Information output method, device, computer equipment and medium based on artificial intelligence

Abstract

The present application is applicable to the field of artificial intelligence technology, and provides an information output method, device, computer equipment and medium based on artificial intelligence, the method comprising: obtaining the patient's symptom information and disease detection results, performing disease identification on the symptom information and disease detection results, and obtaining the patient's disease; determining a first prescription according to the patient's disease, and querying the pathological information of the patient's disease; performing pathological matching on the disease detection results according to the pathological information, and generating a second prescription according to the matching results of the pathological diagnosis; obtaining the patient's diagnosis record, and screening the first prescription and the second prescription for contraindication drugs according to the diagnosis record; generating prescription output information according to the first prescription and the second prescription after the contraindication drug screening, and outputting the prescription output information. Based on the patient's symptom information and disease detection results, the present application can automatically push accurate prescription information to patients and / or doctors, which helps to improve the efficiency and accuracy of prescription writing.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to an information output method, device, computer equipment and medium based on artificial intelligence. Background Art

[0002] As people pay more attention to health and the number of patients increases, the demand for medical treatment is also increasing. However, in medical institutions, disease diagnosis is mainly based on the doctor's personal experience. There are too few experienced and senior doctors to meet the huge demand for medical treatment.

[0003] In the existing disease diagnosis process, doctors prescribe medicine based on the patient's physical signs, physical sensations and other information combined with the doctor's own experience, which results in a longer consultation time for each patient and reduces the efficiency of prescribing medicine. Summary of the invention

[0004] In view of this, the embodiments of the present application provide an information output method, apparatus, computer device and medium based on artificial intelligence to solve the problem of low efficiency in prescribing medicines during the existing doctor's consultation process.

[0005] A first aspect of an embodiment of the present application provides an information output method based on artificial intelligence, comprising:

[0006] Acquire the patient's symptom information and disease test results, and perform disease identification on the symptom information and the disease test results to obtain the patient's disease;

[0007] Determine a first prescription according to the patient's disease, and query pathological information of the patient's disease, wherein the pathological information includes physical sign information of the corresponding patient's disease at different disease degrees;

[0008] Performing pathological matching on the disease detection result according to the pathological information, and generating a second prescription according to the matching result of the pathological diagnosis;

[0009] Obtaining the patient's diagnosis record, and screening the first prescription and the second prescription for contraindications according to the diagnosis record;

[0010] Generate prescription output information based on the first prescription and the second prescription after contraindicated drug screening, and output the prescription output information.

[0011] Further, determining the first prescription according to the patient's disease and querying the pathological information of the patient's disease includes:

[0012] Obtaining the disease number of the patient's disease, and matching the disease number with a pre-stored prescription query table to obtain the first prescription, wherein the prescription query table stores the correspondence between different disease numbers and corresponding fixed prescriptions;

[0013] The disease number is matched with a pre-stored pathology query table to obtain the pathology information, wherein the pathology query table stores the corresponding relationship between different disease numbers and corresponding pathology information.

[0014] Furthermore, obtaining the patient's diagnosis record and screening the first prescription and the second prescription for contraindications according to the diagnosis record includes:

[0015] Querying the contraindicated drugs recorded in the diagnosis record, and matching the contraindicated drugs with the drugs in the first prescription and the second prescription respectively;

[0016] If the contraindicated drug is successfully matched with a drug in the first prescription or the second prescription, the matched drug in the first prescription or the second prescription is deleted.

[0017] Furthermore, the method further comprises:

[0018] Querying the consulting doctor according to the patient's disease and determining the consulting doctor's consultation status;

[0019] If the consulting doctor's consulting status is idle, a consulting session is established between the consulting doctor and the patient, and the symptom information, the disease detection result, the patient's disease and the prescription output information are sent in the consulting session.

[0020] Furthermore, after determining the consulting status of the consulting doctor, the method further includes:

[0021] If the consulting doctor's consulting status is busy, query the consulting doctor's current consulting session, and send the current consulting session to the patient;

[0022] If the patient joins the current consultation session, the historical session record of the current consultation session is sent to the patient, and the patient is set to a state of no right to speak.

