Information recommendation processing method and device, terminal and computer readable storage medium

Abstract

The embodiment of the invention discloses an information recommendation processing method and device, a terminal and a computer readable storage medium, and the method comprises the steps: firstly obtaining a performance index value and a performance index threshold value of an information recommendation service, and determining a performance index detection result based on the performance index value and the performance index threshold value; and determining a service operation state of the information recommendation service based on the performance index detection result, and determining a service processing strategy for the information recommendation service based on the service operation state. The service operation state of the information recommendation service is accurately positioned through the performance index value and the performance index threshold value, and after the service operation state of the information recommendation service is obtained, the service processing strategy corresponding to the service operation state is determined, so that grading processing of different service operation states of the information recommendation service is realized, and the processing efficiency is improved. Therefore, the technical problem that the information recommendation service is difficult to provide normal service due to the fact that the information recommendation service reaches the capacity bottleneck caused by jitter of the information recommendation service is solved.

Description

Technical Field

[0001] The present application relates to the field of computer network technology, and in particular to an information recommendation processing method, device, terminal and computer-readable storage medium. Background Art

[0002] With the rapid development of Internet media, it has become a common way to realize the monetization of media resources by placing information recommendation resources through information recommendation services. In the process of placing information recommendation resources through information recommendation services, there will be a sudden increase in traffic, which will cause the information recommendation service to jitter and reach the capacity bottleneck of the information recommendation service. However, it is difficult to determine the problem of the information recommendation service itself based on the capacity bottleneck, making it difficult for the information recommendation service to provide normal services. Summary of the invention

[0003] The embodiments of the present application provide an information recommendation processing method, device, terminal and computer-readable storage medium, which can solve the technical problem that the information recommendation service reaches a capacity bottleneck due to the jitter of the information recommendation service caused by a sudden increase in traffic, but it is difficult to determine the information recommendation service itself based on the capacity bottleneck, making it difficult for the information recommendation service to provide normal services.

[0004] In a first aspect, an embodiment of the present application provides an information recommendation processing method, the method comprising:

[0005] Acquire a performance indicator value and a performance indicator threshold of the information recommendation service, and determine a performance indicator detection result based on the performance indicator value and the performance indicator threshold;

[0006] The service operation status of the information recommendation service is determined based on the performance indicator detection result, and the service processing strategy for the information recommendation service is determined based on the service operation status.

[0007] Optionally, the obtaining a performance indicator value and a performance indicator threshold of the information recommendation service, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, includes:

[0008] Obtain the information recommendation request processing time and the request processing time threshold of the information recommendation service, and determine the first performance indicator detection result based on the information recommendation request processing time and the request processing time threshold; and / or, obtain the service module request processing time and the module processing time threshold of the information recommendation service, and determine the second performance indicator detection result based on the service module request processing time and the module processing time threshold; and / or, obtain the service concurrency parameter amount and the concurrency parameter amount threshold of the information recommendation service, and determine the third performance indicator detection result based on the service concurrency parameter amount and the concurrency parameter amount threshold;

[0009] A performance indicator detection result is generated based on at least one of the first performance indicator detection result, the second performance indicator detection result, and the third performance indicator detection result.

[0010] Optionally, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0011] The determining the service operation status of the information recommendation service based on the performance indicator detection result includes:

[0012] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is less than or equal to the concurrency parameter amount threshold, it is determined that the service operation status of the information recommendation service is an abnormal module operation state.

[0013] Optionally, the determining a service processing strategy for the information recommendation service based on the service running state includes:

[0014] If the service operation state is a module operation abnormal state, determining a target operation abnormal module from the information recommendation service, the target operation abnormal module being a module whose service module request processing time is longer than the module processing time threshold;

[0015] The module computing amount is downgraded for the target abnormal operation module in the information recommendation service.

[0016] Optionally, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0017] The determining of a service processing strategy for the information recommendation service based on the service running state includes:

[0018] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is less than or equal to the concurrency parameter amount threshold, it is determined that the service operation status of the information recommendation service is an overloaded computing state.

[0019] Optionally, the determining a service processing strategy for the information recommendation service based on the service running state includes:

[0020] If the service operation state is an overloaded computing state, the information recommendation service is subjected to a system computing capacity degradation process.

[0021] Optionally, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0022] The determining the service operation status of the information recommendation service based on the performance indicator detection result includes:

[0023] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is greater than the concurrency parameter amount threshold, it is determined that the service operation status of the information recommendation service is a concurrent overload state.

[0024] Optionally, the determining a service processing strategy for the information recommendation service based on the service running state includes:

[0025] If the service operation state is a concurrent overload state, the information recommendation request received by the information recommendation service is obtained, the priority level of the information recommendation request is determined based on a preset priority mapping relationship, and the information recommendation request received by the information recommendation service is graded, screened and limited based on the priority level of the information recommendation request.

[0026] Optionally, before obtaining the performance indicator value and the performance indicator threshold of the information recommendation service, the method further includes:

[0027] Obtaining a first request quantity value of information recommendation requests received by the information recommendation service within a unit time window, and if the first request quantity value is greater than or equal to a first preset request quantity value, executing the step of obtaining a performance indicator value and a performance indicator threshold value of the information recommendation service; and / or,

[0028] Obtaining a second request quantity value of information recommendation requests received by the information recommendation service within the statistical time window, and when the second request quantity value is greater than or equal to a second preset request quantity value, executing the step of obtaining a performance indicator value and a performance indicator threshold value of the information recommendation service;

[0029] Among them, when the statistical time window is smaller than the unit time window, the second preset request amount value is greater than the first preset request amount value.

[0030] Optionally, the information recommendation request processing time of obtaining the information recommendation service includes:

[0031] Obtaining the request processing time corresponding to the information recommendation request processed by the information recommendation service within a unit time window, sorting the request processing time based on the duration of the request processing time to obtain a time ranking, determining a target request processing time at a preset proportional position in the time ranking, and determining the information recommendation request processing time based on the target request processing time;

[0032] The obtaining of the service concurrent parameter quantity and concurrent parameter quantity threshold of the information recommendation service includes:

[0033] Obtaining the number of information recommendation requests received and not yet processed by the information recommendation service, and determining a service concurrency parameter amount based on the number of information recommendation requests;

[0034] Determine, within at least two adjacent cycles, a maximum number of information recommendation requests processed by the information recommendation service within a unit time window of each cycle;

[0035] Determine the time series information of the at least two adjacent periods, determine the weighted parameter corresponding to the maximum number of each period based on the time series information, and determine the concurrent parameter quantity threshold based on the maximum number of each period and the weighted parameter corresponding to the maximum number.

