Information pushing method and device, equipment and storage medium

Abstract

The embodiment of the invention discloses an information pushing method and device, equipment and a storage medium, and relates to the technical field of computers, and the method can comprise the steps: obtaining all candidate reception data of a reception user; wherein each piece of candidate diagnosis reception data comprises a diagnosis reception data set respectively corresponding to the diagnosis reception user in each piece of candidate diagnosis reception business; each reception data set comprises reception data of the reception user for at least one doctor seeing user; sorting the candidate diagnosis reception data according to the time interval between the business execution time of the candidate diagnosis reception data and the current moment, and determining target diagnosis reception data from the candidate diagnosis reception data according to the sorting result; determining to-be-pushed information based on the doctor seeing users corresponding to the target doctor receiving data; and pushing the to-be-pushed information to a client corresponding to the reception user. By adopting the technical scheme of the embodiment of the invention, the patient management efficiency of a doctor can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of Internet medical technology, and in particular to an information push method, device, equipment and storage medium. Background Art

[0002] Currently, doctors can manage patients on the Internet medical platform (for example, reminding patients to return for follow-up visits). Specifically, the Internet medical platform can summarize the medical data of all online patients to obtain a large wide table containing various medical information of all online patients (for example, the data tables related to the medical data of online patients, such as the electronic medical records, are assembled through associated fields to obtain a large wide table with rich medical information); when a doctor wants to manage a patient, he can first search for a row of medical information corresponding to the patient in the large wide table based on a certain key medical information of the patient (for example, the patient's name), and then manage the patient based on the information found.

[0003] However, in the process of implementing the present invention, it is found that there are at least the following problems in the prior art: since the same doctor may see multiple patients within a certain period of time, the doctor may forget the key medical information of the patient to be managed. In this case, the doctor needs to spend a lot of time searching for the information corresponding to the patient to be managed row by row in the large wide table. This will affect the doctor's management efficiency of the patient. Summary of the invention

[0004] The embodiments of the present invention provide an information push method, device, equipment and storage medium, which can improve the management efficiency of doctors for patients.

[0005] In a first aspect, an embodiment of the present invention provides an information push method, which may include: obtaining candidate reception data of a reception user; wherein each candidate reception data includes a reception data set corresponding to the reception user in each candidate reception service; each reception data set includes reception data of the reception user for at least one reception user; sorting each candidate reception data according to the time interval between the service execution time of each candidate reception data and the current moment, and determining each target reception data from each candidate reception data according to the sorting result; determining the information to be pushed based on the reception user corresponding to each target reception data; and pushing the information to be pushed to the client corresponding to the reception user.

[0006] In a second aspect, an embodiment of the present invention further provides an information push device, which may include: an acquisition module, a sorting processing module, an information determination module, and an information push module;

[0007] Specifically, the acquisition module is used to obtain each candidate reception data of the reception user; wherein each candidate reception data includes the reception data set corresponding to the reception user in each candidate reception service; each reception data set includes the reception data of the reception user for at least one reception user; the sorting processing module is used to sort each candidate reception data according to the time interval between the service execution time of each candidate reception data and the current time, and determine each target reception data from each candidate reception data according to the sorting result; the information determination module is used to determine the information to be pushed based on the reception users corresponding to each target reception data; the information pushing module is used to push the information to be pushed to the client corresponding to the reception user.

[0008] In a third aspect, an embodiment of the present invention provides an information push device, the information push device comprising:

[0009] one or more processors;

[0010] A memory for storing one or more programs;

[0011] When the one or more programs are executed by the one or more processors, the one or more processors implement the information push method provided by any embodiment of the present invention.

[0012] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements an information push method as provided in any embodiment of the present invention.

[0013] In a fifth aspect, an embodiment of the present invention further provides a computer program product on which a computer program is stored, and when the program is executed by a processor, the information push method provided by any embodiment of the present invention is implemented.

[0014] The embodiments of the above invention have the following advantages or beneficial effects:

[0015] In the technical solution provided by the embodiment of the present invention, when it is determined that a certain doctor (corresponding to the receiving user in the embodiment of the present invention) has the need to manage patients (corresponding to the visiting user in the embodiment of the present invention), each candidate receiving data of the receiving user can be obtained; each candidate receiving data includes the receiving data set corresponding to each candidate receiving service of the receiving user, and each receiving data set includes the receiving data of the receiving user for at least one visiting user, that is, each candidate receiving data is the receiving data generated by the receiving user in the process of receiving different visiting users by executing the candidate receiving service (one receiving process can execute one candidate receiving service or multiple candidate receiving services); then, each candidate receiving data can be sorted according to the time interval between the service execution time of each candidate receiving data and the current time, and each target receiving data can be determined from each candidate receiving data according to the sorting result; then, based on the visiting users corresponding to each target receiving data, information to be pushed can be obtained, and the information to be pushed can be pushed to the client corresponding to the receiving user. Since in actual applications, after the patient has executed the candidate treatment service for a patient, the patient will generally soon have the need to manage the patient. Therefore, the closer the service execution time corresponding to the candidate treatment data is to the current moment (i.e., the shorter the time interval with the current moment), the higher the possibility that the patient has the need to manage the patient corresponding to the candidate treatment data; conversely, the farther the service execution time corresponding to the candidate treatment data is from the current moment (i.e., the longer the time interval with the current moment), the lower the possibility that the patient has the need to manage the patient corresponding to the candidate treatment data. Based on this, in the embodiment of the present invention, each candidate treatment data can be sorted according to the time interval between the service execution time of each candidate treatment data and the current moment, and according to the sorting result, multiple target treatment data (corresponding to each target treatment data in the embodiment of the present invention) whose service execution time is closest to the current moment (i.e., the shortest time interval with the current moment) are determined from each candidate treatment data. Then, the treatment users corresponding to each target treatment data are the treatment users that the treatment user has the need to manage in the near future. Then, the information of these determined patients (corresponding to the information to be pushed in the embodiment of the present invention) is pushed to the patient, and the patient can quickly find the information of the patients who currently need to be managed (i.e., the patients to be managed) from the pushed information, without having to search for the information in the large wide table. In this way, when the doctor forgets the key medical information of the patient to be managed, the doctor does not need to spend a lot of time searching for the information. It can be seen that in the embodiment of the present invention, by pushing the information of multiple patients who may need to be managed by the doctor in the near future, the doctor's management efficiency for the patients can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1It is a flowchart of an information push method provided by an embodiment of the present invention;

[0017] Figure 2 This is a simplified flow chart of obtaining candidate consultation data provided by an embodiment of the present invention;

[0018] Figure 3 It is a simplified flowchart of a trigger information acquisition request provided by an embodiment of the present invention;

[0019] Figure 4 It is a flowchart of another information push method provided by an embodiment of the present invention;

[0020] Figure 5 This is a simplified flowchart of determining information to be pushed provided by an embodiment of the present invention;

[0021] Figure 6 It is a flowchart of another information push method provided by an embodiment of the present invention;

[0022] Figure 7 It is a schematic diagram of the architecture of an information push device provided by an embodiment of the present invention;

[0023] Figure 8 It is a simplified flowchart of determining target information provided by an embodiment of the present invention;

[0024] Fig. 9 It is a simplified flowchart of an information push method provided by an embodiment of the present invention;

[0025] Fig.10 It is a structural schematic diagram of an information push device provided by an embodiment of the present invention;

[0026] Fig.11 It is a structural diagram of an information push device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0027] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0028] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0029] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the embodiments of the present invention are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0030] It should be noted that, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0031] In the description of the embodiments of the present invention, unless otherwise specified, “plurality” or “each” means two or more than two.