[0023] Furthermore, querying the consulting doctor according to the patient's disease and determining the consulting doctor's consulting status includes:

[0024] Determine a consultation clinic according to the disease number of the patient's disease, and obtain a consultation image of the consultation clinic;

[0025] Perform face recognition on the consultation image, and determine the consulting doctor and the consulting doctor's consultation status according to the face recognition result.

[0026] Furthermore, it is characterized in that the disease identification is performed on the symptom information and the disease detection result to obtain the patient's disease, including:

[0027] Extracting characteristic words from the symptom information to obtain disease characteristic words, and searching for disease sign data based on the disease characteristic words;

[0028] The disease detection result is compared with the disease sign data, and the patient's disease is determined based on the disease data comparison result.

[0029] A second aspect of an embodiment of the present application provides an information output device, including:

[0030] A disease identification unit, used to obtain the patient's symptom information and disease test results, and perform disease identification on the symptom information and the disease test results to obtain the patient's disease;

[0031] A pathology query unit, configured to determine a first prescription according to the patient's disease, and query pathology information of the patient's disease, wherein the pathology information includes physical sign information of the corresponding patient's disease at different disease degrees;

[0032] A pathology matching unit, configured to perform pathology matching on the disease detection result according to the pathology information, and generate a second prescription according to the matching result of the pathology diagnosis;

[0033] a drug screening unit, configured to obtain the patient's diagnosis record, and screen the first prescription and the second prescription for contraindicated drugs according to the diagnosis record;

[0034] The information output unit is used to generate prescription output information according to the first prescription and the second prescription after contraindicated drug screening, and output the prescription output information.

[0035] A third aspect of an embodiment of the present application provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the computer device, wherein when the processor executes the computer program, each step of the artificial intelligence-based information output method provided in the first aspect is implemented.

[0036] The fourth aspect of an embodiment of the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the artificial intelligence-based information output method provided in the first aspect.

[0037] The embodiments of the present application provide an artificial intelligence-based information output method, device, computer equipment and medium. The first prescription is determined by the patient's disease, and the necessary prescription corresponding to the patient's disease can be effectively obtained. By querying the pathological information of the patient's disease and performing a pathological diagnosis on the disease detection results according to the pathological information, the auxiliary prescription required for the patient's current symptoms can be effectively obtained. The first prescription and the second prescription are screened for contraindicated drugs through the diagnosis records, which prevents the patient from taking contraindicated drugs. Accurate prescription information can be automatically pushed to the patient and / or doctor, which helps to improve the efficiency and accuracy of prescribing. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 This is a flowchart of an implementation of an information output method based on artificial intelligence provided in an embodiment of the present application;

[0040] Figure 2 is a flowchart of an implementation method of an information output method based on artificial intelligence provided by another embodiment of the present application;

[0041] Figure 3 is a structural block diagram of an information output device provided in an embodiment of the present application;

[0042] Figure 4 It is a structural block diagram of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0045] AI basic technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing technology, operation / interaction systems, mechatronics, etc. AI software technologies mainly include computer vision technology, robotics technology, biometrics technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0046] In the embodiment of the present application, based on artificial intelligence technology, an artificial intelligence-based information output method is implemented, and the automatically generated prescription output information can be output to the doctor, which facilitates the doctor's diagnosis of the patient and improves the efficiency of prescribing medicines.

[0047] See also Figure 1 , Figure 1 The following is a flowchart of an implementation of an artificial intelligence-based information output method provided in an embodiment of the present application. The artificial intelligence-based information output method is applied to any computer device, which may be a server, a mobile phone, a tablet, or a wearable smart device. The artificial intelligence-based information output method includes:

[0048] Step S10, obtaining the patient's symptom information and disease detection results, and performing disease identification on the symptom information and the disease detection results to obtain the patient's disease;

[0049] In this embodiment, the information output method based on artificial intelligence is applied to the cloud medical server. While waiting for consultation, the patient can directly send symptom information and disease detection results to the cloud medical server through a mobile phone. The cloud medical server performs disease identification on the acquired symptom information and disease detection results to identify the patient's disease based on the patient's symptom information and disease detection results. Optionally, in this embodiment, the type of the patient's disease can be a chronic disease.

