Remote diagnosis and treatment service method and device based on big data and medium

Abstract

The embodiment of the invention discloses a remote diagnosis and treatment service method and device based on big data and a medium, and relates to the technical field of elderly medical care, and the method comprises the steps: receiving remote diagnosis and treatment service request information triggered by a plurality of household patients, and crawling historical treatment data of each household patient based on a user identifier and a big data technology; according to each piece of historical doctor seeing data and the user attribute feature information, generating a health state prediction model of each household patient; according to the health state prediction model and the current body monitoring data, predicted health data of each household patient is generated, and the medical care service level of each household patient is determined; matching the predicted health data of each household patient with a plurality of reception user portraits, and determining a specified remote reception user corresponding to the household patient; and according to the medical care service level of each home patient, establishing a remote diagnosis and treatment channel between the appointed remote reception user and the home patient in sequence, and carrying out remote diagnosis and treatment service through the remote diagnosis and treatment channel.

Description

Technical Field

[0001] The present invention relates to the field of geriatric medical care technology, and in particular to a remote diagnosis and treatment service method, equipment and medium based on big data. Background Art

[0002] With the rapid development of society and the improvement of economic level, the combination of medical industry and various technologies is becoming more and more common. In the medical field, due to the large proportion of elderly users suffering from diseases and the difficulty of seeing a doctor and receiving treatment for elderly users, the diagnosis and treatment of elderly users need special attention. In order to further improve the quality of life of elderly users, home medical care has emerged. By setting up a medical care platform, elderly patients can achieve remote diagnosis and treatment at home. The medical care platform uses large-screen TVs, mobile phones, computers, service outlets and other channels as service entrances, forming a multi-screen interactive, online and offline integrated service system, integrating remote diagnosis and treatment, health consultation, physiological monitoring and other service contents.

[0003] At present, in remote diagnosis and treatment services, multiple doctors are usually provided for elderly patients, and the elderly users or accompanying personnel can choose by themselves. However, due to the lack of scientific knowledge of the diseases suffered by elderly patients or their accompanying family members, and the lack of understanding of the doctor's expertise in diagnosis and treatment, the selected doctors may not match; in addition, when there are multiple elderly patients who need remote diagnosis and treatment at the same time, each elderly patient has a different health status and there are differences in the urgency of diagnosis and treatment. In the scenario of remote diagnosis and treatment of multiple elderly patients, it is impossible to orderly allocate doctors according to the actual situation of each elderly patient. Therefore, the existing remote diagnosis and treatment services have the problem of mismatching the doctors selected by patients, and cannot meet the needs of orderly and reasonable allocation in the scenario of remote diagnosis and treatment of multiple elderly patients. Summary of the invention

[0004] One or more embodiments of the present specification provide a remote diagnosis and treatment service method, device and medium based on big data, which are used to solve the following technical problems: the existing remote diagnosis and treatment services have the problem of mismatch between the doctors selected by the patients themselves, and cannot meet the needs of orderly and reasonable allocation in the scenario of remote diagnosis and treatment of multiple elderly patients.

[0005] One or more embodiments of this specification adopt the following technical solutions:

[0006] One or more embodiments of the present specification provide a remote diagnosis and treatment service method based on big data, characterized in that the method includes: receiving remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawling the historical medical treatment data of each home patient based on the user identifier and big data technology in each of the service request information; generating a health status prediction model for each home patient according to each of the historical medical treatment data and the user attribute feature information of each home patient obtained in advance; generating predicted health data for each home patient through the health status prediction model of each home patient and the current body monitoring data of each home patient obtained in advance, so as to determine the medical care service level of each home patient; obtaining the reception user portraits of multiple remote reception users who provide remote medical care services, matching the predicted health data of each home patient with the reception user portraits of the multiple remote reception users, and determining the designated remote reception user corresponding to each home patient; according to the medical care service level of each home patient, sequentially establishing a remote diagnosis and treatment channel between the designated remote reception user and the home patient, and performing remote diagnosis and treatment services through the remote diagnosis and treatment channel.

[0007] Furthermore, a health status prediction model for each home patient is generated based on each of the historical medical data and the user attribute characteristic information of each home patient obtained in advance, specifically including: obtaining the user attribute characteristic information of each home patient, wherein the user attribute characteristic information includes gender identification, age and work information; determining the disease identification, illness duration and treatment data in the historical medical data; according to the user attribute characteristic information and the disease identification in the historical medical data, obtaining the disease data of multiple reference patients corresponding to the home patient in a preset big data analysis library; wherein the disease data includes a reference disease identification, illness duration and treatment process, the user attribute characteristic information of each reference patient is the same as the user attribute characteristic information of the home patient, and the reference disease identification of the reference patient is the same as the disease identification of the home patient; based on the disease data of the multiple reference patients, an initial health prediction model corresponding to the home patient is constructed; according to the illness duration and treatment data in the historical medical data, the initial health prediction model is updated to obtain a current health status prediction model for each home patient.

[0008] Furthermore, predicted health data of each home-based patient is generated through a health status prediction model of each home-based patient and pre-acquired current physical monitoring data of each home-based patient to determine the medical care service level of each home-based patient, specifically including: acquiring the current physical monitoring data of each home-based patient, wherein the current physical monitoring data includes blood pressure data, heart rate data, body temperature data, blood oxygen saturation data, blood sugar data and weight data; generating predicted health data of each home-based patient based on the current physical monitoring data and the health status prediction model of the home-based patient, wherein the predicted health data includes a disease identifier and disease indicator prediction data corresponding to the disease identifier; acquiring indicator reference data corresponding to the disease identifier in a pre-constructed expert knowledge base based on the disease identifier in the predicted health data; and determining the medical care service level of each home-based patient based on the indicator reference data and the disease indicator prediction data.

