Multi-cascade popularity prediction method

Abstract

The invention discloses a multi-cascade popularity prediction method, which comprises the following steps: S01, establishing a plurality of service node links, generating a popularity acquisition window to identify a service node with the maximum calling amount, and recording the service node with the maximum calling amount to obtain a service extraction group; s02, constructing the popular information atlas according to the service extraction group; s03, screening the popular information atlas for the first time according to a user-defined recommendation program so as to form N data packets, and dividing other data into N + n data packets according to a preset program, and respectively storing the N + n data packets; and S04, recommending the data of the N data packets to the user, automatically generating a plurality of project keywords of the N + n data packets, and recording each similar project in the data of the N data packets. According to the multi-cascade popularity prediction method provided by the invention, the popularity information is captured in multiple dimensions, so that the formulation of a more efficient service scheduling strategy is assisted.

Description

Technical Field

[0001] The present invention relates to computer programs, and particularly to a multi-cascade popularity prediction method. Background Art

[0002] The service deployment mode based on cloud computing and microservice architecture has become the mainstream application mode of various SaaS platforms today. In the microservice architecture, the most common scenario is the mutual invocation between microservices. A large number of microservice nodes, external users, and the invocation relationships between microservices together form a dynamic complex network. When new user requirements arise or microservice applications are updated (added, modified, deleted), it can be regarded as a perturbation to this dynamic complex network. In the operation and maintenance process of large-scale complex business systems, how to quickly identify key service nodes, predict data flow directions, and perform service call load balancing for various perturbation behaviors is particularly important, and it can provide key decision-making basis for the distributed deployment and dynamic operation and maintenance of large-scale microservices. Summary of the Invention

[0003] The purpose of the present invention is to provide a multi-cascade popularity prediction method to solve the above problems.

[0004] To achieve the above purpose, the present invention provides the following technical solution: A multi-cascade popularity prediction method, including the following steps:

[0005] S01. Establish multiple service node links, generate a popularity acquisition window to identify the service node with the most invocations, and include the service node with the most invocations to obtain a service extraction group;

[0006] S02. Construct the popularity information graph according to the service extraction group;

[0007] S03. According to the service call recommendation program defined by the user, perform the first screening on the popularity information graph to form N data packets, and divide the remaining data into N + n data packets according to a preset program, and store them separately;

[0008] S04. Recommend the N data packet data to the user, automatically generate multiple project keywords for the N + n data packets, record each similar project in the N data packet data, generate a recommendation score according to the number of invocations, and determine the project recommendation preferences of the N data packet data.

[0009] Preferably, before obtaining the service extraction group in step S01, perform concept induction on the invocation data to obtain inductive structure data, extract the data transmitted in the same time period of the popularity acquisition window to obtain target data, and perform relationship extraction on the target data to obtain extracted relationship data;

[0010] Perform attribute extraction on the target data and the extracted relationship data respectively to obtain target data attributes and relationship extraction attributes. Update the target data and the extracted relationship data according to the target data attributes and relationship extraction attributes to obtain updated target data and updated relationship data;

[0011] Based on the updated target data and the updated relationship data.

[0012] Preferably, the service with the highest call volume in step S01 is the one with the highest call volume of the current application;

[0013] Among them, the number of collection items with the highest call volume is not less than ten.

[0014] Preferably, constructing the popularity information graph according to the service extraction group in step S02 includes:

[0015] Extract the project service in the target data of the service extraction group, and query the project service in the pre-constructed current popularity sequence recommendation table;

[0016] Construct the sequence relationship between the service corresponding to the project service and the subsequent call service,

[0017] Construct the popularity information graph according to the sequence relationship and the service extraction group.

[0018] Preferably, the method of dividing the remaining data into N + n data packets according to a preset program in step S03 includes:

[0019] According to the information key in the popularity information graph, at least divide it into an infrastructure layer, a data layer, a communication layer, an algorithm scheduling layer, and an application layer;

[0020] Generate data packets based on the obtained information key items.

[0021] Preferably, in step S04, generate a corresponding service extraction group according to the determined project recommendation preferences of the N data packet data, and modify the service extraction group synchronously.

[0022] Preferably, the generated popularity acquisition window in step S01 includes at least the content setting of the service extraction group, and limits the content of the service extraction group through the content setting;

[0023] If the content of the service extraction group is greater than or equal to the first preset threshold, select the information of the first preset threshold from the service extraction group and recommend it to the user;

[0024] If the content of the service extraction group is less than or equal to the first preset threshold, the service extraction group and the secondary service group with the number of selected information equal to the difference between the second preset threshold and the content of the service extraction group are recommended to the user.