[0050] Optionally, in this step, disease identification is performed by inputting the patient's symptom information and disease detection results into a pre-trained disease recognition model to obtain the patient's disease. In this embodiment, the disease recognition model is trained according to the disease sample data until the disease recognition model converges to obtain the pre-trained disease recognition model. The disease sample data includes the correspondence between different patient diseases and corresponding sample symptoms and sample disease detection results, so that the pre-trained disease recognition model can effectively identify the corresponding patient disease based on the input symptom information and disease detection results.

[0051] Step S20, determining a first prescription according to the patient's disease, and querying pathological information of the patient's disease;

[0052] Among them, the pathological information includes the physical sign information of the corresponding patient's disease at different disease levels. For example, pathological information A1 includes the physical sign information corresponding to the patient's disease B1 at early, middle and late disease levels respectively. The physical sign information is used to judge the severity and criticality of the patient's condition. The physical sign information includes heart rate, pulse, blood pressure, respiration, pain, blood oxygen, pupil and corneal reflex information, etc. The first prescription is used to characterize the basic prescription corresponding to the target chronic disease.

[0053] Optionally, in this step, determining the first prescription according to the patient's disease and querying the pathological information of the patient's disease includes:

[0054] Obtaining a disease number of the patient's disease, and matching the disease number with a pre-stored prescription query table to obtain the first prescription;

[0055] Matching the disease number with a pre-stored pathology query table to obtain the pathology information;

[0056] Among them, the prescription query table stores the correspondence between different disease numbers and corresponding fixed prescriptions. The disease number is used to characterize the corresponding patient disease, and the disease numbers of different patient diseases are different. The pathology query table stores the correspondence between different disease numbers and corresponding pathology information. In this step, by matching the disease number with the pre-stored prescription query table, the basic prescription corresponding to the patient's disease can be effectively obtained.

[0057] Furthermore, in this step, the symptom information and the disease detection results are used to identify the disease to obtain the patient's disease, including:

[0058] Extracting characteristic words from the symptom information to obtain disease characteristic words, and searching for disease sign data based on the disease characteristic words;

[0059] The disease characteristic words are used to characterize the diseases involved in the symptom information. In this step, the disease characteristic words are extracted from the symptom information through the disease recognition model, so that the disease characteristic words used to characterize the symptom information can be effectively obtained;

[0060] Comparing the disease detection result with the disease physical sign data, and determining the patient's disease according to the disease data comparison result;

[0061] Among them, the disease data is compared with the standard physical sign data to determine whether there is abnormal data in the disease detection result, and the patient's disease is determined based on the abnormal data in the disease detection result. Optionally, in this step, the patient's disease is obtained by matching the abnormal data in the disease detection result with a pre-stored disease query table.

[0062] Step S30, performing pathological matching on the disease detection result according to the pathological information, and generating a second prescription according to the matching result of the pathological diagnosis;

[0063] Among them, a pathological diagnosis is performed on the disease detection results according to the pathological information to determine the patient's current disease state. Since the auxiliary prescriptions corresponding to different disease states are different, in this step, a second prescription is generated according to the matching results of the pathological diagnosis, thereby improving the accuracy of subsequent prescription output information.

[0064] Optionally, in this step, the disease state corresponding to the disease detection result is determined by matching the physical sign information stored in the disease detection result with the characteristic information stored in the pathological information.

[0065] Step S40, obtaining the patient's diagnosis record, and screening the first prescription and the second prescription for contraindications according to the diagnosis record;

[0066] The diagnostic record stores the patient's historical disease test results, historical prescriptions, allergy information, and contraindication drugs. In this step, the first prescription and the second prescription are screened for contraindication drugs through the diagnostic record, which improves the accuracy of subsequent prescription output information and prevents the patient from taking contraindication drugs or allergy drugs.