[0009] Furthermore, based on the indicator reference data and the disease indicator prediction data, the medical care service level of each of the home patients is determined, specifically including: calculating the prediction difference between the disease indicator prediction data and the indicator reference data; generating an indicator deviation based on the ratio of the prediction difference to the indicator reference data; and determining the medical care service level of each of the home patients according to the indicator deviation.

[0010] Furthermore, the predicted health data of each of the home-based patients is matched with the reception user portraits of the multiple remote reception users to determine the designated remote reception user corresponding to each of the home-based patients, specifically comprising: generating a predicted medical portrait of the remote reception medical staff corresponding to the home-based patient based on the predicted health data of each of the home-based patients, wherein the predicted medical portrait includes the attributes of the disease being treated, the attributes of the reception time and the attributes of the reception waiting time of the remote reception medical staff; matching the predicted medical portrait with the reception user portraits in a preset reception user portrait library to determine the degree of match between the predicted medical portrait and the multiple reception user portraits; determining the designated reception user portrait with a degree of match greater than a preset threshold as the designated remote reception user corresponding to each of the home-based patients; establishing a correspondence between the home-based patient and the designated remote reception user, and storing the correspondence in a preset reception correspondence table.

[0011] Furthermore, before matching the predicted medical and nursing portrait with the reception user portrait in the preset reception user portrait library, the method also includes: obtaining the current reception status of the reception user corresponding to each reception user portrait in the reception user portrait library, wherein the current reception status includes any one of a busy state and an idle state; based on the current reception status of each of the reception users, screening out a plurality of first reception user portraits corresponding to the first reception users in the reception user portrait library, wherein the current reception status of each of the first reception users is an idle state; sending a test signal to the reception terminal corresponding to each of the first reception users, wherein the test signal is used to test whether the first reception user has the conditions for remote consultation, and when the first reception user has the conditions for remote consultation, returning a confirmation signal; according to the confirmation signal, determining at least one designated first reception user from the plurality of first reception users, so as to match the predicted medical and nursing portrait with the reception user portrait corresponding to the at least one designated reception user, wherein the at least one designated first reception user has returned a confirmation signal.

[0012] Furthermore, according to the medical care service level of each home-based patient, remote diagnosis and treatment channels are established between the designated remote reception user and the home-based patient in turn, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channels, specifically including: classifying the multiple home-based patients according to the medical care service level of each home-based patient to obtain a patient group corresponding to each medical care service level; sorting the multiple patient groups among groups according to the medical care service level corresponding to each patient group to obtain an inter-group order; when there are multiple home-based patients in the patient group, obtaining the indicator deviation degree of each home-based patient in the group, sorting the multiple home-based patients in the group according to the indicator deviation degree to obtain an intra-group order; obtaining a diagnosis and treatment order for the multiple home-based patients through the inter-group order and the intra-group order, so as to establish remote diagnosis and treatment channels between the designated remote reception user and the home-based patient in turn according to the diagnosis and treatment order, and provide remote diagnosis and treatment services through the remote diagnosis and treatment channels.

[0013] Furthermore, according to the medical and nursing service level of each of the home patients, remote diagnosis and treatment channels are established between the designated remote reception user and the home patients in turn. After performing remote diagnosis and treatment services through the remote diagnosis and treatment channels, the method further includes: after performing remote diagnosis and treatment services for the home patients, obtaining diagnosis and treatment service data, wherein the diagnosis and treatment service data include disease treatment suggestions; based on the disease treatment suggestions in the diagnosis and treatment service data, matching at least one medical and nursing service corresponding to the disease treatment suggestions; and pushing the at least one medical and nursing service to the home patients, wherein the medical and nursing services include any one or more of health care services, emergency rescue services, and surrounding medical resources recommendation services.

[0014] One or more embodiments of this specification provide a remote diagnosis and treatment service device based on big data, including:

[0015] at least one processor; and,

[0016] a memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to:

[0018] Receive remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawl the historical medical data of each home patient based on the user identifier and big data technology in each service request information; generate a health status prediction model for each home patient according to each historical medical data and the user attribute feature information of each home patient obtained in advance; generate predicted health data for each home patient through the health status prediction model of each home patient and the current body monitoring data of each home patient obtained in advance, so as to determine the medical care service level of each home patient; obtain the reception user portraits of multiple remote reception users who provide remote medical care services, match the predicted health data of each home patient with the reception user portraits of the multiple remote reception users, and determine the designated remote reception user corresponding to each home patient; according to the medical care service level of each home patient, establish remote diagnosis and treatment channels between the designated remote reception users and the home patients in turn, and provide remote diagnosis and treatment services through the remote diagnosis and treatment channels.

