Data recommendation method and device, electronic equipment and computer readable medium

Abstract

The invention discloses a data recommendation method and device, electronic equipment and a computer readable medium, and relates to the technical field of computers.The method comprises the steps that in response to a data recommendation request, a corresponding grouping identifier and an abnormal identifier are obtained, and a corresponding recommendation value hash table and a follow-up visit plan identifier hash table are determined according to the grouping identifier and the abnormal identifier; the recommendation value hash table stores recommendation values and corresponding double linked lists, and the follow-up plan identifier hash table stores follow-up plan identifiers and corresponding linked list nodes; obtaining preset index updating data in real time, obtaining a new recommendation value based on the preset index updating data, and updating the position of the corresponding linked list node according to the new recommendation value in response to the fact that the new recommendation value is inconsistent with the original recommendation value to obtain an updated double linked list; and based on the updated double linked list, generating a target recommended follow-up visit plan identifier list and pushing the target recommended follow-up visit plan identifier list to the target terminal. The efficiency of doctor screening and follow-up visit plan sending is improved, and the matching degree of the follow-up visit plan and the current condition of the patient is improved.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a data recommendation method, device, electronic device and computer-readable medium. Background Art

[0002] At present, follow-up is a tool for regularly understanding changes in patients' conditions and guiding their recovery. In online medical scenarios, it has more complete doctor-patient triggers, higher fulfillment rates, and richer follow-up plans. The quality of follow-up is mainly reflected in the design of the follow-up plan. How doctors can quickly find a follow-up plan that is more suitable for the current patient among a large number of follow-up plans is particularly important for improving the level of medical services and the doctor-patient experience. Follow-up plans are only displayed by department classification and manually searched by doctors. Doctors' screening of follow-up plans is inefficient and the experience is poor. Doctors' choice of follow-up depends on subjective judgment and personal experience. The system cannot give doctors better recommendations and guidance. The sent follow-up plan may not match the patient's current condition, or there may be a more suitable follow-up plan. Summary of the invention

[0003] In view of this, the embodiments of the present application provide a data recommendation method, device, electronic device and computer-readable medium, which can solve the problems of low efficiency of existing doctors' screening follow-up plans, poor matching between the follow-up plans recommended by doctors and the current conditions of patients, and poor patient experience of the follow-up plans recommended by doctors.

[0004] To achieve the above objective, according to one aspect of an embodiment of the present application, a data recommendation method is provided, comprising:

[0005] In response to a data recommendation request, a corresponding group identifier and an exception identifier are obtained, and then a corresponding recommendation value hash table and a follow-up plan identifier hash table are determined according to the group identifier and the exception identifier, wherein the recommendation value hash table stores the recommendation value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, and the bidirectional linked list contains linked list nodes, and each linked list node includes a key-value pair consisting of the follow-up plan identifier and the recommended value;

[0006] Acquire preset indicator update data in real time, and then obtain a new recommended value based on the preset indicator update data, and in response to the new recommended value being inconsistent with the original recommended value, update the position of the corresponding linked list node according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node;

[0007] Based on the updated bidirectional linked list, a target recommended follow-up plan identifier list is generated and pushed to the target terminal.

[0008] Optionally, according to the new recommended value, the position of the corresponding linked list node is updated, including:

[0009] Determine the corresponding follow-up plan identifier according to the preset indicator update data, and then determine the corresponding linked list node according to the corresponding follow-up plan identifier;

[0010] According to the original recommended value, determine the corresponding bidirectional linked list;

[0011] The corresponding linked list node is updated based on the new recommended value to obtain an updated linked list node, and then the updated linked list node is disconnected from the corresponding bidirectional linked list and updated to the bidirectional linked list corresponding to the new recommended value.

[0012] Optionally, disconnecting the updated linked list node from the corresponding bidirectional linked list and updating it to the bidirectional linked list corresponding to the new recommended value includes:

[0013] In response to the new recommended value existing in the recommended value hash table, determining a bidirectional linked list corresponding to the new recommended value based on the recommended value hash table;

[0014] The updated linked list node is disconnected from the corresponding doubly linked list and inserted into the head of the doubly linked list corresponding to the new recommended value.

[0015] Optionally, disconnecting the updated linked list node from the corresponding bidirectional linked list and updating it to the bidirectional linked list corresponding to the new recommended value includes:

[0016] In response to the new recommended value not existing in the recommended value hash table, the updated linked list node is disconnected from the corresponding bidirectional linked list, and then a new bidirectional linked list is generated based on the updated linked list node, and the new recommended value is stored in the recommended value hash table and the new bidirectional linked list is stored accordingly.

[0017] Optionally, based on the updated bidirectional linked list, a target recommended follow-up plan identifier list is generated and pushed to the target terminal, including:

[0018] Based on the updated doubly linked list, determine the target doubly linked list where the maximum recommendation value is located;

[0019] Starting from the head of the target bidirectional linked list, a preset number of linked list nodes are sequentially obtained, and a target recommended follow-up plan identifier list is generated based on the follow-up plan identifiers corresponding to the preset number of linked list nodes;

[0020] Push the target recommended follow-up plan identification list to the target terminal.

[0021] Optionally, obtain preset indicator update data in real time, including:

[0022] Obtain in real time the number of sends, purchases and fulfillments corresponding to each follow-up plan identifier in the follow-up plan identifier hash table.

[0023] In addition, the present application also provides a data recommendation device, including:

[0024] An acquisition unit is configured to obtain a corresponding grouping identifier and an exception identifier in response to a data recommendation request, and then determine a corresponding recommendation value hash table and a follow-up plan identifier hash table according to the grouping identifier and the exception identifier, wherein the recommendation value hash table stores the recommendation value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, and the bidirectional linked list contains linked list nodes, and each linked list node includes a key-value pair consisting of the follow-up plan identifier and the recommended value;

[0025] an updating unit configured to obtain preset indicator update data in real time, and then obtain a new recommended value based on the preset indicator update data, and in response to the new recommended value being inconsistent with the original recommended value, update the position of the corresponding linked list node according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node;

[0026] The data recommendation unit is configured to generate a target recommended follow-up plan identifier list based on the updated bidirectional linked list and push it to the target terminal.

