Intelligent operation and maintenance method, system and medium of medical service operation platform

Abstract

The present invention relates to an intelligent operation and maintenance method, system and medium of a medical service operation platform, belonging to the technical field of medical operation platforms. The present invention evaluates access delay feature data based on time series, obtains access delay membership change data within a preset time, thereby constructing an access delay membership prediction model according to the access delay membership change data within the preset time, and predicts the access delay membership of the current timestamp through the access delay membership prediction model, and finally performs access diversion on each access channel of the medical service operation platform based on the access delay membership of the current timestamp. The present invention can evaluate the user access data in each access channel, thereby diverting user access data to abnormal access channels, and can further optimize the operation and maintenance of the medical service operation platform, making the operation and maintenance of the medical service operation platform more reasonable.

Description

Technical Field

[0001] The present invention relates to the technical field of medical operation platforms, and in particular to an intelligent operation and maintenance method, system and medium for a medical service operation platform. Background Art

[0002] With the rapid development of Internet communications and computer technology, Internet medical care has gradually become a complete medical system in recent years to make up for the shortcomings of traditional medical care. Since 2018, a large number of Internet companies have entered the medical and health market, and various Internet medical platforms such as Chunyu Doctor, WeDoctor, and Good Doctor have emerged in the application market. The development of the "Internet + Medical Health" service system has optimized the allocation of medical resources, met the needs of multi-level and personalized medical services, overcome time and space barriers, enabled patients in remote areas to receive high-quality medical services, and realized the sharing of medical resources. However, during the use of the medical service operation platform, there are usually multiple access channels. Since the number of user visits changes dynamically, once the number of user visits rises to a certain number, there will be access jams and access delays, and in severe cases, the platform may even be paralyzed, which is not conducive to the operation and maintenance of the medical service operation platform. Summary of the invention

[0003] The present invention overcomes the deficiencies of the prior art and provides an intelligent operation and maintenance method, system and medium for a medical service operation platform.

[0004] To achieve the above object, the technical solution adopted by the present invention is:

[0005] The first aspect of the present invention provides an intelligent operation and maintenance method of a medical service operation platform, comprising:

[0006] Obtain user access data information of each channel of the medical service operation platform within a preset time, and obtain access delay characteristic data of each access channel based on the user access data information of each channel;

[0007] Constructing access delay characteristic data based on time series according to the access delay characteristic data of each access channel, and obtaining access delay membership change data within a preset time by evaluating the access delay characteristic data based on time series;

[0008] Building an access delay membership prediction model based on access delay membership change data within a preset time, and predicting the access delay membership of the current timestamp through the access delay membership prediction model;

[0009] Based on the access delay affiliation of the current timestamp, access to each access channel of the medical service operation platform is directed.

[0010] Furthermore, in this method, user access data information of each channel of the medical service operation platform within a preset time is obtained, and access delay characteristic data of each channel is obtained according to the user access data information of each channel, specifically including:

[0011] Build a medical service operation platform and configure several access channels for the medical service operation platform. Perform different visitor number tests on each access channel in the medical service operation platform to obtain access delay characteristic data of the access channel under different visitor numbers.

[0012] Introduce graph neural network, input the access delay feature data of access channels under different visitor numbers into the graph neural network, take the access channel as the first node, the visitor number as the second node, and the access delay feature data as the third node;

[0013] A topological structure graph is constructed based on the first node, the second node, and the third node, a related adjacency matrix is ​​obtained according to the topological structure graph, a knowledge graph is constructed, and the related adjacency matrix is ​​input into the knowledge graph for storage;

[0014] Obtain user access data information of various channels of the medical service operation platform within a preset time, input the user access data information of various channels of the medical service operation platform within the preset time into the knowledge graph for data matching, and obtain access delay feature data of each access channel.

[0015] Furthermore, in this method, access delay characteristic data based on time series is constructed according to the access delay characteristic data of each access channel, and the access delay characteristic data based on time series is evaluated to obtain access delay membership change data within a preset time, specifically including:

[0016] Constructing a timestamp, obtaining access delay characteristic data of each access channel at each timestamp, and constructing access delay characteristic data based on a time series according to the access delay characteristic data of each access channel at each timestamp;

[0017] Constructing an access delay membership threshold range indicator, and dividing the access delay membership of each timestamp of the access delay feature data based on the time series according to the access delay membership threshold range indicator to obtain the access delay membership of each timestamp;

[0018] By sorting the access delay membership of each timestamp in chronological order, access delay membership change data within a preset time is obtained, and the access delay membership change data within the preset time is output.

