calculation model can be generated. And moreover, the matched data is trained by using the contextual Loss function, and a similarity calculation model of the receptor and the donor is more reasonable to learn.
Drawings
Fig. 1 is a schematic view of an application scenario of a metric learning method for intestinal flora transplantation matching according to an embodiment of the present invention;
FIG. 2 is a flow chart of a metric learning method for intestinal flora transplantation matching in an embodiment of the present invention;
FIG. 3 is a comparison of donor and recipient data before and after normalization;
FIG. 4 is a detailed flowchart of step S200 in FIG. 2;
FIG. 5 is a block diagram of a metric learning system for gut flora transplant matching in accordance with an embodiment of the present invention;
FIG. 6 is a block diagram of a metric learning system for gut flora transplant matching in accordance with another embodiment of the present invention;
FIG. 7 is a schematic diagram of a computer device in an embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments, and it is obvious that the embodiments described below are part of the embodiments of the present invention, and are only used for illustrating the present invention, but not for limiting the scope of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The measurement learning method for intestinal flora transplantation matching provided by the invention can be applied to a terminal or a server shown in figure 1. The terminal can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers and portable wearable devices, and the server can be implemented by an independent server or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a method for cohort matching of intestinal flora transplantation according to a preferred embodiment of the present invention comprises the steps of:
and S100, constructing a twin neural network.
The twin neural Network (Simense Network) is a coupling architecture established based on two artificial neural networks, the twin neural Network takes two samples as input and outputs the representation of embedding high-dimensional space to compare the similarity degree of the two samples, the narrow twin neural Network is formed by splicing two neural networks with the same structure and shared weight, the weight can be optimized by an energy function or classification loss, and the generalized twin neural Network (also called Pseudo-Simense Network, Pseudo-twin neural Network) is formed by splicing two arbitrary neural networks and can be composed of a convolutional neural Network, a cyclic neural Network and the like. In the supervised learning paradigm, the twin neural network maximizes the characterization of different labels and minimizes the characterization of the same label, and in the unsupervised or unsupervised learning paradigm, the twin neural network can minimize the characterization between the original input and the interfering input.
In order to face the metric learning of the gut flora exact match, the embodiment of the invention preferably adopts the weight-shared twin neural network, and because the donor and the receptor in the gut flora match have certain similarity, the weight-shared twin neural network model can be more suitable for the gut flora exact match. In this embodiment, the two neural networks of the twin neural network are the same neural network, such as LSTM neural network or CNN neural network.
S200, inputting donor data and acceptor data into the twin neural network for training to obtain donor measurement characteristics and acceptor measurement characteristics.
In this embodiment, before the donor data and the recipient data are input into the twin neural network, the donor data and the recipient data are normalized first, for the effect of the normalization, please refer to fig. 3, the left graph in fig. 3 is the original data of the donor and the recipient, the right graph is the normalized data of the donor and the recipient, b is the deviation, w is the weight, and the center indicates the minimum cost to be achieved. The right hand side of figure 3 appears more symmetrical and can show the effect of this embodiment on normalizing the data. If the range of features varies widely, the values of the different weights will also vary widely as they occur, and it will take more time to select a perfect set of weights. However, if normalized data is used, the weights do not change much, and thus an ideal weight set is obtained in a short time. Furthermore, if raw data is used, a lower learning rate must be used to accommodate different contour heights. But in case of normalized data we have more spherical profiles and by choosing a larger learning rate we can directly achieve the minimum. Therefore, when features are on similar scales, it becomes easy to optimize weights and biases. Therefore, the embodiment carries out standardized processing on the donor data and the acceptor data, which is more beneficial to the subsequent training of the neural network, and can improve the training efficiency and save the cost.
In step S200, see, 4, the training of the twin neural network on the donor data and the recipient data comprises the steps of:
s201, extracting donor data characteristics and acceptor data characteristics from the donor data and the acceptor data respectively by the twin neural network;
and S202, mapping the donor data characteristics and the acceptor data characteristics to a new space respectively to form donor metric characteristics and acceptor metric characteristics represented in the new space.
Through the training of the twin neural network, donor measurement characteristics and acceptor measurement characteristics represented in a new space can be obtained, and the donor measurement characteristics and the acceptor measurement characteristics are vector characteristics, so that the Euler distance of the donor measurement characteristics and the acceptor measurement characteristics can be calculated in the following process. The new space is denoted as the latent variable space.
S300, learning and training the donor metric characteristics and the acceptor metric characteristics through a loss function, and outputting a training result.
The present embodiment performs learning training on the donor metric features and the recipient metric features by the following loss functions:
Figure BDA0003417537340000061
wherein W is the network weight, Y is the pair tag,
Figure BDA0003417537340000062
the characteristics are measured for the donor and,
Figure BDA0003417537340000063
measuring characteristics for receptors, DWIs composed of
Figure BDA0003417537340000064
And
Figure BDA0003417537340000065
the euler distance in the latent variable space, m, is a predetermined threshold.
During the learning and training, if
Figure BDA0003417537340000066
And
Figure BDA0003417537340000067
belong to the same class, if the sample is positive, Y is 0, and D is adjustedWTo a minimum, i.e. to minimize the tuning parameter
Figure BDA0003417537340000068
And
Figure BDA0003417537340000069
the previous distance; if it is not
Figure BDA00034175373400000610
And
Figure BDA00034175373400000611
not as a negative sample, Y is 1, and if DWLess than a predetermined threshold, DWIncreasing to the predetermined threshold. By training the matching data, including positive samples (matching) and negative samples (mismatching), using the contextual Loss function, it is more reasonable to learn a computational model of the similarity between the recipient and the donor.
According to the measurement learning method for the intestinal flora transplantation match, the twin neural Network (Simase Network) is utilized to perform matching measurement learning on the receipt of the donor and the receiver transplanted to the intestinal flora, a more accurate matching measurement calculation model is generated, and the learned similarity calculation model of the donor and the donor can be more reasonable through the loss function training matching data.
In a second aspect, an embodiment of the present invention provides a metric learning system for intestinal flora transplantation, and referring to fig. 5, the system includes:
the network construction module 1 is used for constructing a twin neural network;
the characteristic processing module 2 is used for inputting donor data and acceptor data into the twin neural network for training to obtain donor measurement characteristics and acceptor measurement characteristics;
and the matching learning module 3 is used for performing matching learning training on the donor metric characteristic and the receptor metric characteristic through a loss function and outputting a training result.
In one embodiment, referring to fig. 6, the system further comprises: and the standardization module 4 is used for carrying out standardization processing on the donor data and the receptor data.
According to the measurement learning system of the intestinal flora transplantation match type, the twin neural network constructed by the network construction module is used for learning and training the donor data and the receptor data, and the loss function is used for matching the data, so that not only can a more accurate matching measurement calculation model be generated, but also the learned similarity calculation model of the receptor and the donor can be more reasonable.
It should be noted that, all or part of the modules in the metric learning system for intestinal flora transplantation can be implemented by software, hardware and their combination. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules. For the specific definition of the metric learning system for the intestinal flora transplantation match, reference is made to the above definition of the metric learning method for the intestinal flora transplantation match, and the two have the same functions and effects, and are not described herein again.
Furthermore, an embodiment of the present invention also proposes a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the above-mentioned method.
An embodiment of the present invention also provides a computer device, see fig. 7, including a memory 701, a processor 702, and a computer program stored on the memory and executable on the processor, wherein the processor 702 implements the steps of the above method when executing the program. The processor 702 and the memory 701 may be connected by a bus or other means, and fig. 6 illustrates an example of a connection by a bus.
The memory 701 is a non-volatile computer-readable storage medium, and can be used for storing non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules corresponding to the cohort typing system for intestinal flora transplantation in the embodiment of the present invention. The processor 702 executes various functional applications and data processing of the server by running the nonvolatile software program, instructions and modules stored in the memory 701, so as to implement the group matching system for intestinal flora transplantation in the above system embodiment.
The memory 701 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of a group matching system for intestinal flora transplantation, and the like. Further, the memory 701 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 701 may optionally include memory remotely located from processor 702, and such remote memory may be connected to the enteric flora-grafted cohort typing system via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Finally, it should be noted that: the above-mentioned embodiments are only specific embodiments of the present invention, which are used for illustrating the technical solutions of the present invention and not for limiting the same, and the protection scope of the present invention is not limited thereto, although the present invention is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive the technical solutions described in the foregoing embodiments or equivalent substitutes for some technical features within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present invention, and they should be construed as being included therein. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.

