CN117558393A - Anorectal patient information arrangement method and system based on artificial intelligence - Google Patents
Anorectal patient information arrangement method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117558393A CN117558393A CN202410048770.7A CN202410048770A CN117558393A CN 117558393 A CN117558393 A CN 117558393A CN 202410048770 A CN202410048770 A CN 202410048770A CN 117558393 A CN117558393 A CN 117558393A
- Authority
- CN
- China
- Prior art keywords
- patient information
- thread
- information
- artificial intelligence
- anorectal patient
- 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.)
- Granted
Links
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 187
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000000611 regression analysis Methods 0.000 claims description 31
- 230000004927 fusion Effects 0.000 claims description 21
- 238000011158 quantitative evaluation Methods 0.000 claims description 17
- 238000011156 evaluation Methods 0.000 claims description 14
- 238000000605 extraction Methods 0.000 claims description 14
- 238000007726 management method Methods 0.000 claims description 7
- 230000003993 interaction Effects 0.000 claims description 6
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 238000013215 result calculation Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 12
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 201000010099 disease Diseases 0.000 description 3
- 208000014617 hemorrhoid Diseases 0.000 description 3
- 238000010415 tidying Methods 0.000 description 3
- 210000000436 anus Anatomy 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 206010048946 Anal abscess Diseases 0.000 description 1
- 206010061424 Anal cancer Diseases 0.000 description 1
- 206010002153 Anal fissure Diseases 0.000 description 1
- 206010059313 Anogenital warts Diseases 0.000 description 1
- 208000009115 Anorectal Malformations Diseases 0.000 description 1
- 206010002581 Anorectal stenosis Diseases 0.000 description 1
- 208000016583 Anus disease Diseases 0.000 description 1
- 208000032170 Congenital Abnormalities Diseases 0.000 description 1
- 206010010356 Congenital anomaly Diseases 0.000 description 1
- 206010010774 Constipation Diseases 0.000 description 1
- 208000009531 Fissure in Ano Diseases 0.000 description 1
- 206010021639 Incontinence Diseases 0.000 description 1
- 206010029333 Neurosis Diseases 0.000 description 1
- 206010036774 Proctitis Diseases 0.000 description 1
- 208000012287 Prolapse Diseases 0.000 description 1
- 208000004680 Rectal Fistula Diseases 0.000 description 1
- 208000015634 Rectal Neoplasms Diseases 0.000 description 1
- 208000015815 Rectal disease Diseases 0.000 description 1
- 206010038074 Rectal polyp Diseases 0.000 description 1
- 206010038080 Rectal ulcer Diseases 0.000 description 1
- 201000007696 anal canal cancer Diseases 0.000 description 1
- 206010002156 anal fistula Diseases 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 208000035475 disorder Diseases 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 210000002429 large intestine Anatomy 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 210000004877 mucosa Anatomy 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 208000015238 neurotic disease Diseases 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 208000003154 papilloma Diseases 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 208000022075 polyp of rectum Diseases 0.000 description 1
- 206010038038 rectal cancer Diseases 0.000 description 1
- 201000010727 rectal prolapse Diseases 0.000 description 1
- 210000000664 rectum Anatomy 0.000 description 1
- 201000001275 rectum cancer Diseases 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 201000009890 sinusitis Diseases 0.000 description 1
- 208000017520 skin disease Diseases 0.000 description 1
- 230000008733 trauma Effects 0.000 description 1
- 201000008827 tuberculosis Diseases 0.000 description 1
Classifications
-
- 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
- G16H10/00—ICT specially adapted for the handling or processing of patient-related medical or healthcare data
- G16H10/60—ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G16H50/70—ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
- Pathology (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
Abstract
According to the anorectal patient information arrangement method and system based on artificial intelligence, thread coefficients of a first artificial intelligence thread and a second artificial intelligence thread are debugged according to comparison results, and the configured first artificial intelligence thread and second artificial intelligence thread are obtained; and receiving anorectal patient information to be analyzed, and extracting description knowledge information of the anorectal patient information to be analyzed through the configured first artificial intelligent thread to sort the anorectal patient information. The multi-catalog configuration is carried out on the two threads through the covering catalog combination configuration anorectal patient information between the item catalog and anorectal patient information description knowledge similarity, the thread coefficients of the two threads are debugged according to the comparison result, and the working efficiency of the configured threads is improved, so that the information arrangement efficiency is improved, and related information can be quickly and reliably inquired when anorectal patient information is required to be inquired later.
Description
Technical Field
The application relates to the technical field of data arrangement, in particular to an anorectal patient information arrangement method and system based on artificial intelligence.
Background
In a broad sense: all stalk diseases occurring on anus and large intestine are called anorectal diseases, and the common diseases are more than 100. In a narrow sense: there are 30 or more common diseases occurring in the anus and rectum, such as: internal hemorrhoids, external hemorrhoids, mixed hemorrhoids, anal fissure, anal fistula, perianal abscess, anal skin disease, anal sinusitis, proctitis, rectal ulcers, constipation at the outlet, rectal prolapse, proctoscope, prolapse in the rectal mucosa, anorectal stenosis, anal incontinence, anal canal cancer, rectal cancer, anal papilloma, rectal polyp, anorectal tuberculosis, anal neurosis, condyloma acuminata, anorectal congenital deformity, anorectal trauma, and the like.
At present, as anorectal patients are more and more, the arrangement of the information of anorectal patients is a very difficult problem, which may lead to disorder of information exchange and is not easy to find when relevant information is queried, so that a scheme is needed to improve the technical problems.
Disclosure of Invention
In order to improve the technical problems in the related art, the application provides an anorectal patient information arrangement method and system based on artificial intelligence.
