CN117238532A - Intelligent follow-up method and device - Google Patents
Intelligent follow-up method and device Download PDFInfo
- Publication number
- CN117238532A CN117238532A CN202311490206.2A CN202311490206A CN117238532A CN 117238532 A CN117238532 A CN 117238532A CN 202311490206 A CN202311490206 A CN 202311490206A CN 117238532 A CN117238532 A CN 117238532A
- Authority
- CN
- China
- Prior art keywords
- follow
- target
- risk level
- level
- preset
- 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
- 238000000034 method Methods 0.000 title claims abstract description 57
- 238000013145 classification model Methods 0.000 claims abstract description 85
- 201000010099 disease Diseases 0.000 claims abstract description 45
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 45
- 238000003745 diagnosis Methods 0.000 claims abstract description 36
- 238000013507 mapping Methods 0.000 claims abstract description 34
- 238000004364 calculation method Methods 0.000 claims abstract description 23
- 230000003993 interaction Effects 0.000 claims description 72
- 210000002784 stomach Anatomy 0.000 claims description 62
- 206010003694 Atrophy Diseases 0.000 claims description 42
- 230000037444 atrophy Effects 0.000 claims description 42
- 208000005718 Stomach Neoplasms Diseases 0.000 claims description 19
- 206010017758 gastric cancer Diseases 0.000 claims description 19
- 201000011549 stomach cancer Diseases 0.000 claims description 19
- 210000003238 esophagus Anatomy 0.000 claims description 15
- 238000012552 review Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 7
- 206010054949 Metaplasia Diseases 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 5
- 238000012790 confirmation Methods 0.000 claims description 5
- 230000000977 initiatory effect Effects 0.000 claims description 4
- 230000000968 intestinal effect Effects 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 description 14
- 238000013473 artificial intelligence Methods 0.000 description 11
- 230000006870 function Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 8
- 238000013135 deep learning Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000001839 endoscopy Methods 0.000 description 3
- 210000001035 gastrointestinal tract Anatomy 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000002360 preparation method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000013519 translation Methods 0.000 description 2
- 206010058314 Dysplasia Diseases 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013479 data entry Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 230000001079 digestive effect Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000002496 gastric effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000002980 postoperative effect Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000001356 surgical procedure Methods 0.000 description 1
- 238000003786 synthesis reaction Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application discloses an intelligent follow-up method and device, which are used for determining the disease part category of a target patient based on disease label information; respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk level systems; determining each follow-up time interval corresponding to each target risk level based on the time mapping relation of each target risk level and the corresponding preset level to obtain at least two follow-up time intervals; determining a follow-up time plan based on the examination time of the target patient and the target follow-up time interval; when reaching an intelligent follow-up time point in the follow-up time plan, interacting with the target patient; if the target patient meets the re-diagnosis condition, determining a re-diagnosis medical resource; generating a medical resource reservation record based on the resource selection information of the target patient; the medical resource reservation record is sent to the target patient. The application can improve the follow-up efficiency.
Description
Technical Field
The application relates to the technical field of artificial intelligence, in particular to an intelligent follow-up method and device.
Background
The number of patients is large during the digestion endoscopy, the time for the endoscopy selection is relatively concentrated, the diagnosis receiving pressure of the medical center is heavy, and the satisfactory preoperative education effect is difficult to achieve. Furthermore, the procedural requirements for gut preparation tend to be complex, and patients have difficulty understanding and memorizing, especially those with low health literacy and aggressiveness. In order to achieve better preoperative announce effects of digestive endoscopy, many health announce methods such as educational manuals, cartoon vision teaching aids, educational videos, short message services, telephones, social media, and smart phone applications have been developed in recent years. The method comprises the steps of short message service, telephone, social media and the like, wherein the method needs to accurately acquire the appointment information of the patient. However, the efficiency is lower by mainly relying on manual follow-up at present.
I.e. the efficiency of the follow-up in the prior art is low.
Disclosure of Invention
The embodiment of the application provides an intelligent follow-up method and device, which can improve follow-up efficiency.
In a first aspect, the intelligent follow-up method provided by the application includes:
acquiring disease label information of a target patient;
determining a disease site category of the target patient based on the disease label information;
acquiring at least two different risk level classification models corresponding to at least two different diseased part categories under the condition that the diseased part categories of the target patient are at least two;
respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models;
determining corresponding preset level time mapping relations based on the diseased part categories corresponding to the target risk levels respectively, wherein different diseased part categories correspond to different preset level time mapping relations;
determining each follow-up time interval corresponding to each target risk level based on each target risk level and the corresponding preset level time mapping relation respectively, and obtaining at least two follow-up time intervals;
Determining the minimum value of at least two follow-up time intervals as a target follow-up time interval;
determining a follow-up time plan based on the examination time of the target patient and the target follow-up time interval, wherein the follow-up time plan includes at least one intelligent follow-up time point;
when an intelligent follow-up time point in the follow-up time plan is reached, a preset follow-up text template is called;
interacting with the target patient based on the preset follow-up text template to obtain interaction information;
judging whether the target patient meets the re-diagnosis condition or not based on the interaction information;
if the target patient meets the re-diagnosis condition, determining re-diagnosis medical resources from a preset medical resource library based on the disease part category corresponding to the target follow-up time interval;
transmitting the re-diagnosis medical resource to a target patient and acquiring resource selection information returned by the target patient;
generating a medical resource reservation record based on the resource selection information of the target patient;
and sending the medical resource reservation record to the target patient.
Optionally, the interaction with the target patient based on the preset follow-up text template to obtain interaction information includes:
Initiating a voice interaction request to the target patient;
when the target patient responds to the voice interaction request, converting the preset follow-up text template into voice follow-up data;
performing voice communication with the target patient based on the voice follow-up data to obtain voice interaction data;
converting the voice interaction data into text data to obtain the interaction information;
and when the target patient does not respond to the voice interaction request, sending the preset follow-up text template to the target patient in a short message and mail mode to obtain the interaction information fed back by the target patient.
Optionally, the performing a voice call with the target patient based on the voice follow-up data to obtain voice interaction data includes:
transmitting the voice follow-up data to the target patient;
acquiring feedback information fed back by the target patient based on the voice follow-up data;
extracting keywords from the feedback information to obtain key information;
judging whether a target answer matched with the key information exists in a preset answer library or not;
if a target answer matched with the key information exists in a preset answer library, sending the target answer to a target patient;
And ending the call when the target patient does not respond or receives a confirmation instruction of the target patient in excess of the preset time, and determining the data of the call as voice interaction data.