[0067] Optionally, in this step, obtaining the patient's diagnosis record and screening the first prescription and the second prescription for contraindications according to the diagnosis record includes:

[0068] Querying the contraindicated drugs recorded in the diagnosis record, and matching the contraindicated drugs with the drugs in the first prescription and the second prescription respectively;

[0069] If the contraindicated drug successfully matches the drug in the first prescription or the second prescription, deleting the matched drug in the first prescription or the second prescription;

[0070] Among them, if the contraindicated drug is successfully matched with the drug in the first prescription or the second prescription, it is determined that the first prescription or the second prescription contains contraindicated drugs that the patient cannot take. By deleting the matched drugs in the first prescription or the second prescription, the accuracy of subsequent prescription output information is improved.

[0071] Optionally, in this step, if the contraindicated drug is successfully matched with the drug in the first prescription, the matched drug in the first prescription is deleted, and the associated drug corresponding to the deleted drug is queried. The associated drug has similar efficacy to the corresponding deleted drug. The queried associated drug is added to the first prescription, and the associated drug is marked as a replacement in the first prescription. The replacement mark is used to remind the doctor that the associated drug is a replacement drug.

[0072] Step S50, generating prescription output information according to the first prescription and the second prescription after contraindication drug screening, and outputting the prescription output information;

[0073] Among them, the prescription output information is obtained by combining the drugs in the first prescription and the second prescription after the contraindicated drug screening. By outputting the prescription output information, a prescription reference is effectively provided for the doctor's diagnosis of the patient. Preferably, in this step, the prescription output information can also be directly sent to the patient to achieve the effect of automatically pushing accurate prescription information to the patient.

[0074] In this step, the cloud medical server effectively facilitates the corresponding doctor to view the prescription output information by storing the prescription output information in the patient's disease test results.

[0075] In this embodiment, the first prescription is determined by the patient's disease, and the necessary prescription corresponding to the patient's disease can be effectively obtained. By querying the pathological information of the patient's disease and performing a pathological diagnosis on the disease detection results based on the pathological information, the auxiliary prescription required for the patient's current symptoms can be effectively obtained. The first prescription and the second prescription are screened for contraindicated drugs through the diagnosis records, which prevents the patient from taking contraindicated drugs. Accurate prescription information can be automatically pushed to the patient and / or doctor, which helps to improve the efficiency and accuracy of prescribing.

[0076] See also Figure 2 , Figure 2 is a flowchart of an implementation of an information output method based on artificial intelligence provided by another embodiment of the present application. Figure 1 Embodiment, the information output method based on artificial intelligence provided in this embodiment is used for Figure 1 The steps after step S50 in the embodiment are further refined, including:

[0077] Step S60, querying the consulting doctor according to the patient's disease and determining the consulting doctor's consultation status;

[0078] Among them, the disease number of the patient's disease is matched with the pre-stored doctor query table to obtain the consulting doctor, and the consulting status of the consulting doctor is determined by querying the usage status of the corresponding account of the consulting doctor. The doctor query table stores the correspondence between different disease numbers and corresponding consulting doctors; in this step, the consulting doctor can use online diagnosis to consult the patient.

[0079] Optionally, in this step, the consulting status of the consulting doctor can be determined by obtaining an image of the consulting clinic corresponding to the consulting doctor and performing face recognition based on the image of the consulting clinic.

[0080] Specifically, in this step, querying the consulting doctor according to the patient's disease and determining the consulting doctor's consulting status includes:

[0081] Determine a consultation clinic according to the disease number of the patient's disease, and obtain a consultation image of the consultation clinic;

[0082] Performing face recognition on the consultation image, and determining the consulting doctor and the consulting doctor's consultation status according to the face recognition result;

[0083] Among them, face recognition is performed on the consultation image to determine the doctor and patient in the consultation image. When it is detected that there is no patient in the consultation image, the consultation status of the consulting doctor is determined to be idle. When it is detected that there is a patient in the consultation image, the consultation status of the consulting doctor is determined to be busy.

[0084] Step S70, if the consulting doctor's consulting state is idle, a consulting session is established between the consulting doctor and the patient, and the symptom information, the disease detection result, the patient's disease and the prescription output information are sent in the consulting session;

[0085] Among them, if the consultation status is idle, a consultation session is established between the consulting doctor and the patient, which facilitates the communication between the patient and the consulting doctor, and provides data reference for the doctor's consultation operation by sending symptom information, disease test results, target chronic diseases and prepared prescriptions in the consultation session.