In a first aspect, an anorectal patient information sorting method based on artificial intelligence is provided, and the anorectal patient information sorting method based on artificial intelligence includes: respectively inputting configuration anorectal patient information, a carried item catalog and a covering catalog into a first artificial intelligent thread and a second artificial intelligent thread for configuration, wherein the covering catalog is used for calibrating configuration anorectal patient information with an anorectal patient information description knowledge sharing coefficient larger than a preset target value; obtaining a comparison result between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread; debugging thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread according to the comparison result to obtain a configured first artificial intelligence thread and second artificial intelligence thread; the second artificial intelligence thread is used for loading core information of the second artificial intelligence thread for description knowledge extraction to the first artificial intelligence thread so as to realize mutual description knowledge extraction learning of the first artificial intelligence thread and the second artificial intelligence thread, and the configured first artificial intelligence thread and second artificial intelligence thread are obtained, so that the configured first artificial intelligence thread carries the core information of the second artificial intelligence thread for description knowledge extraction; and receiving anorectal patient information to be analyzed, and extracting description knowledge information of the anorectal patient information to be analyzed through a configured first artificial intelligent thread to carry out anorectal patient information arrangement.
Further, the anorectal patient information arrangement method based on artificial intelligence further comprises the following steps: obtaining anorectal patient configuration information, wherein the anorectal patient configuration information carries a matter catalog; determining preset anorectal patient information corresponding to each item catalog type; clustering preset anorectal patient information corresponding to different item catalogue types, and clustering preset anorectal patient information with anorectal patient information description knowledge sharing coefficients larger than preset target values; and generating a covering catalog of clustered preset anorectal patient information.
Further, the step of clustering the preset anorectal patient information corresponding to different item catalog types, and clustering the preset anorectal patient information with the anorectal patient information description knowledge sharing coefficient larger than the preset target value includes: extracting anorectal patient information description knowledge of preset anorectal patient information corresponding to each item catalog type; clustering anorectal patient information description knowledge which corresponds to each item catalog type and is preset with anorectal patient information through a clustering function; clustering the preset anorectal patient information with the anorectal patient information description knowledge sharing coefficient larger than the preset target value.
Further, the step of inputting the information of the anorectal patient to be configured, the carried item catalog and the covering catalog into the first artificial intelligence thread and the second artificial intelligence thread to be configured respectively includes: performing association, similarity, interaction degree and/or conversion debugging treatment on the information of the configured anorectal patients; and respectively inputting the debugged and processed anorectal patient information, the carried item catalogue and the covering catalogue into a first artificial intelligent thread and a second artificial intelligent thread for configuration.
Further, the step of obtaining a comparison result between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread includes: and calculating a comparison result between regression analysis information of the first artificial intelligent thread and the second artificial intelligent thread through a comparison result calculation formula, and building a quantitative evaluation model corresponding to the comparison result.
Further, the step of debugging the thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread by combining the comparison result to obtain the configured first artificial intelligence thread and second artificial intelligence thread includes: integrating and configuring the quantitative evaluation model by combining with an original evaluation index model of the first artificial intelligent thread to obtain a configured first artificial intelligent thread; and integrating and configuring the quantitative evaluation model by combining with an original evaluation index model of the second artificial intelligent thread to obtain the configured second artificial intelligent thread.
Further, the step of receiving anorectal patient information to be analyzed, extracting description knowledge information of the anorectal patient information to be analyzed through a configured first artificial intelligent thread, and performing anorectal patient information arrangement comprises the following steps: receiving regression analysis anorectal patient information, and identifying data to be analyzed in the regression analysis anorectal patient information through a target analysis thread; reading the data to be analyzed to generate anorectal patient information to be analyzed; and inputting the anorectal patient information to be analyzed into a configured first artificial intelligent thread, and extracting the description knowledge information after all convolutions to carry out anorectal patient information arrangement.
Further, the step of extracting the description knowledge information after all convolutions to carry out anorectal patient information arrangement comprises the following steps: extracting description knowledge information of a preset layer after all convolutions; determining a plurality of labels to which the descriptive knowledge information belongs; obtaining target anorectal patient information with a preset number of sharing coefficients with the descriptive knowledge information under each label distributed from large to small; respectively inputting the preset number of target anorectal patient information under each label into the configured first artificial intelligent thread, and extracting the description knowledge information of a preset layer after all the preset number of target anorectal patient information under each label are convolved; calculating a fusion value of difference information between the description knowledge information of each target anorectal patient information under the same label and the description knowledge information of the anorectal patient information to be analyzed; and determining the label with the smallest fusion value as a target label, and obtaining target anorectal patient information with the smallest difference information under the target label as an anorectal patient information arrangement result.
Further, the step of calculating a fusion value of difference information between the descriptive knowledge information of each target anorectal patient information and the descriptive knowledge information of the anorectal patient information to be analyzed under the same label includes: calculating difference information between the description knowledge information of each target anorectal patient information under the same label and the description knowledge information of the anorectal patient information to be analyzed; distributing the information of each target anorectal patient under the same label according to the sequence from small to large of the difference information; weighting the difference information of each target anorectal patient information under the same label according to the distribution condition; and calculating the fusion value of the difference information of each target anorectal patient information under the same label after the weighting treatment.
In a second aspect, an artificial intelligence based anorectal patient information management system is provided comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute the computer program to implement the method as described above.
