Intelligent medical system based on big data

Abstract

The invention discloses an intelligent medical system based on big data, which comprises a data collection module, a diagnostic analysis module and an evaluation management module, and is characterized in that the data collection module is used for collecting facial features of doctors, disease information uploaded by users and medical record data of the users; the diagnosis management module is used for analyzing the fatigue degree of a doctor, adjusting and analyzing whether medicines used by a user interact or not, the evaluation management module is used for reminding the user to take the medicines on time, the user evaluates the doctor, and the data collection module, the diagnosis management module and the evaluation management module are in communication connection with one another. The data collection module comprises a visual module, an information input module and a medical record collection module, the visual module is used for collecting facial features of a doctor, the information input module is used for inputting focus information into the system by a user, and the system has the advantages that the safety of medicine use is improved, and the fatigue degree of the diagnosis doctor is reduced.

Description

Technical Field

[0001] The present invention relates to the field of medical technology, and in particular to an intelligent medical system based on big data. Background Art

[0002] With the rapid development of Internet technology, my country's intelligent medical technology has also developed rapidly. People can seek medical treatment online, and doctors can diagnose some minor illnesses and prescribe medicines through online medical treatment. However, due to the large number of users in the diagnosis process of existing technologies, the number of users handled by the diagnosing doctors varies greatly, so that the fatigue level of the diagnosing doctors is also different. The doctor's excessive fatigue will affect the accuracy of the diagnosis results. Moreover, when the diagnosing doctor is too tired, he may forget to ask the user's history of drug allergies, which may endanger the user's life safety. In addition, most users do not understand the interaction of drugs when using drugs. Taking multiple drugs together will cause the loss of efficacy after drug interaction or the drug interaction will endanger the user's life safety. Therefore, it is necessary to design an intelligent medical system based on big data to improve the safety of drug use and reduce the fatigue level of diagnosing doctors. Summary of the invention

[0003] The purpose of the present invention is to provide an intelligent medical system based on big data to solve the problems raised in the above background technology.

[0004] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent medical system based on big data, comprising a data collection module, a diagnosis analysis module and an evaluation management module, characterized in that: the data collection module is used to collect facial features of doctors, symptom information uploaded by users and medical records of users, the diagnosis management module is used to analyze the fatigue level of doctors and make adjustments and analyze whether the drugs currently used by users will interact with each other, the evaluation management module is used to remind users to take drugs on time, and users evaluate doctors, and the data collection module, the diagnosis management module and the evaluation management module are connected to each other in communication;

[0005] The intelligent analysis module includes a fatigue analysis submodule and a drug analysis submodule. The fatigue analysis submodule is used to analyze the fatigue level of the current diagnosing doctor, and the drug analysis submodule is used to analyze whether the user can use the current drug or whether the current drugs will be dangerous when used simultaneously.

[0006] The drug authority management module includes an authority detection submodule and a drug application submodule. The authority detection submodule is used to detect whether the current diagnosing doctor has the authority to prescribe the current drug, and the drug application module is used to apply for drugs from superiors or apply for drug adjustment from other hospitals.

[0007] According to the above technical solution, the data collection module includes a visual module, an information entry module and a medical record collection module. The visual module is used to collect the facial features of the doctor, the information entry module is used for the user to enter the lesion information and the information of the medicine used simultaneously into the system, and the case collection module is used to retrieve the user's medical record data according to the current user information.

[0008] According to the above technical solution, the diagnosis management module includes an intelligent analysis module and a drug authority management module. The intelligent analysis module is used to analyze the doctor's fatigue level and make adjustments. It is used to analyze whether the user is allergic to the drugs currently prescribed by the doctor and whether the drugs used at the same time will have pharmacological effects that may cause danger to the body. The drug authority management module is used to manage the diagnostic doctor's authority to prescribe drugs.

[0009] According to the above technical solution, the evaluation management module includes a medication reminder module, and the medication reminder module is used to remind the user to take medication on time.