[0019] One or more embodiments of this specification provide a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to:

[0020] Receive remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawl the historical medical data of each home patient based on the user identifier and big data technology in each service request information; generate a health status prediction model for each home patient according to each historical medical data and the user attribute feature information of each home patient obtained in advance; generate predicted health data for each home patient through the health status prediction model of each home patient and the current body monitoring data of each home patient obtained in advance, so as to determine the medical care service level of each home patient; obtain the reception user portraits of multiple remote reception users who provide remote medical care services, match the predicted health data of each home patient with the reception user portraits of the multiple remote reception users, and determine the designated remote reception user corresponding to each home patient; according to the medical care service level of each home patient, establish remote diagnosis and treatment channels between the designated remote reception users and the home patients in turn, and provide remote diagnosis and treatment services through the remote diagnosis and treatment channels.

[0021] At least one of the above-mentioned technical solutions adopted in the embodiments of this specification can achieve the following beneficial effects: through the above-mentioned technical solution, a health status prediction model for each home-based patient is generated through the historical medical data and user attribute characteristic information of each home-based patient, and the predicted health data is obtained to determine the medical and nursing service level of each home-based patient. The disease development law of home-based patients is taken into consideration, the health status of home-based patients is predicted, the urgency of diagnosis and treatment is quantified, and the medical and nursing service level is determined; the reception user portrait is obtained, the predicted health data of each home-based patient is matched with the reception user portraits of multiple remote reception users, and the designated remote reception user corresponding to each home-based patient is determined, which ensures the matching degree between the patient and the medical staff, further improves the efficiency of diagnosis and treatment services, and can meet the reasonable allocation needs in the scenario of remote diagnosis and treatment of multiple elderly patients; according to the medical and nursing service level of each home-based patient, remote diagnosis and treatment channels between the designated remote reception users and the home-based patients are established in turn to meet the orderly allocation needs in the scenario of remote diagnosis and treatment of multiple elderly patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of this specification or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art description. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. In the drawings:

[0023] Figure 1 A flowchart of a remote diagnosis and treatment service method based on big data provided in an embodiment of this specification;

[0024] Figure 2 A schematic diagram of the structure of a remote diagnosis and treatment service device based on big data provided in an embodiment of this specification. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of this specification.

[0026] With the rapid development of society and the improvement of economic level, the combination of medical industry and various technologies is becoming more and more common. In the medical field, due to the large proportion of elderly users suffering from diseases and the difficulty of seeing a doctor and receiving treatment for elderly users, the diagnosis and treatment of elderly users need special attention. In order to further improve the quality of life of elderly users, home medical care has emerged. By setting up a medical care platform, elderly patients can achieve remote diagnosis and treatment at home. The medical care platform uses large-screen TVs, mobile phones, computers, service outlets and other channels as service entrances, forming a multi-screen interactive, online and offline integrated service system, integrating remote diagnosis and treatment, health consultation, physiological monitoring and other service contents.

[0027] At present, in remote diagnosis and treatment services, multiple doctors are usually provided for elderly patients, and the elderly users or accompanying personnel can choose by themselves. However, due to the lack of scientific knowledge of the diseases suffered by elderly patients or their accompanying family members, and the lack of understanding of the doctor's expertise in diagnosis and treatment, the selected doctors may not match; in addition, when there are multiple elderly patients who need remote diagnosis and treatment at the same time, each elderly patient has a different health status and there are differences in the urgency of diagnosis and treatment. In the scenario of remote diagnosis and treatment of multiple elderly patients, it is impossible to orderly allocate doctors according to the actual situation of each elderly patient. Therefore, the existing remote diagnosis and treatment services have the problem of mismatching the doctors selected by patients, and cannot meet the needs of orderly and reasonable allocation in the scenario of remote diagnosis and treatment of multiple elderly patients.

[0028] The embodiments of this specification provide a remote diagnosis and treatment service method based on big data. It should be noted that the execution subject in the embodiments of this specification can be a server or any device with data processing capabilities. Figure 1 A flowchart of a remote diagnosis and treatment service method based on big data provided in the embodiment of this specification is shown in FIG. Figure 1 As shown, it mainly includes the following steps:

[0029] Step S101, receiving remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawling the historical medical data of each home patient based on the user identifier in each service request information and big data technology.

[0030] In one embodiment of the present specification, it can be applied to a medical care platform. A home patient logs in to the medical care platform using a TV, mobile phone or PC and triggers a remote diagnosis and treatment service request. For example, the remote diagnosis and treatment service request can be triggered by clicking a remote diagnosis and treatment service button on the corresponding interface. The remote diagnosis and treatment service request includes the user ID of the requesting user. The requesting user here is a home patient who needs remote diagnosis and treatment services.

[0031] Through the user ID of home patients and the use of big data technology, the historical medical data of home patients can be crawled from the medical database. The medical database is a medical database composed of various hospitals, pharmacies and various medical institutions. The user ID can be the processed user name and identity information, which can fully protect the patient's personal privacy data.

[0032] Step S102, generating a health status prediction model for each home patient based on each historical medical consultation data and pre-acquired user attribute feature information of each home patient.

[0033] A health status prediction model for each home patient is generated based on each of the historical medical data and the user attribute characteristic information of each home patient obtained in advance, specifically including: obtaining the user attribute characteristic information of each home patient, wherein the user attribute characteristic information includes gender identification, age and work information; determining the disease identification, illness duration and treatment data in the historical medical data; according to the user attribute characteristic information and the disease identification in the historical medical data, obtaining the disease data of multiple reference patients corresponding to the home patient in a preset big data analysis library; wherein the disease data includes a reference disease identification, illness duration and treatment process, the user attribute characteristic information of each reference patient is the same as the user attribute characteristic information of the home patient, and the reference disease identification of the reference patient is the same as the disease identification of the home patient; based on the disease data of the multiple reference patients, an initial health prediction model corresponding to the home patient is constructed; according to the illness duration and treatment data in the historical medical data, the initial health prediction model is updated to obtain a current health status prediction model for each home patient.