According to the anorectal patient information arrangement method and system based on the artificial intelligence, the anorectal patient information, the carried item catalogue and the coverage catalogue are input into a first artificial intelligence thread and a second artificial intelligence thread respectively for configuration; obtaining a comparison result between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread; debugging thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread according to the comparison result to obtain the configured first artificial intelligence thread and second artificial intelligence thread; and receiving anorectal patient information to be analyzed, and extracting description knowledge information of the anorectal patient information to be analyzed through the configured first artificial intelligent thread to sort the anorectal patient information. Therefore, the multi-catalog configuration is carried out on the two threads through the covering catalog between the anorectal patient information with similar item catalog and anorectal patient information description knowledge and the anorectal patient information configuration, the thread coefficients of the two threads are debugged according to the comparison result, and the working efficiency of the configured threads is improved, so that the information arrangement efficiency is improved, and related information can be quickly and reliably inquired when the anorectal patient information is required to be inquired later.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered limiting the scope, and that other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of an anorectal patient information sorting method based on artificial intelligence according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.
Referring to fig. 1, an anorectal patient information sorting method based on artificial intelligence is shown, which may include the following technical solutions described in steps 101-104.
In step 101, the anorectal patient information, the carried item catalog and the coverage catalog are respectively input into a first artificial intelligence thread and a second artificial intelligence thread for configuration, and the coverage catalog is used for calibrating the anorectal patient information with the anorectal patient information description knowledge sharing coefficient larger than a preset target value.
Further, descriptive knowledge may be understood as a feature. The item directory may be understood as an object identification.
For example, anorectal patient information may be obtained from an anorectal examination apparatus.
Artificial intelligence (Artificial Intelligence, AI) is a theory, method, technique, and application system that simulates, extends, and extends human intelligence using a digital computer or a machine controlled by a digital computer, perceives the environment, obtains knowledge, and uses the knowledge to obtain optimal results. In other words, artificial intelligence is an integrated technology of computer science that attempts to understand the essence of intelligence and to produce a new intelligent machine that can react in a similar manner to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, makes the machines carry the functions of perception, reasoning and decision.
The artificial intelligence technology is a comprehensive subject, and relates to the technology with wide fields, namely the technology with a hardware level and the technology with a software level. Artificial intelligence infrastructure technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation/interaction systems, mechatronics, and the like. The artificial intelligence software technology mainly comprises a computer vision technology, a voice processing technology, a natural language processing technology, machine learning/deep learning and other directions.
The embodiment of the application applies a multi-catalog classification technology, namely, the information of the anorectal patient can be configured to carry one or two catalogs, and the first artificial intelligent thread can be an artificial intelligent thread with a deeper thread layer number and a narrower thread channel.
Furthermore, the anorectal patient information, the carried item catalogue and the coverage catalogue are respectively input into the first artificial intelligence thread and the second artificial intelligence thread for configuration, and the coverage catalogue is also introduced on the premise of the item catalogue, so that the first artificial intelligence thread and the second artificial intelligence thread after learning can learn the ability of identifying item types configuring anorectal patient information, and the description knowledge relevance between similar anorectal patient information under the same label can be enhanced.
In one possible implementation, the steps of inputting the anorectal patient information, the carried item catalog and the coverage catalog into the first artificial intelligence thread and the second artificial intelligence thread respectively for configuration may include the following.
(1) And carrying out association, similarity, interaction degree and/or conversion debugging treatment on the information of the configured anorectal patients.
(2) And respectively inputting the debugged and processed anorectal patient information, the carried item catalogue and the covering catalogue into a first artificial intelligent thread and a second artificial intelligent thread for configuration.
The method comprises the steps of carrying out random degree association, similarity, interaction degree and conversion debugging on information of the configured anorectal patient, enhancing the richness of a configuration set, and respectively inputting the information of the configured anorectal patient, the carried item catalog and the covering catalog into a first artificial intelligent thread and a second artificial intelligent thread for configuration after the debugging processing, so that the robustness of the artificial intelligent thread can be enhanced.
In step 102, a comparison between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread is obtained.
Because the thread structures of the first artificial intelligence thread and the second artificial intelligence thread are inconsistent, the core information describing knowledge extraction is different, the embodiment of the application can draw the advantages of the first artificial intelligence thread and the second artificial intelligence thread, namely, the comparison result formed between the regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread for the same configuration anorectal patient information is obtained, the lower the comparison result is, the closer the regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread is explained, the higher the comparison result is, and the thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread can be regulated and optimized through the comparison result.
In one possible implementation, the step of obtaining a comparison between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread may include: and calculating a comparison result between regression analysis information of the first artificial intelligent thread and the second artificial intelligent thread through a comparison result calculation formula, and building a quantitative evaluation model corresponding to the comparison result.
Illustratively, the quantitative evaluation model may be understood as a divergence loss function.
In step 103, the thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread are debugged according to the comparison result, so that the configured first artificial intelligence thread and second artificial intelligence thread are obtained.
In order to enable the learning opponent models of the first artificial intelligence thread and the second artificial intelligence thread to debug thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread according to comparison results in a reverse conduction mode, the first artificial intelligence thread and the second artificial intelligence thread can load the core information describing the knowledge extraction to the second artificial intelligence thread, and similarly, the second artificial intelligence thread loads the core information describing the knowledge extraction to the first artificial intelligence thread.
Further, a comparison result formed between the regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread after the thread coefficient debugging can be continuously obtained, and the first artificial intelligence thread and the second artificial intelligence thread can mutually describe knowledge extraction learning due to the fact that the thread coefficient debugging is carried out before, and the comparison result becomes smaller, so that the comparison result becomes smaller and smaller until convergence, namely, the mutual learning of the first artificial intelligence thread and the second artificial intelligence thread is achieved, the configured first artificial intelligence thread and second artificial intelligence thread are obtained, so that the configured first artificial intelligence thread not only processes the details of anorectal patient information more accurately, but also carries better description knowledge extraction capability due to the fact that core information of the second artificial intelligence thread is learned, and the description knowledge relevance between similar anorectal patient information under the same label can be better determined on the premise that anorectal patient information can be identified through multi-catalog configuration.