[0010] According to the above technical solution, the evaluation management module also includes a diagnosis evaluation module and a medical reminder module. The diagnosis evaluation module is used for users to evaluate diagnostic doctors, and the diagnosis reminder module is used to remind users to go to the doctor when the user continues to use the drug for more than the treatment course.

[0011] According to the above technical solution, the operation method of the intelligent medical system mainly includes the following steps:

[0012] Step S1: Through the visual module, the facial features of the current diagnosing doctor are photographed in real time during the operation of the system; through the information input module, the user's condition data and lesion images are input into the system; the information of the drugs used by the user is input into the system; through the medical record collection module, all medical record data are collected into the system according to the identity information of the current user;

[0013] Step S2: When the diagnosing doctor prescribes a drug, the system starts the authority detection submodule to start detecting whether the current diagnosing doctor has the authority to prescribe the current drug;

[0014] Step S3: After determining the drug for the user's condition, the system sends a communication signal to start the drug analysis submodule, and starts to analyze the mutual influence between the prescribed drugs and the drugs used at the same time, and removes the prescribed drugs according to the medication records in the user's medical records.

[0015] Step S4: During the work of the diagnosing doctor, the system starts the fatigue analysis submodule to assess the fatigue level of the diagnosing doctor and allocates patients according to the fatigue level;

[0016] Step S5: When the user picks up medicine, the current user's medicine code is obtained, the medicine is extracted according to the medicine code, and the user is reminded to take the medicine according to the doctor's advice. At the same time, when the user's symptoms are unclear, the user is reminded to go to the hospital for medical treatment and the doctor is evaluated through the diagnosis and evaluation module.

[0017] According to the above technical solution, step S2 further includes the following steps:

[0018] Step S21: when analyzing the user's condition, the user's condition description and lesion picture are retrieved, the user's condition data and lesion picture data are scanned and identified, and the diagnosing doctor prescribes medicine according to the user's diagnosis result;

[0019] Step S22: Retrieve the code of the currently prescribed drug and the number of the current diagnosing doctor, and identify the category to which the current drug code belongs. If the current drug is a restricted management drug, the current diagnosing doctor will retrieve the list of drug codes that the current diagnosing doctor can prescribe based on the number of the current diagnosing doctor, and compare the code of the prescribed drug. If the code of the currently prescribed drug is in the list of drug codes that the doctor can prescribe, the code of the currently prescribed drug will be marked as usable, otherwise it will be marked as unusable. By identifying whether the current diagnosing doctor has the right to use the currently prescribed drug, it is possible to avoid the current diagnosing doctor's operating error in prescribing restricted management drugs, avoid the drug being used by the user, and cause danger to the user, thereby improving the safety of drug management.

[0020] According to the above technical solution, step S3 further includes the following steps:

[0021] Step S31: retrieve the currently prescribed drug code, retrieve all the medical records of the current user, identify the drug codes and allergy drug codes that the user can use in the case, and for the drug codes prescribed by the current diagnosing doctor, if there is an allergy drug code in the drug codes prescribed by the current diagnosing doctor, mark the drug as unavailable, otherwise retrieve the drug code that will react with the currently prescribed drug and cannot be used at the same time, compare the prescribed drug code with the drug code that cannot be used at the same time, if there are drugs that react with each other in the prescribed drugs, mark the drugs that can react as unavailable, identify the mark, read the main function of the unavailable drug, and replace it according to the main function;

[0022] Step S32: when the user detects whether the current drug is allergic, the drug name input by the user is retrieved, and the names of allergic drugs in the medical record are compared with the drug name input by the user. If the drug name currently input by the user exists among the allergic drugs in the user's medical record, the user is reminded that the drug cannot be used, otherwise the user is reminded that the drug can be used. When the user detects a drug reaction, the drug name input by the user is retrieved, and the name of the drug that reacts with the drug is retrieved according to the drug name, and the drug name input by the user is compared. If the drug name input by the user exists, the drug is marked as unavailable, otherwise the user is reminded that the current drugs can be used at the same time, the marked unavailable drug is retrieved, the efficacy of the unavailable drug is identified, the name of the drug that will not interact with other drugs in the database is retrieved based on the efficacy, and the user is reminded to purchase the drug for use.