[0086] In this step, a consultation session between the consulting doctor and the patient can be established based on any group chat application, and the consultation session can effectively facilitate the doctor's consultation of the patient.

[0087] Step S80, if the consulting doctor's consulting status is busy, query the consulting doctor's current consulting session, and send the current consulting session to the patient;

[0088] Among them, if the consultation status is busy, by querying the current consultation session of the consulting doctor and sending the current consultation session to the patient, it is convenient for the patient to query the current consultation status and to refer to the doctor's answers to questions during the diagnosis process.

[0089] Step S90, if the patient joins the current consultation session, the historical session record of the current consultation session is sent to the patient, and the patient is set to a state of no right to speak;

[0090] Among them, if the patient joins the current consultation session, the historical session record of the current consultation session is sent to the patient, which effectively facilitates the patient's understanding of the doctor's consultation process, and sets the patient to a state without the right to speak, preventing the patient from interfering with the doctor's consultation in the current consultation session.

[0091] It should be noted that the patient's privacy information needs to be deleted in the historical conversation record to prevent the leakage of the patient's privacy information. The privacy information includes the patient's name, patient's age, patient's address and patient's diagnosis results, etc. The historical conversation record includes the communication record between the doctor and the corresponding patient, based on the communication record to facilitate the patient's understanding of the consultation process.

[0092] In this embodiment, the consultation status of the consulting doctor is determined by querying the usage status of the corresponding account of the consulting doctor. If the consultation status is idle, a consultation session is established between the consulting doctor and the patient to facilitate communication between the patient and the consulting doctor, and symptom information, disease detection results, patient disease and prescription output information are sent in the consultation session to provide data reference for the doctor's consultation operation. If the consultation status is busy, the current consultation session of the consulting doctor is queried and sent to the patient, which facilitates the patient's query on the current consultation status and provides a reference for the patient's answers to the doctor's questions during the diagnosis process.

[0093] See also Figure 3 , Figure 3 1 is a structural block diagram of an information output device 100 provided in an embodiment of the present application. In this embodiment, each unit included in the information output device 100 is used to execute Figure 1 , Figure 2 For details, please refer to the steps in the corresponding embodiment. Figure 1 , Figure 2 as well as Figure 1 , Figure 2 For the convenience of explanation, only the parts related to this embodiment are shown. Figure 3The information output device 100 includes: a disease identification unit 10, a pathology query unit 11, a pathology matching unit 12, a drug screening unit 13 and an information output unit 14, wherein:

[0094] The disease identification unit 10 is used to obtain the patient's symptom information and disease detection results, and to identify the patient's disease on the symptom information and the disease detection results. In this unit, the patient's disease is obtained by inputting the patient's symptom information and disease detection results into a pre-trained disease identification model for disease identification. In this embodiment, the pre-trained disease identification model is obtained by training the disease identification model according to the disease sample data until the disease identification model converges. The disease sample data includes the correspondence between different patient diseases and the corresponding sample symptoms and sample disease detection results, so that the pre-trained disease identification model can effectively identify the corresponding patient disease based on the input symptom information and disease detection results.

[0095] The disease identification unit 10 is further used to: extract characteristic words from the symptom information to obtain disease characteristic words, and query disease sign data according to the disease characteristic words;

[0096] The disease detection result is compared with the disease sign data, and the patient's disease is determined based on the disease data comparison result.

[0097] The pathology query unit 11 is used to determine the first prescription according to the patient's disease and query the pathology information of the patient's disease, which includes the physical sign information of the corresponding patient's disease at different disease levels. For example, the pathology information A1 includes the physical sign information corresponding to the patient's disease B1 at the early, middle and late disease levels, respectively. The physical sign information is used to judge the severity and criticality of the patient's condition. The physical sign information includes heart rate, pulse, blood pressure, respiration, pain, blood oxygen, pupil and corneal reflection information, etc. The first prescription is used to characterize the basic prescription corresponding to the target chronic disease.