In one possible implementation embodiment, the step of debugging the thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread according to the comparison result to obtain the configured first artificial intelligence thread and second artificial intelligence thread may include the following.
(1) And integrating and configuring the quantitative evaluation model by combining with an original evaluation index model of the first artificial intelligent thread to obtain the configured first artificial intelligent thread.
(2) And integrating and configuring the quantitative evaluation model by combining with an original evaluation index model of the second artificial intelligence thread to obtain the configured second artificial intelligence thread.
The quantitative evaluation model is combined with the original evaluation index model of the first artificial intelligent thread to conduct integrated configuration, so that the original evaluation index model of the first artificial intelligent thread can be combined with the quantitative evaluation model to conduct integrated configuration, namely, the first artificial intelligent thread can continuously learn core information of the second artificial intelligent thread under a normal configuration state until the original evaluation index model and the quantitative evaluation model are converged at the same time, and the configured first artificial intelligent thread is obtained.
Furthermore, the quantitative evaluation model is combined with the original evaluation index model of the second artificial intelligent thread to carry out integrated configuration, so that the original evaluation index model of the second artificial intelligent thread can be combined with the quantitative evaluation model to carry out integrated configuration, namely, the second artificial intelligent thread can continuously learn the core information of the first artificial intelligent thread under the normal configuration state until the original evaluation index model and the quantitative evaluation model are converged at the same time, and the configured second artificial intelligent thread is obtained.
In step 104, anorectal patient information to be analyzed is received, and description knowledge information of the anorectal patient information to be analyzed is extracted through the configured first artificial intelligent thread to carry out anorectal patient information arrangement.
After the first artificial intelligence thread and the second artificial intelligence thread are configured, regression analysis anorectal patient information uploaded by a user can be received, the regression analysis anorectal patient information can cover data to be analyzed, and the data to be analyzed can be read to generate anorectal patient information to be analyzed.
In order to solve the technical problem, the description knowledge information of the anorectal patient information to be analyzed can be extracted through the first artificial intelligent thread after the multi-catalog configuration, and the description knowledge information is different from the description knowledge information in the prior art, because the configuration covering the catalog is introduced, the target anorectal patient information under the same label can be better distinguished, and the condition that the anorectal patient information is arranged abnormally due to label selection errors is avoided.
In one possible implementation manner, the step of receiving anorectal patient information to be analyzed, extracting description knowledge information of the anorectal patient information to be analyzed through the configured first artificial intelligence thread, and performing anorectal patient information arrangement may include the following.
(1) And receiving regression analysis anorectal patient information, and identifying data to be analyzed in the regression analysis anorectal patient information through a target analysis thread.
(2) And reading the data to be analyzed to generate anorectal patient information to be analyzed.
(3) And inputting the anorectal patient information to be analyzed into a configured first artificial intelligent thread, and extracting the description knowledge information after all convolutions to carry out anorectal patient information arrangement.
The method comprises the steps of receiving regression analysis anorectal patient information, wherein the regression analysis anorectal patient information can be anorectal patient information which is uploaded by a user and covers data to be analyzed, identifying the data to be analyzed in the regression analysis anorectal patient information through a target analysis thread, operating the data to be analyzed, reading a part of the data to be analyzed, and generating the anorectal patient information to be analyzed.
Further, inputting the anorectal patient information to be analyzed into a configured first artificial intelligent thread, extracting description knowledge information after all convolutions, calculating description knowledge information of the anterior several anorectal patient information in each label through the configured first artificial intelligent thread according to the description knowledge information from the anterior several anorectal patient information most similar under each label in a background library, calculating a difference fusion value between the description knowledge information of the anterior several anorectal patient information in each label and the description knowledge information of the anorectal patient information to be analyzed, determining the label with the lowest difference fusion value as a tidying label, and determining the anorectal patient information with the smallest difference in the tidying label as tidying anorectal patient information for display.
In one possible implementation, the step of extracting the descriptive knowledge information after all convolutions for anorectal patient information arrangement may include the following.
(1.1) extracting descriptive knowledge information of a preset layer after all convolutions.
(1.2) determining a plurality of labels to which the descriptive knowledge information belongs.
(1.3) obtaining target anorectal patient information with a preset number under each tag of which the sharing coefficient with the descriptive knowledge information is distributed from large to small.
And (1.4) respectively inputting the preset number of target anorectal patient information under each label into the configured first artificial intelligent thread, and extracting the descriptive knowledge information of the preset layer after all convolution of the preset number of target anorectal patient information under each label.
And (1.5) calculating a fusion value of difference information between the description knowledge information of each target anorectal patient information under the same label and the description knowledge information of the anorectal patient information to be analyzed.
And (1.6) determining the label with the smallest fusion value as a target label, and obtaining target anorectal patient information with the smallest difference information under the target label as an anorectal patient information arrangement result.
The method comprises the steps of extracting description knowledge information of a preset layer after all convolutions are extracted through a configured first artificial intelligence thread, and determining a plurality of labels related to the description knowledge information, namely determining a plurality of labels to which the description knowledge information most probably belongs.
