CN116741331A - Diagnostic information generation method, device, storage medium and computer equipment - Google Patents
Diagnostic information generation method, device, storage medium and computer equipment Download PDFInfo
- Publication number
- CN116741331A CN116741331A CN202310789573.6A CN202310789573A CN116741331A CN 116741331 A CN116741331 A CN 116741331A CN 202310789573 A CN202310789573 A CN 202310789573A CN 116741331 A CN116741331 A CN 116741331A
- Authority
- CN
- China
- Prior art keywords
- information
- patient
- facial
- state description
- illness state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000001815 facial effect Effects 0.000 claims abstract description 100
- 238000003745 diagnosis Methods 0.000 claims abstract description 50
- 238000001514 detection method Methods 0.000 claims description 12
- 230000014509 gene expression Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000003741 hair volume Effects 0.000 claims description 5
- 230000008569 process Effects 0.000 description 5
- 230000009471 action Effects 0.000 description 3
- 238000013475 authorization Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 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
- G16H15/00—ICT specially adapted for medical reports, e.g. generation or transmission thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
-
- 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
- Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Primary Health Care (AREA)
- Epidemiology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
The application provides a diagnostic information generation method, a diagnostic information generation device, a storage medium and computer equipment, wherein the diagnostic information generation method comprises the following steps: responding to a diagnosis request of an authorized patient, acquiring a facial image of the authorized patient, and receiving target illness state description information of the authorized patient, wherein the target illness state description information is text information; performing face attribute identification processing on the face image to obtain face attribute information; generating patient information according to the target illness state description information and the facial attribute information; and inputting the patient information into a medical large language model which is acquired in advance, and outputting the preliminary diagnosis information of the authorized patient. By combining the facial attribute information with the medical large model, the basic condition of the patient can be effectively obtained, and the basic information of the patient can be accurately identified and applied, so that the model can individually assist doctors to make more accurate treatment schemes according to specific conditions faced by different patients.
Description
Technical Field
The present application relates to the field of artificial intelligence technologies, and in particular, to a diagnostic information generating method, apparatus, storage medium, and computer device.
Background
Medical large language models are powerful tools based on natural language processing techniques and deep learning algorithms that can learn and analyze various types of medical data such as medical literature, case reports, and clinical guidelines. These medical data are widely available, and relate to cases in various medical fields, as well as to the expertise contributed by a large number of experienced doctors and researchers. In medical practice, the large medical language model has a plurality of potential application scenes, can assist doctors in diagnosing and treating medicines more quickly and accurately, can assist doctors in recording medical records, and helps medical researchers to perform scientific exploration.
Although the medical large language model is widely regarded as a powerful and important technical means, in practical application, the existing medical large language model cannot effectively obtain the basic condition of a patient and cannot accurately identify and apply the basic information of the patient, so that the model cannot individually assist doctors to make more accurate treatment schemes according to specific conditions faced by different patients.
Disclosure of Invention
The present application aims to solve at least one of the above technical drawbacks, and in particular, the technical drawbacks of the prior art that the basic information of the patient cannot be accurately identified and applied.
In a first aspect, the present application provides a diagnostic information generating method, the method comprising:
responding to a diagnosis request of an authorized patient, acquiring a facial image of the authorized patient, and receiving target illness state description information of the authorized patient, wherein the target illness state description information is text information;
performing face attribute identification processing on the face image to obtain face attribute information;
generating patient information according to the target illness state description information and the facial attribute information;
and inputting the patient information into a medical large language model which is acquired in advance, and outputting the preliminary diagnosis information of the authorized patient.
In one embodiment, the step of performing facial attribute recognition processing on the facial image to obtain facial attribute information includes:
locating and marking faces in the face image by using a face detection algorithm;
extracting facial features of the marked facial images to obtain facial features corresponding to the facial images;
and carrying out face attribute prediction on the facial features to obtain a prediction result of each face attribute, and taking the prediction result of each face attribute as the face attribute information, wherein the face attributes comprise age, gender, hair volume and expression.