[0027] Optionally, the updating unit is further configured to:

[0028] Determine the corresponding follow-up plan identifier according to the preset indicator update data, and then determine the corresponding linked list node according to the corresponding follow-up plan identifier;

[0029] According to the original recommended value, determine the corresponding bidirectional linked list;

[0030] The corresponding linked list node is updated based on the new recommended value to obtain an updated linked list node, and then the updated linked list node is disconnected from the corresponding bidirectional linked list and updated to the bidirectional linked list corresponding to the new recommended value.

[0031] Optionally, the updating unit is further configured to:

[0032] In response to the new recommended value existing in the recommended value hash table, determining a bidirectional linked list corresponding to the new recommended value based on the recommended value hash table;

[0033] The updated linked list node is disconnected from the corresponding doubly linked list and inserted into the head of the doubly linked list corresponding to the new recommended value.

[0034] Optionally, the updating unit is further configured to:

[0035] In response to the new recommended value not existing in the recommended value hash table, the updated linked list node is disconnected from the corresponding bidirectional linked list, and then a new bidirectional linked list is generated based on the updated linked list node, and the new recommended value is stored in the recommended value hash table and the new bidirectional linked list is stored accordingly.

[0036] Optionally, the data recommendation unit is further configured to:

[0037] Based on the updated doubly linked list, determine the target doubly linked list where the maximum recommendation value is located;

[0038] Starting from the head of the target bidirectional linked list, a preset number of linked list nodes are sequentially obtained, and a target recommended follow-up plan identifier list is generated based on the follow-up plan identifiers corresponding to the preset number of linked list nodes;

[0039] Push the target recommended follow-up plan identification list to the target terminal.

[0040] Optionally, the updating unit is further configured to:

[0041] Obtain in real time the number of sends, purchases and fulfillments corresponding to each follow-up plan identifier in the follow-up plan identifier hash table.

[0042] In addition, the present application also provides a data recommendation electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the one or more processors implement the data recommendation method as described above.

[0043] In addition, the present application also provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the data recommendation method as described above is implemented.

[0044] An embodiment of the above invention has the following advantages or beneficial effects: the present application obtains the corresponding grouping identifier and abnormal identifier in response to the data recommendation request, and then determines the corresponding recommended value hash table and follow-up plan identifier hash table according to the grouping identifier and the abnormal identifier, wherein the recommended value hash table stores the recommended value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, the bidirectional linked list contains linked list nodes, and each linked list node includes a key-value pair consisting of the follow-up plan identifier and the recommended value; obtains the preset indicator update data in real time, and then obtains the new recommended value based on the preset indicator update data, responds to the new recommended value being inconsistent with the original recommended value, updates the position of the corresponding linked list node according to the new recommended value, so as to obtain the updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node; based on the updated bidirectional linked list, generates a target recommended follow-up plan identifier list and pushes it to the target terminal. It can realize the doctor's recommendation of high-quality follow-up plans, improve the efficiency of doctors screening and sending follow-up plans, improve the matching degree between the follow-up plan and the patient's current situation, improve the doctor-patient experience, and further improve the quality of medical services for follow-up before and after diagnosis.

[0045] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings are used to better understand the present application and do not constitute an improper limitation on the present application.

[0047] Figure 1 It is a schematic diagram of the main process of the data recommendation method provided according to an embodiment of the present application;

[0048] Figure 2 It is a schematic diagram of the main process of the data recommendation method provided according to an embodiment of the present application;

[0049] Figure 3 This is a schematic diagram of an application scenario of a data recommendation method provided according to an embodiment of the present application;

[0050] Figure 4 It is a main flow chart of a data recommendation method provided according to an embodiment of the present application;

[0051] Figure 5 is a schematic diagram of main units of a data recommendation device according to an embodiment of the present application;

[0052] Figure 6 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;

[0053] Figure 7 It is a structural diagram of a computer system of a terminal device or server suitable for implementing an embodiment of the present application. DETAILED DESCRIPTION

[0054] The following is an explanation of the exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. It should be noted that in the technical solution of the present disclosure, the collection, collection, update, analysis, processing, use, transmission, storage and other aspects of 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.

[0055] Figure 1 is a schematic diagram of the main process of the data recommendation method provided according to an embodiment of the present application, such as Figure 1 As shown, the data recommendation method includes:

[0056] Step S101, in response to a data recommendation request, obtain the corresponding group identifier and exception identifier, and then determine the corresponding recommendation value hash table and follow-up plan identifier hash table based on the group identifier and exception identifier, wherein the recommendation value hash table stores the recommendation value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, the bidirectional linked list contains linked list nodes, and each linked list node includes a key-value pair consisting of a follow-up plan identifier and a recommended value.

[0057] In this embodiment, the execution entity of the data recommendation method (for example, it can be a server) can receive the data recommendation request through a wired connection or a wireless connection. The application scenario of the embodiment of the present application can be a scenario in which a doctor recommends a follow-up plan to a patient in an online medical scenario. Follow-up is a tool for regularly understanding changes in the patient's condition and guiding the patient's recovery. In online medical scenarios, there are more complete doctor-patient triggers, higher compliance rates, and richer follow-up plans. The quality of follow-up is mainly reflected in the design of the follow-up plan. How doctors can quickly find a follow-up plan that is more suitable for the current patient among a large number of follow-up plans is particularly important for improving the level of medical services and improving the doctor-patient experience. After receiving the data recommendation request, the execution entity can obtain the group identifier and exception identifier corresponding to the request. For example, the group identifier can be such as Figure 3 The abnormality indicator can be as follows: Figure 3 In the embodiment of the present application, the group identifier may also be the department name of the company, and the abnormal identifier may also be the error name generated by the company department, etc. The embodiment of the present application does not specifically limit the group identifier and the disease identifier.

[0058] For example, the execution subject can define a key-value pair, where the key is the group identifier + exception identifier, and the value is the follow-up plan hash table and the recommended value hash table. For example, the recommended value can be a reflection of the importance and activity of the follow-up plan. For example, the recommended value rv is calculated as follows:

[0059] rv = number of follow-up plan sends * a + number of follow-up plan purchases * b + number of follow-up plan fulfillments * c

[0060] Among them, a+b+c=1.