[0032] Figure 1 This is a flowchart of an information push method provided in an embodiment of the present invention, which can be applied to an application scenario in which a doctor (i.e., a patient receiving user in an embodiment of the present invention) manages a patient (i.e., a patient visiting user in an embodiment of the present invention) on an Internet medical platform. This method can be executed by an information push device provided in an embodiment of the present invention, which can be implemented in software and / or hardware and integrated in an information push device.

[0033] The information push method provided in the embodiment of the present invention can be applied to an Internet medical platform, which can push information to be pushed to a client corresponding to the patient according to the candidate patient data of the patient. Correspondingly, the information push device integrated with the information push device can be a corresponding device of the Internet medical platform, such as a server or server cluster of the Internet medical platform.

[0034] like Figure 1 As shown, the information push method provided by the embodiment of the present invention specifically includes the following steps:

[0035] S110, obtaining each candidate consultation data of the consultation user.

[0036] Among them, each candidate reception data includes the reception data set corresponding to each candidate reception service; each reception data set includes the reception data of the reception user for at least one patient. The candidate reception service may be the reception service that the reception user may perform in the process of receiving the patient, and different candidate reception services correspond to different service types; in a possible implementation, each candidate reception service may include a prescription service, an electronic medical record filling service, and a medical questionnaire filling service. Exemplarily, each candidate reception data may include a reception data set A corresponding to the prescription service, a reception data set B corresponding to the electronic medical record filling service, and a reception data set C corresponding to the medical questionnaire filling service.

[0037] Taking the reception data set A as an example, the reception data set A includes the reception data generated by the reception user when performing prescription services for multiple patients. Exemplarily, the reception data set A includes the reception data corresponding to the patient A, the patient B, and the patient C. Taking the determination of the reception data corresponding to the patient A as an example, the electronic prescription generated when the reception user performs the prescription service for the patient A can be obtained first, and then the electronic prescription can be converted into standard reception data through a predetermined standard data conversion protocol. The standard reception data can be the candidate reception data corresponding to the patient A. Among them, the standard data conversion protocol defines the prescription information fields that need to be extracted from the electronic prescription (for example, the prescription information fields can include patient personal information, diagnosis results, prescription time, drug name, drug dosage, frequency of use, etc.). Similarly, the standard data conversion protocol also defines information fields that need to be extracted from original medical data such as electronic medical records and medical questionnaires, which are used to convert original medical data such as electronic medical records and medical questionnaires into standard consultation data (that is, converting original medical data from different data sources into unified structured data).

[0038] Optionally, each candidate consultation data may also be consultation data obtained after data cleaning processing is performed on the standard consultation data. The data cleaning process may include three processing steps: data filtering, data transcoding, and data escape.

[0039] For example, refer to Figure 2 , is a simplified flow chart of obtaining candidate consultation data provided by an embodiment of the present invention. Figure 2As shown, when the patient performs candidate treatment services such as prescription writing, electronic medical record filling, and medical questionnaire filling on the Internet medical platform, original medical data such as electronic prescriptions, electronic medical records, and medical questionnaires will be generated. The Internet medical platform has a built-in data collector, which can monitor the execution of each candidate treatment service through the message middleware. After monitoring that a candidate treatment service has generated some original medical data, the original medical data can be converted into standard treatment data through the standard data conversion protocol, and then the standard treatment data can be verified. After the verification is passed, the standard treatment data will be written to each node of kafka (an open source stream processing platform) (for example Figure 2 Node 1, Node 2 in the data). The data verification process can verify the data type of each field in the standard consultation data, so as to filter out the data that is meaningless to the subsequent data processing process, so as to improve the data processing speed and save computing resources. Taking electronic prescriptions as an example, if the data format of the field value corresponding to the prescription information field of drug dosage in a certain standard consultation data is not a numerical value, the data verification process can filter out the standard consultation data.

[0040] In addition, if Figure 2 As shown, the Internet medical platform can also have a built-in data cleaner, which can pull the required standard consultation data from Kafka according to business needs. For example, when it is necessary to push information to a certain consultation user, the standard consultation data for the consultation user can be pulled from Kafka. In addition, the data cleaner can obtain the cleaning rules from the configuration center of the Internet medical platform, and then use multiple built-in threads (for example, Figure 2 Thread1, Thread2, and Thread3 in the process of filtering, transcoding, and escaping the standard consultation data pulled from Kafka to obtain candidate consultation data for the consultation user, and then store the obtained candidate consultation data in the database corresponding to the information push center of the Internet medical platform (for example, Figure 2ElasticSearch in), the information push center can push information to the patient based on each candidate consultation data. Among them, the filtering rule corresponding to the data filtering processing step can be to check the key information fields of the standard consultation data. If the key information fields of a certain standard consultation data are missing, the standard consultation data is screened out. Taking electronic prescriptions as an example, if a certain standard consultation data lacks the electronic signature of the doctor who prescribes the prescription, the standard consultation data is screened out. The transcoding rule corresponding to the data transcoding processing step can be a rule for transcoding the medical information fields in the standard consultation data. Still taking electronic prescriptions as an example, if the field value corresponding to the prescription information field of the frequency of medication in a certain standard consultation data is "3 times", the transcoding rule can be used to convert "3 times" to "three times a day". The escape rule corresponding to the data escape processing step can be, based on the corpus of the consultation user, to escape the colloquial medical information fields in the standard consultation data into medical information fields that comply with medical standards. Taking electronic prescriptions as an example, if in a certain standard consultation data, the field value corresponding to the prescription information field of the drug name is "Dahuang Tablets", then the escape rules can be used to convert "Dahuang Tablets" into "Dahuang Sodium Bicarbonate".

[0041] In the embodiment of the present invention, by filtering, transcoding, escaping and other cleaning processes, data that is meaningless to the subsequent data processing process can be screened out, and data that does not meet medical standards can be converted into data that meets medical standards. In this way, the data processing speed can be improved when determining the information to be pushed, and the computing resources and storage resources of the Internet medical platform can be saved.

[0042] It should be noted that in the embodiments of the present invention, the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of the user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Take necessary measures for user personal information to prevent illegal access to user personal information data and maintain user personal information security, network security and national security. For example, after obtaining the patient's original medical data, when processing the original medical data, it is necessary to first use technical means to de-identify or encrypt the original medical data.

[0043] S120 , sorting the candidate diagnosis data according to the time interval between the service execution time of each candidate diagnosis data and the current time, and determining each target diagnosis data from the candidate diagnosis data according to the sorting result.

[0044] The service execution time corresponding to the candidate consultation data may be the generation time of the original medical data corresponding to the candidate consultation data. For example, if the original medical data corresponding to the candidate consultation data is an electronic prescription, the service execution time corresponding to the candidate consultation data may be the field value corresponding to the prescription information field of the prescription issuance time in the electronic prescription.