Optionally, the intelligent follow-up method includes:
if no target answer matched with the key information exists in the preset answer library, calling a preset text analysis model, wherein the preset text analysis model is obtained by fine tuning a preset large-scale language model;
analyzing the feedback information based on the preset text analysis model to obtain user intention;
judging whether a target answer matched with the user intention exists in the preset answer library or not;
and if a target answer matched with the user intention exists in a preset answer library, sending the target answer to a target patient.
Optionally, the at least two diseased part categories are respectively a stomach category and an esophagus category, the stomach category corresponds to the stomach risk level classification model, and the esophagus category corresponds to the esophagus risk level classification model; the target risk levels corresponding to the stomach risk level classification model are a moderate atrophy level, an intestinal metaplasia level, a high atrophy level, a low boundary unclear level, a low boundary clear level and a high stomach cancer level respectively, wherein the moderate atrophy level, the intestinal metaplasia level, the high atrophy level, the low boundary unclear level, the low boundary clear level and the high stomach cancer level are from low to high; the corresponding target risk levels of the esophageal risk level classification model are respectively a low esophageal level, a middle esophageal level and a high esophageal level, and the low esophageal level, the middle esophageal level and the high esophageal level are from low to high;
The step of respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models comprises the following steps:
performing risk level calculation on the illness state label information based on the stomach risk level classification model to obtain a target risk level corresponding to the stomach risk level classification model;
and calculating the risk level of the illness state label information based on the esophageal risk level classification model to obtain a target risk level corresponding to the esophageal risk level classification model.
Optionally, the performing risk level calculation on the condition label information based on the stomach risk level classification model to obtain a target risk level corresponding to the stomach risk level classification model includes:
respectively inputting the illness state label information into the stomach risk level classification model to obtain stomach initial risk levels, wherein the stomach initial risk levels are any one of atrophy levels, intestinal grade, stomach cancer low grade and stomach cancer high grade;
if the stomach risk level is a low stomach cancer level, obtaining a gastroscope image;
Inputting the gastroscope image into a pre-trained boundary definition detection model, and judging whether the gastroscope image is of a focus boundary definition type or not;
if the gastroscope image is a focus boundary clear type, determining a boundary clear low level as a target risk level of the stomach risk level classification model; and if the gastroscope image is not in the focus boundary clear category, determining the boundary unclear low level as the target risk level of the stomach risk level classification model.
Optionally, the intelligent follow-up method includes:
if the stomach risk level is an atrophy level, inputting the gastroscope image into a pre-trained atrophy part detection model to obtain the atrophy part in the gastroscope image;
if the atrophy part comprises all parts in the preset part set, determining the high atrophy level as a target risk level corresponding to the esophageal risk level classification model; and if the atrophy part does not comprise all parts in a preset part set, determining the moderate atrophy level as a target risk level corresponding to the esophageal risk level classification model, wherein the preset part set comprises a stomach anterior wall, a stomach posterior wall and a stomach major curve.
In a second aspect, the present application provides an intelligent follow-up device, including:
the first acquisition module is used for acquiring illness state label information of a target patient;
a first determining module for determining a disease part category of the target patient based on the disease label information;
the second acquisition module is used for acquiring at least two different risk level classification models corresponding to at least two different diseased part categories under the condition that the diseased part categories of the target patient are at least two;
the risk calculation module is used for respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models;
the third acquisition module is used for determining corresponding preset level time mapping relations based on the diseased part categories corresponding to the target risk levels respectively, wherein different diseased part categories correspond to different preset level time mapping relations;
the second determining module is used for determining each follow-up time interval corresponding to each target risk level based on each target risk level and a corresponding preset level time mapping relation respectively to obtain at least two follow-up time intervals, wherein the follow-up time intervals are reduced along with the increase of the target risk level in the preset level mapping relation;
A third determining module, configured to determine a minimum value of at least two of the follow-up time intervals as a target follow-up time interval;
a fourth determination module for determining a follow-up time plan based on the examination time of the target patient and the target follow-up time interval, wherein the follow-up time plan includes at least one intelligent follow-up time point;
the calling module is used for calling a preset follow-up character template when an intelligent follow-up time point in the follow-up time plan is reached;
the interaction module is used for interacting with the target patient based on the preset follow-up text template to obtain interaction information;
the judging module is used for judging whether the target patient meets the re-diagnosis condition or not based on the interaction information;
a fifth determining module, configured to determine a review medical resource from a preset medical resource library based on a disease part category corresponding to the target follow-up time interval if the target patient meets a review condition;
the first sending module is used for sending the re-diagnosis medical resource to a target patient and acquiring resource selection information returned by the target patient;
a generation module for generating a medical resource reservation record based on the resource selection information of the target patient;
And the second sending module is used for sending the medical resource reservation record to the target patient.
In a third aspect, the present application provides an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor is configured to execute the computer program in the memory, to implement the steps in the intelligent follow-up method provided by the present application.
In a fourth aspect, the present application provides a computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor for implementing the steps in the intelligent follow-up method provided by the present application.
In a fifth aspect, the present application provides a computer program product comprising a computer program or instructions which, when executed by a processor, implement the steps in the intelligent follow-up method provided by the present application.
In the application, compared with the related art, the disease label information of the target patient is obtained; determining the disease part category of the target patient based on the disease label information; acquiring at least two different risk level classification models corresponding to at least two different disease part categories under the condition that the disease part categories of the target patient are at least two; respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models; determining corresponding preset level time mapping relations based on the diseased part categories corresponding to the target risk levels respectively, wherein different diseased part categories correspond to different preset level time mapping relations; determining each follow-up time interval corresponding to each target risk level based on the time mapping relation of each target risk level and the corresponding preset level to obtain at least two follow-up time intervals; determining a minimum value of at least two follow-up time intervals as a target follow-up time interval; determining a follow-up time plan based on the examination time of the target patient and the target follow-up time interval, wherein the follow-up time plan includes at least one intelligent follow-up time point; when an intelligent follow-up time point in the follow-up time plan is reached, a preset follow-up text template is called; interacting with a target patient based on a preset follow-up text template to obtain interaction information; judging whether the target patient meets the re-diagnosis condition or not based on the interaction information; if the target patient meets the re-diagnosis condition, determining re-diagnosis medical resources from a preset medical resource library based on the disease part category corresponding to the target follow-up time interval; transmitting the re-diagnosis medical resource to a target patient and acquiring resource selection information returned by the target patient; generating a medical resource reservation record based on the resource selection information of the target patient; the medical resource reservation record is sent to the target patient. The application can improve the follow-up efficiency.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the description of the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic view of a scenario of an intelligent follow-up system provided by an embodiment of the present application;
FIG. 2 is a flow chart of one embodiment of an intelligent follow-up method provided by an embodiment of the present application;
FIG. 3 is a schematic diagram of a preset level time mapping relationship in one embodiment of an intelligent follow-up method according to an embodiment of the present application;
FIG. 4 is a schematic diagram of an embodiment of an intelligent follow-up device according to an embodiment of the present application;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
It should be noted that the principles of the present application are illustrated as implemented in a suitable computing environment. The following description is based on illustrative embodiments of the application and should not be taken as limiting other embodiments of the application not described in detail herein.