[0061] The recommended value of the follow-up plan is calculated by the weighted sum of the three result characteristics (number of shipments, number of purchases, and number of fulfillments). The weights a, b, and c can be set according to the degree of influence of each characteristic on the result.

[0062] The execution subject can obtain the corresponding value according to the obtained group identifier and exception identifier as the key, namely the recommended value hash table and the follow-up plan hash table. Among them, the recommended value hash table stores the recommended value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node. The bidirectional linked list contains linked list nodes, and each linked list node includes a key-value pair consisting of the follow-up plan identifier and the recommended value.

[0063] Figure 3 FIG. 1 is a schematic diagram of an application scenario of a data recommendation method provided according to an embodiment of the present application. Figure 3 As shown, the corresponding recommended value hash table and follow-up plan identifier hash table are obtained from the department ID + disease ID. Among them, the recommended value hash table stores:

[0064] Recommended value 1 and the corresponding bidirectional linked list: head, key = follow-up plan ID2, value = recommended value 1, key = follow-up plan ID3, value = recommended value 1, tail;

[0065] Recommended value 2 and the corresponding bidirectional linked list: head, key = follow-up plan ID1, value = recommended value 2, key = follow-up plan ID5, value = recommended value 2, tail;

[0066] Recommended value 3 and the corresponding bidirectional linked list: head, key = follow-up plan ID4, value = recommended value 3, key = follow-up plan ID8, value = recommended value 3, key = follow-up plan ID6, value = recommended value 3, tail;

[0067] Recommended value 4 and the corresponding bidirectional linked list: head, key = follow-up plan ID7, value = recommended value 4, tail.

[0068] In the recommended value hash table, the activity of the linked list node near the head is greater than that of the linked list node near the tail. The linked list node near the head is the previous linked list node of the adjacent linked list node near the tail, and the linked list node near the tail is the next linked list node of the adjacent linked list node near the head.

[0069] like Figure 3 As shown, for example, in the follow-up plan identifier hash table, the following are stored:

[0070] Follow-up plan ID and corresponding linked list node. The linked list node is a linked list node in a bidirectional linked list stored in the recommended value hash table. The corresponding linked list node can be quickly located through the follow-up plan ID to achieve rapid update of the corresponding data.

[0071] For example, the hash table of follow-up plans stores:

[0072] Follow-up plan ID1 and corresponding linked list node key = follow-up plan ID1, value = recommended value 2;

[0073] Follow-up plan ID2 and corresponding linked list node key = follow-up plan ID2, value = recommended value 1;

[0074] Follow-up plan ID3 and corresponding linked list node key = follow-up plan ID3, value = recommended value 1;

[0075] Follow-up plan ID4 and corresponding linked list node key = follow-up plan ID4, value = recommended value 3;

[0076] Follow-up plan ID5 and corresponding linked list node key = follow-up plan ID5, value = recommended value 2;

[0077] Follow-up plan ID6 and corresponding linked list node key = follow-up plan ID6, value = recommended value 3;

[0078] Follow-up plan ID7 and corresponding linked list node key = follow-up plan ID7, value = recommended value 4;

[0079] Follow-up plan ID8 and corresponding linked list node key=follow-up plan ID8, value=recommended value 3.

[0080] The hash table of the follow-up plan can quickly locate which bidirectional linked list has changed the recommended value of the follow-up plan, and timely update the position of the bidirectional linked list where the corresponding linked list node is located according to the change of the recommended value. The follow-up plan ID is the unique value of the follow-up plan, that is, the follow-up plan identifier. The linked list node where the changed recommended value is located is found through the follow-up plan ID. The linked list node has the recommended value, the recommended value is found and the new recommended value is calculated, and then the new bidirectional linked list position is quickly updated according to the new recommended value. It can be achieved to recommend high-quality follow-up plans to doctors based on the current doctor-patient characteristics, improve the efficiency of doctors sending follow-up and the matching degree of follow-up plans to patients, enhance patients' willingness to purchase and fulfill contracts, and ultimately increase the number of follow-up orders and follow-up compliance. Follow-up compliance: patients follow the doctor's instructions to follow up regularly according to the plan.

[0081] Step S102, obtaining preset indicator update data in real time, and then obtaining a new recommended value based on the preset indicator update data. In response to the new recommended value being inconsistent with the original recommended value, the position of the corresponding linked list node is updated according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node.

[0082] Specifically, the preset indicator update data is obtained in real time, including: obtaining the number of sending times, the number of purchasing times and the number of fulfillment times corresponding to each follow-up plan identifier in the follow-up plan identifier hash table in real time.

[0083] Among them, the recommended value rv is calculated as follows:

[0084] rv = number of follow-up plan sends * a + number of follow-up plan purchases * b + number of follow-up plan fulfillments * c

[0085] Among them, a+b+c=1.

[0086] The recommended value of the follow-up plan is calculated by the weighted sum of the three result characteristics (number of shipments, number of purchases, and number of fulfillments). The weights a, b, and c can be set according to the degree of influence of each characteristic on the result.

[0087] Update the data according to the preset indicators obtained in real time, that is, update the recommended value rv according to the number of follow-up plan sending, purchase and fulfillment of follow-up plan corresponding to each follow-up plan identifier in the follow-up plan identifier hash table. And update the position of the bidirectional linked list where the corresponding linked list node is located according to whether the updated recommended value is equal to the original recommended value and whether it exists in the recommended value hash table, and update the bidirectional linked list in the recommended value hash table that has changed. It can be realized to dynamically adjust the position of the linked list node of the bidirectional linked list in the recommended value hash table through the dynamic behavior of doctors and patients on the follow-up plan, so that the doctor's recommendation of the follow-up plan is more accurate and more in line with the patient's current situation, improving the doctor-patient experience.

[0088] In the embodiments of the present application, the follow-up plan is a regular plan for regularly understanding the patient's condition and guiding the patient's rehabilitation. Performance is the patient's behavior of completing the tasks in the follow-up plan.