Furthermore, the preset number of target anorectal patient information with the sharing coefficient distributed from large to small is arranged in each label according to the description knowledge information, the preset number of target anorectal patient information under each label is respectively input into the configured first artificial intelligent thread, and the description knowledge information of the preset layer after all convolution of the preset number of target anorectal patient information under each label is extracted. Therefore, the fusion value of the difference information between the description knowledge information of each target anorectal patient information under the same label and the description knowledge information of the anorectal patient information to be analyzed is calculated, the fusion value can reflect the relevance between the anorectal patient information to be analyzed and each label, the label with the smallest fusion value is determined to be the target label with the largest relevance, and the target anorectal patient information with the smallest difference information under the target label is obtained to serve as an anorectal patient information arrangement result, so that the approaching degree of a plurality of labels is distributed and compared when anorectal patient information arrangement is carried out, the target labels can be more accurately arranged, and the optimal anorectal patient information can be found.
As can be seen from the foregoing, in the embodiment of the present application, the information of the anorectal patient, the item catalog carried by the anorectal patient, and the coverage catalog are respectively input into the first artificial intelligence thread and the second artificial intelligence thread for configuration; obtaining a comparison result between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread; debugging thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread according to the comparison result to obtain the configured first artificial intelligence thread and second artificial intelligence thread; and receiving anorectal patient information to be analyzed, and extracting description knowledge information of the anorectal patient information to be analyzed through the configured first artificial intelligent thread to sort the anorectal patient information. Therefore, the multi-catalog configuration is carried out on the two threads through the covering catalog between the anorectal patient information with similar item catalog and anorectal patient information description knowledge and the anorectal patient information configuration, the thread coefficients of the two threads are debugged according to the comparison result, and the working efficiency of the configured threads is improved, so that the information arrangement efficiency is improved, and related information can be quickly and reliably inquired when the anorectal patient information is required to be inquired later.
According to the anorectal patient information arrangement method based on artificial intelligence. The method flow may include the following.
In step 201, anorectal patient information is obtained and preset anorectal patient information corresponding to each item category is determined.
Wherein, a large amount of configured anorectal patient information can be obtained, and the configured anorectal patient information carries a matter catalog.
In step 202, anorectal patient information description knowledge of preset anorectal patient information corresponding to each item catalog type is extracted, anorectal patient information description knowledge of preset anorectal patient information corresponding to each item catalog type is clustered through a clustering function, the preset anorectal patient information with the anorectal patient information description knowledge sharing coefficient larger than a preset target value is clustered, and a clustered coverage catalog of the preset anorectal patient information is generated.
In step 203, association, similarity, interaction degree and/or conversion are/is performed on the information of the anorectal patient, and the information of the anorectal patient after the adjustment, the item catalog carried by the information and the coverage catalog are respectively input into the first artificial intelligence thread and the second artificial intelligence thread for configuration.
In step 204, a comparison result between the regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread is calculated by a comparison result calculation formula, and a quantitative evaluation model corresponding to the comparison result is built.
In step 205, the quantized evaluation model is integrated with the original evaluation index model of the first artificial intelligence thread to obtain a configured first artificial intelligence thread, and the quantized evaluation model is integrated with the original evaluation index model of the second artificial intelligence thread to obtain a configured second artificial intelligence thread.
In step 206, regression analysis anorectal patient information is received, data to be analyzed in the regression analysis anorectal patient information is identified through a target analysis thread, the data to be analyzed is read, and the anorectal patient information to be analyzed is generated.
In step 207, the anorectal patient information to be analyzed is input into the configured first artificial intelligent thread, the description knowledge information of the preset layer after all convolutions is extracted, and a plurality of labels to which the description knowledge information belongs are determined.
In step 208, the target anorectal patient information with the preset number under each label with the shared coefficient distributed from large to small is obtained, the target anorectal patient information with the preset number under each label is respectively input into the configured first artificial intelligent thread, and the description knowledge information of the preset layer after all convolution of the target anorectal patient information with the preset number under each label is extracted.
In step 209, calculating difference information between the description knowledge information of each target anorectal patient information under the same label and the description knowledge information of the anorectal patient information to be analyzed, distributing each target anorectal patient information under the same label according to the order of the difference information from small to large, weighting the difference information of each target anorectal patient information under the same label according to the distribution condition, and calculating a fusion value of the difference information of each target anorectal patient information under the same label after the weighting.
The difference information between the description knowledge information of each target anorectal patient information under the same label and the description knowledge information of the anorectal patient information to be analyzed is calculated, the difference information can be European difference or cosine difference, the smaller the difference information is, the closer the difference information is, the larger the difference information is, the difference between the difference information is, and the distribution of each target anorectal patient information under the same label can be carried out according to the sequence of the difference information from small to large.
Furthermore, the difference information of the anorectal patient information of each target under each label can be weighted according to the distribution condition, and because the configured first artificial intelligent thread carries the capability of distinguishing the similar anorectal patient information under the same label, the difference value of the anorectal patient information to be analyzed and the similar anorectal patient information under the most arranged label can be obviously smaller than the difference value of the anorectal patient information under other labels, and in order to enlarge the distinction of the difference values of the different labels, the difference information of the anorectal patient information of each target under the same label can be weighted according to the ranking sequence.
In step 210, a fusion value of the difference information of each target anorectal patient information under the same label after the weighting processing is calculated, the label with the smallest fusion value is determined as the target label, and the target anorectal patient information with the smallest difference information under the target label is obtained as an anorectal patient information arrangement result.
The method comprises the steps of calculating a fusion value of difference information of each target anorectal patient information under the same label after weighting treatment, reflecting the arrangement degree of the anorectal patient information to be analyzed and each label, determining the label with the smallest fusion value as the most arranged target label, determining the shoe label with the smallest fusion value as the target label, and obtaining the target anorectal patient information with the smallest difference information under the target label as an anorectal patient information arrangement result. Therefore, through the multi-catalog configuration mode and the label arrangement mode, the target label to which the anorectal patient information to be analyzed belongs can be accurately determined, and further, an anorectal patient information arrangement result with high accuracy rate is generated.