[0045] In a possible implementation, the candidate consultation data may be sorted based on the time interval between the service execution time and the current moment (used to characterize the distance between the service execution time and the current moment). Specifically, the candidate consultation data whose service execution time is close to the current moment is sorted before the candidate consultation data whose service execution time is far from the current moment. Then, a preset number of candidate consultation data ranked at the front in the sorting result may be determined as each target consultation data. The preset number may be a number determined in advance, for example, 10.

[0046] S130: Determine information to be pushed based on the patients corresponding to each target consultation data.

[0047] Since each target consultation data is derived from each candidate consultation service, each target consultation data may include multiple target consultation data of the same consultation user. Based on this, in the embodiment of the present invention, after obtaining the consultation users corresponding to each target consultation data, the obtained consultation users can be deduplicated, and the consultation users after deduplication can be determined as the consultation users that need to be recommended to the consultation users.

[0048] In a possible implementation, after determining the patients who need to be recommended to the receiving user, the information of these patients can be rendered based on a predetermined rendering rule to generate a recommendation page (for example, it can be Figure 3 The recommendation page shown in (b) in the figure) is the information to be pushed that needs to be pushed to the client corresponding to the patient.

[0049] S140, pushing the information to be pushed to the client corresponding to the patient.

[0050] Taking the recommended page as an example, after the recommended page is pushed to the client corresponding to the patient, the client corresponding to the patient can present the following information: Figure 3 The recommended page shown in (b) in . Figure 3As shown in (b), the recommendation page displays management controls corresponding to multiple patients such as patient D and patient E, wherein patient D, patient E and other multiple patients are also the patients who need to be recommended to the receiving user. In one possible implementation, the receiving user can find the management control of the patient who currently needs to be managed (such as patient K) from the recommendation page, and select the management control, and then enter the management details page for patient K, so that management of patient K can be started on the management details page. Specifically, the display style of the management details page in the embodiment of the present invention is similar to the management details page triggered by the query operation in the large wide table in the prior art, and the embodiment of the present invention will not be repeated here.

[0051] In the information push method provided by the embodiment of the present invention, when it is determined that a certain doctor (corresponding to the receiving user in the embodiment of the present invention) has the need to manage patients (corresponding to the visiting user in the embodiment of the present invention), each candidate receiving data of the receiving user can be obtained; each candidate receiving data includes the receiving data set corresponding to each candidate receiving service of the receiving user, and each receiving data set includes the receiving data of the receiving user for at least one visiting user, that is, each candidate receiving data is the receiving data generated by the receiving user in the process of receiving different visiting users by executing the candidate receiving service (one receiving process can execute one candidate receiving service or multiple candidate receiving services); then, each candidate receiving data can be sorted according to the time interval between the service execution time of each candidate receiving data and the current time, and each target receiving data can be determined from each candidate receiving data according to the sorting result; then, based on the visiting users corresponding to each target receiving data, the information to be pushed can be obtained, and the information to be pushed can be pushed to the client corresponding to the receiving user. Since in actual applications, after the patient has executed the candidate treatment service for a patient, the patient will generally soon have the need to manage the patient. Therefore, the closer the service execution time corresponding to the candidate treatment data is to the current moment (i.e., the shorter the time interval with the current moment), the higher the possibility that the patient has the need to manage the patient corresponding to the candidate treatment data; conversely, the farther the service execution time corresponding to the candidate treatment data is from the current moment (i.e., the longer the time interval with the current moment), the lower the possibility that the patient has the need to manage the patient corresponding to the candidate treatment data. Based on this, in the embodiment of the present invention, each candidate treatment data can be sorted according to the time interval between the service execution time of each candidate treatment data and the current moment, and according to the sorting result, multiple target treatment data (corresponding to each target treatment data in the embodiment of the present invention) whose service execution time is closest to the current moment (i.e., the shortest time interval with the current moment) are determined from each candidate treatment data. Then, the treatment users corresponding to each target treatment data are the treatment users that the treatment user has the need to manage in the near future. Then, the information of these determined patients (corresponding to the information to be pushed in the embodiment of the present invention) is pushed to the patient, and the patient can quickly find the information of the patients who currently need to be managed (i.e., the patients to be managed) from the pushed information, without having to search for the information in the large wide table. In this way, when the doctor forgets the key medical information of the patient to be managed, the doctor does not need to spend a lot of time searching for the information. It can be seen that in the embodiment of the present invention, by pushing the information of multiple patients who may need to be managed by the doctor in the near future, the doctor's management efficiency for the patients can be improved.

[0052] Reference Figure 4, is a flow chart of another information push method provided by an embodiment of the present invention. The method in this embodiment can be combined with various optional solutions in the information push method provided by the previous embodiment to further optimize the information push method provided by the previous embodiment. Figure 4 As shown, the specific steps include:

[0053] S410, obtaining each candidate consultation data of the consultation user.

[0054] S420, sorting the candidate reception data according to the time interval between the service execution time of each candidate reception data and the current time, and determining each preliminary screening reception data from each candidate reception data according to the sorting result.

[0055] In a possible implementation, the candidate consultation data may be sorted based on the time interval between the service execution time and the current moment (i.e., the distance from the current moment). Specifically, the candidate consultation data whose service execution time is close to the current moment is sorted before the candidate consultation data whose service execution time is far from the current moment. Afterwards, the plurality of candidate consultation data ranked at the front in the sorting result may be determined as the preliminary screening consultation data. For example, the 30 candidate consultation data ranked at the front may be determined as the preliminary screening consultation data.

[0056] Optionally, each candidate reception data is sorted according to the time interval between the business execution time of each candidate reception data and the current moment, and each preliminary screening reception data is determined from each candidate reception data according to the sorting result, including: obtaining each screening rule; for each screening rule, each screening reception data is determined from each candidate reception data according to the current screening rule, and each screening reception data is sorted according to the time interval between the business execution time of each screening reception data and the current moment, and each reception data corresponding to the current screening rule is determined from each screening reception data according to the sorting result; each preliminary screening reception data is determined according to each reception data corresponding to each screening rule.

[0057] Among them, each screening rule includes screening rules corresponding to the business type of each candidate reception business, and screening rules corresponding to each candidate diagnosis result. In a possible implementation, the screening rules corresponding to the business type of each candidate reception business may include screening rules corresponding to the business type of prescription issuance business (for example, the screening rule may be to determine multiple candidate reception data whose business type is prescription issuance business from each candidate reception data), and screening rules corresponding to the business type of electronic medical record filling business (for example, the screening rule may be to determine multiple candidate reception data whose business type is electronic medical record filling business from each candidate reception data). Each candidate diagnosis result may be predetermined and used to describe the possible conclusions of different diseases. Taking the candidate diagnosis result as disease A as an example, the screening rule corresponding to disease A may be to determine multiple candidate reception data whose diagnosis result is disease A from each candidate reception data.

[0058] After determining each screened reception data from each candidate reception data according to the current screening rule, each screened reception data can be sorted based on the length of the time interval between the business execution time and the current moment (i.e., the distance from the current moment). Specifically, the screened reception data whose business execution time is close to the current moment are sorted before the screened reception data whose business execution time is far from the current moment. Then, the multiple screened reception data sorted at the front in the sorting result can be determined as the reception data corresponding to the current screening rule. Taking the current screening rule as a screening rule corresponding to the business type of prescription service as an example, the reception data corresponding to the current screening rule are also multiple candidate reception data whose business type is prescription service and whose business execution time is closest to the current moment. After obtaining the reception data corresponding to each screening rule, the obtained reception data can be deduplicated, and the result of the deduplication process is the initial screening reception data.