[0036] In a second aspect, an embodiment of the present application provides an information recommendation processing platform, the platform comprising:

[0037] An acquisition module, adapted to acquire a performance indicator value and a performance indicator threshold of an information recommendation service, and determine a performance indicator detection result based on the performance indicator value and the performance indicator threshold;

[0038] The processing module is adapted to determine a service operation status of the information recommendation service based on the performance indicator detection result, and determine a service processing strategy for the information recommendation service based on the service operation status.

[0039] In a third aspect, an embodiment of the present application provides a terminal, the terminal comprising:

[0040] Processor; and

[0041] A memory arranged to store computer executable instructions which, when executed, cause the processor to perform a method according to any one of the above.

[0042] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores one or more programs, and when the one or more programs are executed by a processor, implement any of the methods described above.

[0043] The beneficial effects brought about by the technical solutions provided in some embodiments of the present application include at least:

[0044] The embodiment of the present application provides an information recommendation processing method, which first obtains the performance indicator value and performance indicator threshold of the information recommendation service, determines the performance indicator detection result based on the performance indicator value and the performance indicator threshold; determines the service operation status of the information recommendation service based on the performance indicator detection result, and determines the service processing strategy for the information recommendation service based on the service operation status. The embodiment of the present application uses the performance indicator value and the performance indicator threshold to accurately locate the service operation status of the information recommendation service, and after obtaining the service operation status of the information recommendation service, determines the service processing strategy corresponding to the service operation status, thereby achieving hierarchical processing of different service operation states of the information recommendation service to maintain the stable operation of the information recommendation service, thereby solving the problem that the information recommendation service reaches a capacity bottleneck due to the sudden increase in traffic, but it is difficult to determine the information recommendation service itself based on the capacity bottleneck, which makes it difficult for the information recommendation service to provide normal services. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application 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 embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 An exemplary system architecture diagram of an information recommendation processing method provided in an embodiment of the present application;

[0047] Figure 2 A flowchart of an information recommendation processing method provided in an embodiment of the present application;

[0048] Figure 3 A schematic diagram of a process for determining a performance indicator test result provided in an embodiment of the present application;

[0049] Figure 4 A flow chart of determining a service processing strategy for an information recommendation service based on a service running state provided in an embodiment of the present application;

[0050] Figure 5 A schematic diagram of a process for obtaining a service concurrent parameter amount and a concurrent parameter amount threshold for an information recommendation service provided in an embodiment of the present application;

[0051] Figure 6 A schematic diagram of the architecture of an information recommendation processing method provided in an embodiment of the present application;

[0052] Figure 7 A schematic diagram of the working architecture of an information recommendation processing method provided in an embodiment of the present application;

[0053] Figure 8 A schematic diagram of the structure of an information recommendation processing platform provided in an embodiment of the present application;

[0054] Fig. 9 A schematic diagram of the structure of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0055] In order to make the features and advantages of the embodiments of the present application more obvious and easy to understand, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of them. Based on the embodiments in the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the embodiments of the present application.

[0056] With the rapid development of Internet media, it has become a common way to realize the monetization of media resources by placing information recommendation resources through information recommendation services. For example, in the prior art, common information recommendation services may include an advertising engine system, etc. The advertising engine system will recommend a list of advertisements related to the user's interests and hobbies to the user based on the user's interests and hobbies. When the advertising engine system receives a request, the request will be processed by multiple sub-modules in the advertising engine system to recall, filter and layout the advertisements. Among them, the advertising engine system may include a request preprocessing sub-module, a keyword expansion sub-module, a reverse service recall advertisement sub-module, a forward service recall advertisement sub-module, a rough sorting sub-module, a fine sorting sub-module, a budget control sub-module, etc.

[0057] Generally, when providing information recommendation services based on information recommendation systems, there are system jitters during the operation of the information recommendation systems, that is, the system is unstable. When system jitters occur, the system is mainly affected by a sharp increase in traffic or a sharp increase in the high-priority traffic ratio. High-priority traffic refers to high-priority traffic that triggers a large number of advertisements. The problem of a sharp increase in the high-priority traffic ratio can be solved by simplifying the processing and reducing the processing time of each request. The problem of a sharp increase in traffic can be solved by reducing the access of requests. These two types of jitters will cause the system to reach a capacity bottleneck until it collapses and cannot provide services.

[0058] However, there are many factors that affect the capacity of the system, including: the capacity of each sub-module, the environment configuration in which the sub-module runs, and daily functions and optimizations. In order to avoid the system reaching capacity bottlenecks, the prior art provides two current limiting solutions, including fixed current limiting and adaptive current limiting. Fixed current limiting requires pre-stress testing of the system in order to set appropriate parameter thresholds. However, the factors that affect the capacity of the system are not stable, so it is difficult to maintain a fixed current limiting parameter. On the one hand, indifferent adaptive current limiting cannot guarantee the business requirements for system latency. On the other hand, the monetization efficiency of different traffic varies greatly, and there is a need for different current limiting levels in different scenarios.

[0059] In order to solve the above technical problems, the embodiment of the present application provides an information recommendation processing method, firstly obtaining the performance indicator value and performance indicator threshold of the information recommendation service, determining the performance indicator detection result based on the performance indicator value and the performance indicator threshold; determining the service operation status of the information recommendation service based on the performance indicator detection result, and determining the service processing strategy for the information recommendation service based on the service operation status. The embodiment of the present application uses the performance indicator value and the performance indicator threshold to accurately locate the service operation status of the information recommendation service, and after obtaining the service operation status of the information recommendation service, determines the service processing strategy corresponding to the service operation status, thereby realizing hierarchical processing of different service operation states of the information recommendation service to maintain the stable operation of the information recommendation service, thereby solving the problem that the information recommendation service reaches the capacity bottleneck due to the sudden increase in traffic, but it is difficult to determine the information recommendation service itself based on the capacity bottleneck, which makes it difficult for the information recommendation service to provide normal services.

[0060] See also Figure 1 , Figure 1 An exemplary system architecture diagram of an information recommendation processing method provided in an embodiment of the present application.

[0061] like Figure 1 As shown, the system architecture may include an information recommendation processing platform 101, a network 102, and a server 103. The network 102 is used to provide a medium for a communication link between the terminal 101 and the server 103. The network 102 may include various types of wired communication links or wireless communication links, for example, the wired communication link includes an optical fiber, a twisted pair, or a coaxial cable, and the wireless communication link includes a Bluetooth communication link, a Wireless-Fidelity (Wi-Fi) communication link, or a microwave communication link.