In one embodiment, if the medical large language model embeds medical knowledge base information, where the medical knowledge base information includes department information and doctor information, the step of inputting the patient information into a medical large language model acquired in advance, and outputting preliminary diagnosis information of the authorized patient, further includes:
and outputting target department information and target doctor information corresponding to the preliminary diagnosis information.
In one embodiment, the step of receiving the target condition descriptive information of the authorized patient includes:
acquiring initial illness state description information input by the authorized patient, and determining the information type of the initial illness state description information;
if the information type of the initial illness state description information is text information, receiving the initial illness state description information as the target illness state description information;
if the information type of the initial illness state description information is voice information, converting the information type of the initial illness state description information into text information through a voice recognition processing mode, and receiving the converted initial illness state description information as the target illness state description information.
In one embodiment, before the step of inputting the patient information into a pre-acquired medical large language model and outputting preliminary diagnosis information corresponding to the condition description information, the method further includes:
generating system prompt information according to the facial attribute information, and inputting the system prompt information into the medical large language model so that the medical large language model outputs personalized preliminary diagnosis information.
In one embodiment, the method further comprises:
generating initial medical record information according to the patient information and the initial diagnosis information, and associating the initial medical record information with the medical account number of the authorized patient.
In one embodiment, the method further comprises:
and preprocessing the face image, and if the preprocessed face image does not meet the preset face image detection condition, generating prompt information for re-acquiring the face image.
In a second aspect, the present application provides a diagnostic information generating apparatus comprising:
the facial image acquisition module is used for responding to a diagnosis request of an authorized patient, acquiring a facial image of the authorized patient, and receiving target illness state description information of the authorized patient, wherein the target illness state description information is text information;
the facial attribute information acquisition module is used for carrying out facial attribute identification processing on the facial image to obtain facial attribute information;
the patient information generating module is used for generating patient information according to the target illness state description information and the facial attribute information;
the preliminary diagnosis information acquisition module is used for inputting the patient information into a medical large language model acquired in advance and outputting the preliminary diagnosis information of the authorized patient.
In a third aspect, the present application provides a storage medium having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the diagnostic information generation method according to any one of the embodiments described above.
In a fourth aspect, the present application provides a computer device comprising: one or more processors, and memory;
the memory has stored therein computer readable instructions which, when executed by the one or more processors, perform the steps of the diagnostic information generation method of any of the above embodiments.
From the above technical solutions, the embodiment of the present application has the following advantages:
the application provides a diagnostic information generation method, which comprises the following steps: responding to a diagnosis request of an authorized patient, acquiring a facial image of the authorized patient, and receiving target illness state description information of the authorized patient, wherein the target illness state description information is text information; performing face attribute identification processing on the face image to obtain face attribute information; generating patient information according to the target illness state description information and the facial attribute information; and inputting the patient information into a medical large language model which is acquired in advance, and outputting the preliminary diagnosis information of the authorized patient. By combining the facial attribute information with the medical large model, the basic condition of the patient can be effectively obtained, and the basic information of the patient can be accurately identified and applied, so that the model can individually assist doctors to make more accurate treatment schemes according to specific conditions faced by different patients.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained from these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a flow chart of a diagnostic information generating method according to an embodiment of the present application;
fig. 2 is a schematic flow chart of acquiring face attribute information according to an embodiment of the present application;
FIG. 3 is a flowchart illustrating a process for receiving target condition description information according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a diagnostic information generating apparatus according to an embodiment of the present application;
fig. 5 is a schematic diagram of an internal structure of a computer device according to an embodiment of the present application.
Detailed Description
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 be within the scope of the application.
The application provides a diagnostic information generation method. The following embodiments will be described by taking the application of the method to a computer device as an example, and it will be understood that the computer device may be various devices with data processing functions, and may be, but not limited to, a single server, a server cluster, a personal notebook, a desktop computer, and the like. As shown in fig. 1, the diagnostic information generating method of the present application may include the steps of:
s101: responding to a diagnosis request of an authorized patient, acquiring a facial image of the authorized patient, and receiving target illness state description information of the authorized patient, wherein the target illness state description information is text information.