[0059] In an embodiment of the present invention, in the process of sorting each candidate reception data based on the business execution time to determine each preliminary screening reception data, each candidate reception data can be divided into multiple data groups (i.e., data groups composed of screened reception data, and each data group may have overlapping parts) by predetermined screening rules; thereafter, each screened reception data can be sorted based on the business execution time in each data group, and then the sorting results of each data group can be summarized to obtain each preliminary screening reception data. It can be seen that in an embodiment of the present invention, the candidate reception data is sorted by business execution time through multiple statistical dimensions. Since the sorting process of these multiple statistical dimensions can be executed in parallel, the embodiment of the present invention can increase the sorting speed, thereby increasing the speed of determining each preliminary screening reception data.

[0060] S430. For each initial screening reception data, the current initial screening reception data are processed respectively by each predetermined data evaluation rule to obtain each evaluation parameter for the current initial screening reception data, and the total evaluation parameter corresponding to the current initial screening reception data is determined according to each evaluation parameter.

[0061] Among them, each data evaluation rule may be an evaluation rule for evaluating the reliability of the initial screening reception data. Exemplarily, a data evaluation rule may be: determining the number of valid medical information fields (for example, the field value corresponding to the medical information field is not a null value, that is, a valid medical information field) in the current initial screening reception data; determining the number of valid medical information fields as the evaluation parameter of the current initial screening reception data corresponding to the data evaluation rule.

[0062] In a possible implementation, each evaluation parameter can be summed to obtain a total evaluation parameter corresponding to the current initial screening reception data. The higher the value of the total evaluation parameter corresponding to the current initial screening reception data, the higher the reliability of the current initial screening reception data; conversely, the lower the value of the total evaluation parameter corresponding to the current initial screening reception data, the lower the reliability of the current initial screening reception data.

[0063] Optionally, each candidate reception data includes field values ​​corresponding to each medical information field type, each data evaluation rule includes integrity verification rules corresponding to each medical information field type, and different data evaluation rules correspond to different evaluation weights; the total evaluation parameters corresponding to the current initial screening reception data are determined according to each evaluation parameter, including: based on the evaluation weights of the data evaluation rules corresponding to each evaluation parameter, weighted processing is performed on each evaluation parameter to obtain the total evaluation parameters corresponding to the current initial screening reception data.

[0064] The types of each medical information field may be a plurality of predetermined information field types. For example, each medical information field type may include a patient information type, a condition information type, and the like.

[0065] Taking the patient information class as an example, the integrity verification rule corresponding to the patient information class may be to verify the field integrity of the medical information field corresponding to the patient information class in the current initial screening reception data, and obtain the evaluation parameter of the current initial screening reception data corresponding to the integrity verification rule. Exemplarily, if each initial screening reception data has N medical information fields corresponding to the patient information class, for the current initial screening reception data, the number of valid medical information fields in the N medical information fields of the current initial screening reception data is M, then the value of the evaluation parameter of the current initial screening reception data corresponding to the integrity verification rule is M / N.

[0066] In addition, since different types of medical information fields have different importance, different data evaluation rules correspond to different evaluation weights in the embodiment of the present invention. For example, the evaluation weight of the integrity verification rule corresponding to the patient information class may be 1, and the evaluation weight of the integrity verification rule corresponding to the condition information class may be 2.

[0067] In a possible implementation, the total evaluation parameter χ corresponding to the current initial screening data can be determined by expression (1):

[0068]

[0069] Where k represents the number of data evaluation rules, χ k represents the evaluation parameter of the kth data evaluation rule corresponding to the current initial screening data, f k Represents the evaluation weight of the kth data evaluation rule.

[0070] Since the candidate consultation data includes field values ​​corresponding to different types of medical information fields, and the importance of different types of medical information fields is different, in the embodiment of the present invention, different integrity verification rules can be determined for each type of medical information field, and the obtained integrity verification rules are determined as each data evaluation rule; at the same time, according to the importance of each type of medical information field, different evaluation weights are determined for each data evaluation rule. In this way, the accuracy of the determined total evaluation parameters can be improved, thereby improving the reliability of each selected target consultation data, and further improving the accuracy of the determined information to be pushed.

[0071] Further optionally, since the importance of different candidate reception services is different, in actual application, the embodiment of the present invention can also determine the total evaluation parameter of the initial screening reception data in combination with the service weight of the candidate reception service corresponding to the initial screening reception data. In this way, the accuracy of the determined total evaluation parameter can be further improved.

[0072] S440. Determine each target consultation data from each preliminary screening consultation data according to the total evaluation parameters corresponding to each preliminary screening consultation data.

[0073] In a possible implementation, multiple preliminary screening consultation data with the highest values ​​of the total evaluation parameter among the preliminary screening consultation data can be determined as the target consultation data. For example, the 10 preliminary screening consultation data with the highest values ​​of the total evaluation parameter can be determined as the target consultation data.

[0074] S450: Determine the information to be pushed based on the patients corresponding to each target consultation data.

[0075] Optionally, based on the patients corresponding to each target reception data, the information to be pushed is determined, including: based on the patients corresponding to each target reception data, each patient to be pushed is determined; for each patient to be pushed, the target reception data of the current patient is processed by a predetermined service prediction model to obtain each predicted business label of the current patient for each candidate reception business; based on each patient to be pushed and each predicted business label corresponding to each patient to be pushed, the information to be pushed is determined.

[0076] Among them, the business prediction model can be a multi-classification model obtained by training with a predetermined machine learning algorithm, using each sample consultation data as the model input and each sample business label corresponding to each sample consultation data as the model output.

[0077] Exemplarily, each sample service tag and each predicted service tag may include a key patient tag, a follow-up tag, and a tag for joining the hospitalization queue. Taking the key patient tag as an example, the key patient tag has two tag values: "yes" and "no". If the tag value of the key patient tag is "yes", it means that the patient is seriously ill and needs to be paid special attention by the patient (for example, increasing the number of temperature monitoring and blood sugar monitoring, etc.).

[0078] In the embodiment of the present invention, the information to be pushed may include not only the user information of each patient to be pushed, but also the predicted service tags corresponding to each patient to be pushed determined by the service prediction model. In this way, the patient can manage the patient better and faster according to the prompts of each predicted service tag, thereby improving the user experience of the patient for the services provided by the Internet medical platform.

[0079] Optionally, based on the patients corresponding to each target reception data, each patient user to be pushed is determined, including: based on the patients corresponding to each target reception data, each target push user is determined; when the number of users of each target push user is greater than or equal to a predetermined number threshold, each target push user is determined as the patient user to be pushed; when the number of users is less than the number threshold, each target reception data is screened out from each candidate reception data to obtain each remaining reception data, and each supplementary push user is determined based on each remaining reception data, and each patient user to be pushed is determined based on each target push user and each supplementary push user.