[0062] The information recommendation processing platform 101 can interact with the server 103 through the network 102 to receive messages from the server 103 or send messages to the server 103, or the information recommendation processing platform 101 can interact with the server 103 through the network 102 to receive messages or data sent by other users to the server 103. The information recommendation processing platform 101 can be hardware or software. When the information recommendation processing platform 101 is hardware, it can be various terminals, including but not limited to smart watches, smart phones, tablet computers, laptop portable computers, and desktop computers. When the information recommendation processing platform 101 is software, it can be installed in the terminals listed above, which can be implemented as multiple software or software modules (for example: used to provide distributed services), or it can be implemented as a single software or software module, which is not specifically limited here.

[0063] In an embodiment of the present application, the information recommendation processing platform 101 can obtain the performance indicator value and performance indicator threshold of the information recommendation service, and determine the performance indicator detection result based on the performance indicator value and the performance indicator threshold; determine the service operation status of the information recommendation service based on the performance indicator detection result, and determine the service processing strategy for the information recommendation service based on the service operation status.

[0064] The server 103 may be a business server that provides various services. It should be noted that the server 103 may be hardware or software. When the server 103 is hardware, it may be implemented as a distributed server cluster consisting of multiple servers, or it may be implemented as a single server. When the server 103 is software, it may be implemented as multiple software or software modules (for example, for providing distributed services), or it may be implemented as a single software or software module, which is not specifically limited here.

[0065] Alternatively, the system architecture may not include the server 103. In other words, the server 103 may be an optional device in the embodiments of this specification. That is, the method provided in the embodiments of this specification may be applied to a system structure that only includes the information recommendation processing platform 101, and the embodiments of this application are not limited to this.

[0066] It should be understood that Figure 1 The number of terminals, networks and servers in the figure is only for illustration and any number of terminals, networks and servers may be used according to implementation requirements.

[0067] See also Figure 2 , Figure 2A flowchart of an information recommendation processing method provided for an embodiment of the present application. The execution subject of the embodiment of the present application can be an information recommendation processing platform that executes the information recommendation processing method, or a processor in the information recommendation processing platform that executes the information recommendation processing method, or an information recommendation processing service in the information recommendation processing platform that executes the information recommendation processing method. For the convenience of description, the specific execution process of the information recommendation processing method is introduced below by taking the execution subject being a processor in the information recommendation processing platform as an example.

[0068] The information recommendation processing method includes:

[0069] S202: Obtain a performance indicator value and a performance indicator threshold of the information recommendation service, and determine a performance indicator detection result based on the performance indicator value and the performance indicator threshold.

[0070] The information recommendation service may be a service provided by the information recommendation system. The performance indicator value of the information recommendation service is used to measure the operating status of the information recommendation service, and the performance indicator threshold of the information recommendation service is the threshold of the performance indicator value when the information recommendation service provides normal service. The performance indicator type of the performance indicator value may be one or more, and correspondingly, the performance indicator type of the performance indicator threshold may also be one or more, and one performance indicator value may correspond to one performance indicator threshold.

[0071] Optionally, the performance indicator value may include at least one of the information recommendation request processing time, the service module request processing time of the information recommendation service, and the service concurrent parameter amount of the information recommendation service; the performance indicator threshold may include at least one of the request processing time threshold, the module processing time threshold, and the concurrent parameter amount threshold; wherein, the information recommendation request processing time corresponds to the request processing time threshold, the service module request processing time of the information recommendation service corresponds to the module processing time threshold, and the service concurrent parameter amount of the information recommendation service corresponds to the concurrent parameter amount threshold.

[0072] The information recommendation request is a request received by the information recommendation service. The information recommendation service obtains the information recommendation result by receiving the information recommendation request and processing the information recommendation request. The information recommendation request processing time is the total time from when the information recommendation service receives the information recommendation request to when the information recommendation result is obtained. The service module request processing time of the information recommendation service may be the time taken for a service module in the information recommendation service to process the information recommendation request. It should be noted that the information recommendation service may include one or more information recommendation services. The service concurrency parameter quantity of the information recommendation service may be the number of information recommendation requests being processed by the information recommendation service, or the product of the number of information recommendation requests and the estimated processing time of each information recommendation request.

[0073] In addition, in the process of information recommendation by the information recommendation service, there are certain requirements for the time delay of the information recommendation process. For example, in the process of advertising recommendation based on the information recommendation service, it is generally necessary to obtain the advertising recommendation results before the user search results are returned. The time delay requirements of the information recommendation process are usually different in different scenarios. Therefore, the request processing time threshold, the module processing time threshold, and the concurrent parameter amount threshold can all be determined based on different information recommendation scenarios to meet the actual information recommendation needs.

[0074] In this embodiment, after determining the performance indicator value and performance indicator threshold of the information recommendation service, the performance indicator value is compared with its corresponding performance indicator threshold to accurately determine the performance indicator detection result. The performance indicator detection result is used to reflect the service operation status of the information recommendation service. Different performance indicator detection results represent different service operation statuses, thereby realizing the grading of the service operation status of the information recommendation service.

[0075] S204: Determine a service operation status of the information recommendation service based on the performance indicator detection result, and determine a service processing strategy for the information recommendation service based on the service operation status.

[0076] Different performance indicator detection results represent different service operation states. After determining the service operation state of the information recommendation service based on the performance indicator detection results, a corresponding service processing strategy is adopted for the information recommendation service according to the graded service operation state to ensure stable operation of the information recommendation service. It should be noted that the state types of the service operation state may include two or more.

[0077] The embodiment of the present application provides an information recommendation processing method, which first obtains the performance indicator value and performance indicator threshold of the information recommendation service, determines the performance indicator detection result based on the performance indicator value and the performance indicator threshold; determines the service operation status of the information recommendation service based on the performance indicator detection result, and determines the service processing strategy for the information recommendation service based on the service operation status. The service operation status of the information recommendation service is accurately located by the performance indicator value and the performance indicator threshold. After obtaining the service operation status of the information recommendation service, the service processing strategy corresponding to the service operation status is determined, thereby achieving hierarchical processing of different service operation states of the information recommendation service to maintain the stable operation of the information recommendation service, thereby solving the problem that the information recommendation service reaches a capacity bottleneck due to the sudden increase in traffic, but it is difficult to determine the information recommendation service itself based on the capacity bottleneck, which makes it difficult for the information recommendation service to provide normal services.