As can be seen from the foregoing, in the embodiment of the present application, the information of the anorectal patient, the item catalog carried by the anorectal patient, and the coverage catalog are respectively input into the first artificial intelligence thread and the second artificial intelligence thread for configuration; obtaining a comparison result between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread; debugging thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread according to the comparison result to obtain the configured first artificial intelligence thread and second artificial intelligence thread; and receiving anorectal patient information to be analyzed, and extracting description knowledge information of the anorectal patient information to be analyzed through the configured first artificial intelligent thread to sort the anorectal patient information. Therefore, the multi-catalog configuration is carried out on the two threads through the covering catalog between the anorectal patient information with similar item catalog and anorectal patient information description knowledge and the anorectal patient information configuration, the thread coefficients of the two threads are debugged according to the comparison result, and the working efficiency of the configured threads is improved, so that the information arrangement efficiency is improved, and related information can be quickly and reliably inquired when the anorectal patient information is required to be inquired later.
On the basis, an anorectal patient information arranging device based on artificial intelligence is provided, and the device comprises:
the thread configuration module is used for inputting the anorectal patient information, the carried item catalogue and the coverage catalogue into the first artificial intelligent thread and the second artificial intelligent thread respectively for configuration, and the coverage catalogue is used for calibrating the anorectal patient information of which the anorectal patient information description knowledge sharing coefficient is larger than a preset target value;
the result comparison module is used for obtaining a comparison result between regression analysis information of the first artificial intelligent thread and the second artificial intelligent thread;
the coefficient debugging module is used for debugging the thread coefficients of the first artificial intelligent thread and the second artificial intelligent thread by combining the comparison result to obtain the configured first artificial intelligent thread and second artificial intelligent thread; the second artificial intelligence thread is used for loading core information of the second artificial intelligence thread for description knowledge extraction to the first artificial intelligence thread so as to realize mutual description knowledge extraction learning of the first artificial intelligence thread and the second artificial intelligence thread, and the configured first artificial intelligence thread and second artificial intelligence thread are obtained, so that the configured first artificial intelligence thread carries the core information of the second artificial intelligence thread for description knowledge extraction;
the information arrangement module is used for receiving anorectal patient information to be analyzed, extracting description knowledge information of the anorectal patient information to be analyzed through the configured first artificial intelligent thread, and arranging the anorectal patient information.
On the above basis, an artificial intelligence based anorectal patient information management system is shown comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute it to implement the method described above.
On the basis of the above, there is also provided a computer readable storage medium on which a computer program stored which, when run, implements the above method.
In summary, based on the above scheme, the anorectal patient information, the carried item catalog and the coverage catalog are respectively input into the first artificial intelligence thread and the second artificial intelligence thread for configuration; obtaining a comparison result between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread; debugging thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread according to the comparison result to obtain the configured first artificial intelligence thread and second artificial intelligence thread; and receiving anorectal patient information to be analyzed, and extracting description knowledge information of the anorectal patient information to be analyzed through the configured first artificial intelligent thread to sort the anorectal patient information. Therefore, the multi-catalog configuration is carried out on the two threads through the covering catalog between the anorectal patient information with similar item catalog and anorectal patient information description knowledge and the anorectal patient information configuration, the thread coefficients of the two threads are debugged according to the comparison result, and the working efficiency of the configured threads is improved, so that the information arrangement efficiency is improved, and related information can be quickly and reliably inquired when the anorectal patient information is required to be inquired later.
It should be appreciated that the systems and modules thereof shown above may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only with hardware circuitry, such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software, such as executed by various types of processors, and with a combination of the above hardware circuitry and software (e.g., firmware).
It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.
Claims (10)
1. An anorectal patient information arrangement method based on artificial intelligence, which is characterized by comprising the following steps:
respectively inputting configuration anorectal patient information, a carried item catalog and a covering catalog into a first artificial intelligent thread and a second artificial intelligent thread for configuration, wherein the covering catalog is used for calibrating configuration anorectal patient information with an anorectal patient information description knowledge sharing coefficient larger than a preset target value;
obtaining a comparison result between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread;
debugging thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread according to the comparison result to obtain a configured first artificial intelligence thread and second artificial intelligence thread; the second artificial intelligence thread is used for loading core information of the second artificial intelligence thread for description knowledge extraction to the first artificial intelligence thread so as to realize mutual description knowledge extraction learning of the first artificial intelligence thread and the second artificial intelligence thread, and the configured first artificial intelligence thread and second artificial intelligence thread are obtained, so that the configured first artificial intelligence thread carries the core information of the second artificial intelligence thread for description knowledge extraction;
and receiving anorectal patient information to be analyzed, and extracting description knowledge information of the anorectal patient information to be analyzed through a configured first artificial intelligent thread to carry out anorectal patient information arrangement.
2. The artificial intelligence based anorectal patient information management method according to claim 1, further comprising:
obtaining anorectal patient configuration information, wherein the anorectal patient configuration information carries a matter catalog; determining preset anorectal patient information corresponding to each item catalog type;
clustering preset anorectal patient information corresponding to different item catalogue types, and clustering preset anorectal patient information with anorectal patient information description knowledge sharing coefficients larger than preset target values;
and generating a covering catalog of clustered preset anorectal patient information.
3. The method for organizing anorectal patient information based on artificial intelligence according to claim 2, wherein the step of clustering the predetermined anorectal patient information corresponding to the different item catalog categories, and clustering the predetermined anorectal patient information having the anorectal patient information description knowledge sharing coefficient larger than the predetermined target value, comprises:
extracting anorectal patient information description knowledge of preset anorectal patient information corresponding to each item catalog type;
clustering anorectal patient information description knowledge which corresponds to each item catalog type and is preset with anorectal patient information through a clustering function;
clustering the preset anorectal patient information with the anorectal patient information description knowledge sharing coefficient larger than the preset target value.