[0080] In a possible implementation, when the number of users is less than a quantity threshold, the difference between the number of users and the number of users of the quantity threshold can be determined first, and each target reception data can be screened out from each candidate reception data to obtain each remaining reception data; then, each remaining reception data can be used as each new candidate reception data, and the new candidate reception data can be processed to obtain each new target reception data; thereafter, a plurality of reception users can be randomly selected from the reception users corresponding to each new target reception data, and the number of selected reception users is equal to the difference between the number of users, then the plurality of selected reception users are also the supplementary push users in the embodiment of the present invention.

[0081] In the embodiment of the present invention, since the data source of the recommended users is the real consultation data generated by the consultation users when performing the candidate consultation services, the consultation users corresponding to each candidate consultation data are all patients who have actually been treated by the consultation users. Based on this, in the process of determining the consultation users to be pushed, the embodiment of the present invention can adopt a push strategy of pushing as many consultations as possible, that is, ensuring that the number of users of each consultation user to be pushed reaches a predetermined threshold. In this way, the recommendation range can be expanded while ensuring the accuracy of the recommendation, thereby further improving the recommendation hit rate.

[0082] S460: Push the information to be pushed to the client corresponding to the patient.

[0083] Optionally, the information to be pushed is pushed to the client corresponding to the seeing user, including: upon receiving an information acquisition request initiated by the client, the information to be pushed is pushed to the client.

[0084] The information acquisition request is a request initiated by the client in response to an information acquisition operation performed by the patient receiving user on the client. Exemplarily, the information acquisition operation may be a selection operation performed by the patient receiving user on an information acquisition control in a patient management page.

[0085] Reference Figure 3 , is a simplified flow chart of a trigger information acquisition request provided by an embodiment of the present invention. Figure 3 As shown in (a), it is the page view of the patient management page of the client. When the receiving user has the need to manage the patient users, he can enter the information in the information input box (corresponding to Figure 3 Alternatively, the patient can select the information acquisition control in the patient management page to trigger the client to initiate an information acquisition request to the server of the Internet medical platform. After receiving the information acquisition request, the server can push the determined recommended page as the information to be pushed to the client, and the client can present the following information: Figure 3 The style shown in (b) in .

[0086] Since the process of determining the information to be pushed takes a certain amount of time, in the embodiment of the present invention, the information to be pushed can be determined in advance, and when the patient has management needs, the predetermined information to be pushed can be directly pushed to the client corresponding to the patient. In this way, when the patient has management needs, the information to be pushed can be quickly recommended to the patient, thereby improving the user's experience of using the services provided by the Internet medical platform.

[0087] Optionally, the information push method provided by the embodiment of the present invention further includes: executing periodic information determination tasks with a preset time period as a period.

[0088] The task content of the information determination task includes: obtaining candidate reception data of the reception user in the previous task cycle; sorting the candidate reception data according to the time interval between the business execution time of each candidate reception data and the current time, and determining each target reception data from each candidate reception data according to the sorting result; determining the information to be pushed based on the patient users corresponding to each target reception data. The preset duration can be a predetermined duration, such as 24 hours.

[0089] Although the timing of generating the original medical data is random and uncontrollable, it is found through point-of-use testing that the management behavior of the receiving user is periodic. Based on this, in the embodiment of the present invention, the information to be pushed can be periodically determined by executing the information determination task. In this way, compared with determining the information to be pushed in real time, the performance requirements for the Internet medical platform (for example, computing power performance requirements) can be reduced.

[0090] Reference Figure 5 , is a simplified flow chart of determining information to be pushed provided by an embodiment of the present invention. Figure 5As shown, the Internet medical platform has a built-in data extractor, which can extract consultation data from ElasticSearch based on a preset time period and a predetermined extraction rule. Among them, the extraction rule can be to extract the corresponding screening consultation data group according to each predetermined screening rule; for each screening consultation data group, multiple consultation data with the closest business execution time to the current moment in the current screening consultation data group are screened out and stored in a cache list. For example, the corresponding screening consultation data group can be extracted according to screening rule A, and the 10 consultation data with the closest business execution time to the current moment in the screening consultation data group are screened out and stored in a cache list. Afterwards, the initial screening consultation data stored in the cache list can be subjected to secondary escape processing to obtain the evaluation parameters corresponding to each initial screening consultation data. Then, the weighted counter can obtain the weighted rules from the configuration center, and perform weighted processing on the evaluation parameters corresponding to each initial screening reception data through the weighted rules to obtain the total evaluation parameters corresponding to each initial screening reception data, and can determine each target reception data from each initial screening reception data according to each total evaluation parameter. After determining each target reception data, each reception user to be pushed can be determined based on the reception users corresponding to each target reception data, and a patient data pool can be obtained; and, the target reception data of each reception user to be pushed can be processed through the business prediction model, and each predicted business tag corresponding to each reception user to be pushed can be determined to obtain a business tag pool. Finally, the information to be pushed can be determined based on the patient data pool and the business tag pool.

[0091] In the embodiment of the present invention, on the basis of the above-mentioned embodiment, since in actual application, different candidate reception data have different reliability, the information to be pushed determined based on the candidate reception data with higher reliability is more accurate than the information to be pushed determined based on the candidate reception data with lower reliability. Based on this, in the embodiment of the present invention, after obtaining each candidate reception data of the reception user, each candidate reception data can be preliminarily screened based on the business execution time to obtain each preliminary screening reception data; then, for each preliminary screening reception data, the reliability of the current preliminary screening reception data can be evaluated by the predetermined data evaluation rules to obtain the total evaluation parameters used to characterize the reliability of the current preliminary screening reception data; then, based on the total evaluation parameters corresponding to each preliminary screening reception data, each preliminary screening reception data is screened for the second time to obtain each target reception data. Compared with the target reception data directly screened according to the business execution time of the candidate reception data, in the embodiment of the present invention, the target reception data with higher reliability can be screened out by combining the business execution time of the candidate reception data and the total evaluation parameters, so that the information to be pushed with higher accuracy can be determined. In this way, it can be ensured that the information to be pushed contains the information of the patients to be managed, thereby improving the recommendation hit rate.

[0092] It should be noted that the information push method proposed in the embodiment of the present invention and the aforementioned embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, reference can be made to the aforementioned embodiment, and the beneficial effects of the aforementioned embodiment are also applicable to this embodiment.

[0093] Reference Figure 6 , which is a flow chart of another information push method provided by an embodiment of the present invention. The method in this embodiment can be combined with various optional solutions in the information push method provided by the previous embodiment to further optimize the information push method provided by the previous embodiment. Figure 6 As shown, the specific steps include:

[0094] S610: Obtain each candidate consultation data of the consultation user.

[0095] S620, sorting the candidate diagnosis data according to the time interval between the service execution time of each candidate diagnosis data and the current time, and determining each target diagnosis data from each candidate diagnosis data according to the sorting result.

[0096] S630: Determine the information to be pushed based on the patients corresponding to each target consultation data.

[0097] S640: Determine whether the consultation scene identifier is the first scene identifier.

[0098] S650: When the consultation scene identifier is the first scene identifier, push the information to be pushed to the client; when the consultation scene identifier is the second scene identifier, push the target information to the client.

[0099] Among them, the accuracy of the push information required for the consultation scenario corresponding to the second scenario identifier is higher than that of the consultation scenario corresponding to the first scenario identifier. For example, the consultation scenario corresponding to the first scenario identifier may be a scenario with a small number of transactions and a single business authority (for example, the only user receiving the consultation is the attending physician); the consultation scenario corresponding to the second scenario identifier may be a scenario with a large number of transactions and complex business authorities (for example, the users receiving the consultation include not only the attending physician but also the assistant physician, etc.).