[0089] Step S103: Generate a target recommended follow-up plan identifier list based on the updated bidirectional linked list and push it to the target terminal.

[0090] Specifically, based on the updated bidirectional linked list, a target recommended follow-up plan identification list is generated and pushed to the target terminal, including: based on the updated bidirectional linked list, determining the target bidirectional linked list (for example, the head, key = follow-up plan ID7, value = recommended value 4, tail) where the maximum recommended value (for example, the current maximum recommended value 4) is located; starting from the head of the target bidirectional linked list, obtaining a preset number (for example, topN) of linked list nodes in sequence, and generating a target recommended follow-up plan identification list based on the follow-up plan identifications corresponding to the preset number of linked list nodes (if there is only one linked list node in the current target bidirectional linked list, then N = 1, and only one corresponding target recommended follow-up plan identification can be recommended, for example, follow-up plan ID7); pushing the target recommended follow-up plan identification list to the target terminal.

[0091] In an embodiment of the present application, the target terminal may be a mobile phone, computer, etc. used by a doctor. The embodiment of the present application does not specifically limit the type of the target terminal. The target terminal may be a key-operated elderly phone or a touch screen machine. The embodiment of the present application does not specifically limit the version and model of the target terminal.

[0092] For example, the final effect of the data recommendation method of the embodiment of the present application is to recommend to the doctor the topN follow-up recommendation plans with the highest recommendation value rv and the most recent activity (the bidirectional linked list under the recommendation value starts from the head) under the current department and disease. N can be any custom integer, and the embodiment of the present application does not specifically limit N.

[0093] This embodiment obtains the corresponding grouping identifier and abnormal identifier in response to the data recommendation request, and then determines the corresponding recommended value hash table and follow-up plan identifier hash table according to the grouping identifier and abnormal identifier, wherein the recommended value hash table stores the recommended value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, the bidirectional linked list contains linked list nodes, and each linked list node includes a key-value pair consisting of the follow-up plan identifier and the recommended value; obtains the preset indicator update data in real time, and then obtains the new recommended value based on the preset indicator update data, and in response to the new recommended value being inconsistent with the original recommended value, updates the position of the corresponding linked list node according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node; based on the updated bidirectional linked list, generates a target recommended follow-up plan identifier list and pushes it to the target terminal. It can realize the doctor's recommendation of high-quality follow-up plans, improve the efficiency of doctors screening and sending follow-up plans, improve the matching degree between the follow-up plan and the patient's current situation, improve the doctor-patient experience, and further improve the quality of medical services for follow-up before and after diagnosis.

[0094] Figure 2 is a schematic diagram of the main flow of a data recommendation method provided according to an embodiment of the present application, such as Figure 2 As shown, the data recommendation method includes:

[0095] Step S201, in response to a data recommendation request, obtain the corresponding group identifier and exception identifier, and then determine the corresponding recommendation value hash table and follow-up plan identifier hash table based on the group identifier and exception identifier, wherein the recommendation value hash table stores the recommendation value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, the bidirectional linked list contains linked list nodes, and each linked list node includes a key-value pair consisting of a follow-up plan identifier and a recommended value.

[0096] The data recommendation request may also be a recommendation request for a solution required to remedy an error generated by a department. The present application embodiment does not specifically limit the type and content of the data recommendation request. The present application uses the example of a doctor recommending a follow-up plan to a patient to illustrate the relevant data recommendation method.

[0097] Step S202, obtaining preset indicator update data in real time, and then obtaining a new recommended value based on the preset indicator update data.

[0098] The preset indicator update data may be the update data of the number of follow-up plan sending, the number of follow-up plan purchasing and the number of follow-up plan fulfillment in the real-time follow-up plan hash table. The embodiment of the present application does not specifically limit the preset indicators.

[0099] Step S203, in response to the new recommended value being inconsistent with the original recommended value, a corresponding follow-up plan identifier is determined according to the preset indicator update data, and then a corresponding linked list node is determined according to the corresponding follow-up plan identifier.

[0100] The preset indicator update data includes the number of follow-up plan sending times, the number of follow-up plan purchase times, and the number of follow-up plan fulfillment times. It can be known that the preset indicator update data is associated with the follow-up plan identifier, so as to obtain the update data of the relevant indicators of the follow-up plan identifier in a timely manner. After determining the follow-up plan identifier, since the follow-up plan identifier and the corresponding linked list node are in a one-to-one correspondence, the linked list node corresponding to the follow-up plan identifier can be determined. For example, when the follow-up plan identifier corresponding to the preset indicator update data is follow-up plan ID1, the corresponding linked list node is uniquely determined as a linked list node storing key=follow-up plan ID1, value=recommended value 2.

[0101] Step S204, determining a corresponding bidirectional linked list according to the original recommended value.

[0102] The original recommended value, for example, is the recommended value 2, then the bidirectional linked list corresponding to the recommended value 2 is the corresponding bidirectional linked list. For example, the corresponding follow-up plan identifier determined by the preset indicator update data is, for example, the follow-up plan ID1. When the original recommended value is the recommended value 2, the recommended value 2 and the corresponding bidirectional linked list are: head, key = follow-up plan ID1, value = recommended value 2, key = follow-up plan ID5, value = recommended value 2, tail. The linked list node that needs to be repositioned is: key = follow-up plan ID1, value = recommended value 2. The updated new recommended value can be, for example, the recommended value 4.

[0103] Step S205 , updating the corresponding linked list node based on the new recommended value to obtain an updated linked list node, and then disconnecting the updated linked list node from the corresponding bidirectional linked list and updating it to the bidirectional linked list corresponding to the new recommended value.

[0104] If the new recommended value is 4, then the recommended value in the linked list node that needs to be repositioned is updated to be 4, and the updated linked list node is: key = follow-up plan ID1, value = recommended value 4. The updated linked list node is disconnected from the updated bidirectional linked list corresponding to recommended value 2, that is, from the head, key = follow-up plan ID1, value = recommended value 4, key = follow-up plan ID5, value = recommended value 2, and the tail is disconnected to obtain a free key = follow-up plan ID1, value = recommended value 4 node, and the free key = follow-up plan ID1, value = recommended value 4 node is inserted into the position closest to the head of the bidirectional linked list corresponding to recommended value 4.