[0078] See also Figure 3 , Figure 3A schematic diagram of a process for determining a performance indicator detection result provided in an embodiment of the present application. In an embodiment provided in the present application, obtaining a performance indicator value and a performance indicator threshold of an information recommendation service in S202, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, including:

[0079] S302: Obtain the information recommendation request processing time and the request processing time threshold of the information recommendation service, and determine the first performance indicator detection result based on the information recommendation request processing time and the request processing time threshold; and / or, obtain the service module request processing time and the module processing time threshold of the information recommendation service, and determine the second performance indicator detection result based on the service module request processing time and the module processing time threshold; and / or, obtain the service concurrency parameter amount and the concurrency parameter amount threshold of the information recommendation service, and determine the third performance indicator detection result based on the service concurrency parameter amount and the concurrency parameter amount threshold;

[0080] S304: Generate a performance indicator detection result based on at least one of the first performance indicator detection result, the second performance indicator detection result, and the third performance indicator detection result.

[0081] Optionally, obtaining a performance indicator value and a performance indicator threshold of the information recommendation service, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, includes:

[0082] Obtaining an information recommendation request processing time and a request processing time threshold of the information recommendation service, and determining a first performance indicator detection result based on the information recommendation request processing time and the request processing time threshold;

[0083] Based on the first performance indicator detection result, a performance indicator detection result is generated.

[0084] Among them, when the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the service operation status of the information recommendation service is a module operation abnormality state or an overload operation state. When the service operation status is a module operation abnormality state, it indicates that the module's computational amount is large, and the target operation abnormality module in the information recommendation service can be downgraded to reduce the computational amount of the target operation abnormal module; when the service operation status is an overload operation state, it indicates that the overall computational amount of the information recommendation service is large, and the system computational amount of the information recommendation service can be downgraded to reduce the overall computational amount of the information recommendation service.

[0085] When the first performance indicator detection result is that the information recommendation request processing time is less than or equal to the request processing time threshold, it can be considered that the information recommendation service status is normal.

[0086] Optionally, obtaining a performance indicator value and a performance indicator threshold of the information recommendation service, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, includes:

[0087] Obtaining a service module request processing time and a module processing time threshold of the information recommendation service, and determining a second performance indicator detection result based on the service module request processing time and the module processing time threshold;

[0088] Based on the second performance indicator detection result, generate a performance indicator detection result

[0089] Among them, when the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, it indicates that the computational amount of the service module is large. At this time, when the service operation status is an abnormal module operation state, the module computational amount downgrade processing can be performed on the target abnormal operation module in the information recommendation service to reduce the computational amount of the target abnormal operation module.

[0090] When the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, it can be considered that the service module in the information recommendation service is running normally and the information recommendation service is in a normal state.

[0091] Optionally, obtaining a performance indicator value and a performance indicator threshold of the information recommendation service, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, includes:

[0092] Obtaining a service concurrent parameter quantity and a concurrent parameter quantity threshold of the information recommendation service, and determining a third performance indicator detection result based on the service concurrent parameter quantity and the concurrent parameter quantity threshold;

[0093] Based on the third performance indicator detection result, a performance indicator detection result is generated.

[0094] Among them, when the third performance indicator detection result is that the service concurrent parameter quantity is greater than the concurrent parameter quantity threshold, the service operation state of the information recommendation service is a concurrent overload state at this time, and the information recommendation request received by the information recommendation service can be obtained, and the priority level of the information recommendation request is determined based on the preset priority mapping relationship, and the information recommendation request received by the information recommendation service is graded, screened and limited based on the priority level of the information recommendation request. It should be noted that the priority level of the information recommendation request can be determined based on the potential economic effect of the information recommendation request. For example, when the information recommendation request can trigger a large number of advertisements, it can be considered that the priority level of the information recommendation request is high.

[0095] When the third performance indicator detection result is that the service concurrent parameter quantity is less than or equal to the concurrent parameter quantity threshold, the service operation status of the information recommendation service is normal.

[0096] Optionally, obtaining a performance indicator value and a performance indicator threshold of the information recommendation service, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, includes:

[0097] Obtaining an information recommendation request processing time and a request processing time threshold for an information recommendation service, and determining a first performance indicator detection result based on the information recommendation request processing time and the request processing time threshold; and, obtaining a service module request processing time and a module processing time threshold for the information recommendation service, and determining a second performance indicator detection result based on the service module request processing time and the module processing time threshold;

[0098] A performance indicator detection result is generated based on the first performance indicator detection result and the second performance indicator detection result.

[0099] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, and the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, then the service operation status of the information recommendation service is the module operation abnormality state. When the service operation status is the module operation abnormality state, it indicates that the module has a large amount of computation. The module computational downgrade processing can be performed on the target operation abnormality module in the information recommendation service to reduce the computational amount of the target operation abnormality module.

[0100] When the first performance indicator detection result is that the information recommendation request processing time is less than or equal to the request processing time threshold, and the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, the service operation status of the information recommendation service is normal.

[0101] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, and the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, it indicates that the service module is working normally and the overall computational amount of the information recommendation service is large. At this time, the system computational amount of the information recommendation service can be downgraded to reduce the overall computational amount of the information recommendation service.

[0102] Optionally, obtaining a performance indicator value and a performance indicator threshold of the information recommendation service, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, includes:

[0103] Obtaining an information recommendation request processing time and a request processing time threshold for an information recommendation service, and determining a first performance indicator detection result based on the information recommendation request processing time and the request processing time threshold; and, obtaining a service concurrent parameter amount and a concurrent parameter amount threshold for the information recommendation service, and determining a third performance indicator detection result based on the service concurrent parameter amount and the concurrent parameter amount threshold;

[0104] A performance indicator detection result is generated based on the first performance indicator detection result and the third performance indicator detection result.

[0105] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is greater than the concurrent parameter amount threshold, the service operation status of the information recommendation service is a concurrent overload state. The information recommendation request received by the information recommendation service can be obtained, and the priority level of the information recommendation request can be determined based on the preset priority mapping relationship. The information recommendation request received by the information recommendation service is graded, screened and limited based on the priority level of the information recommendation request.

[0106] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold, the service operation status of the information recommendation service is an abnormal module operation state, indicating that the computational amount of the service module is large. The module computational amount downgrade processing can be performed on the target abnormal operation module in the information recommendation service to reduce the computational amount of the target abnormal operation module.

[0107] When the first performance indicator detection result is that the information recommendation request processing time is less than or equal to the request processing time threshold, and the third performance indicator detection result is that the service concurrent parameter quantity is less than or equal to the concurrent parameter quantity threshold, the operating status of the information recommendation service is normal.