[0098] The pathology query unit 11 is further used to: obtain the disease number of the patient's disease, and match the disease number with a pre-stored prescription query table to obtain the first prescription, wherein the prescription query table stores the correspondence between different disease numbers and corresponding fixed prescriptions;

[0099] The disease number is matched with a pre-stored pathology query table to obtain the pathology information. The prescription query table stores the correspondence between different disease numbers and corresponding fixed prescriptions. The disease number is used to characterize the corresponding patient disease. The disease numbers of different patient diseases are different. The pathology query table stores the correspondence between different disease numbers and corresponding pathology information. In this unit, by matching the disease number with the pre-stored prescription query table, the basic prescription corresponding to the patient's disease can be effectively obtained.

[0100] The pathology matching unit 12 is used to perform pathology matching on the disease detection result according to the pathology information, and generate a second prescription according to the matching result of the pathology diagnosis. The disease detection result is pathologically diagnosed according to the pathology information to determine the patient's current disease state. Since the auxiliary prescriptions corresponding to different disease states are different, this unit generates the second prescription according to the matching result of the pathology diagnosis, thereby improving the accuracy of the subsequent prescription output information.

[0101] The drug screening unit 13 is used to obtain the patient's diagnosis record and screen the first prescription and the second prescription for contraindication drugs according to the diagnosis record. The diagnosis record stores the patient's historical disease test results, historical prescriptions, allergy information, and contraindication drugs. In this unit, the first prescription and the second prescription are screened for contraindication drugs through the diagnosis record, which improves the accuracy of subsequent prescription output information and prevents the patient from taking contraindication drugs or allergy drugs.

[0102] The drug screening unit 13 is further used to: query the contraindicated drugs recorded in the diagnosis record, and match the contraindicated drugs with the drugs in the first prescription and the second prescription respectively;

[0103] If the contraindicated drug successfully matches the drug in the first prescription or the second prescription, the matched drug in the first prescription or the second prescription is deleted. Wherein, if the contraindicated drug successfully matches the drug in the first prescription or the second prescription, it is determined that there are contraindicated drugs in the first prescription or the second prescription that the patient cannot take. By deleting the matched drugs in the first prescription or the second prescription, the accuracy of the subsequent prescription output information is improved. Optionally, in this unit, if the contraindicated drug successfully matches the drug in the first prescription, the matched drug in the first prescription is deleted, and the associated drug corresponding to the deleted drug is queried. The associated drug has similar efficacy to the corresponding deleted drug. The queried associated drug is added to the first prescription, and the associated drug is replaced in the first prescription. The replacement mark is used to remind the doctor that the associated drug is a replacement drug.

[0104] The information output unit 14 is used to generate prescription output information according to the first prescription and the second prescription after the contraindication drug screening, and output the prescription output information. The prescription output information is obtained by combining the drugs in the first prescription and the second prescription after the contraindication drug screening, and by outputting the prescription output information, a prescription reference is effectively provided for the doctor's diagnosis of the patient.

[0105] The information output unit 14 is also used to: query the consulting doctor according to the patient's disease and determine the consulting doctor's consultation status;

[0106] If the consulting doctor's consulting status is idle, a consulting session is established between the consulting doctor and the patient, and the symptom information, the disease detection result, the patient's disease and the prescription output information are sent in the consulting session.

[0107] Among them, the disease number of the patient's disease is matched with the pre-stored doctor query table to obtain the consulting doctor, and the consulting status of the consulting doctor is determined by querying the usage status of the corresponding account of the consulting doctor. The doctor query table stores the correspondence between different disease numbers and corresponding consulting doctors; in this unit, the consulting doctor can use online diagnosis to consult the patient.

[0108] Optionally, if the consultation status is idle, a consultation session is established between the consulting doctor and the patient, thereby facilitating communication between the patient and the consulting doctor, and providing data reference for the doctor's consultation operation by sending symptom information, disease test results, target chronic diseases and prepared prescriptions in the consultation session.

[0109] Optionally, the information output unit 14 is further used to: if the consultation status of the consulting doctor is busy, query the current consultation session of the consulting doctor, and send the current consultation session to the patient;

[0110] If the patient joins the current consultation session, the historical session record of the current consultation session is sent to the patient, and the patient is set to a state of no right to speak.