[0105] Specifically, the updated linked list node is disconnected from the corresponding bidirectional linked list and updated to the bidirectional linked list corresponding to the new recommended value, including: in response to the existence of the new recommended value in the recommended value hash table, determining the bidirectional linked list corresponding to the new recommended value based on the recommended value hash table; disconnecting the updated linked list node from the corresponding bidirectional linked list and inserting it into the header of the bidirectional linked list corresponding to the new recommended value.

[0106] For example, if the recommended value corresponding to the follow-up plan identifier in the recommended value hash table changes, the corresponding linked list node is deleted from the original bidirectional linked list, the bidirectional linked list corresponding to the new recommended value is found, and the header of the bidirectional linked list corresponding to the new recommended value is inserted.

[0107] Specifically, the updated linked list node is disconnected from the corresponding bidirectional linked list and updated to the bidirectional linked list corresponding to the new recommended value, including: in response to the new recommended value not existing in the recommended value hash table, the updated linked list node is disconnected from the corresponding bidirectional linked list, and then a new bidirectional linked list is generated based on the updated linked list node, the new recommended value is stored in the recommended value hash table and the new bidirectional linked list is stored accordingly.

[0108] If the new recommended value does not exist in the recommended value hash table, a new correspondence between the new recommended value and the corresponding new bidirectional linked list is created, and the new recommended value is inserted into the position closest to the head of the new bidirectional linked list. For example, when the new recommended value is the recommended value 5, and the corresponding new linked list node is key = follow-up plan ID1, value = recommended value 5, and the recommended value 5 does not exist in the original recommended value hash table, a new correspondence between the recommended value 5 and the new linked list node key = follow-up plan ID1, value = recommended value 5 is created in the original recommended value hash table, and the new linked list node is inserted into the head of the new bidirectional linked list. The stored recommended value 5 and the corresponding new bidirectional linked list are obtained: head, key = follow-up plan ID1, value = recommended value 5, tail.

[0109] Step S206, obtaining an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node.

[0110] Step S207: Generate a target recommended follow-up plan identifier list based on the updated bidirectional linked list and push it to the target terminal.

[0111] The updated doubly linked list may include the latest doubly linked list corresponding to all recommended values ​​in the updated recommended value hash table. When the real-time recommended value hash table contains recommended value 1, recommended value 2, recommended value 3, recommended value 4, and recommended value 5, the updated doubly linked list may be the latest in real time:

[0112] Recommended value 1 and the corresponding bidirectional linked list: head, key = follow-up plan ID2, value = recommended value 1, key = follow-up plan ID3, value = recommended value 1, tail;

[0113] Recommended value 2 and the corresponding bidirectional linked list: head, key = follow-up plan ID1, value = recommended value 2, key = follow-up plan ID5, value = recommended value 2, tail;

[0114] Recommended value 3 and the corresponding bidirectional linked list: head, key = follow-up plan ID4, value = recommended value 3, key = follow-up plan ID8, value = recommended value 3, key = follow-up plan ID6, value = recommended value 3, tail;

[0115] Recommended value 4 and the corresponding bidirectional linked list: head, key = follow-up plan ID7, value = recommended value 4, tail;

[0116] Recommended value 5 and the corresponding new bidirectional linked list: head, key = follow-up plan ID1, value = recommended value 5, tail.

[0117] The embodiment of the present application can enable doctors to recommend high-quality follow-up plans based on the real-time latest recommendation value hash table and follow-up plan identification hash table, improve the efficiency of doctors in screening and sending follow-up plans, improve the matching degree between follow-up plans and patients' current conditions, improve the doctor-patient experience, and further improve the quality of follow-up medical services before and after diagnosis.

[0118] Figure 3 1 is a schematic diagram of an application scenario of a data recommendation method provided according to an embodiment of the present application. The recommended value rv is calculated as follows:

[0119] rv = number of follow-up plan sends * a + number of follow-up plan purchases * b + number of follow-up plan fulfillments * c

[0120] Among them, a+b+c=1.

[0121] The recommended value of the follow-up plan is calculated by the weighted sum of the three result characteristics (number of shipments, number of purchases, and number of fulfillments). The weights a, b, and c can be set according to the degree of influence of each characteristic on the result.

[0122] Cache initialization:

[0123] 1) Calculate the recommended values ​​of the follow-up plans corresponding to all follow-up plan identifiers using the above recommended value calculation formula, and group them by recommended values.

[0124] 2) The follow-up plan set corresponding to each recommended value is constructed into a bidirectional linked list, and the linked list node node contains the follow-up plan id and the recommended value.

[0125] 3) Create a recommendation value hash table to store the recommendation values ​​and the corresponding doubly linked list.

[0126] 4) Create a follow-up plan identification hash table to store the follow-up plan ID and the corresponding linked list node node.

[0127] 5) Define the key value as: department ID + disease ID, and the value value as: follow-up plan identification hash table and recommendation value hash table.

[0128] like Figure 3 As shown, the corresponding recommended value hash table and follow-up plan identifier hash table are obtained from the department ID + disease ID. Among them, the recommended value hash table stores:

[0129] Recommended value 1 and the corresponding bidirectional linked list: head, key = follow-up plan ID2, value = recommended value 1, key = follow-up plan ID3, value = recommended value 1, tail;

[0130] Recommended value 2 and the corresponding bidirectional linked list: head, key = follow-up plan ID1, value = recommended value 2, key = follow-up plan ID5, value = recommended value 2, tail;

[0131] Recommended value 3 and the corresponding bidirectional linked list: head, key = follow-up plan ID4, value = recommended value 3, key = follow-up plan ID8, value = recommended value 3, key = follow-up plan ID6, value = recommended value 3, tail;

[0132] Recommended value 4 and the corresponding bidirectional linked list: head, key = follow-up plan ID7, value = recommended value 4, tail.