In the step, under the condition of patient authorization, a diagnosis request of an authorized patient is received, a face acquisition device is called to acquire the face image of the authorized patient, and text information corresponding to illness state description information input by the authorized patient is received as target illness state description information. The face collection device may be a built-in camera of the computer device or an externally-connected camera of the computer device, which is not particularly limited in the application. The patient is authorized to input the illness description information into the computer device in a typing mode, a handwriting input mode, a voice input mode or a disease keyword input mode, and the application is not limited in particular.
Further, when the patient initiates the diagnosis request, whether the patient is authorized or not is determined, if not, prompt information requesting authorization is generated to prompt the patient to authorize first and then initiate the diagnosis request, and if so, the diagnosis request of the patient is received. The authorization content comprises the authority for acquiring the facial image of the patient and the authority for carrying out identification processing on the facial image of the patient.
S102: and carrying out face attribute identification processing on the face image to obtain face attribute information.
In this step, the face attribute information may be directly extracted from the face image, or the face feature may be extracted from the face image, and the face attribute information may be obtained from the face feature.
The face attribute recognition algorithm used in the face attribute recognition process may be implemented using a machine learning technique such as deep learning, or may be implemented using a face attribute recognition network, for example, deep face series, faceNet, VGGFace, sphereFace, cosFace, and ArcFace, which is not particularly limited in the present application. Facial attribute information refers to obtaining various attributes and information about a face, including but not limited to age, gender, expression, race, eyewear, beard, skin tone, etc., by analyzing and identifying features and characteristics in a facial image.
S103: and generating patient information according to the target illness state description information and the facial attribute information.
In this step, patient information with consistency is generated according to the target condition description information and the facial attribute information, for example, a complete patient information paragraph may be formed before the facial attribute information of the patient is inserted into the target condition description information, or the medical history in the medical account of the patient may be integrated with the target condition description information and the facial attribute information to form patient information with patient basic information, past medical history and current condition description.
S104: and inputting the patient information into a medical large language model which is acquired in advance, and outputting the preliminary diagnosis information of the authorized patient.
In the step, the patient information is input into a medical large language model, the medical large language model analyzes the patient face attribute information and the illness state description information in the patient information by using medical data, and finally, the preliminary diagnosis information of the authorized patient is output so as to personally assist doctors in making more accurate medical schemes.
The application provides a diagnostic information generation method, which comprises the following steps: responding to a diagnosis request of an authorized patient, acquiring a facial image of the authorized patient, and receiving target illness state description information of the authorized patient, wherein the target illness state description information is text information; performing face attribute identification processing on the face image to obtain face attribute information; generating patient information according to the target illness state description information and the facial attribute information; and inputting the patient information into a medical large language model which is acquired in advance, and outputting the preliminary diagnosis information of the authorized patient. By combining the facial attribute information with the medical large model, the basic condition of the patient can be effectively obtained, and the basic information of the patient can be accurately identified and applied, so that the model can individually assist doctors to make more accurate treatment schemes according to specific conditions faced by different patients.
The diagnostic information generation method provided by the application can be realized on actual physical equipment, and the original medical large language model deployment equipment comprises an algorithm server for deploying a medical large model and a screen with voice input and output for patient interaction, and only a camera for acquiring the face is needed to be added on the basis of the original medical large language model deployment equipment. The intelligent screen integrating voice input and output and provided with the camera can be integrated into one screen by using the front-end interaction device. In summary, compared with the prior art, the diagnostic information generation method provided by the application can improve the efficiency and quality of intelligent medical service, enhance the automation degree of a large medical language model, and has higher practicability and superiority.
As shown in fig. 2, in one embodiment, the step of performing facial attribute recognition processing on the facial image to obtain facial attribute information includes:
s201: locating and marking faces in the face image by using a face detection algorithm;
s202: extracting facial features of the marked facial images to obtain facial features corresponding to the facial images;
s203: and carrying out face attribute prediction on the facial features to obtain a prediction result of each face attribute, and taking the prediction result of each face attribute as the face attribute information, wherein the face attributes comprise age, gender, hair volume and expression.