[0019] Furthermore, in the present method, an access delay membership prediction model is constructed according to the access delay membership change data within a preset time, specifically including:

[0020] A Markov model is introduced, and access delay membership change data within a preset time is input into the Markov model to obtain a transition probability value of the access delay membership transferring to other access delay memberships at each timestamp;

[0021] A transition probability matrix is ​​constructed according to the transition probability value of the access delay membership transferring to another access delay membership in each timestamp, and an access delay membership prediction model is constructed based on a deep neural network;

[0022] The transition probability matrix is ​​input into the access delay membership prediction model, and when the loss function of the access delay membership prediction model converges to a preset value, the access delay membership prediction model is output.

[0023] Furthermore, in this method, predicting the access delay membership of the current timestamp by using the access delay membership prediction model specifically includes:

[0024] Obtaining access delay membership change data within a current preset time, and inputting the access delay membership change data within the current preset time into an access delay membership prediction model for prediction;

[0025] Obtain a transition probability value of the access delay membership of the current timestamp being transferred to another access delay membership through prediction, and preset a transition probability threshold to determine whether the transition probability value of the access delay membership of the current timestamp being transferred to another access delay membership is greater than the transition probability threshold;

[0026] When the transition probability value of the access delay membership of the current timestamp to another access delay membership is greater than the transition probability threshold, the other access delay membership is output as the access delay membership of the current timestamp;

[0027] When the transition probability value of the access delay membership of the current timestamp transferring to another access delay membership is not greater than the transition probability threshold, the access delay membership of the current timestamp is output.

[0028] Furthermore, in this method, access to each access channel of the medical service operation platform is directed based on the access delay membership of the current timestamp, specifically including:

[0029] Obtaining the access delay membership of each access channel at the current timestamp according to the access delay membership of the current timestamp, and determining whether the access delay membership of each access channel at the current timestamp is greater than a preset access delay membership;

[0030] When the access delay membership of the access channel at the current timestamp is greater than the preset access delay membership, the corresponding access channel is regarded as an abnormal access channel; when the access delay membership of the access channel at the current timestamp is not greater than the preset access delay membership, the corresponding access channel is regarded as a normal access channel;

[0031] Obtaining user access data information of abnormal access channels and user access data information of normal access channels, introducing a genetic algorithm, setting a genetic generation according to the genetic algorithm, setting a user access data constraint threshold condition, and inputting the user access data information of the abnormal access channels and the user access data information of the normal access channels into the genetic algorithm;

[0032] Initialize the diversion quantity according to the user access data information of the abnormal access channel, and divert the diversion quantity to the normal access channel. When the user access data information in each access channel is greater than the user access data constraint threshold condition, it is inherited according to the genetic generation and the diversion quantity is adjusted until the user access data information in each access channel is no longer greater than the user access data constraint threshold condition.

[0033] A second aspect of the present invention provides an intelligent operation and maintenance system for a medical service operation platform, the system comprising a memory and a processor, the memory comprising an intelligent operation and maintenance method program for the medical service operation platform, and when the intelligent operation and maintenance method program for the medical service operation platform is executed by the processor, the following steps are implemented:

[0034] Obtain user access data information of each channel of the medical service operation platform within a preset time, and obtain access delay characteristic data of each access channel based on the user access data information of each channel;

[0035] Constructing access delay characteristic data based on time series according to the access delay characteristic data of each access channel, and obtaining access delay membership change data within a preset time by evaluating the access delay characteristic data based on time series;

[0036] Building an access delay membership prediction model based on access delay membership change data within a preset time, and predicting the access delay membership of the current timestamp through the access delay membership prediction model;

[0037] Based on the access delay affiliation of the current timestamp, access to each access channel of the medical service operation platform is directed.

[0038] The third aspect of the present invention provides a computer-readable storage medium, which includes an intelligent operation and maintenance method program for a medical service operation platform. When the intelligent operation and maintenance method program for the medical service operation platform is executed by a processor, any step of the intelligent operation and maintenance method for the medical service operation platform is implemented.