[0023] According to the above technical solution, step S4 further includes the following steps:

[0024] Step S41: retrieve the facial visual image and body visual image of the current diagnosing doctor, scan and identify the facial feature nodes of the current diagnosing doctor, anchor the eye bag edge nodes, connect the edge nodes to form an eye bag model, construct a grid model with the same grid size, overlap the eye bag model and the grid model, calculate the number of grids occupied by the eye bags after overlapping, and the grid data represents the area size of the eye bags, anchor the eye bag position, identify the RGB color value in the eye bag visual image, compare the threshold set by the system, mark the RGB color value greater than the threshold, retrieve the fatigue parameters in the database, and give the influence coefficients α and β of the eye bag area size and eye bag color on the doctor's fatigue according to the fatigue parameters in the database;

[0025] Step S42: Retrieve the duration of each diagnosis by the current diagnosing doctor and the rest duration between two diagnoses, and calculate the fatigue level of the current diagnosing doctor through a formula Where, i = 1, 2, 3, ... n, j = 1, 2, 3 ... n, P represents the fatigue of the current diagnosing doctor, T represents the time it takes for the current diagnosing doctor to diagnose a user's condition, t represents the rest time of the current diagnosing doctor in the interval between diagnoses, and n represents the number of users diagnosed by the current diagnosing doctor;

[0026] Step S43: When the doctor's fatigue level is greater than the first threshold, the current doctor number is retrieved, the department to which the current number belongs is identified, and a doctor is retrieved from the current department to replace the doctor. When the doctor's fatigue level is greater than the second threshold and less than the first threshold, the auxiliary diagnosis device is started, the current user's condition description is obtained, the diagnosis model is retrieved to identify the main features of the user's condition, and the diagnosis results and prescribed drugs in the database are retrieved based on the main features. When the doctor's fatigue level is less than the second threshold, the fatigue levels of all diagnosing doctors are retrieved and sorted in ascending order. If the diagnosing doctor's fatigue level is greater than the third threshold and less than the second threshold, the diagnosis is suspended for rest. Otherwise, the work continues until the fatigue level is greater than the second threshold. At this time, all diagnosing doctors are adjusted to work.

[0027] According to the above technical solution, in step S5, after the user extracts the medicine, the medication reminder module is started, the usage method of the current medicine is obtained, an alarm is set according to the usage method of the current medicine, the user is reminded to take the medicine on time during the medication time period, and the treatment time of the current medicine is retrieved. If the user's condition is still not improved at the end of the treatment time, a voice reminder is issued to remind the current user to go to the hospital for examination and treatment as soon as possible. The user can evaluate the service of the diagnostic doctor through the diagnosis evaluation module.