[0111] Among them, if the patient joins the current consultation session, the historical session record of the current consultation session is sent to the patient, which effectively facilitates the patient's understanding of the doctor's consultation process, and sets the patient to a state without the right to speak, preventing the patient from interfering with the doctor's consultation in the current consultation session.

[0112] It should be noted that the patient's privacy information needs to be deleted in the historical conversation record to prevent the leakage of the patient's privacy information. The privacy information includes the patient's name, patient's age, patient's address and patient's diagnosis results, etc. The historical conversation record includes the communication record between the doctor and the corresponding patient, based on the communication record to facilitate the patient's understanding of the consultation process.

[0113] Furthermore, the information output unit 14 is also used to: determine a consultation clinic according to the disease number of the patient's disease, and obtain a consultation image of the consultation clinic;

[0114] Performing face recognition on the consultation image, and determining the consulting doctor and the consulting doctor's consultation status according to the face recognition result. Wherein, by performing face recognition on the consultation image to determine the doctor and the patient in the consultation image, when it is detected that there is no patient in the consultation image, the consulting doctor's consultation status is determined to be an idle state, and when it is detected that there is a patient in the consultation image, the consulting doctor's consultation status is determined to be a busy state.

[0115] In this embodiment, the first prescription is determined by the patient's disease, and the necessary prescription corresponding to the patient's disease can be effectively obtained. By querying the pathological information of the patient's disease and performing a pathological diagnosis on the disease detection results based on the pathological information, the auxiliary prescription required for the patient's current symptoms can be effectively obtained. The first prescription and the second prescription are screened for contraindicated drugs through the diagnosis records, which prevents the patient from taking contraindicated drugs. Accurate prescription information can be automatically pushed to the patient and / or doctor, which helps to improve the efficiency and accuracy of prescribing.

[0116] Figure 4 2 is a structural block diagram of a computer device 2 provided in another embodiment of the present application. Figure 4 As shown, the computer device 2 of this embodiment includes: a processor 20, a memory 21, and a computer program 22 stored in the memory 21 and executable on the processor 20, such as a program of an information output method based on artificial intelligence. When the processor 20 executes the computer program 22, the steps in each embodiment of the above-mentioned information output method based on artificial intelligence are implemented, such as Figure 1 S10 to S50 as shown, or Figure 2 Alternatively, the processor 20 implements the above when executing the computer program 22 Figure 3 The functions of each unit in the corresponding embodiment are, for example, Figure 3 For details on the functions of units 10 to 14 shown, please refer to Figure 3 The relevant descriptions in the corresponding embodiments are not repeated here.

[0117] Exemplarily, the computer program 22 may be divided into one or more units, which are stored in the memory 21 and executed by the processor 20 to complete the present application. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 22 in the computer device 2. For example, the computer program 22 may be divided into a disease identification unit 10, a pathology query unit 11, a pathology matching unit 12, a drug screening unit 13, and an information output unit 14, and the specific functions of each unit are as described above.

[0118] The computer device may include, but is not limited to, a processor 20 and a memory 21. Those skilled in the art will appreciate that Figure 4 It is only an example of the computer device 2 and does not constitute a limitation of the computer device 2. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device may also include input and output devices, network access devices, buses, etc.

[0119] The processor 20 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0120] The memory 21 may be an internal storage unit of the computer device 2, such as a hard disk or memory of the computer device 2. The memory 21 may also be an external storage device of the computer device 2, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the computer device 2. Further, the memory 21 may also include both an internal storage unit of the computer device 2 and an external storage device. The memory 21 is used to store the computer program and other programs and data required by the computer device. The memory 21 may also be used to temporarily store data that has been output or is to be output.

[0121] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0122] If the integrated module is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Among them, the computer-readable storage medium can be non-volatile or volatile. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable storage medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in computer-readable storage media can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable storage media do not include electrical carrier signals and telecommunication signals.