[0039] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0040] The present invention obtains user access data information of each channel of the medical service operation platform within a preset time, and obtains access delay characteristic data of each access channel according to the user access data information of each channel, and then constructs access delay characteristic data based on time series according to the access delay characteristic data of each access channel, and obtains access delay membership change data within a preset time by evaluating the access delay characteristic data based on time series, thereby constructing an access delay membership prediction model according to the access delay membership change data within the preset time, and predicting the access delay membership of the current timestamp through the access delay membership prediction model, and finally based on the access delay membership of the current timestamp, the access diversion of each access channel of the medical service operation platform is performed. The present invention can evaluate the user access data in each access channel, thereby diverting user access data to abnormal access channels, and can further optimize the operation and maintenance of the medical service operation platform, making the operation and maintenance of the medical service operation platform more reasonable. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, drawings of other embodiments can be obtained based on these drawings without paying creative work.

[0042] Figure 1 The overall method flow chart of the intelligent operation and maintenance method of the medical service operation platform is shown;

[0043] Figure 2 A first method flow chart of the intelligent operation and maintenance method of the medical service operation platform is shown;

[0044] Figure 3 A second method flow chart of the intelligent operation and maintenance method of the medical service operation platform is shown;

[0045] Figure 4 The system block diagram of the intelligent operation and maintenance system of the medical service operation platform is shown. DETAILED DESCRIPTION

[0046] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0047] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0048] like Figure 1 As shown, the first aspect of the present invention provides an intelligent operation and maintenance method of a medical service operation platform, comprising:

[0049] S102: Obtain user access data information of each channel of the medical service operation platform within a preset time, and obtain access delay characteristic data of each access channel according to the user access data information of each channel;

[0050] S104: constructing access delay characteristic data based on time series according to the access delay characteristic data of each access channel, and obtaining access delay membership change data within a preset time by evaluating the access delay characteristic data based on time series;

[0051] S106: constructing an access delay membership prediction model according to the access delay membership change data within a preset time, and predicting the access delay membership of the current timestamp through the access delay membership prediction model;

[0052] S108: Based on the access delay membership of the current timestamp, access to each access channel of the medical service operation platform is directed.

[0053] It should be noted that the present invention can evaluate the user access data in each access channel, thereby diverting user access data to abnormal access channels, and can further optimize the operation and maintenance of the medical service operation platform, making the operation and maintenance of the medical service operation platform more reasonable.

[0054] like Figure 2 As shown, further, in this method, user access data information of each channel of the medical service operation platform within a preset time is obtained, and access delay characteristic data of each channel is obtained according to the user access data information of each channel, specifically including:

[0055] S202: construct a medical service operation platform, and configure a number of access channels for the medical service operation platform, and obtain access delay characteristic data of the access channel under different visitor numbers by testing each access channel in the medical service operation platform with different visitor numbers;

[0056] S204: Introduce a graph neural network, input the access delay feature data of the access channel under different visitor numbers into the graph neural network, use the access channel as the first node, the visitor number as the second node, and the access delay feature data as the third node;

[0057] S206: construct a topological structure graph based on the first node, the second node, and the third node, obtain a related adjacency matrix according to the topological structure graph, construct a knowledge graph, and input the related adjacency matrix into the knowledge graph for storage;

[0058] S208: Obtain user access data information of each channel of the medical service operation platform within a preset time, input the user access data information of each channel of the medical service operation platform within the preset time into the knowledge graph for data matching, and obtain access delay characteristic data of each access channel.

[0059] It should be noted that the user access data information is the number of user accesses. Within a certain range, due to the limited data processing capacity of the server, the different numbers of different access users will result in different access delays. For example, when the number of accesses is 10,000, the access delay is 10ms; when the number of accesses is 20,000, the access delay is 30ms. This method can obtain the access delay feature data of each access channel.