[0034] In one embodiment of the present specification, user attribute characteristic information of home patients is obtained. When obtaining the user attribute characteristic information, the gender, age and work information of the home patients can be obtained by crawling the patient's personal information in the medical database. In addition, the historical medical data includes the disease identification, illness duration and treatment data. The disease identification is used to indicate the name of the current disease, and the treatment data includes historical medication, historical examination results, etc.

[0035] According to the user attribute characteristic information and the disease identification in the historical medical data, the disease data of multiple reference patients with the same disease and the same attribute characteristics as the home patient are obtained in the preset big data analysis library. The disease data includes the reference disease identification, duration of illness and treatment process. In other words, the disease suffered by the reference patient, the work attribute in the work information, the age and gender are the same as those of the home patient. Introducing work attributes can avoid the problem of inaccurate prediction when predicting health status due to work reasons causing a certain disease to not develop according to the law of the disease.

[0036] Through the disease data of multiple reference patients, an initial health prediction model corresponding to the home patient is constructed. The initial health prediction model is obtained based on the disease data of reference patients with the same disease type and basic characteristic information as the home patient. It should be noted that the big data analysis library stores relatively complete reference patient disease data, that is, the reference patient disease data is all data of the disease stage, such as heart rate, blood pressure and other physical indicator data, which has a good reference for the development of the disease of patients of the same type. Therefore, the initial health prediction model better represents the development trend of the disease in such patients. The illness duration and treatment data in the historical medical data indicate the current stage of the disease of the home patient. The initial health prediction model is updated through the illness duration and treatment data to obtain the current health status prediction model of each home patient, ensuring the user-specific and disease stage-specific nature of the prediction model.

[0037] Step S103, generating predicted health data for each home patient through the health status prediction model of each home patient and the current body monitoring data of each home patient acquired in advance, so as to determine the medical care service level of each home patient.

[0038] Generate predicted health data for each home patient through a health status prediction model for each home patient and pre-acquired current physical monitoring data for each home patient to determine the medical care service level for each home patient, specifically including: acquiring the current physical monitoring data for each home patient, wherein the current physical monitoring data includes blood pressure data, heart rate data, body temperature data, blood oxygen saturation data, blood sugar data and weight data; generate predicted health data for each home patient based on the current physical monitoring data and the health status prediction model for the home patient, wherein the predicted health data includes a disease identifier and disease indicator prediction data corresponding to the disease identifier; acquire indicator reference data corresponding to the disease identifier in a pre-constructed expert knowledge base based on the disease identifier in the predicted health data; determine the medical care service level for each home patient based on the indicator reference data and the disease indicator prediction data.

[0039] Based on the indicator reference data and the disease indicator prediction data, the medical care service level of each of the home patients is determined, specifically including: calculating the prediction difference between the disease indicator prediction data and the indicator reference data; generating an indicator deviation degree based on the ratio of the prediction difference to the indicator reference data; and determining the medical care service level of each of the home patients according to the indicator deviation degree.

[0040] In one embodiment of the present specification, the current body monitoring data of each home patient is collected through a body monitoring module, and the body monitoring module here can be multiple intelligent collection terminals, such as bracelets, weight scales, etc. The current body monitoring data of each home patient is obtained, including blood pressure data, heart rate data, body temperature data, blood oxygen saturation data, blood sugar data and weight data. According to the current body monitoring data and the health status prediction model of the home patient, the predicted health data of each home patient is generated, and the predicted health data includes the disease identification and the disease index prediction data corresponding to the disease identification. It should be noted that the current body monitoring data represents the current disease stage of the home patient, and the disease index prediction data according to the law of disease development is obtained through the body monitoring data corresponding to the current disease stage and the health status prediction model. According to the disease identification in the predicted health data, the indicator reference data corresponding to the disease identification is obtained in the pre-constructed expert knowledge base. The indicator reference data here can be a data range or a standard value, for example, a standard heart rate range.

[0041] The medical and nursing service level of each home patient is determined by the indicator reference data and the disease indicator prediction data. When the indicator reference data is a standard value, first, the predicted difference between the disease indicator prediction data and the indicator reference data is calculated. The size relationship between the disease indicator prediction data and the indicator reference data is uncertain, and the absolute value of the difference is taken here; then, the ratio of the absolute value of the predicted difference to the indicator reference data is calculated to generate the indicator deviation. The greater the indicator deviation, the greater the deviation between the disease indicator prediction data of the home patient and the standard data, and the higher the medical and nursing service level of the home patient, that is, the higher the urgency of diagnosis and treatment of the home patient. The medical and nursing service level can be divided into level one, level two and level three, where the level one is higher than the level two, and the level two is higher than the level three. The medical and nursing service level corresponding to different indicator deviations can be determined by setting the deviation threshold of each medical and nursing service level. For example, the first-level deviation threshold is 50%, and the second-level deviation threshold is 10%. When the indicator deviation is not less than 50% of the first-level deviation threshold, it is determined as the first-level medical and nursing service level. When the indicator deviation is not less than 10% and less than 50%, it is determined as the second-level medical and nursing service level. When the indicator deviation is less than 10%, it is determined as the third-level medical and nursing service level. The above content is only for exemplary display and can be set according to actual needs.