In the following description of the present application reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or a different subset of all possible embodiments and can be combined with each other without conflict.
In the following description of the present application, the terms "first", "second", "third" and "third" are merely used to distinguish similar objects from each other, and do not represent a particular ordering of the objects, it being understood that the "first", "second", "third" may be interchanged with a particular order or sequence, as permitted, to enable embodiments of the present application described herein to be practiced otherwise than as illustrated or described herein.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.
In order to be able to improve the follow-up efficiency, embodiments of the present application provide an intelligent follow-up method, an intelligent follow-up device, an electronic apparatus, a computer readable storage medium and a computer program product. The intelligent follow-up method can be executed by the intelligent follow-up device or electronic equipment integrated with the intelligent follow-up device.
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to fall within the scope of the application.
Referring to fig. 1, the present application further provides an intelligent follow-up system, as shown in fig. 1, where the intelligent follow-up system includes an electronic device 100, and the intelligent follow-up device provided by the present application is integrated in the electronic device 100.
The electronic device 100 may be any device with a processor and having a processing capability, such as a mobile electronic device with a processor, such as a smart phone, a tablet computer, a palm computer, a notebook computer, and a smart speaker, or a stationary electronic device with a processor, such as a desktop computer, a television, a server, and an industrial device.
In addition, the intelligent follow-up system may also include a memory 200 for storing raw data, intermediate data, and result data.
In the embodiment of the application, the memory may be a cloud memory, cloud storage (cloud storage) is a new concept which extends and develops in the concept of cloud computing, and the distributed cloud storage system (hereinafter referred to as a storage system) refers to a storage system which provides data storage and service access functions together by integrating a large number of storage devices (storage devices are also referred to as storage nodes) of different types in a network through application software or application interfaces through functions such as cluster application, grid technology, distributed storage file systems and the like.
At present, the storage method of the storage system is as follows: when creating logical volumes, each logical volume is allocated a physical storage space, which may be a disk composition of a certain storage device or of several storage devices. The client stores data on a certain logical volume, that is, the data is stored on a file system, the file system divides the data into a plurality of parts, each part is an object, the object not only contains the data but also contains additional information such as a data Identification (ID) and the like, the file system writes each object into a physical storage space of the logical volume, and the file system records storage position information of each object, so that when the client requests to access the data, the file system can enable the client to access the data according to the storage position information of each object.
The process of allocating physical storage space for the logical volume by the storage system specifically includes: physical storage space is divided into stripes in advance according to the set of capacity measures for objects stored on a logical volume (which measures tend to have a large margin with respect to the capacity of the object actually to be stored) and redundant array of independent disks (RAID, redundant Array of Independent Disk), and a logical volume can be understood as a stripe, whereby physical storage space is allocated for the logical volume.
It should be noted that, the schematic view of the scenario of the intelligent follow-up system shown in fig. 1 is only an example, and the intelligent follow-up system and scenario described in the embodiment of the present application are for more clearly describing the technical solution of the embodiment of the present application, and do not constitute a limitation on the technical solution provided by the embodiment of the present application, and those skilled in the art can know that, with the evolution of the intelligent follow-up system and the appearance of a new service scenario, the technical solution provided by the embodiment of the present application is equally applicable to similar technical problems.
The following will describe in detail. The numbers of the following examples are not intended to limit the preferred order of the examples.
Referring to fig. 2, fig. 2 is a flow chart of an embodiment of an intelligent follow-up method according to the present application, and as shown in fig. 2, the flow chart of the intelligent follow-up method according to the present application is as follows:
201. and acquiring condition label information of the target patient.
In the embodiment of the present application, the target patient may be any patient, and the disease label information may include a plurality of disease labels. Specifically, as shown in table one, the disease label may include "surgery", "ESD and ESD postoperative" "," polypectomy "," dysplasia no degree ", etc., which may be set according to the specific situation.
Table one: a plurality of condition labels in condition label information.
202. And determining the disease part category of the target patient based on the disease label information.
In the embodiment of the application, the type of the diseased part of the target patient can be stomach type or esophagus type, and the diseased part is set according to specific conditions. Specifically, keyword extraction is carried out on the illness state label information to obtain a keyword set, and if the keyword set contains a stomach, the illness part category of the target patient is determined to be a stomach category; if the key set contains 'esophagus', determining that the diseased part category of the target patient is the esophagus category.
203. And under the condition that the categories of the diseased parts of the target patient are at least two, acquiring at least two different risk level classification models corresponding to the at least two different diseased part categories.
In the case where the disease site category of the target patient is 0, follow-up is not required.
Under the condition that the categories of the diseased parts of the target patient are one, acquiring a risk level classification model corresponding to the categories of the diseased parts, and performing risk level calculation on the illness state label information based on the risk level classification model to obtain a target risk level corresponding to the risk level classification model; determining a corresponding preset level time mapping relation based on the diseased part category corresponding to the target risk level; determining a follow-up time interval corresponding to the target risk level based on the target risk level and a corresponding preset level time mapping relation to obtain a follow-up time interval; the resulting one of the follow-up time intervals is determined as the target follow-up time interval.
In the embodiment of the application, different disease part categories correspond to different risk level classification models. The risk level classification model is a pre-trained neural network model.
In a specific embodiment, the at least two diseased site categories are a stomach category corresponding to the stomach risk level classification model and an esophageal category corresponding to the esophageal risk level classification model, respectively.
Artificial intelligence (Artificial Intelligence, AI) is a theory, method, technique, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and extend human intelligence, sense the environment, acquire knowledge, and use 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 way to human intelligence. Artificial intelligence, i.e. research on design principles and implementation methods of various intelligent machines, enables the machines to have functions of sensing, 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. Artificial intelligence software technology mainly includes Machine Learning (ML) technology, wherein Deep Learning (DL) is a new research direction in Machine Learning, which is introduced into Machine Learning to make it closer to an original target, i.e., artificial intelligence. At present, deep learning is mainly applied to the fields of machine vision, natural voice processing and the like.
Deep learning is the inherent regularity and presentation hierarchy of learning sample data, and information obtained during such learning processes greatly aids in interpretation of data such as text, image and sound. By using the deep learning technology and the corresponding sample set, the network model for realizing different functions can be trained.
204. And respectively carrying out risk level calculation on the illness state label information based on the at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models.