Claims (10)

1. A method of metric learning of gut flora transplant match, the method comprising:
constructing a twin neural network;
inputting donor data and acceptor data into the twin neural network for training to obtain donor metric characteristics and acceptor metric characteristics;
and performing learning training on the donor metric characteristics and the receptor metric characteristics through a loss function, and outputting a training result.
2. The method of claim 1, wherein the step of inputting donor data and recipient data into the twin neural network for training to obtain donor metric characteristics and recipient metric characteristics comprises:
the twin neural network extracts donor data characteristics and acceptor data characteristics from the donor data and the acceptor data respectively;
and mapping the donor data features and the acceptor data features to a new space respectively to form donor metric features and acceptor metric features represented in the new space.
3. The method of claim 1, wherein the donor metric features and the recipient metric features are learning trained by the following loss function:
Figure FDA0003417537330000011
wherein W is the network weight, Y is the pair label,
Figure FDA0003417537330000012
the characteristics are measured for the donor and,
Figure FDA0003417537330000013
measuring characteristics for receptors, DWIs composed of
Figure FDA0003417537330000014
And
Figure FDA0003417537330000015
the euler distance in the latent variable space, m, is a predetermined threshold.
4. The method of claim 3, wherein the intestinal flora graft matching metric learning method is performed if
Figure FDA0003417537330000021
And
Figure FDA0003417537330000022
belong to the same class, if the sample is positive, Y is 0, and D is adjustedWIs the minimum value; if it is used
Figure FDA0003417537330000023
And
Figure FDA0003417537330000024
not as a negative sample, Y is 1, and if DWLess than a predetermined threshold, DWIncreasing to the predetermined threshold.
5. The method of claim 1, wherein the step of inputting donor data and recipient data into the twin neural network for training further comprises:
the donor and recipient data were normalized.
6. The method of claim 1, wherein both neural networks of the twin neural network are LSTM neural networks or CNN neural networks.
7. A system for metric learning of gut flora transplant patterns, the system comprising:
the network construction module is used for constructing a twin neural network;
the characteristic processing module is used for inputting donor data and acceptor data into the twin neural network for training to obtain donor measurement characteristics and acceptor measurement characteristics;
and the matching learning module is used for performing matching learning training on the donor metric characteristic and the receptor metric characteristic through a loss function and outputting a training result.
8. The system of claim 7, further comprising:
and the standardization module is used for carrying out standardization processing on the donor data and the receptor data.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method of any of claims 1 to 6 are implemented when the computer program is executed by the processor.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 6.
CN202111559769.3A 2021-12-17 2021-12-17 Metric learning method, system, equipment and medium for intestinal flora transplantation matching Pending CN114496094A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111559769.3A CN114496094A (en) 2021-12-17 2021-12-17 Metric learning method, system, equipment and medium for intestinal flora transplantation matching