[0042] When the indicator reference data is a data range, first determine whether the disease indicator prediction data is within the value range. If not, calculate the absolute value of the difference between the disease indicator prediction data and the data at both ends of the data range, determine the smaller absolute value of the difference and the corresponding reference value at one end of the data range, and calculate the ratio of the absolute value of the difference to the reference data as the indicator deviation. For example, the data range is 5-8, the predicted data is 9, the absolute values ​​of the difference are 1 and 4 respectively, and the reference value at one end of the data range corresponding to the absolute value of the difference 1 is 8, then calculate the ratio of 1 to 8 as the indicator deviation.

[0043] The indicator deviation is obtained through the patient indicator prediction data, and the medical and nursing service level of home patients is determined based on the indicator deviation. The urgency of diagnosis and treatment of home patients is quantified, and combined with the patient's predicted data, it has predictive power.

[0044] Step S104, obtaining the user portraits of multiple remote consultation users who provide remote medical and nursing services, matching the predicted health data of each home patient with the user portraits of the multiple remote consultation users, and determining the designated remote consultation user corresponding to each home patient.

[0045] The predicted health data of each home patient is matched with the reception user portraits of the multiple remote reception users to determine the designated remote reception user corresponding to each home patient, specifically including: generating a predicted medical portrait of the remote reception medical staff corresponding to the home patient according to the predicted health data of each home patient, wherein the predicted medical portrait includes the disease attributes, reception time attributes and reception waiting time attributes of the remote reception medical staff; matching the predicted medical portrait with the reception user portraits in a preset reception user portrait library to determine the matching degree between the predicted medical portrait and the multiple reception user portraits; determining the designated reception user portrait with a matching degree greater than a preset threshold as the designated remote reception user corresponding to each home patient; establishing a corresponding relationship between the home patient and the designated remote reception user, and storing it in a preset reception correspondence table.

[0046] In one embodiment of the present specification, a predicted medical portrait of the remote medical staff corresponding to the home patient is generated based on the predicted health data of each home patient, and the predicted medical portrait includes the diagnosis disease attribute, the diagnosis time attribute and the diagnosis waiting time attribute of the remote medical staff. The diagnosis disease attribute corresponding to the generated predicted medical portrait is the same as the disease type corresponding to the predicted health data of the home patient, that is, the diagnosis disease attribute of the predicted medical portrait can meet the diagnosis and treatment requirements of the disease suffered by the home patient; the diagnosis time attribute refers to the diagnosis time required for the diagnosis and treatment of the predicted health data; the diagnosis waiting time attribute refers to the waiting time that can be allowed for the stage corresponding to the predicted health data, for example, in an emergency, the level time is relatively short.

[0047] The predicted medical and nursing portraits are matched with the reception user portraits in the pre-set reception user portrait library to determine the matching degree between the predicted medical and nursing portraits and multiple reception user portraits. The designated reception user portraits with a matching degree greater than the preset threshold are used as the designated remote reception user corresponding to each home patient, and a correspondence between home patients and designated remote reception users is established and stored in a preset reception correspondence table for subsequent calls. Determining remote reception users by user portrait matching achieves the accuracy of matching between home patients and remote reception users, and combined with predicted health data, the matched remote reception users are more suitable for the actual situation of home patients, further improving the diagnosis and treatment efficiency.

[0048] Before matching the predicted medical and nursing portrait with the reception user portraits in the preset reception user portrait library, the method also includes: obtaining the current reception status of the reception user corresponding to each reception user portrait in the reception user portrait library, wherein the current reception status includes any one of a busy state and an idle state; based on the current reception status of each of the reception users, screening out a plurality of first reception user portraits corresponding to the first reception users in the reception user portrait library, wherein the current reception status of each of the first reception users is an idle state; sending a test signal to the reception terminal corresponding to each of the first reception users, wherein the test signal is used to test whether the first reception user has the conditions for remote consultation, and when the first reception user has the conditions for remote consultation, returning a confirmation signal; according to the confirmation signal, determining at least one designated first reception user from the plurality of first reception users, so as to match the predicted medical and nursing portrait with the reception user portrait corresponding to the at least one designated reception user, wherein the at least one designated first reception user has returned a confirmation signal.

[0049] In one embodiment of the present specification, since the patient portraits in the patient portrait library include all patients, there may be cases where the patient is in the patient status or busy with offline diagnosis and treatment, or the patient does not carry a terminal device, etc., resulting in the situation where the patient cannot be diagnosed after the patient corresponding to the patient at home is determined. Before performing user portrait matching, the status of the patient in the patient portrait library is confirmed.

[0050] First, obtain the current reception status of each reception user portrait in the reception user portrait library. The current reception status includes any one of a busy state and an idle state. When the reception user is idle, the idle state flag can be set. When the reception user is receiving a consultation, the state can be set to a busy state by clicking a button. The idle state flag here can be a green flag, and the busy state flag can be a red flag.