[0060] Furthermore, in this method, access delay characteristic data based on time series is constructed according to the access delay characteristic data of each access channel, and the access delay characteristic data based on time series is evaluated to obtain access delay membership change data within a preset time, specifically including:

[0061] Constructing a timestamp, obtaining access delay characteristic data of each access channel at each timestamp, and constructing access delay characteristic data based on a time series according to the access delay characteristic data of each access channel at each timestamp;

[0062] Constructing an access delay membership threshold range indicator, and dividing the access delay membership of each timestamp of the access delay feature data based on the time series according to the access delay membership threshold range indicator to obtain the access delay membership of each timestamp;

[0063] By sorting the access delay membership of each timestamp in chronological order, access delay membership change data within a preset time is obtained, and the access delay membership change data within the preset time is output.

[0064] It should be noted that the access delay membership includes low delay membership, medium delay membership, and high delay membership. Technical personnel in this field can set certain access delay membership threshold range indicators. For example, the low delay membership is 0ms to 100ms for low delay membership, and 100ms to 200ms for medium delay membership. Personnel in this field can make settings according to more practical requirements.

[0065] Furthermore, in the present method, an access delay membership prediction model is constructed according to the access delay membership change data within a preset time, specifically including:

[0066] A Markov model is introduced, and access delay membership change data within a preset time is input into the Markov model to obtain a transition probability value of the access delay membership transferring to other access delay memberships at each timestamp;

[0067] A transition probability matrix is ​​constructed according to the transition probability value of the access delay membership transferring to another access delay membership in each timestamp, and an access delay membership prediction model is constructed based on a deep neural network;

[0068] The transition probability matrix is ​​input into the access delay membership prediction model, and when the loss function of the access delay membership prediction model converges to a preset value, the access delay membership prediction model is output.

[0069] It should be noted that the Markov Model is a statistical model that is widely used in various natural language processing applications such as speech recognition, automatic part-of-speech tagging, phonetic-to-character conversion, probabilistic grammar, etc. After long-term development, especially its successful application in speech recognition, it has become a universal statistical tool. In fact, during the visit process, the number of people constantly changes within the preset time, and the visit membership will also change to a certain extent. By inputting the change data of the visit delay membership within the preset time into the Markov model, the transition probability value of the visit delay membership in each timestamp to other visit delay memberships is calculated, such as the transition probability value of the low visit delay membership to the medium visit delay membership, and the transition probability value of the low visit delay membership to the high visit delay membership.

[0070] Furthermore, in this method, predicting the access delay membership of the current timestamp by using the access delay membership prediction model specifically includes:

[0071] Obtaining access delay membership change data within a current preset time, and inputting the access delay membership change data within the current preset time into an access delay membership prediction model for prediction;

[0072] Obtain a transition probability value of the access delay membership of the current timestamp being transferred to another access delay membership through prediction, and preset a transition probability threshold to determine whether the transition probability value of the access delay membership of the current timestamp being transferred to another access delay membership is greater than the transition probability threshold;

[0073] When the transition probability value of the access delay membership of the current timestamp to another access delay membership is greater than the transition probability threshold, the other access delay membership is output as the access delay membership of the current timestamp;

[0074] When the transition probability value of the access delay membership of the current timestamp transferring to another access delay membership is not greater than the transition probability threshold, the access delay membership of the current timestamp is output.

[0075] It should be noted that when the transition probability value of the access delay membership of the current timestamp to another access delay membership is greater than the transition probability threshold, it means that the access delay membership of the current timestamp has been transferred, otherwise, no transfer has occurred. This method can further improve the accuracy of access delay membership evaluation for the current timestamp.

[0076] like Figure 3 As shown, further, in this method, access to each access channel of the medical service operation platform is directed based on the access delay membership of the current timestamp, specifically including:

[0077] S302: Obtain the access delay membership of each access channel at the current timestamp according to the access delay membership of the current timestamp, and determine whether the access delay membership of each access channel at the current timestamp is greater than a preset access delay membership;

[0078] S304: when the access delay membership of the access channel at the current timestamp is greater than the preset access delay membership, the corresponding access channel is regarded as an abnormal access channel; when the access delay membership of the access channel at the current timestamp is not greater than the preset access delay membership, the corresponding access channel is regarded as a normal access channel;

[0079] S306: Obtain user access data information of abnormal access channels and user access data information of normal access channels, introduce a genetic algorithm, set a genetic generation according to the genetic algorithm, set a user access data constraint threshold condition, and input the user access data information of abnormal access channels and user access data information of normal access channels into the genetic algorithm;

[0080] S308: Initialize the diversion quantity according to the user access data information of the abnormal access channel, and divert the diversion quantity to the normal access channel. When the user access data information in each access channel is greater than the user access data constraint threshold condition, it is inherited according to the genetic generation and the diversion quantity is adjusted until the user access data information in each access channel is no longer greater than the user access data constraint threshold condition.