[0108] Optionally, obtaining a performance indicator value and a performance indicator threshold of the information recommendation service, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, includes:

[0109] Obtaining a service module request processing time and a module processing time threshold for the information recommendation service, and determining a second performance indicator detection result based on the service module request processing time and the module processing time threshold; and, obtaining a service concurrent parameter amount and a concurrent parameter amount threshold for the information recommendation service, and determining a third performance indicator detection result based on the service concurrent parameter amount and the concurrent parameter amount threshold;

[0110] A performance indicator detection result is generated based on the second performance indicator detection result and the third performance indicator detection result.

[0111] When the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is greater than the concurrent parameter amount threshold, the module operation abnormal state and the overload computing state are triggered at the same time. After the module computing amount is downgraded for the target operation abnormal module in the information recommendation service, the system computing amount of the information recommendation service can also be downgraded to reduce the overall computing amount of the information recommendation service.

[0112] When the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is greater than the concurrent parameter amount threshold, the service operation status of the information recommendation service is a concurrent overload state. The information recommendation request received by the information recommendation service can be obtained, and the priority level of the information recommendation request can be determined based on the preset priority mapping relationship. The information recommendation request received by the information recommendation service is graded, screened and limited based on the priority level of the information recommendation request.

[0113] When the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold, and the service operation status is a module operation abnormal state at this time, the module calculation amount downgrade processing can be performed on the target operation abnormal module in the information recommendation service to reduce the calculation amount of the target operation abnormal module.

[0114] In an embodiment provided in the present application, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0115] Determining the service operation status of the information recommendation service based on the performance indicator detection result in S204 includes:

[0116] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold, it is determined that the service operation status of the information recommendation service is an abnormal module operation state.

[0117] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, it indicates that the information recommendation service is not running normally. At this time, the second performance indicator detection result and the third performance indicator detection result are further determined. When the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold, it indicates that there is an abnormal operation of the service module.

[0118] At this time, see Figure 4 , Figure 4 A flow chart of determining a service processing strategy for an information recommendation service based on a service running state provided in an embodiment of the present application. In S204, determining a service processing strategy for an information recommendation service based on a service running state includes:

[0119] S402: If the service operation state is a module operation abnormal state, determine a target operation abnormal module from the information recommendation service, where the target operation abnormal module is a module whose service module request processing time is greater than a module processing time threshold.

[0120] When the service operation status is the module operation abnormality status, it indicates that there is a service module operation abnormality in the information recommendation service. Generally, the service module that is operating abnormally is generally caused by the overload of computing volume, which causes the service module to time out equal to the processing time of the service module request. The service module that is operating abnormally is taken as the target module that is operating abnormally, and the module whose service module request processing time is greater than the module processing time threshold is determined to determine the target module that is operating abnormally, thereby determining the target module that is operating abnormally from the information recommendation service.

[0121] S404: Perform module computing amount degradation processing on the target abnormal operation module in the information recommendation service.

[0122] After determining the target abnormal operation module in the information recommendation service, the target abnormal operation module is subjected to module computational degradation processing. For example, the target abnormal operation module may be operated using a simpler model than before to reduce the computational load; or the operation program in the target abnormal operation module may be simplified to reduce the computational load.

[0123] In an embodiment provided in the present application, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0124] Determining the service operation status of the information recommendation service based on the performance indicator detection result in S204 includes:

[0125] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold, it is determined that the service operation status of the information recommendation service is an overloaded computing state.

[0126] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, it indicates that the information recommendation service is not running normally. At this time, the second performance indicator detection result and the third performance indicator detection result are further determined. When the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold, it indicates that each service module in the information recommendation service is running normally and the concurrency of the information recommendation service is normal. However, at this time, the information recommendation request processing time is greater than the request processing time threshold, indicating that the service operation state of the information recommendation service is an overloaded operation state, that is, the information recommendation service as a whole is in an overloaded operation state.

[0127] At this time, in S204, a service processing strategy for the information recommendation service is determined based on the service operation status, including:

[0128] If the service operation status is an overloaded computing status, the system computing capacity of the information recommendation service will be downgraded.

[0129] When the service operation status is in the overload computing state, the service module is normal, and the current concurrency of the information recommendation service does not exceed the maximum concurrency, indicating that the traffic has increased sharply or the high quotient ratio has increased sharply, resulting in an increase in the overall computing amount of the information recommendation service. Therefore, the system computing amount of the information recommendation service can be downgraded. Specifically, the module computing amount can be downgraded for some or all service modules in the information recommendation service.

[0130] In addition, the information recommendation requests received by the information recommendation service can be obtained, the priority levels of the information recommendation requests can be determined based on a preset priority mapping relationship, and the information recommendation requests received by the information recommendation service can be graded and screened based on the priority levels of the information recommendation requests. When processing information recommendation requests with a low priority level, the system computing power of the information recommendation service can be downgraded in advance; when processing information recommendation requests with a high priority level, the system computing power of the information recommendation service may not be downgraded.

[0131] In an embodiment provided in the present application, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0132] Determining the service operation status of the information recommendation service based on the performance indicator detection result in S204 includes:

[0133] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is greater than the concurrency parameter amount threshold, it is determined that the service operation status of the information recommendation service is a concurrent overload state.

[0134] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, it indicates that the information recommendation service is not running normally. At this time, the second performance indicator detection result and the third performance indicator detection result are further determined. When the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold and the third performance indicator detection result is that the service concurrent parameter amount is greater than the concurrent parameter amount threshold, it indicates that the system capacity of the information recommendation service has reached a bottleneck, that is, the information recommendation service cannot handle so many information recommendation requests, indicating that the service operation status of the information recommendation service is a concurrent overload state.

[0135] At this time, in S204, a service processing strategy for the information recommendation service is determined based on the service operation status, including:

[0136] If the service operation status is a concurrent overload state, the information recommendation request received by the information recommendation service is obtained, the priority level of the information recommendation request is determined based on a preset priority mapping relationship, and the information recommendation request received by the information recommendation service is graded, screened and limited based on the priority level of the information recommendation request.

[0137] When the service operation state is a concurrent overload state, the information recommendation request received by the information recommendation service is obtained. The information recommendation request received by the information recommendation service is the information recommendation request received by the information recommendation service and not yet processed. The priority level of the information recommendation request is determined based on the preset priority mapping relationship. The preset priority mapping relationship can pre-link the information recommendation request and the priority level through a mapping relationship based on the economic effect of the information recommendation request. Generally, the higher the economic effect of the information recommendation request, the higher the priority level, and the lower the economic effect of the information recommendation request, the lower the priority level.

[0138] After determining the priority level of the information recommendation request, in order to ensure the stable operation of the information recommendation service while ensuring that the information recommendation service revenue is less affected, the priority levels of the information recommendation requests are arranged in descending order or ascending order, and the information recommendation requests with a priority level lower than a preset target priority level may be discarded based on the priority level of the information recommendation request. Here, the preset target priority level may be determined based on the user.