[0123] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An information output method based on artificial intelligence, characterized in that: include: Acquire the patient's symptom information and disease test results, and perform disease recognition on the symptom information and the disease test results through a pre-trained disease recognition model to obtain the patient's disease; Determine a first prescription according to the patient's disease, and query pathological information of the patient's disease, wherein the pathological information includes physical sign information of the corresponding patient's disease at different disease degrees; Performing pathology matching on the disease detection result according to the pathology information, and generating a second prescription according to the pathology matching result; Obtaining the patient's diagnosis record, and screening the first prescription and the second prescription for contraindications according to the diagnosis record; generating prescription output information according to the first prescription and the second prescription after contraindication drug screening, and outputting the prescription output information; The method further comprises: Querying the consulting doctor according to the patient's disease and determining the consulting doctor's consultation status; If the consulting doctor's consulting status is idle, a consulting session is established between the consulting doctor and the patient, and the symptom information, the disease detection result, the patient's disease and the prescription output information are sent in the consulting session.

2. The information output method based on artificial intelligence according to claim 1, characterized in that: Determining the first prescription according to the patient's disease and querying the pathological information of the patient's disease includes: Obtaining the disease number of the patient's disease, and matching the disease number with a pre-stored prescription query table to obtain the first prescription, wherein the prescription query table stores the correspondence between different disease numbers and corresponding fixed prescriptions; The disease number is matched with a pre-stored pathology query table to obtain the pathology information, wherein the pathology query table stores the corresponding relationship between different disease numbers and corresponding pathology information.

3. The information output method based on artificial intelligence according to claim 1, characterized in that: The obtaining of the patient's diagnosis record and screening the first prescription and the second prescription for contraindications according to the diagnosis record includes: Querying the contraindicated drugs recorded in the diagnosis record, and matching the contraindicated drugs with the drugs in the first prescription and the second prescription respectively; If the contraindicated drug is successfully matched with a drug in the first prescription or the second prescription, the matched drug in the first prescription or the second prescription is deleted.

4. The information output method based on artificial intelligence according to claim 1, characterized in that: The determining of the consultation status of the consulting doctor further includes: If the consulting doctor's consulting status is busy, query the consulting doctor's current consulting session, and send the current consulting session to the patient; If the patient joins the current consultation session, the historical session record of the current consultation session is sent to the patient, and the patient is set to a state of no right to speak.

5. The information output method based on artificial intelligence according to claim 1, characterized in that: The querying of the consulting doctor according to the patient's disease and determining the consulting doctor's consulting status include: Determine a consultation clinic according to the disease number of the patient's disease, and obtain a consultation image of the consultation clinic; Perform face recognition on the consultation image, and determine the consulting doctor and the consulting doctor's consultation status according to the face recognition result.

6. The information output method based on artificial intelligence according to any one of claims 1 to 5, characterized in that: The step of performing disease identification on the symptom information and the disease detection result to obtain the patient's disease includes: Extracting characteristic words from the symptom information to obtain disease characteristic words, and searching for disease sign data based on the disease characteristic words; The disease detection result is compared with the disease sign data, and the patient's disease is determined based on the disease data comparison result.

7. An information output device based on artificial intelligence, characterized in that: include: A disease identification unit is used to obtain the patient's symptom information and disease detection results, and perform disease identification on the symptom information and the disease detection results through a pre-trained disease identification model to obtain the patient's disease; A pathology query unit, configured to determine a first prescription according to the patient's disease, and query pathology information of the patient's disease, wherein the pathology information includes physical sign information of the corresponding patient's disease at different disease degrees; A pathology matching unit, configured to perform pathology matching on the disease detection result according to the pathology information, and generate a second prescription according to the pathology matching result; a drug screening unit, configured to obtain the patient's diagnosis record, and screen the first prescription and the second prescription for contraindication drugs according to the diagnosis record; an information output unit, configured to generate prescription output information according to the first prescription and the second prescription after contraindication drug screening, and output the prescription output information; The information output unit is also used to: query the consulting doctor according to the patient's disease and determine the consulting doctor's consultation status; If the consulting doctor's consulting status is idle, a consulting session is established between the consulting doctor and the patient, and the symptom information, the disease detection result, the patient's disease and the prescription output information are sent in the consulting session.

8. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images