[0025] In the above technical solution, a multi-cascade popularity prediction method provided by the present invention has the following beneficial effects: it can quickly capture the global spatio-temporal characteristics of cascade nodes, the relative spatio-temporal characteristics of different nodes, and the node relationship characteristics between different node users, so as to extract all the intricate node relationships existing in the observed cascade, and can provide important data support for the prediction of information popularity. Thus, a method for judging the current user's needs by using information popularity is used to formulate a microservice operation and maintenance mode to maintain the stable operation of the overall SaaS service. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required in the embodiments. Obviously, the drawings in the following description are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings.

[0027] Figure 1 It is a schematic flowchart structure diagram provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0029] Embodiment 1

[0030] As Figure 1 shown, a multi-cascade popularity prediction method includes the following steps:

[0031] S01. Establish multiple service node links, generate a popularity acquisition window to identify the service with the most calls, and include the service with the most calls to obtain a service extraction group;

[0032] S02. Construct a popularity information graph according to the service extraction group;

[0033] S03. According to the service call recommendation program defined by the user, perform the first screening on the popularity information graph to form N data packets, and the remaining data is divided into N + n data packets according to a preset program and stored separately;

[0034] S04. Recommend the data of N data packets to the user, automatically generate multiple project keywords for N + n data packets, record each similar item in the N data packet data, generate a recommendation score based on the call times, and determine the project recommendation preferences of the N data packet data.

[0035] Embodiment 2

[0036] Before obtaining the service extraction group in step S01, perform concept induction on the course data to obtain the inductive structure data, extract the data transmitted in the same time period of the popularity acquisition window to obtain the target data, and perform relationship extraction on the target data to obtain the extraction relationship data.

[0037] Perform attribute extraction on the target data and the extraction relationship data respectively to obtain the target data attributes and relationship extraction attributes. According to the target data attributes and relationship extraction attributes, update the target data and the extraction relationship data to obtain the updated target data and the updated relationship data.

[0038] Based on the updated target data and the updated relationship data.

[0039] Embodiment 3

[0040] The service with the most calls in step S01 is the one with the highest call volume in the current application.

[0041] Among them, the number of collection items with the highest call volume is not less than ten.

[0042] Embodiment 4

[0043] In step S02, construct a popularity information graph according to the service extraction group, including:

[0044] Extract the project services in the target data of the service extraction group, and query the project services in the pre-constructed current popularity sequence recommendation table;

[0045] Construct the sequence relationship between the service corresponding to the project service and the subsequent called service,

[0046] Construct a popularity information graph according to the sequence relationship and the service extraction group.

[0047] Embodiment 5

[0048] The method of dividing the remaining data into N + n data packets in step S03 includes:

[0049] According to the information keys in the popularity information graph, at least divide it into an infrastructure layer, a data layer, a communication layer, an algorithm scheduling layer, and an application layer;

[0050] Generate data packets based on the obtained information key items.

[0051] Example Six

[0052] In step S04, according to the item recommendations and preferences determined from the N packet data, corresponding service extraction groups are generated, and the service extraction groups are modified synchronously.

[0053] Example Seven

[0054] In step S01, the popularity acquisition window generated includes at least the setting of the content of the service extraction group, and the content of the service extraction group is restricted by the content setting;

[0055] If the content of the service extraction group is greater than or equal to the first preset threshold, information with the first preset threshold is selected from the service extraction group and recommended to the user;

[0056] If the content of the service extraction group is less than or equal to the first preset threshold, the service extraction group and a secondary service group with the number of selected information equal to the difference between the second preset threshold and the content of the service extraction group are recommended to the user.

[0057] The above technology can quickly capture the global spatio-temporal features of cascade nodes, the relative spatio-temporal features of different nodes, and the node relationship features between different service nodes, so as to extract all the intricate node relationships existing in the observed cascade, and can provide important data support for the prediction of information popularity. Thus, a method for judging the current user's needs using information popularity, a microservice operation and maintenance mode, and maintaining the stable operation of the overall SaaS service can be realized.

[0058] Those skilled in the art should understand that the embodiments of the present invention can be provided as a method, a system, or a computer program product. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0059] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, and the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate means for realizing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks.

[0060] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce a manufacture including an instruction means that implements the functions specified in one or more of the processes Figure 1 or blocks Figure 1 specified in one or more of the blocks.

[0061] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, such that a series of operational steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes Figure 1 or blocks Figure 1 specified in one or more of the blocks.

[0062] Specific embodiments are used in the present invention to illustrate the principles and implementation manners of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present invention.

[0063] The embodiments of the present application also provide a specific implementation manner of an electronic device capable of implementing all the steps in the method in the above embodiments. The electronic device specifically includes the following:

[0064] A processor, a memory, a communications interface, and a bus;

[0065] Wherein, the processor, the memory, and the communications interface communicate with each other through the bus;

[0066] The processor is used to call the computer program in the memory, and when the processor executes the computer program, all the steps in the method in the above embodiments are implemented.

[0067] The embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps in the method in the above embodiments. A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, all the steps in the method in the above embodiments are implemented.