[0133] In the recommended value hash table, the activity of the linked list node near the head is greater than that of the linked list node near the tail. The linked list node near the head is the previous linked list node of the adjacent linked list node near the tail, and the linked list node near the tail is the next linked list node of the adjacent linked list node near the head.

[0134] like Figure 3 As shown, for example, in the follow-up plan identifier hash table, the following are stored:

[0135] Follow-up plan ID and corresponding linked list node. The linked list node is a linked list node in a bidirectional linked list stored in the recommended value hash table. The corresponding linked list node can be quickly located through the follow-up plan ID to achieve rapid update of the corresponding data.

[0136] For example, the hash table of follow-up plans stores:

[0137] Follow-up plan ID1 and corresponding linked list node key = follow-up plan ID1, value = recommended value 2;

[0138] Follow-up plan ID2 and corresponding linked list node key = follow-up plan ID2, value = recommended value 1;

[0139] Follow-up plan ID3 and corresponding linked list node key = follow-up plan ID3, value = recommended value 1;

[0140] Follow-up plan ID4 and corresponding linked list node key = follow-up plan ID4, value = recommended value 3;

[0141] Follow-up plan ID5 and corresponding linked list node key = follow-up plan ID5, value = recommended value 2;

[0142] Follow-up plan ID6 and corresponding linked list node key = follow-up plan ID6, value = recommended value 3;

[0143] Follow-up plan ID7 and corresponding linked list node key = follow-up plan ID7, value = recommended value 4;

[0144] Follow-up plan ID8 and corresponding linked list node key=follow-up plan ID8, value=recommended value 3.

[0145] exist Figure 3 In the design of two hash tables and a bidirectional linked list, both cache query efficiency and cache operation efficiency are improved. The key of the hash table is used to store the recommended value, and the value is a bidirectional linked list. The node node contains the follow-up plan ID and the recommended value rv. The bidirectional linked list stores all follow-up plans under the recommended value.

[0146] At the same time, the hash table key value is also stored for the follow-up plan ID, and the value points to the linked list node position of the corresponding follow-up plan ID, so as to quickly query the current recommended value of a follow-up plan. The design of the bidirectional linked list also ensures the rapid change of the follow-up plan under different recommended values.

[0147] Figure 4 FIG. 1 is a schematic diagram of the main flow of a data recommendation method provided according to an embodiment of the present application. Figure 4 As shown, in the online medical scenario, when a data recommendation request is received, the execution subject can query the recommendation list, obtain the key (department ID + disease ID) of the consultation doctor-patient information, read the recommended value hash table in the cache based on the key, take the N more active follow-up plan identifiers corresponding to the maximum recommended value to form a recommended follow-up plan identifier list, and then return the determined follow-up plan identifier list to the doctor. When the number of times the follow-up plan is sent, the number of purchases, and the number of fulfillments change in real time, the changed follow-up plan ID is obtained and the follow-up plan hash table in the cache is read based on the changed follow-up plan ID, and the current follow-up plan node corresponding to the changed follow-up plan ID is taken. The current follow-up plan node is the corresponding linked list node in the bidirectional linked list in the recommended value hash table, and the recommended value of the linked list node is updated, and then the position of the corresponding linked list node is updated based on the updated recommended value, and the cache is refreshed based on the position of the updated linked list node. The purpose of the cache design in the embodiment of the present application is to quickly locate the most recommended follow-up plan under the current doctor-patient relationship and display it to the doctor for selection. After analyzing the follow-up plan, we found that the key features of the doctor-patient relationship are as follows: the doctor's department and the patient's disease. The recommendation value can be calculated through the three result features of the number of sends, the number of purchases, and the number of fulfillments. Under the dimension of the classification feature combination (department + disease), the result features are calculated to obtain the recommended value of each follow-up plan. Through the cache structure design, it supports the rapid acquisition of the follow-up plan with the highest recommended value under the current doctor-patient relationship, and can continuously maintain the cache in subsequent follow-up sends.

[0148] For example, the steps of actually implementing the data recommendation method of the embodiment of the present application can be as follows:

[0149] Step 1. Get the doctor's department and patient's disease under the current doctor-patient relationship, assemble them into a key to obtain the recommended value hash table.

[0150] Step 2. Take the current maximum recommended value, obtain the follow-up plan linked list under the recommended value, and build a list from the head to the bottom in order to recommend it to the doctor.

[0151] Step 3. The doctor selects a follow-up plan to send based on the list recommended by the system.

[0152] Step 4. Based on the sent follow-up plan ID, find the linked list node in the bidirectional linked list through the follow-up plan identifier hash table, recalculate the recommended value based on the new number of transmissions, and if the recommended value changes, delete the node from the original linked list, find the linked list of the new recommended value, and insert it into the head of the table. If the recommended value does not exist, recreate it. The activity of the follow-up plan decreases from the head to the tail of the bidirectional linked list. The latest linked list node is placed near the head, which means the linked list node corresponding to the most recently used and recently active follow-up plan is recommended to the doctor. The N most active follow-up plans with the highest recommendation value are recommended to the doctor. If the doctor sends this follow-up plan to the patient, the corresponding recommended value will change. Then, according to the follow-up plan ID of the changed recommended value, find which bidirectional linked list it is on, break the linked list node corresponding to the changed recommended value from the bidirectional linked list, and add it to the head of the bidirectional linked list corresponding to the new recommended value. The recommended value is continuously updated, and the top N follow-up plan identifiers with the highest real-time recommended value and the most active are displayed to the doctor.

[0153] 5. The patient selects the follow-up plan sent by the doctor, or manually selects the follow-up plan for purchase on the doctor's homepage, and repeats step 4 based on the purchased follow-up plan ID and the new number of purchases.

[0154] 6. After the patient purchases the follow-up plan, he / she completes the fulfillment on the follow-up plan fulfillment page, answer scale, medical questionnaire and other tasks. According to the fulfilled follow-up plan ID and based on the new fulfillment number, repeat step 4.

[0155] Final effect: Recommend to doctors the topN follow-up recommendation plans with the highest recommendation value rv and the most recent active ones (the bidirectional linked list under the recommendation value starts from the head) under the current department and disease.