In the embodiment of the application, at least two diseased part categories are respectively stomach category and esophagus category, the stomach category corresponds to a stomach risk level classification model, and the esophagus category corresponds to an esophagus risk level classification model; the target risk levels corresponding to the stomach risk level classification model are respectively atrophy level, intestinal grade, unclear boundary low level, clear boundary low level and stomach cancer high level; the corresponding target risk levels of the esophageal risk level classification model are respectively a low esophageal level, a middle esophageal level and a high esophageal level. The stomach risk level classification model is respectively a medium atrophy level, a intestinal tract level, a high atrophy level, a low boundary unclear level, a low boundary clear level and a high stomach cancer level, wherein the medium atrophy level, the intestinal tract level, the high atrophy level, the low boundary unclear level, the low boundary clear level and the high stomach cancer level are from low to high; the corresponding target risk levels of the esophageal risk level classification model are respectively lower esophageal level, middle esophageal level and higher esophageal level, and the lower esophageal level, middle esophageal level and higher esophageal level are from low to high.
In the embodiment of the application, risk level calculation is performed on condition label information based on at least two risk level classification models respectively to obtain at least two target risk levels corresponding to the at least two risk level classification models, and the method comprises the following steps:
(1) And performing risk level calculation on the illness state label information based on the stomach risk level classification model to obtain a target risk level corresponding to the stomach risk level classification model.
(2) And carrying out risk level calculation on the illness state label information based on the esophageal risk level classification model to obtain a target risk level corresponding to the esophageal risk level classification model.
Further, performing risk level calculation on the illness state label information based on the stomach risk level classification model to obtain a target risk level corresponding to the stomach risk level classification model, including:
(1) The illness state label information is respectively input into a stomach risk grade classification model to obtain a stomach initial risk grade, wherein the stomach initial risk grade is any one of a moderate atrophy grade, a intestinal metaplasia grade, a high atrophy grade, a stomach cancer low grade and a stomach cancer high grade, and the grade of the moderate atrophy grade, the intestinal metaplasia grade, the high atrophy grade, the stomach cancer low grade and the stomach cancer high grade is from low to high.
(2) If the stomach risk level is the stomach cancer low level, obtaining a gastroscope image;
(3) Inputting the gastroscope image into a pre-trained boundary definition detection model, and judging whether the gastroscope image is of a focus boundary definition type or not;
(4) If the gastroscope image is a focus boundary clear type, determining a boundary clear low level as a target risk level of the stomach risk level classification model; if the gastroscope image is not in the focus boundary clear category, determining the boundary unclear low level as the target risk level of the stomach risk level classification model.
Further, if the stomach risk level is the atrophy level, inputting the gastroscope image into a pre-trained atrophy part detection model to obtain a atrophy part in the gastroscope image; if the atrophy part comprises all parts in the preset part set, determining the high atrophy level as a target risk level corresponding to the esophageal risk level classification model; if the atrophy part does not comprise all parts in the preset part set, determining the moderate atrophy level as a target risk level corresponding to the esophageal risk level classification model, wherein the preset part set comprises the anterior wall of the stomach body, the posterior wall of the stomach body and the large curve of the stomach body.
205. And determining corresponding preset level time mapping relations based on the disease part categories corresponding to the target risk levels respectively.
Wherein, different diseased part categories correspond to different preset level time mapping relations.
206. And determining each follow-up time interval corresponding to each target risk level based on the time mapping relation of each target risk level and the corresponding preset level to obtain at least two follow-up time intervals.
In the preset level mapping relation, the follow-up time interval is reduced along with the increase of the target risk level.
As shown in fig. 3, two preset level time maps of two stomach and esophagus categories are illustrated in fig. 3. For the esophagus category, the preset level time mapping relation is as follows: the target risk level is lower than the esophagus, and the follow-up time interval is 3-5 years; the target risk levels are respectively the esophageal medium level, and the follow-up time interval is 1-3 years; the target risk level is respectively the high esophageal level, and the follow-up time interval is 0 years.
For stomach category, the preset level time mapping relation is as follows: the target risk level is moderate atrophy level, and the follow-up time interval is 3 years; the target risk levels are intestinal grade respectively, and the follow-up time interval is 2-3 years; the target risk level is a high atrophy level, and the follow-up time interval is 1-2 years; the target risk level is respectively a boundary definition level, and the follow-up time interval is 1 year; the target risk levels are respectively boundary unclear levels, and the follow-up time interval is 6 months; the target risk level is respectively high in gastric cancer, and the follow-up time interval is 0 years.
207. A minimum of at least two follow-up time intervals is determined as a target follow-up time interval.
208. A follow-up time plan is determined based on the examination time of the target patient and the target follow-up time interval. Wherein the follow-up time schedule includes at least one intelligent follow-up time point.
In a specific embodiment, the checking time and the target follow-up time interval are added to obtain a standard follow-up time point, and a time point is not taken before and after the standard follow-up time point at intervals of preset time, so that a plurality of intelligent follow-up time points are obtained, wherein the preset time interval can be one week.
209. When an intelligent follow-up time point in the follow-up time plan is reached, a preset follow-up text template is called.
The preset follow-up text templates comprise hospital names, examination dates, recommended initial review dates, recommended ending review dates and the like. For example, a follow-up text template is preset: the method comprises the steps that an artificial intelligent sight glass center prompts you to check regularly, the gastrointestinal mirror examination is carried out in a hospital on the basis of the examination date, the recommended initial check date to the recommended end check date are check time, the disease has a progressive risk, the time is scheduled to arrive at the hospital for check, and if you have missed the check; [ Hospital name ] the artificial intelligence speculum center cares for your health.
The hospital name and the examination date are the collected basic information, the initial review date and the final review date are the follow-up intervals deduced by the system.
210. And interacting with the target patient based on a preset follow-up text template to obtain interaction information.
In the embodiment of the application, the mode of interacting with the target patient based on the preset follow-up text template comprises telephone, short message and mail. Since the phone can continue to talk, more information can be obtained. The short message is mainly used as a reminder.
In the embodiment of the application, interaction is performed with a target patient based on a preset follow-up text template to obtain interaction information, and the method comprises the following steps:
(1) A voice interaction request is initiated to the target patient.
Specifically, a voice interaction request is initiated to a target patient by utilizing intelligent customer service.
(2) And when the target patient responds to the voice interaction request, converting the preset follow-up text template into voice follow-up data.