[0068] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments. In particular, for the hardware + program type of embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiments. Although the method operation steps as described in the embodiments of this specification are provided, based on conventional or non-creative means, there may be more or fewer operation steps. The order of steps listed in the embodiments is only one way among the execution orders of numerous steps and does not represent the only execution order. When actually executed by a device or terminal product, it can be executed in the order of the method shown in the embodiments or the drawings or executed in parallel (for example, in an environment of parallel processors or multi-threaded processing, or even in a distributed data processing environment). The term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, product or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed, or further includes elements inherent to such process, method, product or device. Without further limitation, it does not exclude the existence of additional identical or equivalent elements in the process, method, product or device including the said elements. For the convenience of description, when describing the above device, it is divided into various modules according to functions and described separately. Of course, when implementing the embodiments of this specification, the functions of each module can be realized in the same or multiple software and / or hardware, or the modules implementing the same function can be realized by a combination of multiple sub-modules or sub-units, etc. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in electrical, mechanical or other forms. The present invention is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of the present invention. It should be understood that each flow and / or block in the flowchart and / or block diagram, as well as the combination of flows and / or blocks in the flowchart and / or block diagram, can be realized by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for realizing the functions specified in one Figure 1 one flow or multiple flows and / or blocks Figure 1 one block or multiple blocks

[0069] Those skilled in the art should understand that the embodiments of this specification can be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification can take the form of all-hardware embodiments, all-software embodiments, or embodiments combining software and hardware aspects. Moreover, the embodiments of this specification can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code. Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for system embodiments, since they are basically similar to method embodiments, the description is relatively simple, and the relevant parts can be referred to the description of the method embodiments. In the description of this specification, the description of reference terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the embodiments of this specification.

[0070] In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples. The above is only the embodiments of the embodiments of this specification and is not used to limit the embodiments of this specification. For those skilled in the art, the embodiments of this specification can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of this specification shall be included within the scope of the claims of the embodiments of this specification.

Claims

1. A multi-cascade popularity prediction method, characterized in that: The following steps are involved: S01, establish multiple service node links, generate a popularity acquisition window, identify the service node with the most calls, and collect the service node with the most calls to obtain a service extraction group; S02, constructing the popular information graph according to the service extraction group; S03, according to the user-defined recommendation program, the popular information map is screened for the first time to form N data packets, and the remaining data is divided into N+n data packets according to a preset program and stored separately; S04. Recommend the N data packets to the user, and automatically generate multiple project keywords for N+n data packets, and record each similar project in the N data packets, and generate a recommendation score based on the number of calls to determine the project recommendation preference of the N data packets.

2. A multi-cascade popularity prediction method according to claim 1, characterized in that: In the step S01, before obtaining the service extraction group, the service data is conceptually summarized to obtain summarized structure data, the data transmitted in the same period of the popularity acquisition window is extracted to obtain target data, and the target data is relationally extracted to obtain extracted relation data; Extracting attributes from the target data and the extracted relationship data respectively to obtain target data attributes and relationship extraction attributes, and updating the target data and the extracted relationship data according to the target data attributes and relationship extraction attributes to obtain updated target data and updated relationship data; Based on the update target data and the update relationship data.

3. A multi-cascade popularity prediction method according to claim 1, characterized in that: The service with the highest call volume in step S01 is the service with the highest call volume in the current system / application; Among them, the collection items with the highest call volume are no less than ten.

4. A multi-cascade popularity prediction method according to claim 1, characterized in that: The step S02 constructs the popular information graph according to the service extraction group, including: Extracting the project service information in the target data of the service extraction group, and querying the pre-constructed current popularity sequence recommendation table for the project service information; Constructing a sequence relationship between the service entity corresponding to the project service and the subsequent calling service, The popular information graph is constructed according to the sequence relationship and the service extraction group.

5. A multi-cascade popularity prediction method according to claim 1, characterized in that: The method of dividing the remaining data into N+n data packets according to a preset program in step S03 includes: According to the key information in the popular information graph, it is divided into at least an infrastructure layer, a data layer, a communication layer, an algorithm scheduling layer and an application layer; Based on the obtained information key items, a data packet is generated.

6. A multi-cascade popularity prediction method according to claim 1, characterized in that: In the step S04, a corresponding service abstraction group is generated according to the determined item recommendation preferences of the N data packets, and the service abstraction group is modified synchronously.

7. A multi-cascade popularity prediction method according to claim 1, characterized in that: The popularity acquisition window generated in step S01 at least includes the service extraction group content setting, and limits the service extraction group content through the content setting; If the content of the service extraction group is greater than or equal to a first preset threshold, selecting information of the first preset threshold from the service extraction group and recommending it to the user; If the content of the service extraction group is less than or equal to the first preset threshold, the service extraction group and a secondary service group whose number of selected information pieces is the difference between the second preset threshold and the content of the service extraction group are recommended to the user.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the multi-cascade popularity prediction method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the multi-cascade popularity prediction method according to any one of claims 1 to 7 are implemented.

Images