[0100] The target information is the information to be pushed based on the candidate consultation data and the behavior data groups corresponding to the candidate consultation users associated with the consultation user. Among them, the candidate consultation users associated with the consultation user can be all consultation users for whom the consultation user has management authority, specifically the consultation users who have been recently consulted by the consultation user. The behavior data group corresponding to the candidate consultation users includes various behavior data of the candidate consultation users within a historical time period (for example, the past month). For example, the behavior data can be the search data, browsing data, etc. of the consultation users for disease-related information.

[0101] Optionally, before pushing the target information to the client, the information push method provided by the embodiment of the present invention also includes: determining a reception data group corresponding to each candidate visiting user from each candidate reception data; for each candidate visiting user, determining the recommendation parameters corresponding to the current candidate visiting user based on the behavior data group of the current candidate visiting user and the reception data group of the current candidate visiting user; determining each user to be pushed from each candidate visiting user based on the recommendation parameters corresponding to each candidate visiting user, and determining the target information based on each user to be pushed.

[0102] The recommendation parameters corresponding to the current candidate patient are used to characterize the hit rate of the current candidate patient to be managed. Specifically, the behavior data group and the patient data group of the current candidate patient can be processed by a predetermined data processing rule to obtain the recommendation parameters corresponding to the current candidate patient.

[0103] In the embodiment of the present invention, the behavior data group and the reception data group of each candidate patient user can be evaluated to obtain the recommendation parameters corresponding to each candidate patient user, and then the users to be pushed can be determined from the candidate patients according to the recommendation parameters. In this way, the hit rate of each user to be pushed hitting the patient to be managed can be improved.

[0104] Optionally, based on the behavior data group of the current candidate user and the reception data group of the current candidate user, determine the recommended parameters corresponding to the current candidate user, including: based on a predetermined vector conversion rule, determine the first vectors corresponding to each behavior data in the behavior data group of the current candidate user, and determine the second vectors corresponding to each reception data in the reception data group of the current candidate user; for each behavior data, match the first vector corresponding to the current behavior data with each second vector, respectively, to obtain each matching parameter corresponding to the current behavior data; based on each matching parameter corresponding to each behavior data, determine the recommended parameters corresponding to the current candidate user.

[0105] Among them, the vector conversion rule can be a predetermined text vectorization representation model, and the first vector and the second vector are both multidimensional vectors. If the behavior data group of the current candidate patient includes X information fields, the behavior data group can be converted into a first vector of X dimensions through the vector conversion rule; if the reception data group of the current candidate patient includes Y information fields, the reception data group can be converted into a second vector of Y dimensions through the vector conversion rule. The specific process of vectorization representation can refer to the relevant description in the prior art, and the embodiments of the present invention will not be repeated here.

[0106] In a possible implementation, the recommendation parameter similarity corresponding to the current candidate medical user can be determined by expression (2):

[0107]

[0108] in, is the algorithm expression of the cosine similarity method, n means that the behavior data group of the current candidate medical user has a total of n behavior data, A i represents the first vector corresponding to the i-th behavior data, m represents the number of m consultation data in the current candidate consultation data group, B j represents the second vector corresponding to the jth patient data, A i ×B j Represents vector multiplication.

[0109] In the embodiment of the present invention, the behavior data of the patient-visiting user can be matched with the patient-receiving data to determine the recommendation parameters corresponding to each candidate patient-visiting user. In this way, the accuracy of the determined recommendation parameters can be improved, thereby improving the hit rate of each determined user to be pushed to the patient to be managed.

[0110] For example, refer to Figure 7 , is a schematic diagram of the architecture of an information push device provided by an embodiment of the present invention. Figure 7 As shown, the information push device includes a service layer, a real-time processing layer, and a batch processing layer. In the process of determining the information to be pushed (for example, a recommended page), the service layer can send the consultation data in the collected business data to the real-time processing layer, and the real-time processing layer can perform periodic incremental calculations on the second data stream to obtain an incremental view, and return the incremental view to the service layer; and the service layer can send the consultation data and behavior data in the collected business data to the batch processing layer, and the batch processing layer can perform periodic batch calculations on the first data stream to obtain a batch view, and return the batch view to the service layer. The service layer can determine the recommended page from the incremental view and the batch view according to the consultation scenario, and push it to the consultation user.

[0111] Reference Figure 8 , is a simplified flow chart of determining target information provided by an embodiment of the present invention. Figure 8 As shown, the Internet medical platform has a built-in data extractor, which can extract the consultation data and behavior data within a historical time period (for example, the past month) from ElasticSearch based on a predetermined extraction rule with a predetermined duration (for example, 1 day). Among them, the extraction rule can be to extract the consultation data group and behavior data group corresponding to each candidate consultation user from ElasticSearch, and store the extracted data in a cache list. Afterwards, the consultation data group and behavior data group stored in the cache list can be subjected to secondary escape processing to obtain the second vector corresponding to each consultation data in the consultation data group, and the first vector corresponding to each behavior data in the behavior data group. Then, the vector matcher can obtain the matching rules from the configuration center, and match the first vector and the second vector through the matching rules to obtain the recommendation parameters corresponding to each candidate patient user, and can determine each user to be pushed from each candidate patient user according to each recommendation parameter to obtain a patient data pool; and can process the behavior data group and the consultation data group of each user to be pushed through the business prediction model to determine each predicted business label corresponding to each user to be pushed to obtain a business label pool. Finally, the target information can be determined based on the patient data pool and the business label pool.

[0112] In the embodiment of the present invention, on the basis of the above-mentioned embodiment, information can be pushed to the patient according to the needs of the patient scenario. Specifically, in the patient scenario with high accuracy requirements for the pushed information, the candidate patient data and the behavior data group can be combined to determine the target information with high accuracy and push it to the patient; and in the patient scenario with low accuracy requirements for the pushed information, only the candidate patient data is used to determine the information to be pushed and push it to the patient. In this way, by adopting different push strategies in different patient scenarios, the needs of different patient scenarios can be met and computing resources can be saved.

[0113] It should be noted that the information push method proposed in the embodiment of the present invention and the aforementioned embodiment belong to the same inventive concept. For technical details not fully described in this embodiment, reference can be made to the aforementioned embodiment, and the beneficial effects of the aforementioned embodiment are also applicable to this embodiment.

[0114] In order to more clearly describe the information push method provided by the embodiment of the present invention, refer to Fig. 9 , is a simplified flow chart of an information push method provided by an embodiment of the present invention. Fig. 9As shown, the information push method may include data processing processes such as data collection, data cleaning, storage calculation, and information push. The data collection process may refer to the relevant part of the data collector in the above description; the data cleaning process may include three processing steps: data filtering, data transcoding, and data escape; the storage calculation process may include the process of determining the information to be pushed and the process of determining the target information, and the specific process may refer to the above description; the information push process may refer to the relevant part of pushing the recommendation page to the client in the above description.

[0115] Fig.10 This is a schematic diagram of the structure of an information pushing device provided by an embodiment of the present invention. The device includes: an acquisition module 1110 , a sorting processing module 1120 , an information determination module 1130 , and an information pushing module 1140 .