[0081] It should be noted that this method is integrated with a genetic algorithm to divert user access data from abnormal access channels until the user access data information in each access channel is no longer greater than the user access data constraint threshold condition, thereby improving the rationality of operation and maintenance of the medical service operation platform.

[0082] In addition, the method may further comprise the following steps:

[0083] Obtaining access delay characteristic data corresponding to user access data of each access channel, and determining that the access delay characteristic data corresponding to the user access data of each access channel is greater than a preset access delay characteristic threshold;

[0084] When the access delay characteristic data corresponding to the user access data of each access channel are greater than the preset access delay characteristic threshold, the preset access delay characteristic threshold is used as a constraint condition, and the number of visitors to each access channel is limited in order, and the limited user access volume is initialized;

[0085] Adjusting the user access data of each access channel according to the limited user access volume, obtaining the adjusted user access data, and obtaining access delay characteristic data corresponding to the adjusted user access data;

[0086] When the access delay characteristic data corresponding to the adjusted user access data is not greater than the preset access delay characteristic threshold, the user access volume for flow limiting is output; when the access delay characteristic data corresponding to the adjusted user access data is not greater than the preset access delay characteristic threshold, the user access volume for flow limiting is readjusted.

[0087] It should be noted that when the access delay characteristic data corresponding to the user access data of each access channel is greater than the preset access delay characteristic threshold, it means that access delay will occur no matter how the traffic is diverted. This method can further optimize the operation and maintenance rationality of the medical service operation platform.

[0088] like Figure 4 As shown, the second aspect of the present invention provides an intelligent operation and maintenance system 4 of a medical service operation platform, the system 4 includes a memory 41 and a processor 42, the memory 41 includes an intelligent operation and maintenance method program of the medical service operation platform, and when the intelligent operation and maintenance method program of the medical service operation platform is executed by the processor, the following steps are implemented:

[0089] Obtain user access data information of each channel of the medical service operation platform within a preset time, and obtain access delay characteristic data of each access channel based on the user access data information of each channel;

[0090] Constructing access delay characteristic data based on time series according to the access delay characteristic data of each access channel, and obtaining access delay membership change data within a preset time by evaluating the access delay characteristic data based on time series;

[0091] Building an access delay membership prediction model based on access delay membership change data within a preset time, and predicting the access delay membership of the current timestamp through the access delay membership prediction model;

[0092] Based on the access delay affiliation of the current timestamp, access to each access channel of the medical service operation platform is directed.

[0093] Furthermore, in this system, user access data information of each channel of the medical service operation platform within a preset time is obtained, and access delay characteristic data of each channel is obtained according to the user access data information of each channel, specifically including:

[0094] Build a medical service operation platform and configure several access channels for the medical service operation platform. Perform different visitor number tests on each access channel in the medical service operation platform to obtain access delay characteristic data of the access channel under different visitor numbers.

[0095] Introduce graph neural network, input the access delay feature data of access channels under different visitor numbers into the graph neural network, take the access channel as the first node, the visitor number as the second node, and the access delay feature data as the third node;

[0096] A topological structure graph is constructed based on the first node, the second node, and the third node, a related adjacency matrix is ​​obtained according to the topological structure graph, a knowledge graph is constructed, and the related adjacency matrix is ​​input into the knowledge graph for storage;

[0097] Obtain user access data information of various channels of the medical service operation platform within a preset time, input the user access data information of various channels of the medical service operation platform within the preset time into the knowledge graph for data matching, and obtain access delay feature data of each access channel.

[0098] Furthermore, in the present system, access delay characteristic data based on time series is constructed according to the access delay characteristic data of each access channel, and the access delay characteristic data based on time series is evaluated to obtain access delay membership change data within a preset time, specifically including:

[0099] Constructing a timestamp, obtaining access delay characteristic data of each access channel at each timestamp, and constructing access delay characteristic data based on a time series according to the access delay characteristic data of each access channel at each timestamp;

[0100] Constructing an access delay membership threshold range indicator, and dividing the access delay membership of each timestamp of the access delay feature data based on the time series according to the access delay membership threshold range indicator to obtain the access delay membership of each timestamp;

[0101] By sorting the access delay membership of each timestamp in chronological order, access delay membership change data within a preset time is obtained, and the access delay membership change data within the preset time is output.