Specifically, after the face image of the authorized patient is acquired, the face in the face image is positioned and marked by using a face detection algorithm so as to accurately acquire face information; extracting facial features of the marked facial images to obtain facial features corresponding to the facial images so as to improve the accuracy of acquiring the facial attribute information; and carrying out face attribute prediction on the face characteristics to obtain a prediction result of each face attribute, and taking the prediction result of each face attribute as face attribute information, wherein the face attributes comprise age, gender, hair volume and expression.
Further, when predicting the facial attribute of the facial feature, a plurality of probability values of each facial attribute may be obtained first, and for each facial attribute, a predicted result of the facial attribute may be obtained from each probability value, for example, a probability value of 90% for 18 years old, a probability value of 40% for 22 years old, and a probability value of 20% for 16 years old in the age attribute, and a predicted result of 18 years old may be obtained from each probability value. Thus, accuracy of face attribute recognition can be improved.
In one embodiment, if the medical large language model embeds medical knowledge base information, the medical knowledge base information includes department information and doctor information, the step of inputting the patient information into a medical large language model acquired in advance, and outputting preliminary diagnosis information of the authorized patient includes:
and outputting target department information and target doctor information corresponding to the preliminary diagnosis information.
Specifically, medical knowledge base information is built in the medical large language model, the medical knowledge base information comprises department information and doctor information, and the diagnosis guiding function of the medical large language model can be added. The method has the advantages that the patient information is input into the medical large language model, the primary diagnosis information of the authorized patient is output, and meanwhile, the target department information and the target doctor information corresponding to the primary diagnosis information are output, so that the patient can be helped to accurately find out the proper departments and doctors, the model can personally assist the doctors to make more accurate treatment schemes according to specific conditions faced by different patients, and the efficiency and quality of intelligent medical services are improved.
As shown in fig. 3, in one embodiment, the step of receiving the target condition description information of the authorized patient includes:
s301: acquiring initial illness state description information input by the authorized patient, and determining the information type of the initial illness state description information;
s302: if the information type of the initial illness state description information is text information, receiving the initial illness state description information as the target illness state description information;
s303: if the information type of the initial illness state description information is voice information, converting the information type of the initial illness state description information into text information through a voice recognition processing mode, and receiving the converted initial illness state description information as the target illness state description information.
Specifically, when the patient inputs the initial illness state description information, the information type of the initial illness state description information is determined first, and whether the initial illness state description information needs to be further processed is judged according to the information type. If the information type of the initial illness state description information is text information, the initial illness state description information can be directly received as target illness state description information without further processing. If the information type of the initial illness state description information is voice information, converting the information type of the initial illness state description information into text information by a voice recognition processing mode, and receiving the converted initial illness state description information as target illness state description information. Therefore, the identification accuracy of the target illness state description information can be improved, and the medical large language model can accurately output the primary diagnosis information of the authorized patient.
In one embodiment, before the step of inputting the patient information into a pre-acquired medical large language model and outputting preliminary diagnosis information corresponding to the condition description information, the method further includes:
generating system prompt information according to the facial attribute information, and inputting the system prompt information into the medical large language model so that the medical large language model outputs personalized preliminary diagnosis information.
Specifically, system prompt information is generated according to the facial attribute information, and is input to the medical large language model, so that the medical large language model outputs personalized preliminary diagnosis information. For example, different prompt languages can be generated for patients with different expressions, so that a better service effect is achieved, if the qi of the patient is identified, the patient can be properly calmed first, and a concise and effective reply can be performed, or for elderly patients, more and more detailed patients possibly need to know, so that the reply needs to be as detailed as possible. Therefore, the basic information of the patient can be accurately applied, and the efficiency and quality of the intelligent medical service are improved.
In one embodiment, the method further comprises:
generating initial medical record information according to the patient information and the initial diagnosis information, and associating the initial medical record information with the medical account number of the authorized patient.