4. The method for organizing anorectal patient information based on artificial intelligence according to claim 1, wherein the step of inputting the anorectal patient information to be configured, the item catalog carried by the anorectal patient information, and the coverage catalog into the first artificial intelligence thread and the second artificial intelligence thread, respectively, for configuration comprises:
performing association, similarity, interaction degree and/or conversion debugging treatment on the information of the configured anorectal patients;
and respectively inputting the debugged and processed anorectal patient information, the carried item catalogue and the covering catalogue into a first artificial intelligent thread and a second artificial intelligent thread for configuration.
5. The method for organizing anorectal patient information based on artificial intelligence according to claim 4, wherein the step of obtaining a comparison result between regression analysis information of the first artificial intelligence thread and the second artificial intelligence thread comprises: and calculating a comparison result between regression analysis information of the first artificial intelligent thread and the second artificial intelligent thread through a comparison result calculation formula, and building a quantitative evaluation model corresponding to the comparison result.
6. The anorectal patient information management method based on artificial intelligence according to claim 5, wherein the step of debugging thread coefficients of the first artificial intelligence thread and the second artificial intelligence thread in combination with the comparison result to obtain the configured first artificial intelligence thread and second artificial intelligence thread comprises the steps of:
integrating and configuring the quantitative evaluation model by combining with an original evaluation index model of the first artificial intelligent thread to obtain a configured first artificial intelligent thread;
and integrating and configuring the quantitative evaluation model by combining with an original evaluation index model of the second artificial intelligent thread to obtain the configured second artificial intelligent thread.
7. The method for arranging anorectal patient information based on artificial intelligence according to claim 4, wherein the step of receiving anorectal patient information to be analyzed, extracting descriptive knowledge information of the anorectal patient information to be analyzed through a configured first artificial intelligence thread, and arranging anorectal patient information comprises the steps of:
receiving regression analysis anorectal patient information, and identifying data to be analyzed in the regression analysis anorectal patient information through a target analysis thread;
reading the data to be analyzed to generate anorectal patient information to be analyzed;
and inputting the anorectal patient information to be analyzed into a configured first artificial intelligent thread, and extracting the description knowledge information after all convolutions to carry out anorectal patient information arrangement.
8. The anorectal patient information management method based on artificial intelligence according to claim 7, wherein the step of extracting the descriptive knowledge information after all convolutions to perform anorectal patient information management comprises:
extracting description knowledge information of a preset layer after all convolutions;
determining a plurality of labels to which the descriptive knowledge information belongs; obtaining target anorectal patient information with a preset number of sharing coefficients with the descriptive knowledge information under each label distributed from large to small; respectively inputting the preset number of target anorectal patient information under each label into the configured first artificial intelligent thread, and extracting the description knowledge information of a preset layer after all the preset number of target anorectal patient information under each label are convolved;
calculating a fusion value of difference information between the description knowledge information of each target anorectal patient information under the same label and the description knowledge information of the anorectal patient information to be analyzed;
and determining the label with the smallest fusion value as a target label, and obtaining target anorectal patient information with the smallest difference information under the target label as an anorectal patient information arrangement result.
9. The method for arranging anorectal patient information based on artificial intelligence according to claim 8, wherein the step of calculating a fusion value of the difference information between the descriptive knowledge information of each target anorectal patient information under the same label and the descriptive knowledge information of the anorectal patient information to be analyzed comprises:
calculating difference information between the description knowledge information of each target anorectal patient information under the same label and the description knowledge information of the anorectal patient information to be analyzed;
distributing the information of each target anorectal patient under the same label according to the sequence from small to large of the difference information;
weighting the difference information of each target anorectal patient information under the same label according to the distribution condition;
and calculating the fusion value of the difference information of each target anorectal patient information under the same label after the weighting treatment.
10. An anorectal patient information management system based on artificial intelligence, comprising a processor and a memory in communication with each other, the processor being adapted to read a computer program from the memory and execute it to implement the method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410048770.7A CN117558393B (en) | 2024-01-12 | 2024-01-12 | Anorectal patient information arrangement method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410048770.7A CN117558393B (en) | 2024-01-12 | 2024-01-12 | Anorectal patient information arrangement method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117558393A true CN117558393A (en) | 2024-02-13 |
| CN117558393B CN117558393B (en) | 2024-03-19 |
Family
ID=89820945