[0102] Furthermore, in the present system, an access delay membership prediction model is constructed according to the access delay membership change data within a preset time, specifically including:

[0103] A Markov model is introduced, and access delay membership change data within a preset time is input into the Markov model to obtain a transition probability value of the access delay membership transferring to other access delay memberships at each timestamp;

[0104] A transition probability matrix is ​​constructed according to the transition probability value of the access delay membership transferring to another access delay membership in each timestamp, and an access delay membership prediction model is constructed based on a deep neural network;

[0105] The transition probability matrix is ​​input into the access delay membership prediction model, and when the loss function of the access delay membership prediction model converges to a preset value, the access delay membership prediction model is output.

[0106] Furthermore, in this system, the access delay membership prediction model is used to predict the access delay membership of the current timestamp, specifically including:

[0107] Obtaining access delay membership change data within a current preset time, and inputting the access delay membership change data within the current preset time into an access delay membership prediction model for prediction;

[0108] Obtain a transition probability value of the access delay membership of the current timestamp being transferred to another access delay membership through prediction, and preset a transition probability threshold to determine whether the transition probability value of the access delay membership of the current timestamp being transferred to another access delay membership is greater than the transition probability threshold;

[0109] When the transition probability value of the access delay membership of the current timestamp to another access delay membership is greater than the transition probability threshold, the other access delay membership is output as the access delay membership of the current timestamp;

[0110] When the transition probability value of the access delay membership of the current timestamp transferring to another access delay membership is not greater than the transition probability threshold, the access delay membership of the current timestamp is output.

[0111] Furthermore, in this system, the access delay membership of the current timestamp is used to guide the access to each access channel of the medical service operation platform, including:

[0112] Obtaining the access delay membership of each access channel at the current timestamp according to the access delay membership of the current timestamp, and determining whether the access delay membership of each access channel at the current timestamp is greater than a preset access delay membership;

[0113] When the access delay membership of the access channel at the current timestamp is greater than the preset access delay membership, the corresponding access channel is regarded as an abnormal access channel; when the access delay membership of the access channel at the current timestamp is not greater than the preset access delay membership, the corresponding access channel is regarded as a normal access channel;

[0114] Obtaining user access data information of abnormal access channels and user access data information of normal access channels, introducing a genetic algorithm, setting a genetic generation according to the genetic algorithm, setting a user access data constraint threshold condition, and inputting the user access data information of the abnormal access channels and the user access data information of the normal access channels into the genetic algorithm;

[0115] Initialize the diversion quantity according to the user access data information of the abnormal access channel, and divert the diversion quantity to the normal access channel. When the user access data information in each access channel is greater than the user access data constraint threshold condition, it is inherited according to the genetic generation and the diversion quantity is adjusted until the user access data information in each access channel is no longer greater than the user access data constraint threshold condition.

[0116] The third aspect of the present invention provides a computer-readable storage medium, which includes an intelligent operation and maintenance method program for a medical service operation platform. When the intelligent operation and maintenance method program for the medical service operation platform is executed by a processor, any step of the intelligent operation and maintenance method for the medical service operation platform is implemented.