In the embodiment of the application, when a target patient responds to a voice interaction request, the follow-up visit starts, and the preset follow-up visit text template is converted into voice follow-up visit data by utilizing voice recognition. Speech recognition (Speech recognition), also known as automatic Speech recognition (English: automatic Speech Recognition, ASR), computer Speech recognition (English: computer Speech Recognition) or Speech-To-Text recognition (English: specific To Text, STT), aims To automatically convert human Speech content into corresponding Text by a computer. Unlike speaker recognition and speaker verification, the latter attempts to identify or verify the speaker making the speech, not the lexical content contained therein. Applications of speech recognition technology include voice dialing, voice navigation, indoor equipment control, voice document retrieval, simple dictation data entry, etc. More complex applications, such as speech-to-speech translation, can be built by combining speech recognition techniques with other natural language processing techniques, such as machine translation and speech synthesis techniques. The fields to which speech recognition technology relates include: signal processing, pattern recognition, probability theory and information theory, sounding and hearing mechanisms, artificial intelligence, and the like.
And when the target patient does not respond to the voice interaction request in the way of exceeding the preset response time, re-initiating the voice interaction request, and when the number of times of repeatedly initiating the voice interaction request exceeds the preset number of times, sending a preset follow-up text template to the target patient in the way of short messages and mails to obtain interaction information fed back by the target patient.
(3) And carrying out voice communication with the target patient based on the voice follow-up data to obtain voice interaction data.
In the embodiment of the application, voice interaction data is obtained by carrying out voice communication with a target patient based on voice follow-up data, and the method comprises the following steps:
the voice follow-up data is sent to the target patient.
And acquiring feedback information of the target patient based on the voice follow-up data feedback. For example, a user initiates a query: what preparation work is needed?
And extracting keywords from the feedback information to obtain the key information. For example, keyword extraction is performed on the feedback information, and the obtained keyword is "ready".
Judging whether a target answer matched with the key information exists in a preset answer library.
In the embodiment of the application, a plurality of answers corresponding to the key information are stored in the preset answer library, matching is performed according to the key information, and whether a target answer matched with the key information exists in the preset answer library is judged. For example, the key information is "ready", and an answer corresponding to "ready" in the preset answer library is searched as a target answer.
If no target answer matched with the key information exists in the preset answer library, calling a preset text analysis model, wherein the preset text analysis model is obtained by fine tuning a preset large-scale language model;
analyzing feedback information based on a preset text analysis model to obtain user intention; judging whether a target answer matched with the user intention exists in a preset answer library or not; if a target answer matched with the user intention exists in the preset answer library, the target answer is sent to a target patient.
In the embodiment of the application, a preset large-scale language model is acquired, and fine adjustment is performed on the preset large-scale language model based on a preset medical question-answer training set to obtain a preset text analysis model. When the keyword matching cannot be matched with the corresponding answer, the semantic analysis is utilized to determine the intention of the user, and then the matching is carried out, so that the accuracy can be improved. Further, a preset large-scale language model is obtained, fine adjustment is conducted on the preset large-scale language model based on a preset medical question-answer training set to obtain a fine adjustment model, quantization training is conducted on the fine adjustment model, and a preset text analysis model is obtained.
If a target answer matched with the key information exists in the preset answer library, the target answer is sent to the target patient.
For example, the key information is "ready", an answer corresponding to "ready" in the preset answer library is searched as a target answer, and the target answer is sent to the target patient.
And ending the call when the target patient does not respond or receives a confirmation instruction of the target patient in excess of the preset time, and determining the data of the call as voice interaction data.
Wherein the preset time may be 1 minute or the like. The confirmation instruction can be various confirmation texts sent by the user.
Further, if the target patient responds, the feedback information of the target patient is obtained, and the feedback information is answered again, so that interaction is completed, and voice interaction data are obtained.
(4) And converting the voice interaction data into text data to obtain interaction information.
(5) When the target patient does not respond to the voice interaction request, the preset follow-up text template is sent to the target patient in a short message and mail mode, and interaction information fed back by the target patient is obtained.
And when the target patient does not respond to the voice interaction request in the way of exceeding the preset response time, re-initiating the voice interaction request, and when the number of times of repeatedly initiating the voice interaction request exceeds the preset number of times, sending a preset follow-up text template to the target patient in the way of short messages and mails to obtain interaction information fed back by the target patient.
Further, if the interaction information is obtained, follow-up call is not performed, and the reminding short message is sent three times.
211. And judging whether the target patient meets the re-diagnosis condition or not based on the interaction information.
In the embodiment of the application, the re-diagnosis condition comprises a plurality of re-diagnosis keywords. And extracting the interaction keywords from the interaction information, judging whether the interaction keywords belong to the re-diagnosis keywords in the re-diagnosis conditions, and judging that the target patient meets the re-diagnosis conditions if the interaction keywords belong to the re-diagnosis keywords in the re-diagnosis conditions. If the interaction keywords do not belong to the review keywords in the review conditions, judging that the target patient does not meet the review conditions.
212. If the target patient meets the re-diagnosis condition, determining the re-diagnosis medical resource from a preset medical resource library based on the disease part category corresponding to the target follow-up time interval.
In the embodiment of the application, the re-diagnosis medical resources comprise a re-diagnosis appointment doctor and appointment time.
213. And sending the re-diagnosis medical resource to the target patient and acquiring resource selection information returned by the target patient.
214. A medical resource reservation record is generated based on the resource selection information of the target patient.
If the resource selection information returned by the target patient is acquired, generating a medical resource reservation record based on the resource selection information of the target patient; and if the resource selection information returned by the target patient is not acquired, ending.
215. The medical resource reservation record is sent to the target patient.
In order to facilitate better implementation of the intelligent follow-up method provided by the embodiment of the application, the embodiment of the application also provides an intelligent follow-up device based on the intelligent follow-up method. The meaning of the nouns is the same as that in the intelligent follow-up method, and specific implementation details refer to the description in the method embodiment.