[0028] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: the present invention, by identifying allergic drugs in medical records and removing allergic drugs from drugs prescribed by doctors, can avoid users using allergic drugs, resulting in life-threatening allergies; by detecting whether prescribed drugs will react, it can avoid using drugs that will react at the same time, resulting in medical accidents that endanger the health of users, thereby improving the safety of people's use of drugs; by judging whether the user is allergic to the current drug, it can avoid users forgetting whether they are allergic to the drug, resulting in accidental ingestion and danger; it can detect whether drugs used by users at the same time will react, and recommend drugs with the same efficacy based on the efficacy, to avoid users using drugs at the same time. It can prevent danger from happening, greatly improving the safety of people's use of drugs. By calculating the size of the eye bags and marking the RGB color values ​​that are greater than the system threshold, it can quickly and preliminarily determine whether the current diagnosing doctor is fatigued. By calculating the fatigue level of the current diagnosing doctor, it can quickly adjust the user allocation according to the fatigue level, further reducing the fatigue level of the diagnosing doctor. By adjusting diagnosing doctors with different fatigue levels, it can avoid diagnosing doctors from working continuously, causing diagnosing doctors to be too tired and reducing the accuracy of diagnostic results. By reminding users to take medicines at regular intervals and reminding users to go to the hospital if their condition still does not improve at the end of the treatment cycle, it can avoid users forgetting to take medicines due to busy work and taking medicines intermittently, which can aggravate their condition. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0030] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0031] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] See also Figure 1 , the present invention provides a technical solution: an intelligent medical system based on big data, including a data collection module, a diagnosis analysis module and an evaluation management module, characterized in that: the data collection module is used to collect the facial features of doctors, the symptom information uploaded by users and the medical record data of users, the diagnosis management module is used to analyze the fatigue level of doctors and make adjustments and analyze whether the drugs currently used by users will interact with each other, the evaluation management module is used to remind users to take drugs on time, and users evaluate doctors, and the data collection module, the diagnosis management module and the evaluation management module are connected to each other in communication;

[0033] The intelligent analysis module includes a fatigue analysis submodule and a drug analysis submodule. The fatigue analysis submodule is used to analyze the fatigue level of the current diagnosing doctor, and the drug analysis submodule is used to analyze whether the user can use the current drug or whether the current drugs will be dangerous when used at the same time.

[0034] The drug authority management module includes an authority detection submodule and a drug application submodule. The authority detection submodule is used to detect whether the current diagnosing doctor has the authority to prescribe the current drug, and the drug application module is used to apply for drugs from superiors or apply for drug adjustment from other hospitals.

[0035] The data collection module includes a visual module, an information entry module and a medical record collection module. The visual module is used to collect the doctor's facial features, the information entry module is used for users to enter lesion information and information on medications used simultaneously into the system, and the case collection module is used to retrieve the user's medical record data based on the current user information.

[0036] The diagnosis management module includes an intelligent analysis module and a drug authority management module. The intelligent analysis module is used to analyze the doctor's fatigue level and make adjustments. It is used to analyze whether the user is allergic to the drugs currently prescribed by the doctor and whether the drugs used at the same time will have pharmacological effects that may cause danger to the body. The drug authority management module is used to manage the diagnostic doctor's authority to prescribe drugs.

[0037] The evaluation management module includes a medication reminder module, which is used to remind users to take medication on time.

[0038] The evaluation management module also includes a diagnosis evaluation module and a medical consultation reminder module. The diagnosis evaluation module is used by users to evaluate diagnostic doctors, and the diagnosis reminder module is used to remind users to seek medical treatment when users continue to use drugs for more than the course of treatment.

[0039] The operation method of the intelligent medical system mainly includes the following steps:

[0040] Step S1: Through the visual module, the facial features of the current diagnosing doctor are photographed in real time during the operation of the system; through the information input module, the user's condition data and lesion images are input into the system; the information of the drugs used by the user is input into the system; through the medical record collection module, all medical record data are collected into the system according to the identity information of the current user;

[0041] Step S2: When the diagnosing doctor prescribes a drug, the system starts the authority detection submodule to start detecting whether the current diagnosing doctor has the authority to prescribe the current drug;

[0042] Step S3: After determining the drug for the user's condition, the system sends a communication signal to start the drug analysis submodule, and starts to analyze the mutual influence between the prescribed drugs and the drugs used at the same time, and removes the prescribed drugs according to the medication records in the user's medical records.

[0043] Step S4: During the work of the diagnosing doctor, the system starts the fatigue analysis submodule to assess the fatigue level of the diagnosing doctor and allocates patients according to the fatigue level;

[0044] Step S5: When the user picks up medicine, the current user's medicine code is obtained, the medicine is extracted according to the medicine code, and the user is reminded to take the medicine according to the doctor's advice. At the same time, when the user's symptoms are unclear, the user is reminded to go to the hospital for medical treatment and the doctor is evaluated through the diagnosis and evaluation module.