[0116] Exemplarily, the acquisition module 1110 can execute S110 in the above method embodiment, the sorting processing module 1120 can execute S120 in the above method embodiment, the information determination module 1130 can execute S130 in the above method embodiment, and the information push module 1140 can execute S140 in the above method embodiment.

[0117] Specifically, the acquisition module 1110 is used to obtain each candidate reception data of the reception user; wherein each candidate reception data includes the reception data set corresponding to the reception user in each candidate reception service; each reception data set includes the reception data of the reception user for at least one reception user; the sorting processing module 1120 is used to sort each candidate reception data according to the time interval between the service execution time of each candidate reception data and the current time, and determine each target reception data from each candidate reception data according to the sorting result; the information determination module 1130 is used to determine the information to be pushed based on the reception users corresponding to each target reception data; the information push module 1140 is used to push the information to be pushed to the client corresponding to the reception user.

[0118] Optionally, in a possible implementation manner, the sorting processing module 1120 is specifically configured to:

[0119] According to the time interval between the business execution time of each candidate reception data and the current moment, each candidate reception data is sorted, and each initial screening reception data is determined from each candidate reception data according to the sorting result; for each initial screening reception data, the current initial screening reception data is processed respectively by each predetermined data evaluation rule to obtain each evaluation parameter for the current initial screening reception data, and the total evaluation parameter corresponding to the current initial screening reception data is determined according to each evaluation parameter; according to the total evaluation parameters corresponding to each initial screening reception data, each target reception data is determined from each initial screening reception data.

[0120] Optionally, in another possible implementation, each candidate reception data includes field values ​​corresponding to each medical information field type, each data evaluation rule includes integrity verification rules corresponding to each medical information field type, and different data evaluation rules correspond to different evaluation weights; the sorting processing module 1120 is also specifically used to: based on the evaluation weights of the data evaluation rules corresponding to each evaluation parameter, perform weighted processing on each evaluation parameter to obtain the total evaluation parameter corresponding to the current initial screening reception data.

[0121] Optionally, in another possible implementation, the sorting processing module 1120 is further configured to:

[0122] Obtain each screening rule; each screening rule includes screening rules corresponding to the business type of each candidate reception business, and screening rules corresponding to each candidate diagnosis result; for each screening rule, determine each screening reception data from each candidate reception data according to the current screening rule, and sort each screening reception data according to the time interval between the business execution time of each screening reception data and the current time, and determine each reception data corresponding to the current screening rule from each screening reception data according to the sorting result; determine each initial screening reception data according to each reception data corresponding to each screening rule.

[0123] Optionally, in another possible implementation, the information push module 1140 is specifically used to:

[0124] When an information acquisition request initiated by a client is received, the information to be pushed is pushed to the client; wherein the information acquisition request is a request initiated by the client in response to an information acquisition operation performed by the patient on the client.

[0125] Optionally, in another possible implementation, the information push device further includes a task execution module;

[0126] The task execution module is used to execute periodic information determination tasks with a preset time period as a cycle; wherein the task content of the information determination task includes: obtaining each candidate reception data of the reception user in the previous task cycle; sorting each candidate reception data according to the time interval between the business execution time of each candidate reception data and the current time, and determining each target reception data from each candidate reception data according to the sorting result; determining the information to be pushed based on the reception users corresponding to each target reception data.

[0127] Optionally, in another possible implementation, the information determination module 1130 is specifically configured to:

[0128] Based on the patients corresponding to each target reception data, each patient to be pushed is determined; for each patient to be pushed, the target reception data of the current patient is processed by a predetermined business prediction model to obtain each predicted business label of the current patient for each candidate reception business; based on each patient to be pushed and each predicted business label corresponding to each patient to be pushed, the information to be pushed is determined.

[0129] Optionally, in another possible implementation, the information determination module 1130 is further configured to:

[0130] Based on the patients corresponding to each target reception data, each target push user is determined; when the number of users of each target push user is greater than or equal to a predetermined number threshold, each target push user is determined as the patient user to be pushed; when the number of users is less than the number threshold, each target reception data is screened out from each candidate reception data to obtain each remaining reception data, and each supplementary push user is determined based on each remaining reception data, and each patient user to be pushed is determined based on each target push user and each supplementary push user.

[0131] Optionally, in another possible implementation, the information push module 1140 is also specifically used to: determine whether the reception scene identifier is the first scene identifier; when the reception scene identifier is the first scene identifier, push the information to be pushed to the client; when the reception scene identifier is the second scene identifier, push the target information to the client; wherein the target information is the information to be pushed determined based on each candidate reception data and the behavior data groups corresponding to each candidate reception user associated with the reception user.

[0132] Optionally, in another possible implementation, the information determination module 1130 is further configured to:

[0133] Before the information push module 1140 pushes the target information to the client, the reception data groups corresponding to each candidate visiting user are determined from each candidate visiting data; for each candidate visiting user, the recommendation parameters corresponding to the current candidate visiting user are determined based on the behavior data group of the current candidate visiting user and the reception data group of the current candidate visiting user; based on the recommendation parameters corresponding to each candidate visiting user, each user to be pushed is determined from each candidate visiting user, and the target information is determined based on each user to be pushed.

[0134] Optionally, in another possible implementation, the information determination module 1130 is specifically used to: determine the first vectors corresponding to each behavior data in the behavior data group of the current candidate patient user based on a predetermined vector conversion rule, and determine the second vectors corresponding to each reception data in the reception data group of the current candidate patient user; for each behavior data, match the first vector corresponding to the current behavior data with each second vector, respectively, to obtain each matching parameter corresponding to the current behavior data; based on each matching parameter corresponding to each behavior data, determine the recommended parameters corresponding to the current candidate patient user.

[0135] The information push device provided in the embodiment of the present invention belongs to the same inventive concept as the information push method provided in the aforementioned embodiments. For details not fully described in the embodiment of the information push device, reference can be made to the relevant contents of the aforementioned method embodiments, and the corresponding beneficial effects can also be referred to the beneficial effect analysis of the aforementioned method embodiments.

[0136] Fig.11 A schematic diagram of the structure of an information push device provided by an embodiment of the present invention. Fig.11 A block diagram of an exemplary information push device 12 suitable for implementing the embodiments of the present invention is shown. Fig.11 The information push device 12 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0137] like Fig.11 As shown, the information push device 12 is in the form of a general-purpose computing device. The components of the information push device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0138] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0139] The information push device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the information push device 12, including volatile and non-volatile media, removable and non-removable media.

[0140] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory (i.e., Fig.11 The information push device 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Fig.11 not shown, usually called a "hard drive"). Although Fig.11 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0141] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0142] The information push device 12 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), may also communicate with one or more devices that enable a user to interact with the information push device 12, and / or may communicate with any device that enables the information push device 12 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed through an input / output (I / O) interface 22. Furthermore, the information push device 12 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) through a network adapter 20. Fig.11 As shown, the network adapter 20 communicates with other modules of the information push device 12 via the bus 18. It should be understood that although Fig.11 Not shown, other hardware and / or software modules may be used in conjunction with the information push device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0143] The processing unit 16 executes various functional applications and data processing by running the programs stored in the system memory 28, such as implementing the steps of the information push method provided by any of the aforementioned embodiments of the present invention.