Specifically, according to the patient information and the preliminary diagnosis information, initial medical record information is generated, and the initial medical record information is associated with the medical account number of the authorized patient, so that a doctor can be helped to conduct medical record, prescription and other works, and the medical work efficiency is improved.
In one embodiment, the method further comprises:
and preprocessing the face image, and if the preprocessed face image does not meet the preset face image detection condition, generating prompt information for re-acquiring the face image.
Specifically, after the facial image is acquired, the facial image is preprocessed, and the preprocessing mode can be selected according to actual conditions, which is not particularly limited by the present application. Judging whether the preprocessed face image meets the preset face image detection condition, if not, generating prompt information for re-acquiring the face image so as to prompt an authorized patient to adjust the posture or the angle, and re-acquiring the face image, thereby improving the accuracy of face attribute information identification. Wherein the face image detection conditions may be selected according to the actual situation, to which the present application is not particularly limited.
The diagnostic information generating apparatus provided in the embodiment of the present application will be described below, and the diagnostic information generating apparatus described below and the diagnostic information generating method described above may be referred to correspondingly to each other. As shown in fig. 4, a diagnostic information generating apparatus provided by the present application may include the following structure:
the facial image acquisition module 401 is configured to respond to a diagnosis request of an authorized patient, acquire a facial image of the authorized patient, and receive target condition description information of the authorized patient, where the target condition description information is text information;
a facial attribute information obtaining module 402, configured to perform facial attribute recognition processing on the facial image to obtain facial attribute information;
a patient information generating module 403, configured to generate patient information according to the target condition description information and the facial attribute information;
the preliminary diagnosis information acquisition module 404 is configured to input the patient information into a pre-acquired medical large language model, and output preliminary diagnosis information of the authorized patient.
In one embodiment, the facial attribute information acquisition module 402 includes:
a face detection unit for locating and marking a face in the face image using a face detection algorithm;
a facial feature extraction unit, configured to perform facial feature extraction on the labeled facial image, to obtain a facial feature corresponding to the facial image;
and the facial attribute information acquisition unit is used for carrying out facial attribute prediction on the facial features to obtain a prediction result of each facial attribute, and taking the prediction result of each facial attribute as the facial attribute information, wherein the facial attributes comprise age, gender, hair volume and expression.
In one embodiment, if the medical large language model embeds medical knowledge base information, the medical knowledge base information includes department information and doctor information, the preliminary diagnosis information obtaining module 404 further includes:
and the diagnosis guiding information output unit is used for outputting target department information and target doctor information corresponding to the preliminary diagnosis information.
In one embodiment, the facial image acquisition module 401 includes:
the initial illness state description information acquisition unit is used for acquiring initial illness state description information input by the authorized patient and determining the information type of the initial illness state description information;
the first target illness state description information acquisition unit is used for receiving the initial illness state description information as the target illness state description information if the information type of the initial illness state description information is text information;
and the second target illness state description information acquisition unit is used for converting the information type of the initial illness state description information into text information through a voice recognition processing mode if the information type of the initial illness state description information is voice information, and receiving the converted initial illness state description information as the target illness state description information.
In one embodiment, before the preliminary diagnostic information acquisition module 404, the apparatus further comprises:
the system prompt information generation module is used for generating system prompt information according to the facial attribute information and inputting the system prompt information into the medical large language model so that the medical large language model outputs personalized preliminary diagnosis information.
In one embodiment, the apparatus further comprises:
and the initial medical record information generation module is used for generating initial medical record information according to the patient information and the initial diagnosis information and associating the initial medical record information with the medical account number of the authorized patient.
In one embodiment, the apparatus further comprises:
the facial image preprocessing module is used for preprocessing the facial image, and if the preprocessed facial image does not meet the preset facial image detection condition, the prompting information for re-acquiring the facial image is generated.
In one embodiment, the present application also provides a storage medium having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the diagnostic information generation method as set forth in any one of the above embodiments.
In one embodiment, the present application also provides a computer device having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the diagnostic information generation method as described in any of the above embodiments.