[0045] Step S2 further comprises the following steps:

[0046] Step S21: when analyzing the user's condition, the user's condition description and lesion picture are retrieved, the user's condition data and lesion picture data are scanned and identified, and the diagnosing doctor prescribes medicine according to the user's diagnosis result;

[0047] Step S22: Retrieve the code of the currently prescribed drug and the number of the current diagnosing doctor, and identify the category to which the current drug code belongs. If the current drug is a restricted management drug, the current diagnosing doctor will retrieve the list of drug codes that the current diagnosing doctor can prescribe based on the number of the current diagnosing doctor, and compare the code of the prescribed drug. If the code of the currently prescribed drug is in the list of drug codes that the doctor can prescribe, the code of the currently prescribed drug will be marked as usable, otherwise it will be marked as unusable. By identifying whether the current diagnosing doctor has the right to use the currently prescribed drug, it is possible to avoid the current diagnosing doctor's operating error in prescribing restricted management drugs, avoid the drug being used by the user, and cause danger to the user, thereby improving the safety of drug management.

[0048] Step S3 further comprises the following steps:

[0049] Step S31: retrieve the currently prescribed drug code, retrieve all the medical records of the current user, identify the drug codes and allergy drug codes that the user can use in the case, and for the drug codes prescribed by the current diagnosing doctor, if there is an allergy drug code in the drug codes prescribed by the current diagnosing doctor, mark the drug as unavailable, otherwise retrieve the drug code that will react with the currently prescribed drug and cannot be used at the same time, compare the prescribed drug code with the drug code that cannot be used at the same time, if there are drugs that react with each other in the prescribed drugs, mark the drugs that can react as unavailable, identify the mark, read the main function of the unavailable drug, and replace it according to the main function. By identifying the allergy drugs in the medical records and removing the allergy drugs in the drugs prescribed by the doctor, it can be avoided that the user uses the allergy drugs, which may cause life-threatening allergies. By detecting whether the prescribed drugs will react, it can be avoided that the drugs that will react are used at the same time, which may cause medical accidents that endanger the health of the user, thereby improving the safety of people's use of drugs;

[0050] Step S32: when the user detects whether the current drug is allergic, the drug name input by the user is retrieved, and the name of the allergic drug in the medical record is compared with the drug name input by the user. If the drug name currently input by the user exists in the allergic drug in the user's medical record, the user is reminded that the drug cannot be used, otherwise the user is reminded that the drug can be used. When the user detects a drug reaction, the drug name input by the user is retrieved, and the name of the drug that reacts with the drug is retrieved according to the drug name, and compared with the drug name input by the user. If the drug exists in the drug name input by the user, the drug is marked as unavailable, otherwise the user is reminded that the current drugs can be used at the same time, and the marked unavailable drugs are retrieved to identify the efficacy of the unavailable drugs. The names of drugs that will not interact with other drugs are retrieved from the database based on the efficacy, and the user is reminded to purchase the drug for use. By judging whether the user is allergic to the current drug, it can avoid the user forgetting whether he is allergic to the drug, resulting in accidental ingestion and danger. It detects whether drugs used by the user at the same time will react, and recommends drugs with the same efficacy based on the efficacy, so as to avoid danger when users use drugs at the same time, thereby greatly improving the safety of people's use of drugs.

[0051] Step S4 further comprises the following steps:

[0052] Step S41: retrieve the facial visual image and body visual image of the current diagnosing doctor, scan and identify the facial feature nodes of the current diagnosing doctor, anchor the eye bag edge nodes, connect the edge nodes to form an eye bag model, construct a grid model with the same grid size, overlap the eye bag model and the grid model, calculate the number of grids occupied by the eye bags after overlapping, and the grid data represents the area size of the eye bags, anchor the eye bag position, identify the RGB color value in the eye bag visual image, compare the system set threshold, mark the RGB color value greater than the threshold, retrieve the fatigue parameters in the database, and give the influence coefficients α and β of the eye bag area size and eye bag color on the doctor's fatigue according to the fatigue parameters in the database, and by calculating the area size of the eye bags and marking the RGB color values ​​greater than the system threshold, it is possible to quickly and preliminarily determine whether the current diagnosing doctor is fatigued;

[0053] Step S42: Retrieve the duration of each diagnosis by the current diagnosing doctor and the rest duration between two diagnoses, and calculate the fatigue level of the current diagnosing doctor through a formula In the formula, i = 1, 2, 3, ... n, j = 1, 2, 3 ... n, P represents the fatigue of the current diagnosing doctor, T represents the time it takes for the current diagnosing doctor to diagnose a user's condition, t represents the rest time of the current diagnosing doctor in the diagnosis interval, and n represents the number of users diagnosed by the current diagnosing doctor. By calculating the fatigue of the current diagnosing doctor, the user allocation can be quickly adjusted according to the fatigue, further reducing the fatigue of the diagnosing doctor;

[0054] Step S43: When the doctor's fatigue level is greater than the first threshold, the current doctor number is retrieved, the department to which the current number belongs is identified, and a doctor is retrieved from the current department to replace the doctor. When the doctor's fatigue level is greater than the second threshold and less than the first threshold, the auxiliary diagnosis device is started, the current user's condition description is obtained, the diagnosis model is retrieved to identify the main features of the user's condition, and the diagnosis results and prescribed drugs in the database are retrieved based on the main features. When the doctor's fatigue level is less than the second threshold, the fatigue levels of all diagnostic doctors are retrieved and the fatigue levels are sorted in ascending order. If the diagnostic doctor's fatigue level is greater than the third threshold and less than the second threshold, the diagnosis is suspended for rest. Otherwise, the work continues until the fatigue level is greater than the second threshold. At this time, all diagnostic doctors are adjusted to work. By adjusting diagnostic doctors with different fatigue levels, it is possible to avoid continuous work of diagnostic doctors, which may cause the diagnostic doctors to be too tired and reduce the accuracy of the diagnostic results.

[0055] In step S5, after the user extracts the medicine, the medication reminder module is started, the usage method of the current medicine is obtained, an alarm is set according to the usage method of the current medicine, the user is reminded to take the medicine on time during the medication time period, and the treatment time of the current medicine is retrieved. If the user's condition is still not improved at the end of the treatment time, a voice reminder is issued to remind the current user to go to the hospital for examination and treatment as soon as possible. The user can evaluate the service of the diagnostic doctor through the diagnosis evaluation module. By reminding the user to take medicine at regular intervals, the user is reminded to go to the hospital if the user's condition still does not improve at the end of the treatment cycle. This can prevent the user from forgetting to take medicine due to busy work, and avoid taking medicine intermittently, which leads to worsening of the condition.

[0056] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0057] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An intelligent medical system based on big data, comprising a data collection module, a diagnosis and analysis module and an evaluation and management module, characterized in that: The data collection module is used to collect the doctor's facial features, the symptom information uploaded by the user and the user's medical record data; the diagnosis management module is used to analyze the doctor's fatigue level and make adjustments and analyze whether the drugs currently used by the user will interact with each other; the evaluation management module is used to remind the user to take the medicine on time and the user to evaluate the doctor; the data collection module, the diagnosis management module and the evaluation management module are connected to each other in communication; The intelligent analysis module includes a fatigue analysis submodule and a drug analysis submodule. The fatigue analysis submodule is used to analyze the fatigue level of the current diagnosing doctor, and the drug analysis submodule is used to analyze whether the user can use the current drug or whether the current drugs will be dangerous when used simultaneously. The drug authority management module includes an authority detection submodule and a drug application submodule. The authority detection submodule is used to detect whether the current diagnosing doctor has the authority to prescribe the current drug, and the drug application module is used to apply for drugs from superiors or apply for drug adjustment from other hospitals.

2. The intelligent medical system based on big data according to claim 1, characterized in that: The data collection module includes a visual module, an information entry module and a medical record collection module. The visual module is used to collect the facial features of the doctor, the information entry module is used for the user to enter the lesion information and the information of the medicine used simultaneously into the system, and the case collection module is used to retrieve the user's medical record data according to the current user information.

3. The intelligent medical system based on big data according to claim 2, characterized in that: The diagnosis management module includes an intelligent analysis module and a drug authority management module. The intelligent analysis module is used to analyze the doctor's fatigue level and make adjustments, to analyze whether the user is allergic to the drugs currently prescribed by the doctor, and to analyze whether the drugs used at the same time will have pharmacological effects that are dangerous to the body. The drug authority management module is used to manage the diagnostic doctor's authority to prescribe drugs.

4. The intelligent medical system based on big data according to claim 3, characterized in that: The evaluation management module includes a medication reminder module, and the medication reminder module is used to remind the user to take medication on time.

5. The intelligent medical system based on big data according to claim 4, characterized in that: The evaluation management module also includes a diagnosis evaluation module and a medical consultation reminder module. The diagnosis evaluation module is used for the user to evaluate the diagnosing doctor, and the diagnosis reminder module is used to remind the user to go to the doctor when the user continues to use the drug for more than the treatment course.

6. The intelligent medical system based on big data according to claim 5, characterized in that: The operation method of the intelligent medical system mainly includes the following steps: Step S1: Through the visual module, the facial features of the current diagnosing doctor are photographed in real time during the operation of the system; through the information input module, the user's condition data and lesion images are input into the system; the information of the drugs used by the user is input into the system; through the medical record collection module, all medical record data are collected into the system according to the identity information of the current user; Step S2: When the diagnosing doctor prescribes a drug, the system starts the authority detection submodule to start detecting whether the current diagnosing doctor has the authority to prescribe the current drug; Step S3: After determining the drug for the user's condition, the system sends a communication signal to start the drug analysis submodule, and starts to analyze the mutual influence between the prescribed drugs and the drugs used at the same time, and removes the prescribed drugs according to the medication records in the user's medical records. Step S4: During the work of the diagnosing doctor, the system starts the fatigue analysis submodule to assess the fatigue level of the diagnosing doctor and allocates patients according to the fatigue level; Step S5: When the user picks up medicine, the current user's medicine code is obtained, the medicine is extracted according to the medicine code, and the user is reminded to take the medicine according to the doctor's advice. At the same time, when the user's symptoms are unclear, the user is reminded to go to the hospital for medical treatment and the doctor is evaluated through the diagnosis and evaluation module.

7. The big data-based intelligent medical system according to claim 6, characterized in that: The step S2 further comprises the following steps: Step S21: when analyzing the user's condition, the user's condition description and lesion picture are retrieved, the user's condition data and lesion picture data are scanned and identified, and the diagnosing doctor prescribes medicine according to the user's diagnosis result; Step S22: Retrieve the code of the currently prescribed drug and the number of the current diagnosing doctor, and identify the category to which the current drug code belongs. If the current drug is a restricted management drug, the current diagnosing doctor will retrieve the list of drug codes that the current diagnosing doctor can prescribe based on the number of the current diagnosing doctor, and compare the code of the prescribed drug. If the code of the currently prescribed drug is in the list of drug codes that the doctor can prescribe, the code of the currently prescribed drug will be marked as usable, otherwise it will be marked as unusable. By identifying whether the current diagnosing doctor has the right to use the currently prescribed drug, it is possible to avoid the current diagnosing doctor's operating error in prescribing restricted management drugs, avoid the drug being used by the user, and cause danger to the user, thereby improving the safety of drug management.

8. The big data-based intelligent medical system according to claim 7, characterized in that: The step S3 further comprises the following steps: Step S31: retrieve the currently prescribed drug code, retrieve all the medical records of the current user, identify the drug codes and allergy drug codes that the user can use in the case, and for the drug codes prescribed by the current diagnosing doctor, if there is an allergy drug code in the drug codes prescribed by the current diagnosing doctor, mark the drug as unavailable, otherwise retrieve the drug code that will react with the currently prescribed drug and cannot be used at the same time, compare the prescribed drug code with the drug code that cannot be used at the same time, if there are drugs that react with each other in the prescribed drugs, mark the drugs that can react as unavailable, identify the mark, read the main function of the unavailable drug, and replace it according to the main function; Step S32: when the user detects whether the current drug is allergic, the drug name input by the user is retrieved, and the names of allergic drugs in the medical record are compared with the drug name input by the user. If the drug name currently input by the user exists among the allergic drugs in the user's medical record, the user is reminded that the drug cannot be used, otherwise the user is reminded that the drug can be used. When the user detects a drug reaction, the drug name input by the user is retrieved, and the name of the drug that reacts with the drug is retrieved according to the drug name, and the drug name input by the user is compared. If the drug name input by the user exists, the drug is marked as unavailable, otherwise the user is reminded that the current drugs can be used at the same time, the marked unavailable drug is retrieved, the efficacy of the unavailable drug is identified, the name of the drug that will not interact with other drugs in the database is retrieved based on the efficacy, and the user is reminded to purchase the drug for use.

9. The big data-based intelligent medical system according to claim 8, characterized in that: The step S4 further comprises the following steps: Step S41: retrieve the facial visual image and body visual image of the current diagnosing doctor, scan and identify the facial feature nodes of the current diagnosing doctor, anchor the eye bag edge nodes, connect the edge nodes to form an eye bag model, construct a grid model with the same grid size, overlap the eye bag model and the grid model, calculate the number of grids occupied by the eye bags after overlapping, and the grid data represents the area size of the eye bags, anchor the eye bag position, identify the RGB color value in the eye bag visual image, compare the threshold set by the system, mark the RGB color value greater than the threshold, retrieve the fatigue parameters in the database, and give the influence coefficients α and β of the eye bag area size and eye bag color on the doctor's fatigue according to the fatigue parameters in the database; Step S42: Retrieve the duration of each diagnosis by the current diagnosing doctor and the rest duration between two diagnoses, and calculate the fatigue level of the current diagnosing doctor through a formula Where, i = 1, 2, 3, ... n, j = 1, 2, 3 ... n, P represents the fatigue of the current diagnosing doctor, T represents the time it takes for the current diagnosing doctor to diagnose a user's condition, t represents the rest time of the current diagnosing doctor in the interval between diagnoses, and n represents the number of users diagnosed by the current diagnosing doctor; Step S43: When the doctor's fatigue level is greater than the first threshold, the current doctor number is retrieved, the department to which the current number belongs is identified, and a doctor is retrieved from the current department to replace the doctor. When the doctor's fatigue level is greater than the second threshold and less than the first threshold, the auxiliary diagnosis device is started, the current user's condition description is obtained, the diagnosis model is retrieved to identify the main features of the user's condition, and the diagnosis results and prescribed drugs in the database are retrieved based on the main features. When the doctor's fatigue level is less than the second threshold, the fatigue levels of all diagnosing doctors are retrieved and sorted in ascending order. If the diagnosing doctor's fatigue level is greater than the third threshold and less than the second threshold, the diagnosis is suspended for rest. Otherwise, the work continues until the fatigue level is greater than the second threshold. At this time, all diagnosing doctors are adjusted to work.

10. The intelligent medical system based on big data according to claim 9, characterized in that: In step S5, after the user extracts the medicine, the medication reminder module is started, the usage method of the current medicine is obtained, an alarm is set according to the usage method of the current medicine, the user is reminded to take the medicine on time during the medication time period, and the treatment time of the current medicine is retrieved. If the user's condition is still not improved at the end of the treatment time, a voice reminder is issued to remind the current user to go to the hospital for examination and treatment as soon as possible. The user can evaluate the service of the diagnostic doctor through the diagnosis evaluation module.

Images