[0051] Secondly, through the current reception status of each reception user, the reception user portrait library is screened to obtain the first reception user portraits corresponding to multiple first reception users whose current reception status is idle. A test signal is sent to the reception terminal corresponding to each first reception user. The test signal is used to test whether the first reception user has the conditions for remote consultation. When the first reception user has the conditions for remote consultation, a confirmation signal is returned. For example, the test signal can be in the form of a pop-up window, and the content of the pop-up window can be set to whether the conditions for consultation are met. If the reception user has the conditions for consultation, click yes, thereby returning a confirmation signal to the medical care platform. Based on at least one confirmation signal received, at least one designated first reception user who has sent a confirmation signal is determined among the multiple first reception users, so as to facilitate the matching of the predicted medical and nursing portrait with the reception user portrait corresponding to at least one designated reception user. The accuracy and pertinence of the matching are further improved.

[0052] Step S105, according to the medical care service level of each home patient, remote diagnosis and treatment channels are established between the designated remote reception users and the home patients in turn, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channels.

[0053] According to the medical care service level of each home patient, a remote diagnosis and treatment channel is established between the designated remote reception user and the home patient in turn, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channel, specifically including: according to the medical care service level of each home patient, a plurality of home patients are classified to obtain a patient group corresponding to each medical care service level; according to the medical care service level corresponding to each patient group, a plurality of patient groups are sorted between groups to obtain an inter-group order; when there are multiple home patients in the patient group, an indicator deviation degree of each home patient in the group is obtained, and according to the indicator deviation degree, the multiple home patients in the group are sorted within the group to obtain an intra-group order; through the inter-group order and the intra-group order, a diagnosis and treatment order for the multiple home patients is obtained, so that according to the diagnosis and treatment order, a remote diagnosis and treatment channel is established between the designated remote reception user and the home patient in turn, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channel.

[0054] In the scenario of remote diagnosis and treatment for multiple elderly patients, there may be multiple elderly patients who need remote diagnosis and treatment at the same time. The health status of each elderly patient is different, and the urgency of diagnosis and treatment varies. It is particularly important to determine the order of diagnosis and treatment services.

[0055] In one embodiment of the present specification, according to the medical care service level of each home patient, home patients belonging to the same medical care service level are divided into a group to obtain a patient group corresponding to each medical care service level. According to the order of the medical care service level corresponding to each patient group from high to low, multiple patient groups are sorted between groups to obtain an inter-group order. In other words, the patient group with a high medical care service level is after the patient group with a low medical care service level.

[0056] When there are multiple home patients in the patient group, obtain the index deviation of each home patient in the group, and sort the multiple home patients in the group in order from large to small according to the index deviation, and obtain the intra-group order. The larger the index deviation is, the higher the order is. Through the inter-group order and the intra-group order, the diagnosis and treatment order of multiple home patients is obtained. For example, the component order is patient group A, patient group B and patient group C, where the order in patient group A is home patient 1, home patient 2, the order in patient group B is home patient 3, home patient 4, and the order in patient group C is home patient 5, home patient 6. Then the obtained diagnosis and treatment order is home patient 1, home patient 2, home patient 3, home patient 4, home patient 5, home patient 6. According to the diagnosis and treatment order, the remote diagnosis and treatment channel between the designated remote reception user and the home patient is established in turn, and the remote diagnosis and treatment service is carried out through the remote diagnosis and treatment channel. The medical and nursing service level of each home patient is determined to determine the urgency of diagnosis and treatment and the order of diagnosis and treatment, thereby ensuring that urgent patients are treated first, further improving the user experience.

[0057] According to the medical and nursing service level of each home patient, a remote diagnosis and treatment channel is established between the designated remote reception user and the home patient in turn. After the remote diagnosis and treatment service is provided through the remote diagnosis and treatment channel, the method also includes: after providing the home patient with the remote diagnosis and treatment service, obtaining diagnosis and treatment service data, wherein the diagnosis and treatment service data includes disease treatment suggestions; based on the disease treatment suggestions in the diagnosis and treatment service data, matching at least one medical and nursing service corresponding to the disease treatment suggestions; pushing the at least one medical and nursing service to the home patient, wherein the medical and nursing service includes any one or more of health care services, emergency rescue services and surrounding medical resources recommendation services.

[0058] In one embodiment of the present specification, after completing the remote diagnosis and treatment service, medical care service push is provided to home patients based on the diagnosis and treatment service data. In actual application scenarios, the diagnosis and treatment service data includes disease treatment suggestions, which can be divided into two types: offline treatment and home recuperation. Offline treatment refers to recommending hospital examination and treatment, and recommending home patients to go to the hospital for systematic treatment. Home recuperation refers to recommending patients to recuperate at home according to doctor's advice, such as taking medicine, food supplements, etc. According to the disease treatment suggestions, the corresponding medical care services are matched and pushed to the user. For example, during offline treatment, emergency rescue services can be pushed to achieve one-click emergency rescue, and surrounding medical resource recommendation services can also be pushed to push surrounding medical institutions that treat the disease to home patients; during home recuperation, health care services can be pushed to promote health and wellness knowledge to home patients. The user experience is further improved, and subsequent targeted services can be provided for home patients.

[0059] Through the above technical scheme, a health status prediction model for each home patient is generated through the historical medical data and user attribute characteristic information of each home patient, and the predicted health data is obtained to determine the medical and nursing service level of each home patient. The disease development law of home patients is taken into consideration, the health status of home patients is predicted, the urgency of diagnosis and treatment is quantified, and the medical and nursing service level is determined; the reception user portrait is obtained, the predicted health data of each home patient is matched with the reception user portraits of multiple remote reception users, and the designated remote reception user corresponding to each home patient is determined, which ensures the matching degree between the patient and the medical staff, further improves the efficiency of diagnosis and treatment services, and can meet the reasonable allocation needs of multiple elderly patients in the scenario of remote diagnosis and treatment; according to the medical and nursing service level of each home patient, remote diagnosis and treatment channels between designated remote reception users and home patients are established in turn to meet the orderly allocation needs of multiple elderly patients in the scenario of remote diagnosis and treatment.