[0139] In an embodiment provided by the present application, before obtaining the performance indicator value and the performance indicator threshold of the information recommendation service in S202, the following is further included:

[0140] Obtaining a first request quantity value of information recommendation requests received by the information recommendation service within a unit time window, and if the first request quantity value is greater than or equal to a first preset request quantity value, executing the step of obtaining a performance indicator value and a performance indicator threshold value of the information recommendation service; and / or,

[0141] Obtaining a second request quantity value of information recommendation requests received by the information recommendation service within the statistical time window, and when the second request quantity value is greater than or equal to a second preset request quantity value, executing the step of obtaining a performance indicator value and a performance indicator threshold value of the information recommendation service;

[0142] When the statistical time window is smaller than the unit time window, the second preset request amount value is greater than the first preset request amount value.

[0143] The unit time window can be used as the statistical period of the information recommendation service. For example, the unit time window can be 500ms or other optional period lengths. The first request value received by the information recommendation service within the unit time window is determined. When the first request value is too small, the number of samples is small and has no statistical significance. Therefore, no operation is performed on the information recommendation service at this time.

[0144] When the first request value is greater than or equal to the first preset request value, there are enough samples at this time, so the data is updated based on the samples, and the steps of obtaining the performance indicator value and the performance indicator threshold of the information recommendation service are executed. For example, when the first request value of the information recommendation request within 500ms is less than 100, the number of samples is too small, and the data in the current unit time window is not used for updating. When the first request value of the information recommendation request within 500ms is greater than or equal to 100, the number of samples meets the requirements, and the data in the current unit time window is used for updating, that is, the steps of obtaining the performance indicator value and the performance indicator threshold of the information recommendation service are executed.

[0145] Of course, in another embodiment, the second request amount value of the information recommendation request received by the information recommendation service within the statistical time window is determined, and when the statistical time window is less than the unit time window, the second preset request amount value is greater than the first preset request amount value. When the second request amount value is greater than or equal to the second preset request amount value, it indicates that there are a large number of information recommendation requests in the information recommendation service in a short period of time, and the status of the information recommendation service needs to be judged in time. Therefore, at this time, the steps of obtaining the performance indicator value and the performance indicator threshold of the information recommendation service can be performed. For example, when the unit time window is 500ms, when the first request amount value of the information recommendation request within less than 500ms is greater than or equal to the second preset request amount value, it indicates that there are a large number of information recommendation requests in the information recommendation service in a short period of time, and the status of the information recommendation service needs to be judged in time. Among them, the second preset request amount value can be 200 or other values ​​set based on actual needs.

[0146] In an embodiment provided by the present application, obtaining the information recommendation request processing time of the information recommendation service in S302 includes:

[0147] Obtain the request processing time corresponding to the information recommendation request processed by the information recommendation service within a unit time window, sort the request processing time based on the duration of the request processing time to obtain the time ranking, determine the target request processing time at a preset proportional position in the time ranking, and determine the information recommendation request processing time based on the target request processing time.

[0148] In a unit time window, the information recommendation service generally processes multiple information recommendation requests. The request processing time of each information recommendation request processed by the information recommendation service in the unit time window is determined, and the request processing time of each information recommendation request is arranged in ascending order to obtain a time ranking. The request processing time of the position that is 99% of the total number of rankings is taken, and the request processing time of the 99% position is taken as the information recommendation request processing time. Alternatively, the average of the request processing time of the 99% position in the most recent unit time windows is taken as the information recommendation request processing time. The request processing time of the position that is 99% of the total number of rankings is TP99 (Top Percentile 99). TP99 can be used to measure the load and responsiveness of the information recommendation service. Using TP99 as a trigger condition to ensure support for the information recommendation business can solve the problem of avoiding degradation and disconnection between business indicators.

[0149] In a feasible implementation, an average value of TP99 within the most recent five unit time windows may be obtained, and the average value of TP99 may be used as the information recommendation request processing duration.

[0150] See also Figure 5 , Figure 5A flow chart of obtaining a service concurrent parameter amount and a concurrent parameter amount threshold of an information recommendation service provided in an embodiment of the present application. In an embodiment provided in the present application, obtaining a service concurrent parameter amount and a concurrent parameter amount threshold of an information recommendation service in S302 includes:

[0151] S502: Obtain the number of information recommendation requests received by the information recommendation service but not yet processed, and determine the service concurrency parameter quantity based on the number of information recommendation requests.

[0152] The number of information recommendation requests received and not yet processed by the information recommendation service, that is, the current QPS (queries per second), is then used to determine the average time required to process the information recommendation request. For example, the average time required to process the information recommendation request can be determined from the most recent several unit time windows, such as 5 unit time windows. Then, the current QPS is multiplied by the average time required for the information recommendation request to obtain the service concurrency parameter.

[0153] S504: Determine, within at least two adjacent cycles, a maximum number of information recommendation requests processed by the information recommendation service within a unit time window of each cycle.

[0154] When each cycle includes at least one unit time window, for example, each cycle may include 5 unit time windows, at least two adjacent cycles closest to the current one are found, and the maximum number of information recommendation requests processed by the information recommendation service within the unit time window of each cycle is determined.

[0155] S506: Determine time series information of at least two adjacent periods, determine a weighted parameter corresponding to the maximum number of each period based on the time series information, and determine a concurrent parameter quantity threshold based on the maximum number of each period and the weighted parameter corresponding to the maximum number.

[0156] The time series information of at least two adjacent cycles, i.e., the time period of each cycle on the timeline, is used to determine the weighted parameter corresponding to the maximum value of each cycle based on the time series information. Since the impact of the most recent event on future events is greater than the impact of the previous event, the first weighted parameter corresponding to the maximum value of the cycle that occurs later is greater than the second weighted parameter corresponding to the maximum value of the cycle that occurs earlier, and the sum of the first weighted parameter and the second weighted parameter is 1. The concurrent parameter threshold value is determined based on the maximum value of each cycle and the weighted parameter corresponding to the maximum value through exponential smoothing. The product of the maximum value of the cycle that occurs later and the first weighted parameter is added to the product of the maximum value of the cycle that occurs earlier and the second weighted parameter to obtain the maximum value of the predicted cycle. Then, the maximum value of the predicted cycle is multiplied by the average time consumed by the information recommendation request to obtain the concurrent parameter threshold value.

[0157] See also Figure 6 , Figure 6 A schematic diagram of the architecture of an information recommendation processing method provided in an embodiment of the present application.