[0117] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0118] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0119] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0120] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0121] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0122] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. An intelligent operation and maintenance method for a medical service operation platform, characterized in that: include: Obtaining user access data information of each channel of the medical service operation platform within a preset time, and obtaining access delay characteristic data of each access channel according to the user access data information of each channel; Constructing access delay characteristic data based on time series according to the access delay characteristic data of each access channel, and obtaining access delay membership change data within a preset time by evaluating the access delay characteristic data based on time series; Building an access delay membership prediction model according to the access delay membership change data within the preset time, and predicting the access delay membership of the current timestamp by using the access delay membership prediction model; Based on the access delay membership of the current timestamp, access is directed to each access channel of the medical service operation platform; Obtaining user access data information of each channel of the medical service operation platform within a preset time, and obtaining access delay characteristic data of each channel according to the user access data information of each channel, specifically including: Constructing a medical service operation platform, and configuring a plurality of access channels for the medical service operation platform, and obtaining access delay characteristic data of the access channel under different visitor numbers by testing each access channel in the medical service operation platform with different visitor numbers; Introducing a graph neural network, inputting the access delay characteristic data of the access channel under different numbers of visitors into the graph neural network, taking the access channel as the first node, the number of visitors as the second node, and the access delay characteristic data as the third node; Constructing a topological structure graph based on the first node, the second node, and the third node, obtaining a related adjacency matrix according to the topological structure graph, constructing a knowledge graph, and inputting the related adjacency matrix into the knowledge graph for storage; Obtaining user access data information of each channel of the medical service operation platform within a preset time, inputting the user access data information of each channel of the medical service operation platform within the preset time into the knowledge graph for data matching, and obtaining access delay characteristic data of each access channel; The following steps are also included: Obtaining access delay characteristic data corresponding to user access data of each access channel, and determining that the access delay characteristic data corresponding to the user access data of each access channel is greater than a preset access delay characteristic threshold; When the access delay characteristic data corresponding to the user access data of each access channel are greater than the preset access delay characteristic threshold, the preset access delay characteristic threshold is used as a constraint condition, and the number of visitors to each access channel is limited in order, and the limited user access volume is initialized; Adjusting the user access data of each access channel according to the limited user access volume, obtaining the adjusted user access data, and obtaining access delay characteristic data corresponding to the adjusted user access data; When the access delay characteristic data corresponding to the adjusted user access data is not greater than the preset access delay characteristic threshold, the limited user access volume is output; when the access delay characteristic data corresponding to the adjusted user access data is greater than the preset access delay characteristic threshold, the limited user access volume is readjusted.

2. According to claim 1, the intelligent operation and maintenance method of a medical service operation platform is characterized in that: Constructing access delay characteristic data based on time series according to the access delay characteristic data of each access channel, and obtaining access delay membership change data within a preset time by evaluating the access delay characteristic data based on time series, specifically including: Constructing a timestamp, obtaining access delay characteristic data of each access channel of each timestamp, and constructing access delay characteristic data based on a time series according to the access delay characteristic data of each access channel of each timestamp; Constructing an access delay membership threshold range indicator, and dividing the access delay membership of each timestamp on the access delay feature data based on the time series according to the access delay membership threshold range indicator to obtain the access delay membership of each timestamp; The access delay membership change data within a preset time is obtained by sorting the access delay membership of each time stamp in chronological order, and the access delay membership change data within the preset time is output.

3. The intelligent operation and maintenance method of a medical service operation platform according to claim 1, characterized in that: Building an access delay membership prediction model according to the access delay membership change data within the preset time specifically includes: Introducing a Markov model, and inputting the access delay membership change data within the preset time into the Markov model, and obtaining a transition probability value of the access delay membership transferring to other access delay memberships in each timestamp; Constructing a transition probability matrix according to the transition probability value of the access delay membership transferring to another access delay membership in each timestamp, and constructing an access delay membership prediction model based on a deep neural network; The transition probability matrix is ​​input into the access delay membership prediction model, and when the loss function of the access delay membership prediction model converges to a preset value, the access delay membership prediction model is output.

4. The intelligent operation and maintenance method of a medical service operation platform according to claim 1, characterized in that: Predicting the access delay membership of the current timestamp by using the access delay membership prediction model specifically includes: Acquire access delay membership change data within a current preset time, and input the access delay membership change data within the current preset time into the access delay membership prediction model for prediction; Obtaining a transition probability value of the access delay membership of the current timestamp being transferred to another access delay membership through prediction, and presetting a transition probability threshold, and determining whether the transition probability value of the access delay membership of the current timestamp being transferred to another access delay membership is greater than the transition probability threshold; When the transition probability value of the access delay membership of the current timestamp transferring to another access delay membership is greater than the transition probability threshold, outputting the other access delay membership as the access delay membership of the current timestamp; When the transition probability value of the access delay membership of the current timestamp transferring to another access delay membership is not greater than the transition probability threshold, the access delay membership of the current timestamp is output.