Schematically, as shown in fig. 5, fig. 5 is a schematic internal structure of a computer device according to an embodiment of the present application, and the computer device 500 may be provided as a server. Referring to FIG. 5, a computer device 500 includes a processing component 502 that further includes one or more processors and memory resources represented by memory 501 for storing instructions, such as applications, executable by the processing component 502. The application program stored in the memory 501 may include one or more modules each corresponding to a set of instructions. Further, the processing component 502 is configured to execute instructions to perform the diagnostic information generation method of any of the embodiments described above.
The computer device 500 may also include a power supply component 503 configured to perform power management of the computer device 500, a wired or wireless network interface 504 configured to connect the computer device 500 to a network, and an input output (I/O) interface 505. The computer device 500 may operate based on an operating system stored in memory 501, such as Windows Server TM, mac OS XTM, unix TM, linux TM, free BSDTM, or the like.
It will be appreciated by those skilled in the art that the structure shown in FIG. 5 is merely a block diagram of some of the structures associated with the present inventive arrangements and is not limiting of the computer device to which the present inventive arrangements may be applied, and that a particular computer device may include more or fewer components than shown, or may combine some of the components, or have a different arrangement of components.
Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Herein, "a," "an," "the," and "the" may also include plural forms, unless the context clearly indicates otherwise. Plural means at least two cases such as 2, 3, 5 or 8, etc. "and/or" includes any and all combinations of the associated listed items.
In the present specification, each embodiment is described in a progressive manner, and each embodiment focuses on the difference from other embodiments, and may be combined according to needs, and the same similar parts may be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. A diagnostic information generation method, the method comprising:
responding to a diagnosis request of an authorized patient, acquiring a facial image of the authorized patient, and receiving target illness state description information of the authorized patient, wherein the target illness state description information is text information;
performing face attribute identification processing on the face image to obtain face attribute information;
generating patient information according to the target illness state description information and the facial attribute information;
and inputting the patient information into a medical large language model which is acquired in advance, and outputting the preliminary diagnosis information of the authorized patient.
2. The diagnostic information generating method according to claim 1, wherein the step of performing face attribute recognition processing on the face image to obtain face attribute information includes:
locating and marking faces in the face image by using a face detection algorithm;
extracting facial features of the marked facial images to obtain facial features corresponding to the facial images;
and carrying out face attribute prediction on the facial features to obtain a prediction result of each face attribute, and taking the prediction result of each face attribute as the face attribute information, wherein the face attributes comprise age, gender, hair volume and expression.
3. The diagnostic information generating method according to claim 1, wherein if medical knowledge base information is built in the medical large language model, the medical knowledge base information including department information and doctor information, the patient information is input to a medical large language model acquired in advance, and preliminary diagnostic information of the authorized patient is output while further comprising:
and outputting target department information and target doctor information corresponding to the preliminary diagnosis information.
4. The diagnostic information generating method according to claim 1, wherein the step of receiving target condition descriptive information of the authorized patient comprises:
acquiring initial illness state description information input by the authorized patient, and determining the information type of the initial illness state description information;
if the information type of the initial illness state description information is text information, receiving the initial illness state description information as the target illness state description information;
if the information type of the initial illness state description information is voice information, converting the information type of the initial illness state description information into text information through a voice recognition processing mode, and receiving the converted initial illness state description information as the target illness state description information.
5. The diagnostic information generating method according to any one of claims 1 to 4, wherein before the step of inputting the patient information to a medical large language model acquired in advance and outputting preliminary diagnostic information corresponding to the condition description information, the method further comprises:
generating system prompt information according to the facial attribute information, and inputting the system prompt information into the medical large language model so that the medical large language model outputs personalized preliminary diagnosis information.
6. The diagnostic information generating method according to any one of claims 1 to 4, characterized in that the method further comprises:
generating initial medical record information according to the patient information and the initial diagnosis information, and associating the initial medical record information with the medical account number of the authorized patient.
7. The diagnostic information generating method according to any one of claims 1 to 4, characterized in that the method further comprises:
and preprocessing the face image, and if the preprocessed face image does not meet the preset face image detection condition, generating prompt information for re-acquiring the face image.