Referring to fig. 4, fig. 4 is a schematic structural diagram of an intelligent follow-up device according to an embodiment of the present application, where the intelligent follow-up device may include a first obtaining module 401, a first determining module 402, a second obtaining module 403, a risk calculating module 404, a third obtaining module 405, a second determining module 406, a third determining module 407, a fourth determining module 408, a calling module 409, an interaction module 410, a judging module 411, a fifth determining module 412, a first sending module 413, a generating module 414, and a second sending module 415,
a first obtaining module 401, configured to obtain condition label information of a target patient;
a first determining module 402, configured to determine a disease portion category of the target patient based on the disease label information;
a second obtaining module 403, configured to obtain at least two different risk classification models corresponding to at least two different disease categories if the disease categories of the target patient are at least two;
The risk calculation module 404 is configured to perform risk level calculation on the condition label information based on at least two risk level classification models, so as to obtain at least two target risk levels corresponding to the at least two risk level classification models;
a third obtaining module 405, configured to determine corresponding preset level time mapping relationships based on the disease part categories corresponding to the target risk levels, where different disease part categories correspond to different preset level time mapping relationships;
a second determining module 406, configured to determine each follow-up time interval corresponding to each target risk level based on each target risk level and a corresponding preset level time mapping relationship, to obtain at least two follow-up time intervals, where the follow-up time intervals decrease with increasing target risk level in the preset level mapping relationship;
a third determining module 407, configured to determine a minimum value of at least two of the follow-up time intervals as a target follow-up time interval;
a fourth determination module 408 for determining a follow-up time plan based on the examination time of the target patient and the target follow-up time interval, wherein the follow-up time plan comprises at least one intelligent follow-up time point;
A calling module 409, configured to call a preset follow-up text template when an intelligent follow-up time point in the follow-up time plan is reached;
the interaction module 410 is configured to interact with the target patient based on the preset follow-up text template to obtain interaction information;
a judging module 411, configured to judge whether the target patient meets a review condition based on the interaction information;
a fifth determining module 412, configured to determine a review medical resource from a preset medical resource library based on the disease portion category corresponding to the target follow-up time interval if the target patient meets the review condition;
a first sending module 413, configured to send the review medical resource to a target patient and obtain resource selection information returned by the target patient;
a generation module 414 for generating a medical resource reservation record based on the resource selection information of the target patient;
a second sending module 415 is configured to send the medical resource reservation record to the target patient.
The specific implementation of each module can be referred to the previous embodiments, and will not be repeated here.
The embodiment of the application also provides electronic equipment, which comprises a memory and a processor, wherein the processor is used for executing the steps in the intelligent follow-up method provided by the embodiment by calling the computer program stored in the memory.
Referring to fig. 5, fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the application.
The electronic device may include one or more processing cores 'processors 101, one or more computer-readable storage media's memory 102, power supply 103, and input unit 104, among other components. It will be appreciated by those skilled in the art that the electronic device structure shown in the figures is not limiting of the electronic device and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components. Wherein:
the processor 101 is a control center of the electronic device, connects various parts of the entire electronic device using various interfaces and lines, performs various functions of the electronic device and processes data by running or executing software programs and/or modules stored in the memory 102, and invoking data stored in the memory 102. Optionally, processor 101 may include one or more processing cores; alternatively, the processor 101 may integrate an application processor that primarily handles operating systems, user interfaces, applications, etc., with a modem processor that primarily handles wireless communications. It will be appreciated that the modem processor described above may not be integrated into the processor 101.
The memory 102 may be used to store software programs and modules, and the processor 101 executes various functional applications and data processing by executing the software programs and modules stored in the memory 102. The memory 102 may mainly include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like; the storage data area may store data created according to the use of the electronic device, etc. In addition, memory 102 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 volatile solid-state storage device. Accordingly, the memory 102 may also include a memory controller to provide access to the memory 102 by the processor 101.
The electronic device further comprises a power supply 103 for powering the various components, optionally, the power supply 103 may be logically connected to the processor 101 by a power management system, whereby the functions of managing charging, discharging, and power consumption are performed by the power management system. The power supply 103 may also include one or more of any of a direct current or alternating current power supply, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and the like.
The electronic device may further comprise an input unit 104, which input unit 104 may be used for receiving input digital or character information and for generating keyboard, mouse, joystick, optical or trackball signal inputs in connection with user settings and function control.
Although not shown, the electronic device may further include a display unit, an image acquisition component, and the like, which are not described herein. In particular, in this embodiment, the processor 101 in the electronic device loads executable codes corresponding to one or more computer programs into the memory 102 according to the following instructions, and the steps in the intelligent follow-up method provided by the present application are executed by the processor 101, for example:
acquiring disease label information of a target patient; determining the disease part category of the target patient based on the disease label information; acquiring at least two different risk level classification models corresponding to at least two different disease part categories under the condition that the disease part categories of the target patient are at least two; respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models; determining corresponding preset level time mapping relations based on the diseased part categories corresponding to the target risk levels respectively, wherein different diseased part categories correspond to different preset level time mapping relations; determining each follow-up time interval corresponding to each target risk level based on each target risk level and a corresponding preset level time mapping relation respectively to obtain at least two follow-up time intervals, wherein the follow-up time intervals decrease along with the increase of the target risk level in the preset level mapping relation; determining a minimum value of at least two follow-up time intervals as a target follow-up time interval; determining a follow-up time plan based on the examination time of the target patient and the target follow-up time interval, wherein the follow-up time plan includes at least one intelligent follow-up time point; when an intelligent follow-up time point in the follow-up time plan is reached, a preset follow-up text template is called; interacting with a target patient based on a preset follow-up text template to obtain interaction information; judging whether the target patient meets the re-diagnosis condition or not based on the interaction information; if the target patient meets the re-diagnosis condition, determining re-diagnosis medical resources from a preset medical resource library based on the disease part category corresponding to the target follow-up time interval; transmitting the re-diagnosis medical resource to a target patient and acquiring resource selection information returned by the target patient; generating a medical resource reservation record based on the resource selection information of the target patient; the medical resource reservation record is sent to the target patient.
It should be noted that, the electronic device provided in the embodiment of the present application and the intelligent follow-up method in the above embodiment belong to the same concept, and detailed implementation processes of the electronic device are described in the above related embodiments, which are not repeated here.
The present application also provides a computer-readable storage medium, on which a computer program is stored, which when executed on a processor of an electronic device provided by an embodiment of the present application, causes the processor of the electronic device to execute the steps in the intelligent follow-up method provided by the present application. The storage medium may be a magnetic disk, an optical disk, a Read Only Memory (ROM), a random access Memory (Random Access Memory, RAM), or the like.
The present application also provides a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions are read from the computer-readable storage medium by a processor of a computer device, and executed by the processor, cause the computer device to perform various alternative implementations of the intelligent follow-up method described above.
The foregoing has described in detail the method and apparatus for intelligent follow-up provided by the present application, and specific examples have been used herein to illustrate the principles and embodiments of the present application, the above examples being for the purpose of helping to understand the method and core ideas of the present application; meanwhile, as those skilled in the art will vary in the specific embodiments and application scope according to the ideas of the present application, the present description should not be construed as limiting the present application in summary.
It should be noted that when the above embodiments of the present application are applied to specific products or technologies, related data concerning users are required to obtain user approval or consent, and the collection, use and processing of the related data are required to comply with related laws and regulations and standards of related countries and regions.