5. The intelligent operation and maintenance method of a medical service operation platform according to claim 1, characterized in that: Based on the access delay membership of the current timestamp, access to each access channel of the medical service operation platform is directed, specifically including: Obtaining the access delay membership of each access channel at the current timestamp according to the access delay membership of the current timestamp, and determining whether the access delay membership of each access channel at the current timestamp is greater than a preset access delay membership; When the access delay membership of the access channel at the current timestamp is greater than the preset access delay membership, the corresponding access channel is regarded as an abnormal access channel; when the access delay membership of the access channel at the current timestamp is not greater than the preset access delay membership, the corresponding access channel is regarded as a normal access channel; Obtaining user access data information of abnormal access channels and user access data information of normal access channels, introducing a genetic algorithm, setting a genetic generation according to the genetic algorithm, setting a user access data constraint threshold condition, and inputting the user access data information of the abnormal access channels and the user access data information of the normal access channels into the genetic algorithm; Initialize the diversion quantity according to the user access data information of the abnormal access channel, and divert the diversion quantity to the normal access channel. When the user access data information in each access channel is greater than the user access data constraint threshold condition, inheritance is performed according to the genetic generation, and the diversion quantity is adjusted until the user access data information in each access channel is no longer greater than the user access data constraint threshold condition.

6. An intelligent operation and maintenance system for a medical service operation platform, characterized in that: The system includes a memory and a processor, wherein the memory includes an intelligent operation and maintenance method program of a medical service operation platform, and when the intelligent operation and maintenance method program of the medical service operation platform is executed by the processor, the following steps are implemented: Obtaining user access data information of each channel of the medical service operation platform within a preset time, and obtaining access delay characteristic data of each access channel according to the user access data information of each channel; Constructing access delay characteristic data based on time series according to the access delay characteristic data of each access channel, and obtaining access delay membership change data within a preset time by evaluating the access delay characteristic data based on time series; Building an access delay membership prediction model according to the access delay membership change data within the preset time, and predicting the access delay membership of the current timestamp by using the access delay membership prediction model; Based on the access delay membership of the current timestamp, access is directed to each access channel of the medical service operation platform; Obtaining user access data information of each channel of the medical service operation platform within a preset time, and obtaining access delay characteristic data of each channel according to the user access data information of each channel, specifically including: Constructing a medical service operation platform, and configuring a plurality of access channels for the medical service operation platform, and obtaining access delay characteristic data of the access channel under different visitor numbers by testing each access channel in the medical service operation platform with different visitor numbers; Introducing a graph neural network, inputting the access delay characteristic data of the access channel under different numbers of visitors into the graph neural network, taking the access channel as the first node, the number of visitors as the second node, and the access delay characteristic data as the third node; Constructing a topological structure graph based on the first node, the second node, and the third node, obtaining a related adjacency matrix according to the topological structure graph, constructing a knowledge graph, and inputting the related adjacency matrix into the knowledge graph for storage; Obtaining user access data information of each channel of the medical service operation platform within a preset time, inputting the user access data information of each channel of the medical service operation platform within the preset time into the knowledge graph for data matching, and obtaining access delay characteristic data of each access channel; The intelligent operation and maintenance method program of the medical service operation platform also includes the following steps: Obtaining access delay characteristic data corresponding to user access data of each access channel, and determining that the access delay characteristic data corresponding to the user access data of each access channel is greater than a preset access delay characteristic threshold; When the access delay characteristic data corresponding to the user access data of each access channel are greater than the preset access delay characteristic threshold, the preset access delay characteristic threshold is used as a constraint condition, and the number of visitors to each access channel is limited in order, and the limited user access volume is initialized; Adjusting the user access data of each access channel according to the limited user access volume, obtaining the adjusted user access data, and obtaining access delay characteristic data corresponding to the adjusted user access data; When the access delay characteristic data corresponding to the adjusted user access data is not greater than the preset access delay characteristic threshold, the limited user access volume is output; when the access delay characteristic data corresponding to the adjusted user access data is greater than the preset access delay characteristic threshold, the limited user access volume is readjusted.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes an intelligent operation and maintenance method program for a medical service operation platform. When the intelligent operation and maintenance method program for a medical service operation platform is executed by a processor, the steps of the intelligent operation and maintenance method for a medical service operation platform as described in any one of claims 1 to 5 are implemented.

Images