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111559769.3A CN114496094A (en) 2021-12-17 2021-12-17 Metric learning method, system, equipment and medium for intestinal flora transplantation matching

Publications (1)

Publication Number Publication Date
CN114496094A true CN114496094A (en) 2022-05-13

Family

ID=81493226

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111559769.3A Pending CN114496094A (en) 2021-12-17 2021-12-17 Metric learning method, system, equipment and medium for intestinal flora transplantation matching

Country Status (1)

Country Link
CN (1) CN114496094A (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140122382A1 (en) * 2008-10-15 2014-05-01 Eric A. Elster Bayesian modeling of pre-transplant variables accurately predicts kidney graft survival
CN112614596A (en) * 2020-12-22 2021-04-06 厦门承葛生物科技有限公司 Donor and acceptor matching method for treating ulcerative colitis by intestinal flora transplantation
CN112784130A (en) * 2021-01-27 2021-05-11 杭州网易云音乐科技有限公司 Twin network model training and measuring method, device, medium and equipment
US20210383892A1 (en) * 2020-06-03 2021-12-09 Xenotherapeutics, Inc. Selection and Monitoring Methods for Xenotransplantation

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140122382A1 (en) * 2008-10-15 2014-05-01 Eric A. Elster Bayesian modeling of pre-transplant variables accurately predicts kidney graft survival
US20210383892A1 (en) * 2020-06-03 2021-12-09 Xenotherapeutics, Inc. Selection and Monitoring Methods for Xenotransplantation
CN112614596A (en) * 2020-12-22 2021-04-06 厦门承葛生物科技有限公司 Donor and acceptor matching method for treating ulcerative colitis by intestinal flora transplantation
CN112784130A (en) * 2021-01-27 2021-05-11 杭州网易云音乐科技有限公司 Twin network model training and measuring method, device, medium and equipment

Similar Documents

Publication Publication Date Title
US20230153619A1 (en) Method for training neural network and related device
WO2019169719A1 (en) Automatic abstract extraction method and apparatus, and computer device and storage medium
US10169683B2 (en) Method and device for classifying an object of an image and corresponding computer program product and computer-readable medium
CN110502976B (en) Training method of text recognition model and related product
WO2021089013A1 (en) Spatial graph convolutional network training method, electronic device and storage medium
CN110598869B (en) Classification method and device based on sequence model and electronic equipment
CN111523640A (en) Training method and device of neural network model
CN109633448B (en) Method and device for identifying battery health state and terminal equipment
WO2023116111A1 (en) Disk fault prediction method and apparatus
CN113298152B (en) Model training method, device, terminal equipment and computer readable storage medium
WO2020173270A1 (en) Method and device used for parsing data and computer storage medium
CN114511042A (en) Model training method and device, storage medium and electronic device
CN115146068A (en) Method, device and equipment for extracting relation triples and storage medium
US11366984B1 (en) Verifying a target object based on confidence coefficients generated by trained models
CN114281932A (en) Method, device and equipment for training work order quality inspection model and storage medium
CN113704534A (en) Image processing method and device and computer equipment
CN115482436B (en) Training method and device for image screening model and image screening method
CN114496094A (en) Metric learning method, system, equipment and medium for intestinal flora transplantation matching
US20220358572A1 (en) Device and method to provide data associated with shopping mall web page
CN113743448B (en) Model training data acquisition method, model training method and device
CN113469237B (en) User intention recognition method, device, electronic equipment and storage medium
US20210334647A1 (en) Method, electronic device, and computer program product for determining output of neural network
CN111091198A (en) Data processing method and device
CN115102852B (en) Internet of things service opening method and device, electronic equipment and computer medium
CN116912919B (en) Training method and device for image recognition model

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20220513

RJ01 Rejection of invention patent application after publication