[0156] The embodiment of the present application is based on the classification and result characteristics of follow-up in the online consultation scenario, designs a cache structure for efficient query and operation, and supports personalized follow-up recommendation plans for different doctors and patients in instant consultation. Recommend high-quality follow-up plans to doctors based on current doctor-patient characteristics, improve the efficiency of doctors' screening and sending follow-up, and the matching degree of follow-up plans to patients, further improve the quality of medical services before and after the diagnosis, improve patients' willingness to purchase and fulfill contracts, and ultimately increase the number of follow-up orders and follow-up compliance.

[0157] Figure 5 is a schematic diagram of the main units of the data recommendation device according to an embodiment of the present application. Figure 5 As shown, the data recommendation device 500 includes an acquisition unit 501 , an update unit 502 and a data recommendation unit 503 .

[0158] The acquisition unit 501 is configured to obtain the corresponding group identifier and exception identifier in response to the data recommendation request, and then determine the corresponding recommendation value hash table and follow-up plan identifier hash table according to the group identifier and the exception identifier, wherein the recommendation value hash table stores the recommendation value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, and the bidirectional linked list contains linked list nodes, and each linked list node includes a key-value pair consisting of the follow-up plan identifier and the recommended value.

[0159] The updating unit 502 is configured to obtain the preset indicator update data in real time, and then obtain a new recommended value based on the preset indicator update data. In response to the new recommended value being inconsistent with the original recommended value, the position of the corresponding linked list node is updated according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node.

[0160] The data recommendation unit 503 is configured to generate a target recommended follow-up plan identifier list based on the updated bidirectional linked list and push the list to the target terminal.

[0161] In some embodiments, the update unit 502 is further configured to: determine the corresponding follow-up plan identifier based on the preset indicator update data, and then determine the corresponding linked list node based on the corresponding follow-up plan identifier; determine the corresponding bidirectional linked list based on the original recommended value; update the corresponding linked list node based on the new recommended value to obtain an updated linked list node, and then disconnect the updated linked list node from the corresponding bidirectional linked list and update it to the bidirectional linked list corresponding to the new recommended value.

[0162] In some embodiments, the update unit 502 is further configured to: in response to the presence of a new recommended value in the recommended value hash table, determine a bidirectional linked list corresponding to the new recommended value based on the recommended value hash table; disconnect the updated linked list node from the corresponding bidirectional linked list and insert it into the header of the bidirectional linked list corresponding to the new recommended value.

[0163] In some embodiments, the update unit 502 is further configured to: in response to the new recommended value not existing in the recommended value hash table, disconnect the updated linked list node from the corresponding bidirectional linked list, and then generate a new bidirectional linked list based on the updated linked list node, store the new recommended value in the recommended value hash table and store the new bidirectional linked list accordingly.

[0164] In some embodiments, the data recommendation unit 503 is further configured to: determine the target bidirectional linked list where the maximum recommendation value is located based on the updated bidirectional linked list; obtain a preset number of linked list nodes in sequence starting from the header of the target bidirectional linked list, and generate a target recommended follow-up plan identifier list based on the follow-up plan identifiers corresponding to the preset number of linked list nodes; and push the target recommended follow-up plan identifier list to the target terminal.

[0165] In some embodiments, the updating unit 502 is further configured to: obtain in real time the number of sending, the number of purchasing, and the number of fulfillment corresponding to each follow-up plan identifier in the follow-up plan identifier hash table.

[0166] It should be noted that the data recommendation method and the data recommendation device of the present application have a corresponding relationship in terms of specific implementation contents, so the repeated contents will not be described again.

[0167] Figure 6 An exemplary system architecture 600 to which the data recommendation method or data recommendation device according to the embodiment of the present application can be applied is shown.

[0168] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0169] Users can use terminal devices 601, 602, and 603 to interact with server 605 through network 604 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 601, 602, and 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).

[0170] The terminal devices 601 , 602 , and 603 may be various electronic devices having a data recommendation processing screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.

[0171] Server 605 can be a server that provides various services, such as a background management server that provides support for data recommendation requests submitted by users using terminal devices 601, 602, and 603 (only as an example). The background management server can respond to the data recommendation request, obtain the corresponding group identifier and exception identifier, and then determine the corresponding recommended value hash table and follow-up plan identifier hash table according to the group identifier and exception identifier, wherein the recommended value hash table stores the recommended value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, and the bidirectional linked list contains linked list nodes, each of which includes a key-value pair consisting of a follow-up plan identifier and a recommended value; obtain the preset indicator update data in real time, and then obtain the new recommended value based on the preset indicator update data, and in response to the new recommended value being inconsistent with the original recommended value, update the position of the corresponding linked list node according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node; based on the updated bidirectional linked list, generate a target recommended follow-up plan identifier list and push it to the target terminal. It can enable doctors to recommend high-quality follow-up plans, improve the efficiency of doctors in screening and sending follow-up plans, improve the matching degree between follow-up plans and patients' current conditions, improve the doctor-patient experience, and further improve the quality of follow-up medical services before and after diagnosis.

[0172] It should be noted that the data recommendation method provided in the embodiment of the present application is generally executed by the server 605 , and accordingly, the data recommendation device is generally arranged in the server 605 .

[0173] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0174] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present application. Figure 7 The terminal device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0175] like Figure 7 As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the computer system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0176] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0177] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present application are executed.

[0178] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Computer-readable storage media may include, for example, but are not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: 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 the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal 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 computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0179] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0180] The units involved in the embodiments described in the present application may be implemented by software or by hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, an update unit, and a data recommendation unit. The names of these units do not, in some cases, constitute limitations on the units themselves.

[0181] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently and not be assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device responds to the data recommendation request, obtains the corresponding group identifier and abnormal identifier, and then determines the corresponding recommended value hash table and follow-up plan identifier hash table according to the group identifier and abnormal identifier, wherein the recommended value hash table stores the recommended value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, and the bidirectional linked list contains linked list nodes, each of which includes a key-value pair consisting of a follow-up plan identifier and a recommended value; obtains preset indicator update data in real time, and then obtains a new recommended value based on the preset indicator update data, and in response to the new recommended value being inconsistent with the original recommended value, updates the position of the corresponding linked list node according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node; based on the updated bidirectional linked list, generates a target recommended follow-up plan identifier list and pushes it to the target terminal.