Claims (10)
1. An intelligent follow-up method, comprising:
acquiring disease label information of a target patient;
determining a disease site category of the target patient based on the disease label information;
acquiring at least two different risk level classification models corresponding to at least two different diseased part categories under the condition that the diseased part categories of the target patient are at least two;
respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models;
determining corresponding preset level time mapping relations based on the diseased part categories corresponding to the target risk levels respectively, wherein different diseased part categories correspond to different preset level time mapping relations;
Determining each follow-up time interval corresponding to each target risk level based on each target risk level and the corresponding preset level time mapping relation respectively, and obtaining at least two follow-up time intervals;
determining the minimum value of at least two follow-up time intervals as a target follow-up time interval;
determining a follow-up time plan based on the examination time of the target patient and the target follow-up time interval, wherein the follow-up time plan includes at least one intelligent follow-up time point;
when an intelligent follow-up time point in the follow-up time plan is reached, a preset follow-up text template is called;
interacting with the target patient based on the preset follow-up text template to obtain interaction information;
judging whether the target patient meets the re-diagnosis condition or not based on the interaction information;
if the target patient meets the re-diagnosis condition, determining re-diagnosis medical resources from a preset medical resource library based on the disease part category corresponding to the target follow-up time interval;
transmitting the re-diagnosis medical resource to a target patient and acquiring resource selection information returned by the target patient;
generating a medical resource reservation record based on the resource selection information of the target patient;
And sending the medical resource reservation record to the target patient.
2. The intelligent follow-up method according to claim 1, wherein the interaction with the target patient based on the preset follow-up text template to obtain interaction information comprises:
initiating a voice interaction request to the target patient;
when the target patient responds to the voice interaction request, converting the preset follow-up text template into voice follow-up data;
performing voice communication with the target patient based on the voice follow-up data to obtain voice interaction data;
converting the voice interaction data into text data to obtain the interaction information;
and when the target patient does not respond to the voice interaction request, sending the preset follow-up text template to the target patient in a short message and mail mode to obtain the interaction information fed back by the target patient.
3. The intelligent follow-up method according to claim 2, wherein the performing a voice call with the target patient based on the voice follow-up data to obtain voice interaction data includes:
transmitting the voice follow-up data to the target patient;
Acquiring feedback information fed back by the target patient based on the voice follow-up data;
extracting keywords from the feedback information to obtain key information;
judging whether a target answer matched with the key information exists in a preset answer library or not;
if a target answer matched with the key information exists in a preset answer library, sending the target answer to a target patient;
and ending the call when the target patient does not respond or receives a confirmation instruction of the target patient in excess of the preset time, and determining the data of the call as voice interaction data.
4. A smart follow-up method as claimed in claim 3, wherein the smart follow-up method comprises:
if no target answer matched with the key information exists in the preset answer library, calling a preset text analysis model, wherein the preset text analysis model is obtained by fine tuning a preset large-scale language model;
analyzing the feedback information based on the preset text analysis model to obtain user intention;
judging whether a target answer matched with the user intention exists in the preset answer library or not;
and if a target answer matched with the user intention exists in a preset answer library, sending the target answer to a target patient.
5. The intelligent follow-up method according to claim 1, wherein the at least two diseased site categories are a stomach category and an esophagus category, respectively, the stomach category corresponding to the stomach risk level classification model, the esophagus category corresponding to the esophagus risk level classification model; the target risk levels corresponding to the stomach risk level classification model are a moderate atrophy level, an intestinal metaplasia level, a high atrophy level, a low boundary unclear level, a low boundary clear level and a high stomach cancer level respectively, wherein the moderate atrophy level, the intestinal metaplasia level, the high atrophy level, the low boundary unclear level, the low boundary clear level and the high stomach cancer level are from low to high; the corresponding target risk levels of the esophageal risk level classification model are respectively a low esophageal level, a middle esophageal level and a high esophageal level, and the low esophageal level, the middle esophageal level and the high esophageal level are from low to high;
the step of respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models comprises the following steps:
performing risk level calculation on the illness state label information based on the stomach risk level classification model to obtain a target risk level corresponding to the stomach risk level classification model;
And calculating the risk level of the illness state label information based on the esophageal risk level classification model to obtain a target risk level corresponding to the esophageal risk level classification model.
6. The intelligent follow-up method according to claim 5, wherein the performing risk level calculation on the condition label information based on the stomach risk level classification model to obtain a target risk level corresponding to the stomach risk level classification model includes:
respectively inputting the illness state label information into the stomach risk level classification model to obtain stomach initial risk levels, wherein the stomach initial risk levels are any one of atrophy levels, intestinal grade, stomach cancer low grade and stomach cancer high grade;
if the stomach risk level is a low stomach cancer level, obtaining a gastroscope image;
inputting the gastroscope image into a pre-trained boundary definition detection model, and judging whether the gastroscope image is of a focus boundary definition type or not;
if the gastroscope image is a focus boundary clear type, determining a boundary clear low level as a target risk level of the stomach risk level classification model; and if the gastroscope image is not in the focus boundary clear category, determining the boundary unclear low level as the target risk level of the stomach risk level classification model.
7. The intelligent follow-up method according to claim 5, wherein the intelligent follow-up method comprises:
if the stomach risk level is an atrophy level, inputting the gastroscope image into a pre-trained atrophy part detection model to obtain the atrophy part in the gastroscope image;
if the atrophy part comprises all parts in the preset part set, determining the high atrophy level as a target risk level corresponding to the esophageal risk level classification model; and if the atrophy part does not comprise all parts in a preset part set, determining the moderate atrophy level as a target risk level corresponding to the esophageal risk level classification model, wherein the preset part set comprises a stomach anterior wall, a stomach posterior wall and a stomach major curve.
8. An intelligent follow-up device, comprising:
the first acquisition module is used for acquiring illness state label information of a target patient;
a first determining module for determining a disease part category of the target patient based on the disease label information;
the second acquisition module is used for acquiring at least two different risk level classification models corresponding to at least two different diseased part categories under the condition that the diseased part categories of the target patient are at least two;
The risk calculation module is used for respectively carrying out risk level calculation on the illness state label information based on at least two risk level classification models to obtain at least two target risk levels corresponding to the at least two risk level classification models;
the third acquisition module is used for determining corresponding preset level time mapping relations based on the diseased part categories corresponding to the target risk levels respectively, wherein different diseased part categories correspond to different preset level time mapping relations;
the second determining module is used for determining each follow-up time interval corresponding to each target risk level based on each target risk level and the corresponding preset level time mapping relation respectively to obtain at least two follow-up time intervals;
a third determining module, configured to determine a minimum value of at least two of the follow-up time intervals as a target follow-up time interval;
a fourth determination module for determining a follow-up time plan based on the examination time of the target patient and the target follow-up time interval, wherein the follow-up time plan includes at least one intelligent follow-up time point;
the calling module is used for calling a preset follow-up character template when an intelligent follow-up time point in the follow-up time plan is reached;
The interaction module is used for interacting with the target patient based on the preset follow-up text template to obtain interaction information;
the judging module is used for judging whether the target patient meets the re-diagnosis condition or not based on the interaction information;
a fifth determining module, configured to determine a review medical resource from a preset medical resource library based on a disease part category corresponding to the target follow-up time interval if the target patient meets a review condition;
the first sending module is used for sending the re-diagnosis medical resource to a target patient and acquiring resource selection information returned by the target patient;
a generation module for generating a medical resource reservation record based on the resource selection information of the target patient;
and the second sending module is used for sending the medical resource reservation record to the target patient.