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410048770.7A Active CN117558393B (en) | 2024-01-12 | 2024-01-12 | Anorectal patient information arrangement method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117558393B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114664458A (en) * | 2022-04-26 | 2022-06-24 | 平安科技（深圳）有限公司 | Patient classification device, computer device and storage medium |
| CN115269865A (en) * | 2022-07-01 | 2022-11-01 | 浙江华巽科技有限公司 | Knowledge graph construction method for auxiliary diagnosis |
| CN115358408A (en) * | 2022-07-22 | 2022-11-18 | 华南师范大学 | Intelligent evolution method based on man-machine hybrid intelligence and medical health model as service platform |
| CN115687618A (en) * | 2022-10-17 | 2023-02-03 | 樊勇 | User intention analysis method and system based on artificial intelligence |
| CN116028689A (en) * | 2023-03-28 | 2023-04-28 | 四川赛尔斯科技有限公司 | Data management and control method and system based on women and child service platform |
| US20230135706A1 (en) * | 2021-11-01 | 2023-05-04 | International Business Machines Corporation | Combined Deep Learning and Knowledge Driven Reasoning for Artificial Intelligence Classification |
| CN116737975A (en) * | 2023-05-15 | 2023-09-12 | 重庆海辉星科技有限公司 | Public health data query method and system applied to image analysis |
| CN116910172A (en) * | 2023-07-17 | 2023-10-20 | 杭州卓深科技有限公司 | Follow-up table generation method and system based on artificial intelligence |
| CN117238437A (en) * | 2023-09-28 | 2023-12-15 | 南京中医药大学 | Knowledge graph-based disease diagnosis auxiliary method and system |
| CN117392470A (en) * | 2023-12-11 | 2024-01-12 | 安徽中医药大学 | Fundus image multi-label classification model generation method and system based on knowledge graph |
-
2024
- 2024-01-12 CN CN202410048770.7A patent/CN117558393B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20230135706A1 (en) * | 2021-11-01 | 2023-05-04 | International Business Machines Corporation | Combined Deep Learning and Knowledge Driven Reasoning for Artificial Intelligence Classification |
| CN114664458A (en) * | 2022-04-26 | 2022-06-24 | 平安科技（深圳）有限公司 | Patient classification device, computer device and storage medium |
| CN115269865A (en) * | 2022-07-01 | 2022-11-01 | 浙江华巽科技有限公司 | Knowledge graph construction method for auxiliary diagnosis |
| CN115358408A (en) * | 2022-07-22 | 2022-11-18 | 华南师范大学 | Intelligent evolution method based on man-machine hybrid intelligence and medical health model as service platform |
| CN115687618A (en) * | 2022-10-17 | 2023-02-03 | 樊勇 | User intention analysis method and system based on artificial intelligence |
| CN116028689A (en) * | 2023-03-28 | 2023-04-28 | 四川赛尔斯科技有限公司 | Data management and control method and system based on women and child service platform |
| CN116737975A (en) * | 2023-05-15 | 2023-09-12 | 重庆海辉星科技有限公司 | Public health data query method and system applied to image analysis |
| CN116910172A (en) * | 2023-07-17 | 2023-10-20 | 杭州卓深科技有限公司 | Follow-up table generation method and system based on artificial intelligence |
| CN117238437A (en) * | 2023-09-28 | 2023-12-15 | 南京中医药大学 | Knowledge graph-based disease diagnosis auxiliary method and system |
| CN117392470A (en) * | 2023-12-11 | 2024-01-12 | 安徽中医药大学 | Fundus image multi-label classification model generation method and system based on knowledge graph |
Non-Patent Citations (3)
| Title |
|---|
| KNOPP MICHELLE I;WARM ERIC J;WEBER DANIELLE;KELLEHER MATTHEW;KINNEAR BENJAMIN;SCHUMACHER DANIEL J;SANTEN SALLY A;MENDONÇA ENEIDA;T: "AI-Enabled Medical Education: Threads of Change, Promising Futures, and Risky Realities Across Four Potential Future Worlds.", 《JMIR MEDICAL EDUCATION》, vol. 9, 25 December 2023 (2023-12-25), pages 50373 * |
| 孙郑煜;鄂海红;宋美娜;王宁;: "基于大数据技术的医学知识图谱构建方法", 《软件》, no. 01, 15 January 2020 (2020-01-15), pages 13 - 17 * |
| 沈军权;徐玉;: "医护合作在肛肠外科患者情绪管理中的效果研究", 医院管理论坛, no. 05, 20 May 2017 (2017-05-20), pages 26 - 28 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117558393B (en) | 2024-03-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20230386024A1 (en) | Systems and methods for image preprocessing | |
| CN111488137B (en) | Code searching method based on common attention characterization learning | |
| US20180260531A1 (en) | Training random decision trees for sensor data processing | |
| US20210342212A1 (en) | Method and system for identifying root causes | |
| CN109817339B (en) | Patient grouping method and device based on big data | |
| CN111008640A (en) | Image recognition model training and image recognition method, device, terminal and medium | |
| JP2022543954A (en) | KEYPOINT DETECTION METHOD, KEYPOINT DETECTION DEVICE, ELECTRONIC DEVICE, AND STORAGE MEDIUM | |
| CN110210625A (en) | Modeling method, device, computer equipment and storage medium based on transfer learning | |
| Norris | Machine Learning with the Raspberry Pi | |
| CN113723618B (en) | SHAP optimization method, equipment and medium | |
| WO2021223449A1 (en) | Method and apparatus for acquiring flora marker, terminal, and storage medium | |
| CN115512823A (en) | Equipment exception handling method and device, exception handling system and equipment | |
| CN112420125A (en) | Molecular attribute prediction method and device, intelligent equipment and terminal | |
| US11164658B2 (en) | Identifying salient features for instances of data | |
| Babu et al. | Implementation of partitional clustering on ILPD dataset to predict liver disorders | |
| Hum et al. | The development of skin lesion detection application in smart handheld devices using deep neural networks | |
| CN117558393B (en) | Anorectal patient information arrangement method and system based on artificial intelligence | |
| CN117235582A (en) | Multi-granularity information processing method and device based on electronic medical record | |
| Caldeira et al. | Image classification benchmark (ICB) | |
| US20230223132A1 (en) | Methods and systems for nutritional recommendation using artificial intelligence analysis of immune impacts | |
| US11416776B2 (en) | Method of and system for identifying and enumerating cross-body degradations | |
| US11797775B1 (en) | Determining emebedding vectors for an unmapped content item using embedding inferenece | |
| Cai et al. | Application and research progress of machine learning in Bioinformatics | |
| Nugroho et al. | Systematic literature review of dermoscopic pigmented skin lesions classification using convolutional neural network (CNN) | |
| Deprez et al. | Machine Learning for Biomedical Applications: With Scikit-Learn and PyTorch |
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 |