[0182] According to the technical solution of the embodiment of the present application, doctors can recommend high-quality follow-up plans, improve the efficiency of doctors in screening and sending follow-up plans, improve the matching degree between follow-up plans and patients' current conditions, improve the doctor-patient experience, and further improve the quality of medical services before and after diagnosis.

[0183] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A data recommendation method, It is characterized in that include: In response to a data recommendation request, a corresponding group identifier and an exception identifier are obtained, and then a corresponding recommendation value hash table and a follow-up plan identifier hash table are determined according to the group identifier and the exception identifier, wherein the recommendation value hash table stores the recommendation value and the corresponding bidirectional linked list, and the follow-up plan identifier hash table stores the follow-up plan identifier and the corresponding linked list node, and the bidirectional linked list contains the linked list nodes, and each of the linked list nodes includes a key-value pair consisting of a follow-up plan identifier and a recommended value; Acquire preset indicator update data in real time, and then obtain a new recommended value based on the preset indicator update data, and in response to the new recommended value being inconsistent with the original recommended value, update the position of the corresponding linked list node according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node; Based on the updated bidirectional linked list, a target recommended follow-up plan identifier list is generated and pushed to the target terminal.

2. The method according to claim 1, It is characterized in that The updating of the position of the corresponding linked list node according to the new recommended value includes: Determine a corresponding follow-up plan identifier according to the preset indicator update data, and then determine a corresponding linked list node according to the corresponding follow-up plan identifier; Determine a corresponding bidirectional linked list according to the original recommended value; The corresponding linked list node is updated based on the new recommended value to obtain an updated linked list node, and then the updated linked list node is disconnected from the corresponding bidirectional linked list and updated to the bidirectional linked list corresponding to the new recommended value.

3. The method according to claim 2, It is characterized in that The step of disconnecting the updated linked list node from the corresponding bidirectional linked list and updating the bidirectional linked list to the new recommended value includes: In response to the new recommended value existing in the recommended value hash table, determining a bidirectional linked list corresponding to the new recommended value based on the recommended value hash table; The updated linked list node is disconnected from the corresponding bidirectional linked list and inserted into the head of the bidirectional linked list corresponding to the new recommended value.

4. The method according to claim 2, It is characterized in that The step of disconnecting the updated linked list node from the corresponding bidirectional linked list and updating the bidirectional linked list to the new recommended value includes: In response to the new recommended value not existing in the recommended value hash table, the updated linked list node is disconnected from the corresponding bidirectional linked list, and a new bidirectional linked list is generated based on the updated linked list node, and the new recommended value is stored in the recommended value hash table and the new bidirectional linked list is stored accordingly.

5. The method according to claim 1, It is characterized in that The step of generating a target recommended follow-up plan identifier list based on the updated bidirectional linked list and pushing the list to the target terminal includes: Based on the updated doubly linked list, determining a target doubly linked list where the maximum recommendation value is located; Sequentially acquiring a preset number of linked list nodes starting from the head of the target bidirectional linked list, and generating a target recommended follow-up plan identifier list based on the follow-up plan identifiers corresponding to the preset number of linked list nodes; Push the target recommended follow-up plan identifier list to the target terminal.

6. The method according to claim 1, It is characterized in that The real-time acquisition of preset indicator update data includes: The sending times, purchasing times and fulfillment times corresponding to each follow-up plan identifier in the follow-up plan identifier hash table are obtained in real time.

7. A data recommendation device, It is characterized in that include: An acquisition unit is configured to obtain a corresponding group identifier and an exception identifier in response to a data recommendation request, and then determine a corresponding recommendation value hash table and a follow-up plan identifier hash table according to the group identifier and the exception identifier, wherein the recommendation value hash table stores a recommendation value and a corresponding bidirectional linked list, and the follow-up plan identifier hash table stores a follow-up plan identifier and a corresponding linked list node, and the bidirectional linked list contains the linked list nodes, and each of the linked list nodes includes a key-value pair consisting of a follow-up plan identifier and a recommended value; an updating unit, configured to obtain preset indicator update data in real time, and then obtain a new recommended value based on the preset indicator update data, and in response to the new recommended value being inconsistent with the original recommended value, update the position of the corresponding linked list node according to the new recommended value to obtain an updated bidirectional linked list, wherein the original recommended value is the recommended value before the update in the corresponding linked list node; The data recommendation unit is configured to generate a target recommended follow-up plan identifier list based on the updated bidirectional linked list and push the list to the target terminal.

8. The device according to claim 7, It is characterized in that The updating unit is further configured to: Determine a corresponding follow-up plan identifier according to the preset indicator update data, and then determine a corresponding linked list node according to the corresponding follow-up plan identifier; Determine a corresponding bidirectional linked list according to the original recommended value; The corresponding linked list node is updated based on the new recommended value to obtain an updated linked list node, and then the updated linked list node is disconnected from the corresponding bidirectional linked list and updated to the bidirectional linked list corresponding to the new recommended value.

9. The device according to claim 8, It is characterized in that The updating unit is further configured to: In response to the new recommended value existing in the recommended value hash table, determining a bidirectional linked list corresponding to the new recommended value based on the recommended value hash table; The updated linked list node is disconnected from the corresponding bidirectional linked list and inserted into the head of the bidirectional linked list corresponding to the new recommended value.

10. The device according to claim 8, It is characterized in that The updating unit is further configured to: In response to the new recommended value not existing in the recommended value hash table, the updated linked list node is disconnected from the corresponding bidirectional linked list, and a new bidirectional linked list is generated based on the updated linked list node, and the new recommended value is stored in the recommended value hash table and the new bidirectional linked list is stored accordingly.

11. A data recommendation electronic device, It is characterized in that include: one or more processors; a storage device 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 method according to any one of claims 1 to 6.

12. A computer readable medium having a computer program stored thereon, It is characterized in that When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images