9. An electronic device comprising a memory storing a computer program and a processor for running the computer program in the memory to perform the steps in the intelligent follow-up method of any of claims 1 to 7.
10. A computer readable storage medium storing a plurality of instructions adapted to be loaded by a processor to perform the steps in the intelligent follow-up method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311490206.2A CN117238532B (en) | 2023-11-10 | 2023-11-10 | Intelligent follow-up method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311490206.2A CN117238532B (en) | 2023-11-10 | 2023-11-10 | Intelligent follow-up method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117238532A true CN117238532A (en) | 2023-12-15 |
| CN117238532B CN117238532B (en) | 2024-01-30 |
Family
ID=89098460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311490206.2A Active CN117238532B (en) | 2023-11-10 | 2023-11-10 | Intelligent follow-up method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117238532B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111312405A (en) * | 2020-02-12 | 2020-06-19 | 宁德市闽东医院 | Health examination gastric cancer screening, evaluating and managing system |
| CN111899229A (en) * | 2020-07-14 | 2020-11-06 | 武汉楚精灵医疗科技有限公司 | Advanced gastric cancer auxiliary diagnosis method based on deep learning multi-model fusion technology |
| CN112802568A (en) * | 2021-02-03 | 2021-05-14 | 紫东信息科技(苏州)有限公司 | Multi-label stomach disease classification method and device based on medical history text |
| US20210287800A1 (en) * | 2020-03-10 | 2021-09-16 | Medius Health | Ai supported personalized, natural language-based patient interface for medical-bot |
| CN113593707A (en) * | 2021-09-29 | 2021-11-02 | 武汉楚精灵医疗科技有限公司 | Stomach early cancer model training method and device, computer equipment and storage medium |
| KR20210134121A (en) * | 2020-04-29 | 2021-11-09 | 주식회사 아펙스에이아이 | System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence |
| CN114724717A (en) * | 2022-04-20 | 2022-07-08 | 山东大学齐鲁医院 | Stomach early cancer high-risk screening system |
| CN116434920A (en) * | 2023-05-31 | 2023-07-14 | 武汉大学人民医院（湖北省人民医院） | Gastrointestinal epithelial metaplasia progression risk prediction method and device |
-
2023
- 2023-11-10 CN CN202311490206.2A patent/CN117238532B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111312405A (en) * | 2020-02-12 | 2020-06-19 | 宁德市闽东医院 | Health examination gastric cancer screening, evaluating and managing system |
| US20210287800A1 (en) * | 2020-03-10 | 2021-09-16 | Medius Health | Ai supported personalized, natural language-based patient interface for medical-bot |
| KR20210134121A (en) * | 2020-04-29 | 2021-11-09 | 주식회사 아펙스에이아이 | System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence |
| CN111899229A (en) * | 2020-07-14 | 2020-11-06 | 武汉楚精灵医疗科技有限公司 | Advanced gastric cancer auxiliary diagnosis method based on deep learning multi-model fusion technology |
| CN112802568A (en) * | 2021-02-03 | 2021-05-14 | 紫东信息科技(苏州)有限公司 | Multi-label stomach disease classification method and device based on medical history text |
| CN113593707A (en) * | 2021-09-29 | 2021-11-02 | 武汉楚精灵医疗科技有限公司 | Stomach early cancer model training method and device, computer equipment and storage medium |
| CN114724717A (en) * | 2022-04-20 | 2022-07-08 | 山东大学齐鲁医院 | Stomach early cancer high-risk screening system |
| CN116434920A (en) * | 2023-05-31 | 2023-07-14 | 武汉大学人民医院（湖北省人民医院） | Gastrointestinal epithelial metaplasia progression risk prediction method and device |
Non-Patent Citations (1)
| Title |
|---|
| 涂洁;陈洞天;任宇飞;: "医院信息系统中疾病风险评估功能设计", 医学信息学杂志, no. 05 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117238532B (en) | 2024-01-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111316281B (en) | Semantic classification method and system for numerical data in natural language context based on machine learning | |
| US20190139642A1 (en) | System and methods for medical image analysis and reporting | |
| CN113724848A (en) | Medical resource recommendation method, device, server and medium based on artificial intelligence | |
| CN109599187A (en) | A kind of online interrogation point examines method, server, terminal, equipment and medium | |
| CN109871440B (en) | Intelligent prompting method, device and equipment based on semantic analysis | |
| CN109979568B (en) | Mental health early warning method, server, family member terminal and system | |
| WO2023029501A1 (en) | Smart interrogation method and apparatus, electronic device, and storage medium | |
| CN116340778A (en) | Medical large model construction method based on multiple modes and related equipment thereof | |
| CN110825164A (en) | Interaction method and system based on wearable intelligent equipment special for children | |
| CN112256827A (en) | Sign language translation method and device, computer equipment and storage medium | |
| CN114999676A (en) | Method, system, apparatus and medium for automatically replying to medical consultation | |
| CN112287085B (en) | Semantic matching method, system, equipment and storage medium | |
| CN117079809B (en) | Method, system and equipment for constructing medical guidance scene assistant based on generated model | |
| EP3901875A1 (en) | Topic modelling of short medical inquiries | |
| CN117373602A (en) | Medical record generation method and device | |
| CN110047569B (en) | Method, device and medium for generating question-answer data set based on chest radiography report | |
| CN117238532B (en) | Intelligent follow-up method and device | |
| CN116956934A (en) | Task processing method, device, equipment and storage medium | |
| CN111524515A (en) | Voice interaction method and device, electronic equipment and readable storage medium | |
| CN116959733A (en) | Medical data analysis method, device, equipment and storage medium | |
| CN114242267A (en) | Neural network-based inquiry reply method, device, equipment and storage medium | |
| CN114510942A (en) | Method for acquiring entity words, and method, device and equipment for training model | |
| CN113314236A (en) | Intelligent question-answering system for hypertension | |
| CN112700862A (en) | Target department determining method and device, electronic equipment and storage medium | |
| Kim et al. | Automatic Diagnosis of medical conditions using Deep Learning with Symptom2Vec |
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 |