8. A diagnostic information generating apparatus, characterized in that the apparatus comprises:
the facial image acquisition module is used for responding to a diagnosis request of an authorized patient, acquiring a facial image of the authorized patient, and receiving target illness state description information of the authorized patient, wherein the target illness state description information is text information;
the facial attribute information acquisition module is used for carrying out facial attribute identification processing on the facial image to obtain facial attribute information;
the patient information generating module is used for generating patient information according to the target illness state description information and the facial attribute information;
the preliminary diagnosis information acquisition module is used for inputting the patient information into a medical large language model acquired in advance and outputting the preliminary diagnosis information of the authorized patient.
9. A storage medium, characterized by: the storage medium having stored therein computer readable instructions which, when executed by one or more processors, cause the one or more processors to perform the steps of the diagnostic information generation method of any of claims 1 to 7.
10. A computer device, comprising: one or more processors, and memory;
stored in the memory are computer readable instructions which, when executed by the one or more processors, perform the steps of the diagnostic information generation method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310789573.6A CN116741331A (en) | 2023-06-29 | 2023-06-29 | Diagnostic information generation method, device, storage medium and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310789573.6A CN116741331A (en) | 2023-06-29 | 2023-06-29 | Diagnostic information generation method, device, storage medium and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116741331A true CN116741331A (en) | 2023-09-12 |
Family
ID=87909660
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310789573.6A Pending CN116741331A (en) | 2023-06-29 | 2023-06-29 | Diagnostic information generation method, device, storage medium and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116741331A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117373594A (en) * | 2023-10-24 | 2024-01-09 | 广州国家实验室 | Medical information determining method, device, equipment and medium |
-
2023
- 2023-06-29 CN CN202310789573.6A patent/CN116741331A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117373594A (en) * | 2023-10-24 | 2024-01-09 | 广州国家实验室 | Medical information determining method, device, equipment and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8438182B2 (en) | Patient identification | |
| CN112016279B (en) | Method, device, computer equipment and storage medium for structuring electronic medical record | |
| CN112035674B (en) | Diagnosis guiding data acquisition method, device, computer equipment and storage medium | |
| CN108899064A (en) | Electronic health record generation method, device, computer equipment and storage medium | |
| CN111985323B (en) | Face recognition method and system based on deep convolutional neural network | |
| WO2021169101A1 (en) | Method and apparatus for generating medical image recognition model, computer device and medium | |
| WO2022057309A1 (en) | Lung feature recognition method and apparatus, computer device, and storage medium | |
| CN112016295A (en) | Symptom data processing method and device, computer equipment and storage medium | |
| CN116741331A (en) | Diagnostic information generation method, device, storage medium and computer equipment | |
| CN112652386A (en) | Triage data processing method and device, computer equipment and storage medium | |
| CN108461130B (en) | Intelligent scheduling method and system for treatment tasks | |
| CN116860935A (en) | Content management method, device, equipment and medium based on prompt word question-answer interaction | |
| CN112151187B (en) | Information query method, device, computer equipment and storage medium | |
| CN117524427A (en) | Intelligent medical image analysis method | |
| WO2021139271A1 (en) | Fm model based method and apparatus for predicting medical hot spot, and computer device | |
| CN111783725A (en) | Face recognition method, face recognition device and storage medium | |
| CN116719840A (en) | Medical information pushing method based on post-medical-record structured processing | |
| KR20210018586A (en) | Method and apparatus for identifying video content using biometric features of characters | |
| CN115588492A (en) | Diagnosis guiding method and system based on artificial intelligence | |
| CN115687136A (en) | Script program processing method, system, computer equipment and medium | |
| CN115116584A (en) | Safe and efficient intelligent medical data analysis method and device based on 5G | |
| CN114238715A (en) | Question-answering system based on social aid, construction method, computer equipment and medium | |
| CN111582404B (en) | Content classification method, device and readable storage medium | |
| US20150302171A1 (en) | Bioimaging grid | |
| CN112784990A (en) | Training method of member inference model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |