Follow-up medicine opening cooperation method and device, electronic equipment and storage medium

Abstract

The invention discloses a follow-up medicine opening cooperation method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a follow-up visit result and historical medicine prescription data of a patient; wherein the follow-up visit result at least comprises current symptom characterization information and a current diagnosis result of the patient; and generating a prescription of the patient based on the current symptom characterization information, the current diagnosis result and the historical prescription data. By adopting the method provided by the invention, the service efficiency of a hospital can be improved to a certain extent.

Description

Technical Field

[0001] The present application relates to the field of medical big data technology, and in particular to a collaborative method, device, electronic device and storage medium for follow-up medication. Background Art

[0002] Follow-up is a method of observation by the hospital to regularly understand the changes in the patient's condition and guide the patient's recovery through communication or other means. Generally, medical staff follow up patients through telephone communication.

[0003] The current follow-up and prescription systems are separated. Patients cannot be automatically prescribed medicine during or after the follow-up. Patients are usually required to go to the hospital in person to register and purchase medicines. Since manual follow-up and offline reception of patient consultations each take a certain amount of time, the service efficiency of the hospital is relatively low. Summary of the invention

[0004] In view of this, the embodiments of the present application provide a follow-up prescription coordination method, device, electronic device and storage medium, aiming to solve the technical problem of low hospital service efficiency in related technologies.

[0005] In a first aspect, the present application provides a collaborative method for follow-up medication prescribing, comprising:

[0006] Obtaining the patient's follow-up results and historical prescription data; wherein the follow-up results at least include the patient's current symptom representation information and current diagnosis results;

[0007] A prescription for the patient is generated based on the current symptom representation information, the current diagnosis result and the historical prescription data.

[0008] In the above solution, based on the current symptom representation information, the current diagnosis result and the historical prescription data, a prescription for the patient is generated, including:

[0009] Based on the current symptom representation information, it is determined that a prescription can be prescribed online for the patient, and then a preliminary version of the prescription is generated based on the current diagnosis result and the current symptom representation information;

[0010] Obtaining medication contraindication information for the patient;

[0011] A prescription for the patient is generated based on the first edition of the prescription, the patient's contraindications information and the historical prescription data.

[0012] In the above scheme, obtaining the follow-up results of the patient includes:

[0013] In response to the follow-up instruction, obtaining the historical diagnosis results of the current patient, and determining a matching follow-up template based on the historical diagnosis results;

[0014] Sending the matched follow-up template to the terminal of the patient; wherein the matched follow-up template is used to collect at least one of the following: patient identity information and current symptom representation information;

[0015] A follow-up template returned by the terminal of the patient is received, and a follow-up result of the patient is determined based on the returned follow-up template.

[0016] In the above solution, determining that a prescription can be issued online for the patient based on the current symptom representation information includes:

[0017] Determining the patient's disease based on the current symptom representation information;

[0018] Determine whether the stage of the patient's disease is a common disease according to the current symptom representation information, the patient's disease, and a pre-stored first mapping relationship between the disease, symptom representation, and disease stage; wherein the common disease refers to a disease with a medication risk level less than a threshold;

[0019] If it is determined to be a common condition, it is determined that a prescription can be issued online for the patient.

[0020] In the above solution, generating a preliminary prescription based on the current diagnosis result and the current symptom representation information includes:

[0021] Based on the current diagnosis result, the current symptom representation information and a pre-stored second mapping relationship, searching for a drug and a corresponding dosage that matches the current diagnosis result and the current symptom representation information; wherein the second mapping relationship includes a correspondence between the diagnosis result, the symptom representation information, the drug and the dosage;

[0022] A preliminary version of the prescription is generated based on the matched drugs and the corresponding dosages.

[0023] In the above scheme, the step of obtaining the patient's prescription based on the first edition of the prescription, the patient's contraindications information and the historical prescription data includes:

[0024] Based on the patient's contraindications, the first version of the prescription is screened to obtain a discarded version of the prescription;

[0025] The prescription for the patient is determined based on the historical prescription data and the discarded version of the prescription.

[0026] In the above scheme, the first version of the prescription is screened based on the patient's contraindications to obtain a discarded version of the prescription, including:

[0027] Based on the patient's medication contraindications information, determining whether all the drugs in the first version of the prescription are prohibited drugs;

[0028] If it is determined that not all of them are banned drugs, the banned drugs are removed from the first version of the prescription to obtain the removed version of the prescription.

[0029] In the above solution, the historical prescription data includes historical diagnosis results and historical symptom representation information; the step of determining the patient's prescription based on the historical prescription data and the discarded prescription includes:

[0030] Comparing the current symptom representation information with the historical symptom representation information, and comparing the current diagnosis result with the historical diagnosis result; wherein the historical symptom representation information is the symptom representation information of the patient at the last follow-up;

[0031] If it is determined that the current symptom representation information is inconsistent with the historical symptom representation information, and / or the current diagnosis result is inconsistent with the historical diagnosis result, the eliminated version of the prescription is determined as the prescription for the patient.

[0032] In the above scheme, the historical prescription data also includes historical drugs and corresponding historical dosages; and determining the patient's prescription based on the historical prescription data and the eliminated prescription also includes:

[0033] If it is determined that the current symptom representation information and the historical symptom representation information, as well as the current diagnosis result and the historical diagnosis result are consistent, a prescription for the patient is generated based on the patient's historical drugs and historical dosages.

[0034] In the above scheme, determining the prescription of the discarded version as the prescription of the patient includes:

[0035] If it is determined that any historical drug exists in the prescription of the eliminated version and the dosage of any historical drug is inconsistent with the corresponding historical dosage, the historical dosage of any historical drug is used as the recommended dosage of any historical drug;

[0036] The patient's prescription is obtained based on the drugs in the eliminated version of the prescription and the recommended dosage of any historical drug.

[0037] In a second aspect, the present application also provides a follow-up medication coordination device, the device comprising:

[0038] A follow-up result acquisition module is used to obtain the patient's follow-up results and historical prescription data; wherein the follow-up results at least include the patient's current symptom manifestations and current diagnosis results;

[0039] A patient prescription generation module is used to generate a prescription for the patient based on the current symptom representation, the current diagnosis result and the historical prescription data.

[0040] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor and a memory for storing a computer program that can be run on the processor, wherein the processor, when running the computer program, executes the steps of the method described in the first aspect.

[0041] In a fourth aspect, an embodiment of the present application further provides a computer storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in the first aspect are implemented.

[0042] The application provides a collaborative method, device, electronic device and storage medium for follow-up and prescription, which obtains the follow-up results and historical prescription data of the patient; wherein the follow-up results at least include the current symptom representation information and the current diagnosis result of the patient; based on the current symptom representation information, the current diagnosis result and the historical prescription data, the patient's prescription is generated. After following up on the patient, the application can intelligently prescribe medicine for the patient based on the historical prescription data and the current symptom representation information and the current diagnosis result in the follow-up results obtained after the follow-up. In this way, the patient can obtain the prescription after the follow-up is completed, so that the patient does not need to go to the hospital to continue to register after the follow-up, which can improve the service efficiency of the hospital to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 This is a flow chart of a method for implementing a collaborative follow-up medication prescription method in one embodiment of the present application;

[0044] Figure 2 This is a flow chart of a method for implementing a collaborative follow-up medication prescription method in another embodiment of the present application;

[0045] Figure 3 This is a flow chart of a method for implementing a collaborative method for follow-up medication prescription in yet another embodiment of the present application;

[0046] Figure 4 This is a schematic diagram of the structure of a follow-up medication coordination device in one embodiment of the present application;

[0047] Figure 5 It is a schematic diagram of the structure of an electronic device in one embodiment of the present application. DETAILED DESCRIPTION

[0048] The present application is further described in detail below in conjunction with the accompanying drawings and embodiments.

[0049] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0050] Before further describing the embodiments of the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations:

[0051] Follow-up: A method of observation in which the hospital regularly uses communication or other means to understand changes in the patient's condition and guide the patient's recovery.

[0052] In order to clearly understand the technical solution of the present application, the solution of the related technology is first introduced in detail.

[0053] In the related art, the follow-up and prescription systems are separated, and the patients cannot be automatically prescribed medicines during or after the follow-up. Usually, the patients need to go to the hospital in person to register and purchase medicines. Since manual follow-up and offline reception of patients for consultation each take a certain amount of time, the service efficiency of the hospital is relatively low.

[0054] Therefore, when facing the technical problems of related technologies, the inventor found through creative research that it is possible to set up a smart prescription for the patient after the follow-up, so that the patient does not need to go to the hospital to continue to register after the follow-up. Specifically: after the process of manual follow-up or intelligent follow-up of the patient is completed, the electronic device generates the follow-up results of the patient. The follow-up results at least include the patient's current symptom representation and the current diagnosis result. Afterwards, the electronic device can generate a prescription that matches the patient's current symptom representation and the current diagnosis result based on these two pieces of information, which is called the patient's prescription. Here, manual follow-up refers to the doctor's follow-up in the form of calling the patient, sending text messages and online messages during the follow-up process. Intelligent follow-up refers to the follow-up process in which the electronic device and the patient "intelligently talk" to follow up. It can be seen from this that after the patient is followed up, the present application can intelligently prescribe a prescription for the patient based on the current symptom representation information and the current diagnosis result in the follow-up results obtained after the follow-up. That is, the patient can obtain the prescription after the follow-up, so that the patient does not need to go to the hospital to continue to register after the follow-up, which can improve the service efficiency of the hospital to a certain extent.

[0055] Figure 1A follow-up prescription collaborative method is provided in one embodiment of the present application. The execution subject of the follow-up prescription collaborative method provided in this embodiment may be an electronic device, and the electronic device may be a cloud platform, a computer device, and a terminal device. The follow-up prescription collaborative method provided in this embodiment includes the following steps:

[0056] Step 101, obtaining the patient's follow-up results and historical prescription data; wherein the follow-up results at least include the patient's current symptom representation information and current diagnosis results.

[0057] Among them, the follow-up results refer to the patient's disease-related information collected after the follow-up process is completed. In addition to the patient's identity information, the patient's follow-up results also include at least the patient's current symptom representation information and the current diagnosis result. The current symptom representation information refers to the patient's symptom representation information collected during the current or current follow-up of the patient. The symptom representation information can be a collection of one or more symptom representations, and the symptom representation refers to the clinical manifestation characteristics of the disease. The current diagnosis result refers to the patient's disease diagnosis information collected during the current / current follow-up of the patient, mainly including the name, type, severity and recovery degree of the disease.

[0058] Specifically, after the process of manual follow-up or intelligent follow-up of the patient is completed, the electronic device generates the follow-up results of the patient. The follow-up results are obtained by manual follow-up. For example, after the doctor follows up with the patient by calling, sending text messages, and online messages, the call records, text messages, or message replies can be manually sorted first, and the sorted content can be input into the electronic device. The input device here can be a built-in electronic device or an external input device, without specific limitation.

[0059] The follow-up results are obtained by intelligent follow-up methods, such as setting up an intelligent AI program (Artificial Intelligence) on an electronic device, which can ask the patient questions based on the doctor's pre-set questions and record the patient's answers. After the process is completed, the follow-up results of the patient are automatically generated. Here, the pre-set questions at least include questions that are strongly related to the patient's current symptom representation information and the current diagnosis results. Other questions can also be set without specific limitation.

[0060] The historical prescription data is data of various stages associated with the last prescription, and the historical prescription data can be used to guide the online prescription this time. The historical prescription data is stored in the second knowledge base of the electronic device.

[0061] Step 102: Generate a prescription for the patient based on the current symptom representation information, the current diagnosis result and the historical prescription data.

[0062] The patient's prescription is a prescription suitable for the patient determined based on the follow-up results collected during the current / current follow-up of the patient. The patient's prescription at least includes the medicine and the corresponding dosage.

[0063] Specifically, based on the current symptom representation information and the current diagnosis results, it is possible to determine which disease the patient may have and which corresponding medicine to prescribe, and then combine historical prescription data to generate a prescription for the patient.

[0064] In one embodiment, after generating the patient's prescription, the follow-up results and the patient's prescription are sent to the attending physician for online confirmation by the attending physician. When the electronic device receives the confirmation message, it first sends a drug sorting task instruction to the drug sorting system, and the drug sorting task instruction includes the patient's prescription; after receiving the drug sorting instruction, the drug sorting system sorts the drugs according to the patient's prescription; after the drug sorting system confirms that the drugs have been sorted, it sends a drug delivery task instruction to the drug mailing system, and the drug delivery task instruction includes the patient's identity information, and the identity information includes the patient's name or identification code, and the patient's permanent address. The drug mailing system receives the drug delivery task instruction and will implement intelligent drug sorting and drug delivery tasks to deliver the drugs to the patient's permanent address. Here, the drug sorting system and the drug mailing system can be program systems embedded in the electronic device, or other program systems independent of the electronic device described in this application, without specific limitation.

[0065] In this application, by obtaining the follow-up results and historical prescription data of the patient; wherein the follow-up results include at least the current symptom representation information and the current diagnosis result of the patient; based on the current symptom representation information, the current diagnosis result and the historical prescription data, the patient's prescription is generated. After following up on the patient, the patient can be prescribed intelligently based on the current symptom representation information and the current diagnosis result in the follow-up results obtained after the follow-up. That is, the patient can obtain the prescription after the follow-up is completed, so that the patient does not need to go to the hospital to continue to register after the follow-up, which can improve the service efficiency of the hospital to a certain extent. In addition, the patient's prescription can be issued online based on the follow-up results obtained after manual follow-up or intelligent follow-up. Compared with the manual follow-up method commonly used in related technologies, this application can also perform intelligent follow-up, with wider follow-up channels and a wider application range of online prescriptions.

[0066] In one embodiment, if Figure 2 As shown, step 101 is first performed, and then when the prescription for the patient is generated based on the current symptom representation information and the current diagnosis result, the following steps are included:

[0067] Step 201, based on the current symptom representation information, determine whether a prescription can be issued online for the patient.

[0068] If it is determined that a prescription cannot be issued online for the patient, step 202 is executed to output a message notification of refusal to generate a prescription and the reason for refusal.

[0069] When executing step 202, the electronic device also stops the process of prescribing medicines, and will not prescribe medicines for the patient. Here, the situation corresponding to the refusal to generate a prescription is that, based on the patient's current symptom representation information, it is determined that the patient's disease is special and / or the condition is serious, and the online prescription cannot be used to prescribe the right medicine or the direct online prescription has a high risk of medication, so the online prescription is refused.

[0070] If it is determined that a prescription can be issued online for the patient, step 203 is executed to generate a preliminary prescription based on the current diagnosis result and the current symptom representation information.

[0071] Among them, the first edition of the prescription is a prescription directly generated based only on the patient's current symptom representation information and the current diagnosis results. Generally speaking, if the patient does not have a special constitution or potential diseases, the first edition of the prescription can be directly used as the patient's prescription. In some cases, because the patient may have a special constitution or potential diseases, the drugs and corresponding dosages in the first edition of the prescription generated only based on the above two pieces of information do not take these factors into account and are not suitable for direct use by the patient, so continue to execute step 204.

[0072] Step 204, obtaining the patient's medication contraindication information.

[0073] The patient's medication contraindication information refers to information related to medication contraindications, for example, patient A is allergic to penicillin.

[0074] The patient's medication contraindications information can be obtained from the third knowledge base, and the historical prescription data can be obtained from the second knowledge base.

[0075] Step 205 , generating a prescription for the patient based on the first edition of the prescription, the patient's contraindications information and the historical prescription data.

[0076] Specifically, based on the initial version of the prescription, combined with the patient's contraindications information and historical prescription data, the initial version of the prescription can be further improved to obtain a prescription that better matches the patient, that is, the patient's prescription, so that it is better suitable for the patient.

[0077] In this embodiment, based on the current symptom representation information, it is determined that a prescription can be issued online for the patient, then based on the current diagnosis result and the current symptom representation information, a first version of the prescription is generated; the patient's contraindication information is obtained; based on the first version of the prescription, the patient's contraindication information and the historical prescription data, a prescription for the patient is generated. After the first version of the prescription is generated based on the current diagnosis result and the current symptom representation information, the patient's prescription is generated by taking full consideration from the perspective of medication safety, that is, combining the patient's contraindication information and historical prescription data, so that the patient's prescription is safer and more secure when applied to the patient.

[0078] In one embodiment, Figure 3 As shown, obtaining the follow-up results of the patient includes the following steps:

[0079] Step 301 : in response to a follow-up instruction, obtaining historical diagnosis results of the current patient, and determining a matching follow-up template based on the historical diagnosis results.

[0080] Whether to follow up the patient and when to follow up the patient can be set in advance in the electronic device. For example, the electronic device can set the follow-up time interval in advance, and send a follow-up instruction to the follow-up system when the follow-up time arrives to trigger the follow-up process for the patient.

[0081] The patient's historical diagnosis results are the disease diagnosis information of the patient collected during the last follow-up of the patient, mainly including the name, type, severity and recovery degree of the disease.

[0082] Several follow-up templates are stored in the follow-up system of the electronic device. The follow-up templates can be classified according to the disease type. One disease type can have one or more disease names. The follow-up instruction carries the patient's historical diagnosis results. Once the electronic device responds to the follow-up instruction, it can match the current patient with a follow-up template that is suitable for his or her disease type (i.e., a matched follow-up template) based on the current patient's historical diagnosis results in the follow-up instruction.

[0083] Step 302: Send the matched follow-up template to the patient's terminal; wherein the matched follow-up template is used to collect at least one of the following: patient identity information and current symptom representation information.

[0084] Among them, the matching follow-up template has a variety of data information to be filled in by the patient, including at least the patient's identity information and the current symptom representation information. The patient's identity information is the data information that represents the patient's identity, such as name, age, and gender. The patient's current symptom representation information is the symptom representation that appeared after the patient's last follow-up. Taking the common cold as an example, the symptom representation includes at least one of cough, fever, headache, etc.

[0085] Step 303: receiving the follow-up template returned by the terminal of the patient, and determining the follow-up result of the patient based on the returned follow-up template.

[0086] The follow-up result of the patient is the follow-up result mentioned in step 101.

[0087] Specifically, after the patient's terminal detects that the patient has filled in the matching follow-up template and confirmed it, it returns the filled-in follow-up template to the electronic device, and the filled-in follow-up template can be referred to as the returned follow-up template. The doctor can preliminarily infer the patient's current diagnosis result based on the patient's current symptom representation information in the returned follow-up template, and give the current diagnosis result to the electronic device. The electronic device obtains the current diagnosis result and the patient's current symptom representation information, and can determine the patient's follow-up result.

[0088] In this embodiment, in response to a follow-up instruction, the historical diagnosis results of the current patient are obtained, and a matching follow-up template is determined based on the historical diagnosis results; the matching follow-up template is sent to the patient's terminal; wherein the matching follow-up template is used to collect at least one of the following: patient identity information and current symptom representation information; the follow-up template returned by the patient's terminal is received, and the follow-up results of the patient are determined based on the returned follow-up template. First, since the follow-up template sent by the electronic device to the patient's terminal matches the patient's historical diagnosis results, the questions based on the matching follow-up template filled out by the patient are targeted, which is conducive to guiding the patient to accurately describe his or her own condition. Secondly, the returned follow-up template obtained based on the matching follow-up template, because the patient's condition description is more accurate, the follow-up results of the patient determined based on this are also more accurate.

[0089] In one embodiment, in this embodiment, step 201 includes the following steps:

[0090] a. Determine the patient's disease based on the current symptom characterization information.

[0091] The mapping relationship between various diseases and corresponding symptom representations is pre-stored in the database of the electronic device. Therefore, the patient's disease can be determined based on the current symptom representation information.

[0092] According to all the symptom representations in the current symptom representation information, the disease pointed to by the most symptom representations can be used as the patient's disease. For example, if there are 10 symptom representations and 7 of them point to lymphoma, it can be determined that the patient's disease is lymphoma.

[0093] b. Determine whether the disease stage of the patient is a common disease based on the current symptom representation information, the patient's disease, and a pre-stored first mapping relationship between the disease, symptom representation, and disease stage.

[0094] The disease stage includes the onset stage and the recovery stage of the disease. The electronic device also pre-stores a first mapping relationship between various diseases, symptom representations, and disease stages. Therefore, according to the patient's disease, symptom representation, and the first mapping relationship, it can be determined whether the disease stage of the patient's disease is a common disease.

[0095] For each disease, according to the stage of the disease, such as recovery status and severity, and the degree of medication risk that the online prescription may cause to the patient, the patient's condition is divided into a dangerous condition with a medication risk greater than or equal to a threshold, and a common condition with a medication risk less than a threshold. Dangerous conditions and symptom representations corresponding to each dangerous condition are pre-stored in the database of the electronic device. Among them, a common condition refers to a condition with a medication risk less than a threshold.

[0096] Based on the current symptom representation information, the corresponding disease type or name is first determined, and then based on the current symptom representation information and the various disease stages under the disease type or name, it is determined whether it is a dangerous condition. After determining the patient's disease name or type, when determining whether it is a dangerous condition based on the current symptom representation information and the various disease stages under the disease type or name, in one embodiment, it is specifically to query whether there is any symptom representation in the current symptom representation information, which is consistent with or matches the symptom representation in the preset dangerous condition (the dangerous condition corresponding to the patient's disease name or type). If any one exists, it is determined to be a dangerous condition; if it does not exist at all, it is determined to be an ordinary condition.

[0097] c. If it is determined to be a common condition, it is determined that a prescription can be issued online for the patient.

[0098] If the condition is common, it is determined that a prescription can be issued online for the patient. As mentioned above, specifically, if it is determined that there is no matching symptom representation at all, it is determined that the condition of the patient is common, and therefore a prescription can be issued online for the patient.

[0099] In one embodiment, for a dangerous condition, the electronic device determines that a prescription cannot be issued online to the patient, and also includes outputting a message notification of refusal to generate a prescription and the reason for refusal.

[0100] In this embodiment, the patient's disease is determined based on the current symptom representation information; based on the current symptom representation information, the patient's disease and a first mapping relationship between the pre-stored disease, symptom representation and disease stage, it is determined whether the patient's disease stage is a common disease; wherein the common disease refers to a disease in which the risk of medication is less than a threshold value; if it is determined to be a common disease, it is determined that a prescription can be issued online for the patient.

[0101] In one embodiment, in this embodiment, step 201 includes the following steps:

[0102] a. Based on the current diagnosis result, the current symptom representation information and a pre-stored second mapping relationship, searching for drugs and corresponding dosages that match the current diagnosis result and the current symptom representation information.

[0103] The second mapping relationship includes the corresponding relationship between the diagnosis result, the symptom representation information, the drug and the dosage. For example, the diagnosis result is leukemia, the symptom representation information includes enlarged lymph nodes and spleen, and difficult bleeding after tooth extraction, and the corresponding drugs are tyrosine kinase inhibitors (X dosage) and hydroxyurea (Y dosage).

[0104] Based on the current diagnosis results and current symptom representation information, matching drugs and corresponding dosages can be determined.

[0105] b. Generate a preliminary version of the prescription based on the matched drugs and corresponding dosages.

[0106] The first version of the prescription includes the matching drugs and corresponding dosages determined above.

[0107] In this embodiment, based on the current diagnosis result, the current symptom representation information and the pre-stored second mapping relationship, the medicine and the corresponding dosage that match the current diagnosis result and the current symptom representation information are searched; wherein the second mapping relationship includes the corresponding relationship between the diagnosis result, the symptom representation information, the medicine and the dosage; according to the matched medicine and the corresponding dosage, the first edition of the prescription is generated. Since the first edition of the prescription is determined and generated based on the current diagnosis result, the current symptom representation information and the second mapping relationship, it can be ensured that the first edition of the prescription preliminarily meets the medication safety requirements.

[0108] In one embodiment, in this embodiment, step 203 includes the following steps:

[0109] a. Based on the patient's contraindications information, the first version of the prescription is screened to obtain a discarded version of the prescription.

[0110] Among them, the medication contraindication information includes the identification or name of the prohibited drugs. The patient's medication contraindication information is individual, and different patients and corresponding medication contraindication information are pre-stored in the third knowledge base of the electronic device in a mapping manner. Usually, these pre-stored medication contraindication information are determined after the last follow-up. However, the patient's prohibited drugs include permanently prohibited drugs or phased prohibited drugs. Permanently prohibited drugs refer to drugs that patients cannot use all the time, and phased prohibited drugs refer to drugs that patients cannot use for a certain period of time, but can use again at another time. It is explained here that the patient's medication contraindication information may change accordingly due to changes in the patient's prohibited drugs.

[0111] In order to ensure the accuracy of the patient's medication contraindication information in the third knowledge base, it needs to be updated in time during or after each follow-up. In one embodiment, a medication contraindication information filling column can be added to the follow-up template for the patient to fill in. This situation is usually for patients whose current follow-up is a long time away from the last follow-up, and who may have visited other hospitals in the meantime and whose medication contraindication information has changed. In another embodiment, after the patient's disease is determined during this follow-up, the medication contraindication information applicable to the disease can be determined based on the patient's current disease. The medication contraindication information for the disease determined here is the patient's latest medication contraindication information.

[0112] In one embodiment, the first version of the prescription is screened based on the patient's contraindications information queried from the third knowledge base, and the filtered objects are the patient's prohibited drugs, that is, the patient's prohibited drugs in the first version of the prescription are removed or filtered out, so that the patient's prohibited drugs do not exist in the obtained eliminated version of the prescription. The eliminated version of the prescription refers to the prescription obtained after further screening the first version of the prescription from the perspective of patient medication safety.

[0113] b. Determine the prescription for the patient based on the historical prescription data and the discarded version of the prescription.

[0114] As mentioned above, the historical prescription data can be used to guide the online prescription this time. After obtaining the eliminated version of the prescription, the historical prescription data can be combined to determine the patient's prescription.

[0115] In this embodiment, based on the patient's contraindications, the first edition of the prescription is screened to obtain a discarded version of the prescription; and the patient's prescription is determined based on the historical prescription data and the discarded version of the prescription. Since the patient's prescription is determined after the first edition of the prescription is screened and then combined with the historical prescription data, both the patient's contraindications and the historical prescription-related information are considered, thereby improving the accuracy of the patient's prescription.

[0116] In one embodiment, in this embodiment, based on the patient's contraindications information, the first version of the prescription is screened to obtain a discarded version of the prescription, including the following steps:

[0117] a. Based on the patient's medication contraindications information, determine whether all the drugs in the first edition of the prescription are prohibited drugs.

[0118] The electronic device first determines whether all the drugs in the first version of the prescription are prohibited drugs for the patient. In one embodiment, if it is determined that all the drugs are prohibited drugs, a message notification of refusing to generate the prescription and the reason for the rejection is output.

[0119] b. If it is determined that not all of the drugs are banned drugs, the banned drugs are removed from the first version of the prescription to obtain the eliminated version of the prescription.

[0120] Among them, not all of them are banned drugs, which means that there is only one banned drug or multiple banned drugs, but not all of them are banned drugs. In the case that not all of them are banned drugs, banned drugs are removed from the first version of the prescription to obtain a deleted version of the prescription.

[0121] For example, if there is only one banned drug, the banned drug is removed to obtain a removed version of the prescription. If there are multiple banned drugs, the banned drugs are removed to obtain a removed version of the prescription.

[0122] In this embodiment, based on the patient's contraindications, it is determined whether all the drugs in the first version of the prescription are prohibited drugs; if it is determined that not all of them are prohibited drugs, the prohibited drugs are removed from the first version of the prescription to obtain the eliminated version of the prescription. Since after determining that not all of the drugs in the first version of the prescription are prohibited drugs, the prohibited drugs are removed to obtain the eliminated version of the prescription, the reliability of the prescription output by the electronic device can be guaranteed.

[0123] In one embodiment, in this embodiment, determining the patient's prescription according to the historical prescription data and the discarded version of the prescription includes the following steps:

[0124] a. Compare the current symptom representation information with the historical symptom representation information, and compare the current diagnosis result with the historical diagnosis result.

[0125] The historical prescription data includes historical diagnosis results and historical symptom representation information. The historical symptom representation information is the symptom representation information of the patient at the last follow-up.

[0126] Here, there are two groups of comparisons, the first group is the current symptom representation information and the historical symptom representation information, and the second group is the current diagnosis results and the historical diagnosis results (hereinafter referred to as the first group and the second group).

[0127] b. If it is determined that the current symptom representation information is inconsistent with the historical symptom representation information, and / or the current diagnosis result is inconsistent with the historical diagnosis result, the eliminated version of the prescription is determined as the patient's prescription.

[0128] The inconsistent comparison results of the first group can be understood as the proportion of the same symptom representation in the current symptom representation information and the same symptom representation in the historical symptom representation is lower than the preset proportion. The inconsistent comparison results of the second group can be understood as the disease type or name in the current diagnosis result is different from the disease type or name in the historical diagnosis result.

[0129] When there is inconsistency in the comparison results of the first group and / or the comparison results of the second group, it indicates that the patient's condition has changed and the last prescription is no longer applicable. It is necessary to use a discarded version of the prescription determined based on the patient's latest condition as the patient's prescription.

[0130] In this embodiment, the current symptom characterization information and the historical symptom characterization information are compared, and the current diagnosis result and the historical diagnosis result are compared; wherein the historical symptom characterization information is the symptom characterization information of the patient at the last follow-up; if it is determined that the current symptom characterization information and the historical symptom characterization information are inconsistent, and / or the current diagnosis result and the historical diagnosis result are inconsistent, then the eliminated version of the prescription is determined as the patient's prescription. When any or both of the two groups of comparison results are inconsistent, it indicates that the patient's condition has changed. Determining to use the eliminated version of the prescription as the patient's prescription based on the patient's latest condition can improve the patient's medication safety.

[0131] In one embodiment, in this embodiment, the follow-up prescription collaborative method also includes the steps of: if it is determined that the current symptom representation information and the historical symptom representation information, as well as the current diagnosis result and the historical diagnosis result are consistent, then determine to generate a prescription for the patient based on the patient's historical drugs and historical dosage.

[0132] Among them, historical prescription data also includes historical drugs and corresponding historical dosages.

[0133] The comparison results of the first group are consistent, which can be understood as the ratio of the symptom representation in the current symptom representation information to the symptom representation in the historical symptom representation being the same is higher than (including equal to) the preset ratio. The comparison results of the second group are consistent, which can be understood as the disease type or name in the current diagnosis result is the same as the disease type or name in the historical diagnosis result.

[0134] When the comparison results of the first group and the second group are consistent, it indicates that the patient's condition has not changed significantly, and the last prescription is applicable, and the current medication situation is determined based on the historical medication situation. That is, the historical drugs are used as the drugs in the prescription for the patient this time, and the historical dosage of the corresponding drugs is used as the dosage in the prescription for the patient this time, so as to obtain the patient's prescription.

[0135] In this embodiment, if it is determined that the current symptom representation information and the historical symptom representation information, as well as the current diagnosis result and the historical diagnosis result are consistent, then a prescription for the patient is generated based on the patient's historical drugs and historical dosage. If the two sets of comparison results are consistent, it indicates that the patient's condition has not changed significantly, and the patient's prescription is determined based on the patient's historical medication, which can also ensure the patient's medication safety and inertia.

[0136] In one embodiment, in this embodiment, when the prescription of the discarded version includes one or more historical drugs, the subsequent execution of determining the prescription of the discarded version as the prescription of the patient includes the following steps:

[0137] a. If it is determined that any historical drug exists in the eliminated version of the prescription and the dosage of any historical drug is inconsistent with the corresponding historical dosage, the historical dosage of any historical drug is used as the recommended dosage of any historical drug.

[0138] Specifically, if it is determined that any historical drug exists in the eliminated version of the prescription, and the dosage of any historical drug is inconsistent with the corresponding historical dosage (the dosage is different), in this case, the historical dosage corresponding to any drug will still be used as the recommended dosage of the drug.

[0139] For example, if there is historical drug A in the deleted version of the prescription, and the recommended dosage is 2 pills per day, and its historical dosage is 1 pill per day, then the modification of the deleted version of the prescription will change the recommended dosage to 1 pill per day.

[0140] b. Obtain the patient's prescription based on the drugs in the eliminated version of the prescription and the recommended dosage of any historical drug.

[0141] Here, other drugs except historical drugs in the eliminated version of the prescription and the corresponding dosage are recommended according to the results generated this time, and the recommended dosage of historical drugs is based on the historical dosage, and the patient's prescription is obtained based on this.

[0142] In this embodiment, if it is determined that any historical drug exists in the prescription of the eliminated version and the dosage of any historical drug is inconsistent with the corresponding historical dosage, the historical dosage of any historical drug is used as the recommended dosage of any historical drug; the patient's prescription is obtained according to the drugs in the prescription of the eliminated version and the recommended dosage of any historical drug. In the case where the prescription of the eliminated version includes one or more historical drugs, the dosage of the historical drugs in the patient's prescription is used as the recommended dosage, which can also ensure the patient's medication safety and inertia.

[0143] In one embodiment, if there is no historical drug in the discarded version of the prescription, the discarded version of the prescription is used as the patient's prescription, and the process directly jumps to the step of outputting the patient's prescription.

[0144] In a specific application embodiment, the present application constructs a follow-up and prescription coordination system, which includes at least a follow-up center module and an intelligent prescription module, and the patient unified user center management module, the follow-up center module and the intelligent prescription module are communicated with each other. The technical solution of this application example involves two parts: intelligent follow-up and intelligent prescription, wherein the object of intelligent follow-up is the patient, and the object of intelligent prescription can be the patient after manual follow-up and intelligent follow-up. The above two parts are exemplarily described below.

[0145] 1. Intelligent follow-up

[0146] a. In response to a follow-up instruction, obtain the historical diagnosis results of the current patient, and determine a matching follow-up template based on the historical diagnosis results.

[0147] Here, the follow-up prescription collaborative system has pre-set the follow-up plan, such as which patients will be followed up at what time. When the follow-up time arrives, the system will actively send a follow-up instruction to the intelligent follow-up module to perform intelligent follow-up on specific patients. In the process of intelligent follow-up of patients, the follow-up template is first matched to the patient based on the patient's historical condition, that is, the historical diagnosis result.

[0148] b. Send a matching follow-up template to the patient's terminal to collect the patient's identity information and current symptom representation information.

[0149] Here, the matching follow-up module sent to the patient is a semi-blank template, with some questions set for the patient to fill in, and text analysis and processing are performed based on the patient's filled-in content, so as to collect the patient's identity information and current symptom representation information. Here, the text analysis and processing method is the existing technology and will not be described in detail.

[0150] c. Receive the follow-up template returned by the patient's terminal, and determine the patient's follow-up result based on the returned follow-up template.

[0151] Here, after the patient has filled in the form, the patient's terminal will send the returned follow-up template to the intelligent follow-up module. The returned follow-up template includes the current symptom representation information, which is sent to the attending physician for online diagnosis by the attending physician, and the patient's current diagnosis result is obtained and transmitted back to the intelligent follow-up module. At this point, the intelligent follow-up module can determine the patient's follow-up result based on the current diagnosis result after diagnosis and the current symptom representation information in the template. After the patient's follow-up results are archived, the intelligent follow-up process ends.

[0152] 2. Intelligent prescription

[0153] The intelligent prescription module includes a first knowledge base, a second knowledge base, a third knowledge base and a prescription output module. The knowledge base is a collection of specific knowledge. For example, the first knowledge base mainly stores the first mapping relationship between diseases, symptom representations and disease stages. The second knowledge base mainly stores the current symptom representation information of all patients, historical prescription data, and the second mapping relationship between diagnosis results, symptom representation information, drugs and dosage. The third knowledge base mainly stores the medication contraindications information of all patients.

[0154] a. Based on the current symptom information, determine whether a prescription can be issued online for the patient.

[0155] Here, the current symptom representation information includes at least one symptom representation, based on which the patient's disease can be roughly determined. Based on the current symptom representation information, the patient's disease and the pre-stored disease, and the first mapping relationship between the symptom representation and the disease stage stored in the first knowledge base, the intelligent prescription module can determine whether the patient's disease is in a common disease stage. Common disease refers to a disease where the risk of medication is less than a threshold. If the intelligent prescription module determines that it is a common disease, the risk of medication is relatively small for the patient, so a prescription can be issued online for the patient.

[0156] b. If it is determined that a prescription can be issued online for the patient, a preliminary prescription is generated based on the current diagnosis results and current symptom representation information.

[0157] Here, when prescribing medicine for common diseases, the intelligent prescription module searches the second mapping relationship pre-stored in the second knowledge base based on the current diagnosis result and the current symptom representation information to obtain the medicine and the corresponding dosage that matches the current diagnosis result and the current symptom representation information.

[0158] c. Obtain information on medication contraindications for patients.

[0159] Here, the intelligent prescription module obtains the patient's medication contraindications information from the third knowledge base to determine which drugs the patient should use with caution.

[0160] d. Based on the patient's contraindications, screen the initial version of the prescription to obtain a discarded version of the prescription.

[0161] Here, the intelligent prescription module determines whether all the drugs in the first version of the prescription are prohibited drugs based on the patient's contraindications. If it is determined that not all of them are prohibited drugs, the prohibited drugs are removed from the first version of the prescription to obtain a removed version of the prescription.

[0162] e. Determine the patient's prescription based on historical prescription data and discarded prescriptions.

[0163] Here, after obtaining the discarded version of the prescription, the intelligent prescription module obtains historical prescription data from the second knowledge base, and the historical prescription data includes historical diagnosis results, historical symptom representation information, historical diagnosis results and historical symptom representation information.

[0164] The intelligent prescription module compares the patient's current symptom representation information with the historical symptom representation information, and compares the current diagnosis result with the historical diagnosis result. If it is determined that the current symptom representation information and the historical symptom representation information are inconsistent, and / or the current diagnosis result and the historical diagnosis result are inconsistent, the eliminated version of the prescription is determined as the patient's prescription. If it is determined that the current symptom representation information and the historical symptom representation information, as well as the previous diagnosis result and the historical diagnosis result are consistent, the patient's prescription is determined based on the patient's historical drugs and historical dosage.

[0165] If it is determined that any historical drug exists in the eliminated version of the prescription and the dosage of any historical drug is inconsistent with the corresponding historical dosage, the historical dosage of any historical drug is used as the recommended dosage of any historical drug. The patient's prescription is obtained based on the drugs in the eliminated version of the prescription and the recommended dosage of any historical drug. In this embodiment, the intelligent follow-up system can obtain the follow-up results of the patient by performing intelligent follow-up on the patient, and can generate the patient's prescription in combination with the historical prescription data obtained from the second knowledge base. In this way, the patient can obtain the prescription after the follow-up is completed, so that the patient does not need to go to the hospital to continue to register after the follow-up, which can improve the service efficiency of the hospital to a certain extent.

[0166] In one embodiment, the follow-up and prescription collaboration system constructed by the present application also includes a patient unified user center management module, a patient holographic health record management module, a full disease course management engine, a follow-up center module, an education center module and a chronic disease management center module.

[0167] The unified user center management module includes medical institution management, department management, user management, pharmaceutical company and pharmacy management, medical alliance management, role authority management and basic data management.

[0168] The patient holographic health record management module includes medical PC health records, doctor mobile terminal and patient health records; the medical PC health records are obtained by connecting to the hospital database; the doctor mobile terminal and patient health records are respectively connected to the medical PC health records; the patient health record obtains the patient treatment record, and the doctor mobile terminal calls the patient health record.

[0169] The full disease management engine includes hospital-wide rules, specialty and disease rule settings, chronic disease rule management, follow-up plans, follow-up type management, specialty follow-up templates and specialty disease follow-up engine library; the specialty disease follow-up engine library provides specialty disease follow-up engine library templates, and the specialty disease follow-up engine library includes template addition, modification and deletion.

[0170] Hospital-wide rules set rules to survey hospital or department satisfaction and manage the health of all patients in the hospital. Hospital-wide rules provide intelligent automatic follow-up services for the entire process before, during and after diagnosis, including health education, discharge reminders, reminders to bring medications when discharged, follow-up reminders, and event notifications.

[0171] The hospital-wide rules are set by the administrator, and the follow-up push rules are configured according to a fixed time period.

[0172] The hospital-wide rules configure push rules for follow-up, which include rules after admission, before admission, before surgery, after surgery, after consultation, after discharge, after transfer out, after transfer in, and after signing the contract.

[0173] The full course of disease management engine configures a follow-up plan, which includes follow-up type, follow-up path, follow-up cycle, rare disease follow-up and scientific research follow-up. Follow-up types include intelligent follow-up, specialist follow-up, regular follow-up, regular check-up, regular inspection, message reminder, chronic disease assessment report, prescription reminder, and health education.

[0174] The follow-up center module includes the follow-up homepage, patient list, follow-up person review, patient migration management, common problem management, prescription renewal management, and long prescription management.

[0175] The chronic disease management center module includes chronic disease group management, chronic disease patient management, abnormal warning, health monitoring, chronic disease indicator management, follow-up chronic disease configuration, health intervention template, chronic disease report template, chronic disease plan association settings and equipment management.

[0176] In one embodiment, the specific steps of establishing the first knowledge base are:

[0177] Step 1: Collect electronic medical records and establish a database;

[0178] Step 2: Establish data extraction rules to extract the relationships and attributes of diagnosis, representation, clinical diagnosis method, drug, and dosage;

[0179] Step 3: Perform text matching on the data in the database and merge the data to obtain the maximum content data;

[0180] Step 4: Compare the data in the database with the maximum content data to obtain feature data;

[0181] Step 5: Based on the same representation fusion feature data, output the database Q of drugs and dosages with different representations under the same diagnosis;

[0182] Step 6: Build a data association database W based on the encyclopedic knowledge database, and output different expressions of diagnosis, representation and medicine, including the scientific name and common name of diagnosis and medicine;

[0183] Step 7: Integrate the data association library and database Q to output the first knowledge base of prescriptions and dosages with different representations under the same diagnosis with different expressions.

[0184] Based on the patient's holographic health record, structured data processing is performed to extract the name, diagnosis, representation, medicine and dosage. The extracted content is one-to-one corresponding, and the relationship and attributes of the name, diagnosis, representation, medicine and dosage are extracted to output a second knowledge base based on the patient.

[0185] Medication contraindications include special populations. Based on the encyclopedia knowledge database, special populations and representations are extracted, and the relationships and attributes between special populations and representations are extracted to establish a third knowledge base.

[0186] In order to implement the method of the embodiment of the present application, the embodiment of the present application also provides a follow-up medication coordination device, such as Figure 4 As shown, the follow-up medication prescribing collaborative device corresponds to the above-mentioned follow-up medication prescribing collaborative method, and each step in the above-mentioned follow-up medication prescribing collaborative method embodiment is also fully applicable to the present follow-up medication prescribing collaborative device embodiment.

[0187] The device 400 includes: a follow-up result acquisition module 401 and a patient prescription generation module 402;

[0188] The follow-up result acquisition module 401 is used to obtain the follow-up results and historical prescription data of the patient; wherein the follow-up results at least include the current symptom manifestation and current diagnosis result of the patient;

[0189] The patient prescription generating module 402 is used to generate a prescription for the patient based on the current symptom representation, the current diagnosis result and the historical prescription data.

[0190] In one embodiment, the patient prescription generation module 402, when generating the patient's prescription based on the current symptom representation information, the current diagnosis result and the historical prescription data, is specifically used to: based on the current symptom representation, determine that a prescription can be issued online for the patient, then generate a preliminary version of the prescription based on the current diagnosis result and the current symptom representation; obtain the patient's medication contraindication information; and generate the patient's prescription based on the preliminary version of the prescription, the patient's medication contraindication information and the historical prescription data.

[0191] In one embodiment, the follow-up result acquisition module 401, when acquiring the follow-up results of the patient, is specifically used to: in response to a follow-up instruction, acquire the historical diagnosis results of the current patient, and determine a matching follow-up template based on the historical diagnosis results; send the matching follow-up template to the patient's terminal; wherein the matching follow-up template is used to collect at least one of the following: patient identity information and current symptom representation information; receive the follow-up template returned by the patient's terminal, and determine the follow-up results of the patient based on the returned follow-up template.

[0192] In one embodiment, the patient prescription generation module 402, when determining that a prescription can be issued online for the patient based on the current symptom representation information, is specifically used to: determine the patient's disease based on the current symptom representation information; determine whether the patient's disease is a common condition based on the current symptom representation information, the patient's disease, and a first mapping relationship between the pre-stored disease, symptom representation, and disease stage; wherein the common condition refers to a condition in which the risk level of medication is less than a threshold; if it is determined to be a common condition, determine that a prescription can be issued online for the patient.

[0193] In one embodiment, the patient prescription generation module 402, when generating a preliminary version of the prescription based on the current diagnosis result and the current symptom representation information, is specifically used to: based on the current diagnosis result, the current symptom representation information and a pre-stored second mapping relationship, search for drugs and corresponding dosages that match the current diagnosis result and the current symptom representation information; wherein the second mapping relationship includes the correspondence between the diagnosis result, the symptom representation information, the drugs and the dosages; and generate a preliminary version of the prescription based on the matching drugs and the corresponding dosages.

[0194] In one embodiment, the patient prescription generation module 402, when generating a patient prescription based on the initial version of the prescription, the patient's contraindications information and the historical prescription data, is specifically used to: screen the initial version of the prescription based on the patient's contraindications information to obtain a discarded version of the prescription; and determine the patient's prescription based on the historical prescription data and the discarded version of the prescription.

[0195] In one embodiment, the patient prescription generation module 402, when screening the first edition of the prescription based on the patient's contraindications information to obtain a discarded version of the prescription, is specifically used to: determine whether all the drugs in the first edition of the prescription are banned drugs based on the patient's contraindications information; if it is determined that not all of them are banned drugs, then eliminate the banned drugs from the first edition of the prescription to obtain the discarded version of the prescription.

[0196] In one embodiment, the historical prescription data includes historical diagnosis results and historical symptom representation information; the patient prescription generation module 402, when determining the patient's prescription based on the historical prescription data and the eliminated version of the prescription, is specifically used to: compare the current symptom representation information with the historical symptom representation information, and compare the current diagnosis result with the historical diagnosis result; wherein the historical symptom representation information is the symptom representation information of the patient at the time of the last follow-up; if it is determined that the current symptom representation information and the historical symptom representation information are inconsistent, and / or the current diagnosis result and the historical diagnosis result are inconsistent, then the eliminated version of the prescription is determined as the patient's prescription.

[0197] In one embodiment, the historical prescription data also includes historical drugs and corresponding historical dosages; the patient prescription generation module 402 is also used for: if it is determined that the current symptom representation information and the historical symptom representation information, as well as the current diagnosis result and the historical diagnosis result are consistent, then determine to generate a prescription for the patient based on the patient's historical drugs and historical dosages.

[0198] In one embodiment, the patient prescription generation module 402, when determining the eliminated version of the prescription as the patient's prescription, is specifically used to: if it is determined that there is any historical drug in the eliminated version of the prescription and the dosage of any historical drug is inconsistent with the corresponding historical dosage, then the historical dosage of any historical drug is used as the recommended dosage of any historical drug; and the patient's prescription is obtained based on the drugs in the eliminated version of the prescription and the recommended dosage of any historical drug.

[0199] In actual application, the follow-up result acquisition module 401 and the patient prescription generation module 402 can be implemented by a processor in the follow-up prescription coordination device 400. Of course, the processor needs to run the computer program in the memory to realize its function.

[0200] It should be noted that: the follow-up prescription collaborative device provided in the above embodiment only uses the division of the above program modules as an example when executing the follow-up prescription collaborative method. In actual applications, the above processing can be assigned to different program modules as needed, that is, the internal structure of the device can be divided into different program modules to complete all or part of the processing described above. In addition, the follow-up prescription collaborative device provided in the above embodiment and the follow-up prescription collaborative method embodiment belong to the same concept. The specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0201] Based on the hardware implementation of the above program modules and in order to implement the method of the embodiment of the present application, the embodiment of the present application also provides an electronic device. Figure 5 Only an exemplary structure of the electronic device is shown, not all structures, and it can be implemented as needed. Figure 5 Partial or complete structure shown.

[0202] like Figure 5 As shown, the electronic device 500 provided in the embodiment of the present application includes: at least one processor 501, a memory 502, a user interface 503 and at least one network interface 504. The various components in the electronic device 500 are coupled together through a bus system 505. It can be understood that the bus system 505 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 505 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, in Figure 5 Various buses are labeled as bus system 505 .

[0203] The user interface 503 may include a display, a keyboard, a mouse, a trackball, a click wheel, keys, buttons, a touch pad or a touch screen.

[0204] The memory 502 in the embodiment of the present application is used to store various types of data to support the operation of the electronic device. Examples of such data include: any computer program used to operate on the electronic device.

[0205] The follow-up and prescribing coordination disclosed in the embodiment of the present application can be applied to the processor 501, or implemented by the processor 501. The processor 501 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the follow-up and prescribing coordination can be completed by the hardware integrated logic circuit or software instructions in the processor 501. The above-mentioned processor 501 can be a general-purpose processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 501 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general-purpose processor can be a microprocessor or any conventional processor, etc. In combination with the steps of the method disclosed in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in the memory 502, and the processor 501 reads the information in the memory 502, and completes the steps of the follow-up and prescribing coordination provided in the embodiment of the present application in combination with its hardware.

[0206] In an exemplary embodiment, the electronic device may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD), field programmable gate array (FPGA), general processor, controller, microcontroller (MCU), microprocessor, or other electronic components to execute the aforementioned method.

[0207] It can be understood that the memory 502 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disk, or a compact disc read-only memory (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM, SyncLink Dynamic Random Access Memory), and direct RAM bus random access memory (DRRAM, Direct Rambus Random Access Memory).The memories described in the embodiments of the present application are intended to include, but are not limited to, these and any other suitable types of memories.

[0208] In an exemplary embodiment, the present application also provides a computer storage medium, namely, a computer storage medium, which may be a computer-readable storage medium, for example, a memory 502 storing a computer program, and the computer program may be executed by a processor 501 of an electronic device to complete the steps described in the method of the present application. The computer-readable storage medium may be a memory such as a ROM, a PROM, an EPROM, an EEPROM, a Flash Memory, a magnetic surface memory, an optical disk, or a CD-ROM.

[0209] It should be noted that: "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence.

[0210] In addition, the technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict.

[0211] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A collaborative method for follow-up and prescribing medicines, characterized in that: include: Obtaining the patient's follow-up results and historical prescription data; wherein the follow-up results at least include the patient's current symptom representation information and current diagnosis results; A prescription for the patient is generated based on the current symptom representation information, the current diagnosis result and the historical prescription data.

2. The method according to claim 1, characterized in that The step of generating a prescription for the patient based on the current symptom representation information, the current diagnosis result and the historical prescription data comprises: Based on the current symptom representation information, it is determined that a prescription can be prescribed online for the patient, and then a preliminary version of the prescription is generated based on the current diagnosis result and the current symptom representation information; Obtaining medication contraindication information for the patient; A prescription for the patient is generated based on the first edition of the prescription, the patient's contraindications information and the historical prescription data.

3. The method according to claim 1 or 2, characterized in that: The obtaining of the follow-up results of the patient includes: In response to the follow-up instruction, obtaining the historical diagnosis results of the current patient, and determining a matching follow-up template based on the historical diagnosis results; Sending the matched follow-up template to the terminal of the patient; wherein the matched follow-up template is used to collect at least one of the following: patient identity information and current symptom representation information; A follow-up template returned by the terminal of the patient is received, and a follow-up result of the patient is determined based on the returned follow-up template.

4. The method according to claim 2, characterized in that: The step of determining that an online prescription can be issued to the patient based on the current symptom representation information comprises: Determining the patient's disease based on the current symptom representation information; Determine whether the stage of the patient's disease is a common disease according to the current symptom representation information, the patient's disease, and a pre-stored first mapping relationship between the disease, symptom representation, and disease stage; wherein the common disease refers to a disease with a medication risk level less than a threshold; If it is determined to be a common condition, it is determined that a prescription can be issued online for the patient.

5. The method according to claim 2, characterized in that: The step of generating a preliminary prescription based on the current diagnosis result and the current symptom representation information includes: Based on the current diagnosis result, the current symptom representation information and a pre-stored second mapping relationship, searching for a drug and a corresponding dosage that matches the current diagnosis result and the current symptom representation information; wherein the second mapping relationship includes a correspondence between the diagnosis result, the symptom representation information, the drug and the dosage; A preliminary version of the prescription is generated based on the matched drugs and the corresponding dosages.

6. The method according to claim 2, characterized in that The step of generating a prescription for a patient based on the first edition of the prescription, the patient's contraindications information and the historical prescription data includes: Based on the patient's contraindications, the first version of the prescription is screened to obtain a discarded version of the prescription; The prescription for the patient is determined based on the historical prescription data and the discarded version of the prescription.

7. The method according to claim 6, characterized in that The method of screening the first version of the prescription based on the patient's contraindications to obtain a discarded version of the prescription includes: Based on the patient's medication contraindications information, determining whether all the drugs in the first version of the prescription are prohibited drugs; If it is determined that not all of them are banned drugs, the banned drugs are removed from the first version of the prescription to obtain the removed version of the prescription.

8. The method according to claim 6, characterized in that The historical prescription data includes historical diagnosis results and historical symptom representation information; and determining the patient's prescription based on the historical prescription data and the discarded prescription includes: Comparing the current symptom representation information with the historical symptom representation information, and comparing the current diagnosis result with the historical diagnosis result; wherein the historical symptom representation information is the symptom representation information of the patient at the last follow-up; If it is determined that the current symptom representation information is inconsistent with the historical symptom representation information, and / or the current diagnosis result is inconsistent with the historical diagnosis result, the eliminated version of the prescription is determined as the prescription for the patient.

9. The method according to claim 8, characterized in that The historical prescription data also includes historical drugs and corresponding historical dosages; and determining the patient's prescription based on the historical prescription data and the eliminated prescription also includes: If it is determined that the current symptom representation information and the historical symptom representation information, as well as the current diagnosis result and the historical diagnosis result are consistent, a prescription for the patient is generated based on the patient's historical drugs and historical dosages.

10. The method according to claim 8, characterized in that The step of determining the prescription of the discarded version as the prescription of the patient comprises: If it is determined that any historical drug exists in the prescription of the eliminated version and the dosage of any historical drug is inconsistent with the corresponding historical dosage, the historical dosage of any historical drug is used as the recommended dosage of any historical drug; The patient's prescription is obtained based on the drugs in the eliminated version of the prescription and the recommended dosage of any historical drug.

11. A follow-up medication coordination device, characterized in that: The device comprises: A follow-up result acquisition module is used to obtain the patient's follow-up results and historical prescription data; wherein the follow-up results at least include the patient's current symptom manifestations and current diagnosis results; The patient prescription generation module is used to generate a prescription for the patient based on the current symptom representation, the current diagnosis result and the historical prescription data.

12. An electronic device, characterized in that: include: A processor and a memory for storing a computer program that can be executed on the processor, wherein: The processor is used to execute the steps of the method according to any one of claims 1 to 10 when running a computer program.

13. A computer storage medium having a computer program stored thereon, 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 10 are implemented.

Images