[0158] like Figure 6 As shown, first, the information recommendation request is processed by multiple working threads to obtain the time consumption of processing the information recommendation request. The information recommendation request is stored in the container (bucket) of the queue (queue). Data is updated based on the processed information recommendation request, that is, the steps of obtaining the performance indicator value and performance indicator threshold of the information recommendation service are executed. In the figure, avgrt is the average time consumption for processing the information recommendation request. According to TP99, QPS, avgrt and the pre-set performance indicator threshold, the status of the system corresponding to the information recommendation service, that is, the service operation status, is determined, and whether the trigger condition TP99 is normal. When TP99 is abnormal, it is determined whether there is a problem with the service module. When the service operation status is the module operation abnormal state, it indicates that the module has a large amount of calculation. The module calculation amount can be downgraded for the target operation abnormal module in the information recommendation service to reduce the calculation amount of the target operation abnormal module.

[0159] When there is no problem with the service module, it is determined whether the maximum concurrency is exceeded, and the service operation state of the information recommendation service is a concurrent overload state. The information recommendation request received by the information recommendation service can be obtained, and the priority level of the information recommendation request is determined based on the preset priority mapping relationship. The information recommendation request received by the information recommendation service is graded and screened based on the priority level of the information recommendation request. At this time, the level of current limiting can be flexibly set based on actual needs. When the maximum concurrency is not exceeded, the overall downgrade is performed, that is, the system computing amount of the information recommendation service is downgraded to reduce the overall computing amount of the information recommendation service. The downgrade level can be set based on actual needs.

[0160] See also Figure 7 , Figure 7 A schematic diagram of the working architecture of an information recommendation processing method provided in an embodiment of the present application.

[0161] 1. First, at the interface layer, after receiving the request, the system status is determined and the decision is made: process the request normally, downgrade or limit the flow. 2. If flow limiting is required, the interface layer directly discards the request. 3. If downgrading is required, then: a. Reduce the amount of calculation at the recall layer; b. Use a simple model calculation at the model layer. Among them, the elastic system is an intervention operation on the information recommendation service, flow limiting means reducing the access of requests, and downgrading means reducing the amount of calculation of the module (including the recall layer and model calculation). The interface layer is used to pre-process the information recommendation request, splice json, and dot log. Splicing json is for easy transmission or storage, and dotting log means log dotting; in the recall layer, bidword (keyword) can be triggered to recall advertisements based on keywords; in the model calculation, it includes rough sorting, fine sorting and re-ranking of advertisements. As the rough sorting, fine sorting and re-ranking are carried out, the number of advertisements becomes smaller and smaller.

[0162] An embodiment of the present application further provides a computer storage medium, which can store multiple instructions, and the instructions are suitable for being loaded by a processor and executing the steps of any method in the above embodiments.

[0163] Figure 8 This is a schematic diagram of the structure of an information recommendation processing platform provided in an embodiment of the present application. Figure 8 shown.

[0164] The information recommendation processing platform 800 includes:

[0165] An acquisition module 810 is adapted to acquire a performance indicator value and a performance indicator threshold of an information recommendation service, and determine a performance indicator detection result based on the performance indicator value and the performance indicator threshold;

[0166] The processing module 820 is adapted to determine the service operation status of the information recommendation service based on the performance indicator detection result, and determine the service processing strategy for the information recommendation service based on the service operation status.

[0167] Optionally, the acquisition module 810 includes:

[0168] An acquisition submodule is adapted to acquire the information recommendation request processing time and the request processing time threshold of the information recommendation service, and determine the first performance indicator detection result based on the information recommendation request processing time and the request processing time threshold; and / or, acquire the service module request processing time and the module processing time threshold of the information recommendation service, and determine the second performance indicator detection result based on the service module request processing time and the module processing time threshold; and / or acquire the service concurrent parameter amount and the concurrent parameter amount threshold of the information recommendation service, and determine the third performance indicator detection result based on the service concurrent parameter amount and the concurrent parameter amount threshold;

[0169] The generating submodule is adapted to generate a performance indicator detection result based on at least one of the first performance indicator detection result, the second performance indicator detection result and the third performance indicator detection result.

[0170] Optionally, the performance indicator detection results include a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result. The processing module 820 is suitable for determining that the service operation status of the information recommendation service is an abnormal module operation status when the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold.

[0171] Optionally, the processing module 820 is also suitable for determining a target abnormal operation module from the information recommendation service if the service operation status is a module operation abnormal state, the target abnormal operation module being a module whose service module request processing time is greater than a module processing time threshold; and performing module computing amount degradation processing on the target abnormal operation module in the information recommendation service.

[0172] Optionally, the performance indicator detection results include a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result. The processing module 820 is suitable for determining that the service operation status of the information recommendation service is an overloaded computing state when the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold.

[0173] Optionally, the processing module 820 is further adapted to perform system computing degradation processing on the information recommendation service if the service operation status is an overload computing status.

[0174] Optionally, the performance indicator detection results include a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result. The processing module 820 is suitable for determining that the service operation status of the information recommendation service is a concurrent overload state when the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is greater than the concurrency parameter amount threshold.

[0175] Optionally, the processing module 820 is also suitable for obtaining the information recommendation request received by the information recommendation service if the service operation status is a concurrent overload state, determining the priority level of the information recommendation request based on a preset priority mapping relationship, and performing graded screening and current limiting processing on the information recommendation request received by the information recommendation service based on the priority level of the information recommendation request.

[0176] Optionally, the information recommendation processing platform 800 further includes:

[0177] A first trigger module is adapted to obtain a first request value of information recommendation requests received by the information recommendation service within a unit time window, and if the first request value is greater than or equal to a first preset request value, execute the step of obtaining a performance indicator value and a performance indicator threshold of the information recommendation service; and / or,

[0178] A second trigger module is adapted to obtain a second request quantity value of information recommendation requests received by the information recommendation service within the statistical time window, and when the second request quantity value is greater than or equal to a second preset request quantity value, execute the step of obtaining a performance indicator value and a performance indicator threshold value of the information recommendation service;

[0179] When the statistical time window is smaller than the unit time window, the second preset request amount value is greater than the first preset request amount value.