[0060] The present specification also provides a remote diagnosis and treatment service device based on big data, such as Figure 2 As shown, the device includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to:

[0061] Receive remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawl the historical medical data of each home patient based on the user identifier and big data technology in each service request information; generate a health status prediction model for each home patient according to each historical medical data and the user attribute feature information of each home patient obtained in advance; generate predicted health data for each home patient through the health status prediction model of each home patient and the current body monitoring data of each home patient obtained in advance, so as to determine the medical care service level of each home patient; obtain the reception user portraits of multiple remote reception users who provide remote medical care services, match the predicted health data of each home patient with the reception user portraits of the multiple remote reception users, and determine the designated remote reception user corresponding to each home patient; according to the medical care service level of each home patient, establish a remote diagnosis and treatment channel between the designated remote reception user and the home patient in turn, and provide remote diagnosis and treatment services through the remote diagnosis and treatment channel.

[0062] The embodiment of the present specification also provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured as follows:

[0063] Receive remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawl the historical medical data of each home patient based on the user identifier and big data technology in each service request information; generate a health status prediction model for each home patient according to each historical medical data and the user attribute feature information of each home patient obtained in advance; generate predicted health data for each home patient through the health status prediction model of each home patient and the current body monitoring data of each home patient obtained in advance, so as to determine the medical care service level of each home patient; obtain the reception user portraits of multiple remote reception users who provide remote medical care services, match the predicted health data of each home patient with the reception user portraits of the multiple remote reception users, and determine the designated remote reception user corresponding to each home patient; according to the medical care service level of each home patient, establish a remote diagnosis and treatment channel between the designated remote reception user and the home patient in turn, and provide remote diagnosis and treatment services through the remote diagnosis and treatment channel.

[0064] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment, and non-volatile computer storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0065] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The devices and media provided in the embodiments of this specification correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0067] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, this specification may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0068] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0069] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0070] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0071] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0072] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0073] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0074] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity 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, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0075] The above description is only one or more embodiments of this specification and is not intended to limit this specification. For those skilled in the art, one or more embodiments of this specification may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of one or more embodiments of this specification shall be included in the scope of the claims of this specification.

Claims

1. A remote diagnosis and treatment service method based on big data, characterized in that: The method comprises: Receive remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawl the historical medical treatment data of each home patient based on the user identifier in each service request information and big data technology; Generate a health status prediction model for each home patient based on each of the historical medical treatment data and pre-acquired user attribute feature information of each home patient; Generate predicted health data of each home patient through a health status prediction model of each home patient and pre-acquired current body monitoring data of each home patient, so as to determine the medical care service level of each home patient; Obtaining user portraits of multiple remote consultation users who provide remote medical care services, matching the predicted health data of each of the home patients with the user portraits of the multiple remote consultation users, and determining a designated remote consultation user corresponding to each of the home patients; According to the medical care service level of each of the home patients, remote diagnosis and treatment channels are established between the designated remote reception user and the home patients in turn, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channels.

2. According to the big data-based remote diagnosis and treatment service method of claim 1, it is characterized in that: Generate a health status prediction model for each home patient based on each of the historical medical treatment data and the pre-acquired user attribute feature information of each home patient, specifically including: Acquire user attribute characteristic information of each of the home patients, wherein the user attribute characteristic information includes gender identification, age and work information; Determine the disease identification, disease duration and treatment data in the historical medical treatment data; According to the user attribute characteristic information and the disease identifier in the historical medical data, obtaining disease data of multiple reference patients corresponding to the home patient in a preset big data analysis library; The disease data includes a reference disease identifier, disease duration and treatment process, the user attribute characteristic information of each reference patient is the same as the user attribute characteristic information of the home patient, and the reference disease identifier of the reference patient is the same as the disease identifier of the home patient; Based on the disease data of the multiple reference patients, construct an initial health prediction model corresponding to the home patient; The initial health prediction model is updated according to the illness duration and treatment data in the historical medical data to obtain a current health status prediction model for each home patient.

3. According to the big data-based remote diagnosis and treatment service method of claim 1, it is characterized in that: Generate predicted health data of each home patient through the health status prediction model of each home patient and the current body monitoring data of each home patient acquired in advance, so as to determine the medical care service level of each home patient, specifically including: Acquire current physical monitoring data of each of the home patients, wherein the current physical monitoring data includes blood pressure data, heart rate data, body temperature data, blood oxygen saturation data, blood sugar data and weight data; Generate predicted health data for each of the home patients according to the current body monitoring data and the health status prediction model of the home patients, wherein the predicted health data includes a disease identifier and disease indicator prediction data corresponding to the disease identifier; According to the disease identifier in the predicted health data, obtaining the indicator reference data corresponding to the disease identifier in a pre-built expert knowledge base; Based on the indicator reference data and the disease indicator prediction data, the medical care service level of each of the home patients is determined.