[0144] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the information push method provided by any embodiment of the present invention.

[0145] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps of the information push method provided in any of the aforementioned embodiments of the present invention are implemented.

[0146] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0147] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0148] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0149] Computer program code for performing the operation of the present invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and also conventional procedural programming languages ​​- such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or information push device. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0150] This embodiment provides a computer program product, on which a computer program is stored. When the program is executed by a processor, the steps of the information push method provided in any of the aforementioned embodiments of the present invention are implemented.

[0151] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0152] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. An information push method, characterized in that: include: Acquire each candidate reception data of the reception user; wherein each candidate reception data includes the reception data set corresponding to each candidate reception service of the reception user; each reception data set includes the reception data of the reception user for at least one reception user; Sorting the candidate patient data according to the time interval between the service execution time of each candidate patient data and the current time, and determining each target patient data from the candidate patient data according to the sorting result; Determine the information to be pushed based on the patients corresponding to each target consultation data; The information to be pushed is pushed to the client corresponding to the patient.

2. The information push method according to claim 1, characterized in that: The step of sorting the candidate patient reception data according to the time interval between the service execution time of the candidate patient reception data and the current time, and determining the target patient reception data from the candidate patient reception data according to the sorting result includes: Sorting the candidate consultation data according to the time interval between the service execution time of each candidate consultation data and the current time, and determining each preliminary screening consultation data from the candidate consultation data according to the sorting result; For each of the initial screening reception data, the current initial screening reception data are processed respectively by each predetermined data evaluation rule to obtain each evaluation parameter for the current initial screening reception data, and the total evaluation parameter corresponding to the current initial screening reception data is determined according to each evaluation parameter; According to the total evaluation parameters respectively corresponding to the various preliminary screening reception data, the various target reception data are determined from the various preliminary screening reception data.

3. The information push method according to claim 2, characterized in that: Each candidate consultation data includes field values ​​corresponding to each medical information field type, each data evaluation rule includes integrity verification rules corresponding to each medical information field type, and different data evaluation rules correspond to different evaluation weights; the total evaluation parameter corresponding to the current initial screening consultation data is determined according to each evaluation parameter, including: Based on the evaluation weights of the data evaluation rules corresponding to the evaluation parameters, the evaluation parameters are weighted to obtain the total evaluation parameters corresponding to the current initial screening consultation data.

4. The information push method according to claim 2, characterized in that: The step of sorting the candidate reception data according to the time interval between the service execution time of each candidate reception data and the current time, and determining each preliminary screening reception data from the candidate reception data according to the sorting result includes: Acquire each screening rule; the screening rules include screening rules corresponding to the service type of each candidate consultation service, and screening rules corresponding to each candidate diagnosis result; For each of the screening rules, determine each screening reception data from each of the candidate reception data according to the current screening rule, sort the screening reception data according to the time interval between the service execution time of each of the screening reception data and the current time, and determine each of the reception data corresponding to the current screening rule from the screening reception data according to the sorting result; The initial screening reception data are determined according to the reception data corresponding to the screening rules.

5. The information push method according to claim 1, characterized in that: The step of pushing the information to be pushed to the client corresponding to the patient includes: Upon receiving the information acquisition request initiated by the client, the information to be pushed is pushed to the client; wherein the information acquisition request is a request initiated by the client in response to the information acquisition operation performed by the patient user on the client.

6. The information push method according to claim 5, characterized in that: The method further comprises: Perform periodic information determination tasks with a preset duration as a cycle; Among them, the task content of the information determination task includes: obtaining the candidate reception data of the reception user in the previous task cycle; sorting the candidate reception data according to the time interval between the business execution time of the candidate reception data and the current time, and determining the target reception data from the candidate reception data according to the sorting result; determining the information to be pushed based on the reception users corresponding to the target reception data.

7. The information push method according to claim 1, characterized in that: The determining of information to be pushed based on the visiting users corresponding to each target visiting data includes: Determine each patient receiving data to be pushed based on the patient receiving data corresponding to each target patient receiving data; For each patient to be pushed, the target patient data of the current patient is processed by a predetermined service prediction model to obtain each predicted service label of the current patient for each candidate patient service; The information to be pushed is determined based on each of the patients to be pushed and each of the predicted service tags respectively corresponding to each of the patients to be pushed.

8. The information push method according to claim 7, characterized in that: The determining each patient receiving user to be pushed based on the patient receiving users corresponding to each target patient receiving data respectively includes: Determine each target push user based on the patient users corresponding to each target consultation data; In the case that the number of each target push user is greater than or equal to a predetermined number threshold, determining each target push user as each medical visit user to be pushed; When the number of users is less than the threshold value, the target consultation data are screened out from the candidate consultation data to obtain the remaining consultation data, and the supplementary push users are determined based on the remaining consultation data, and the consultation users to be pushed are determined based on the target push users and the supplementary push users.

9. The information push method according to any one of claims 1 to 8, characterized in that: The step of pushing the information to be pushed to the client corresponding to the patient includes: Determine whether the patient reception scene identifier is the first scene identifier; When the patient consultation scenario identifier is the first scenario identifier, pushing the information to be pushed to the client; When the consultation scene identifier is the second scene identifier, the target information is pushed to the client; wherein the target information is the information to be pushed determined based on the behavior data groups corresponding to the candidate consultation data and the candidate consultation users associated with the consultation user.

10. The information push method according to claim 9, characterized in that: Before pushing the target information to the client, the method further includes: Determine, from the candidate consultation data, consultation data groups corresponding to the candidate consultation users; For each candidate patient, based on the behavior data group of the current candidate patient and the patient consultation data group of the current candidate patient, determine the recommendation parameter corresponding to the current candidate patient; Based on the recommendation parameters respectively corresponding to the candidate users, the users to be pushed are determined from the candidate users, and the target information is determined based on the users to be pushed.

11. The information push method according to claim 10, characterized in that: The step of determining the recommendation parameters corresponding to the current candidate patient visiting user based on the behavior data group of the current candidate patient visiting user and the patient consultation data group of the current candidate patient visiting user includes: Based on a predetermined vector conversion rule, determine the first vectors corresponding to each behavior data in the behavior data group of the current candidate patient user, and determine the second vectors corresponding to each reception data in the reception data group of the current candidate patient user; For each of the behavior data, matching the first vector corresponding to the current behavior data with each of the second vectors respectively to obtain matching parameters corresponding to the current behavior data; Based on the matching parameters corresponding to the behavior data, the recommendation parameters corresponding to the current candidate medical user are determined.

12. An information push device, characterized in that: include: An acquisition module is used to acquire each candidate reception data of the reception user; wherein each candidate reception data includes a reception data set corresponding to each candidate reception service of the reception user; each reception data set includes reception data of the reception user for at least one reception user; A sorting processing module, used to sort the candidate diagnosis data according to the time interval between the service execution time of each candidate diagnosis data and the current time, and determine each target diagnosis data from the candidate diagnosis data according to the sorting result; An information determination module, used to determine the information to be pushed based on the patient visiting users corresponding to each target consultation data; The information push module is used to push the information to be pushed to the client corresponding to the patient.

13. An information push device, characterized in that: The information push device comprises: one or more processors; A memory for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the information push method as described in any one of claims 1-11.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the information push method according to any one of claims 1 to 11 is implemented.

Images