4. A remote diagnosis and treatment service method based on big data according to claim 3, characterized in that: Based on the index reference data and the disease index prediction data, determining the medical care service level of each of the home patients specifically includes: Calculate the predicted difference between the disease index prediction data and the index reference data; Generate an indicator deviation degree based on the ratio of the predicted difference value to the indicator reference data; The medical care service level of each of the home patients is determined based on the indicator deviation.

5. The remote diagnosis and treatment service method based on big data according to claim 1, characterized in that: Matching the predicted health data of each of the home patients with the user portraits of the multiple remote consultation users, and determining the designated remote consultation user corresponding to each of the home patients, specifically includes: Generate a predicted medical portrait of the remote medical staff corresponding to the home patient based on the predicted health data of each home patient, wherein the predicted medical portrait includes the attributes of the disease diagnosed by the remote medical staff, the attributes of the duration of the consultation, and the attributes of the waiting time for the consultation; Matching the predicted medical and nursing portrait with the reception user portraits in the preset reception user portrait library to determine the matching degree between the predicted medical and nursing portrait and the plurality of reception user portraits; Determine the designated consultation user portrait whose matching degree is greater than a preset threshold as the designated remote consultation user corresponding to each of the home patients; A correspondence between the home patient and the designated remote consultation user is established and stored in a preset consultation correspondence table.

6. A remote diagnosis and treatment service method based on big data according to claim 5, characterized in that: Before matching the predicted medical portrait with the reception user portrait in the preset reception user portrait library, the method further includes: Obtaining the current reception status of the reception user corresponding to each reception user portrait in the reception user portrait library, wherein the current reception status includes any one of a busy state and an idle state; Based on the current reception status of each of the reception users, first reception user portraits corresponding to a plurality of first reception users are screened out from the reception user portrait library, wherein the current reception status of each of the first reception users is an idle state; Sending a test signal to a reception terminal corresponding to each of the first reception users, wherein the test signal is used to test whether the first reception user has remote consultation conditions, and returning a confirmation signal when the first reception user has remote consultation conditions; According to the confirmation signal, at least one designated first reception user is determined from the multiple first reception users, so as to facilitate portrait matching between the predicted medical portrait and the reception user portrait corresponding to the at least one designated first reception user, wherein the at least one designated first reception user returns a confirmation signal.

7. A remote diagnosis and treatment service method based on big data according to claim 4, characterized in that: According to the medical care service level of each home patient, a remote diagnosis and treatment channel is established between the designated remote diagnosis and treatment user and the home patient in turn, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channel, specifically including: According to the medical care service level of each home patient, a plurality of home patients are classified to obtain a patient group corresponding to each medical care service level; According to the medical care service level corresponding to each of the patient groups, multiple patient groups are sorted to obtain an inter-group order; When there are multiple home patients in the patient group, obtaining the index deviation of each home patient in the group, and sorting the multiple home patients in the group according to the index deviation to obtain the order in the group; The diagnosis and treatment order of the multiple home patients is obtained through the inter-group order and the intra-group order, so that the remote diagnosis and treatment channels between the designated remote reception users and the home patients are established in turn according to the diagnosis and treatment order, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channels.

8. The remote diagnosis and treatment service method based on big data according to claim 1, characterized in that: According to the medical care service level of each home patient, a remote diagnosis and treatment channel is established between the designated remote diagnosis and treatment user and the home patient in turn, and after performing remote diagnosis and treatment services through the remote diagnosis and treatment channel, the method further includes: After providing remote diagnosis and treatment services to the home patient, obtaining diagnosis and treatment service data, wherein the diagnosis and treatment service data includes disease treatment recommendations; Based on the disease treatment suggestion in the diagnosis and treatment service data, matching at least one medical care service corresponding to the disease treatment suggestion; The at least one medical care service is pushed to the home patient, wherein the medical care service includes any one or more of health care services, emergency rescue services, and surrounding medical resource recommendation services.

9. A remote diagnosis and treatment service device based on big data, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to: Receive remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawl the historical medical treatment data of each home patient based on the user identifier in each service request information and big data technology; Generate a health status prediction model for each home patient based on each of the historical medical treatment data and pre-acquired user attribute feature information of each home patient; Generate predicted health data of each home patient through a health status prediction model of each home patient and pre-acquired current body monitoring data of each home patient, so as to determine the medical care service level of each home patient; Obtaining user portraits of multiple remote consultation users who provide remote medical care services, matching the predicted health data of each of the home patients with the user portraits of the multiple remote consultation users, and determining a designated remote consultation user corresponding to each of the home patients; According to the medical care service level of each of the home patients, remote diagnosis and treatment channels are established between the designated remote reception user and the home patients in turn, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channels.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: The computer executable instructions are configured to: Receive remote diagnosis and treatment service request information triggered by multiple home patients respectively, and crawl the historical medical treatment data of each home patient based on the user identifier in each service request information and big data technology; Generate a health status prediction model for each home patient based on each of the historical medical treatment data and pre-acquired user attribute feature information of each home patient; Generate predicted health data of each home patient through a health status prediction model of each home patient and pre-acquired current body monitoring data of each home patient, so as to determine the medical care service level of each home patient; Obtaining user portraits of multiple remote consultation users who provide remote medical care services, matching the predicted health data of each of the home patients with the user portraits of the multiple remote consultation users, and determining a designated remote consultation user corresponding to each of the home patients; According to the medical care service level of each of the home patients, remote diagnosis and treatment channels are established between the designated remote reception user and the home patients in turn, and remote diagnosis and treatment services are provided through the remote diagnosis and treatment channels.

Images