[0180] Optionally, the acquisition submodule is adapted to acquire the request processing time corresponding to the information recommendation request processed by the information recommendation service within a unit time window, sort the request processing time based on the duration of the request processing time, obtain the time ranking, determine the target request processing time at a preset proportional position in the time ranking, and determine the information recommendation request processing time based on the target request processing time;

[0181] Obtain the number of information recommendation requests received and not yet processed by the information recommendation service, and determine the service concurrency parameter quantity based on the number of information recommendation requests;

[0182] Determine, in at least two adjacent cycles, a maximum number of information recommendation requests processed by the information recommendation service within a unit time window of each cycle;

[0183] Determine time series information of at least two adjacent periods, determine a weighted parameter corresponding to the maximum quantity of each period based on the time series information, and determine a concurrent parameter quantity threshold based on the maximum quantity of each period and the weighted parameter corresponding to the maximum quantity.

[0184] See also Fig. 9 , Fig. 9 A schematic diagram of the structure of a terminal provided in an embodiment of the present application. Fig. 9As shown, the terminal 900 may include: at least one processor 901 , at least one network interface 904 , a user interface 903 , a memory 905 , and at least one communication bus 902 .

[0185] The communication bus 902 is used to realize the connection and communication between these components.

[0186] The user interface 903 may include a display screen (Display) and a camera (Camera), and the optional user interface 903 may also include a standard wired interface and a wireless interface.

[0187] The network interface 904 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0188] Among them, the processor 901 may include one or more processing cores. The processor 901 uses various interfaces and lines to connect various parts within the entire terminal 900, and executes various functions and processes data of the terminal 900 by running or executing instructions, programs, code sets or instruction sets stored in the memory 905, and calling data stored in the memory 905. Optionally, the processor 901 can be implemented in at least one hardware form of digital signal processing (Digital Signal Processing, DSP), field programmable gate array (Field-Programmable Gate Array, FPGA), and programmable logic array (Programmable Logic Array, PLA). The processor 901 can integrate one or a combination of a central processing unit (Central Processing Unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU) and a modem. Among them, the CPU mainly processes the operating system, user interface and application programs; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communications. It can be understood that the above-mentioned modem may not be integrated into the processor 901, and it can be implemented separately through a chip.

[0189] Among them, the memory 905 may include a random access memory (Random Access Memory, RAM) and may also include a read-only memory (Read-Only Memory, ROM). Optionally, the memory 905 includes a non-transitory computer-readable storage medium. The memory 905 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 905 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store data involved in the above-mentioned various method embodiments, etc. The memory 905 may also be optionally at least one storage device located away from the aforementioned processor 901. As Fig. 9 As shown, the memory 905 as a computer storage medium may include an operating system, a network communication module, a user interface module, and an information recommendation processing program.

[0190] exist Fig. 9 In the terminal 900 shown, the user interface 903 is mainly used to provide an input interface for the user and obtain the data input by the user; and the processor 901 can be used to call the information recommendation processing program stored in the memory 905 and specifically perform the following operations:

[0191] Acquire a performance indicator value and a performance indicator threshold of the information recommendation service, and determine a performance indicator detection result based on the performance indicator value and the performance indicator threshold;

[0192] The service operation status of the information recommendation service is determined based on the performance indicator detection result, and the service processing strategy for the information recommendation service is determined based on the service operation status.

[0193] Optionally, the processor 901 executes the following steps when obtaining a performance indicator value and a performance indicator threshold of the information recommendation service and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold:

[0194] Obtain the information recommendation request processing time and the request processing time threshold of the information recommendation service, and determine the first performance indicator detection result based on the information recommendation request processing time and the request processing time threshold; and / or, obtain the service module request processing time and the module processing time threshold of the information recommendation service, and determine the second performance indicator detection result based on the service module request processing time and the module processing time threshold; and / or, obtain the service concurrency parameter amount and the concurrency parameter amount threshold of the information recommendation service, and determine the third performance indicator detection result based on the service concurrency parameter amount and the concurrency parameter amount threshold;

[0195] A performance indicator detection result is generated based on at least one of the first performance indicator detection result, the second performance indicator detection result, and the third performance indicator detection result.

[0196] Optionally, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0197] When the processor 901 determines the service running status of the information recommendation service based on the performance indicator detection result, it specifically performs the following steps:

[0198] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold, it is determined that the service operation status of the information recommendation service is an abnormal module operation state.

[0199] Optionally, when the processor 901 determines the service processing strategy for the information recommendation service based on the service running state, the processor 901 specifically performs the following steps:

[0200] If the service operation state is a module operation abnormal state, a target operation abnormal module is determined from the information recommendation service, where the target operation abnormal module is a module whose service module request processing time is greater than a module processing time threshold;

[0201] The module computing capacity is downgraded for the target module with abnormal operation in the information recommendation service.

[0202] Optionally, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0203] When the processor 901 determines the service processing strategy for the information recommendation service based on the service running state, it specifically performs the following steps:

[0204] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrent parameter amount is less than or equal to the concurrent parameter amount threshold, it is determined that the service operation status of the information recommendation service is an overloaded computing state.

[0205] Optionally, when the processor 901 determines the service processing strategy for the information recommendation service based on the service running state, the processor 901 specifically performs the following steps:

[0206] If the service operation status is an overloaded computing status, the system computing capacity of the information recommendation service will be downgraded.

[0207] Optionally, the performance indicator detection result includes a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result.

[0208] When the processor 901 determines the service running status of the information recommendation service based on the performance indicator detection result, it specifically performs the following steps:

[0209] When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is greater than the concurrency parameter amount threshold, it is determined that the service operation status of the information recommendation service is a concurrent overload state.

[0210] Optionally, when the processor 901 determines the service processing strategy for the information recommendation service based on the service running state, the processor 901 specifically performs the following steps:

[0211] If the service operation status is a concurrent overload state, the information recommendation request received by the information recommendation service is obtained, the priority level of the information recommendation request is determined based on a preset priority mapping relationship, and the information recommendation request received by the information recommendation service is graded, screened and limited based on the priority level of the information recommendation request.

[0212] Optionally, before obtaining the performance indicator value and the performance indicator threshold of the information recommendation service, the processor 901 further performs the following steps:

[0213] Obtaining a first request quantity value of information recommendation requests received by the information recommendation service within a unit time window, and if the first request quantity value is greater than or equal to a first preset request quantity value, executing the step of obtaining a performance indicator value and a performance indicator threshold value of the information recommendation service; and / or,

[0214] Obtaining a second request quantity value of information recommendation requests received by the information recommendation service within the statistical time window, and when the second request quantity value is greater than or equal to a second preset request quantity value, executing the step of obtaining a performance indicator value and a performance indicator threshold value of the information recommendation service;

[0215] When the statistical time window is smaller than the unit time window, the second preset request amount value is greater than the first preset request amount value.

[0216] Optionally, when the processor 901 executes the process of obtaining the information recommendation request processing time of the information recommendation service, the processor 901 specifically performs the following steps:

[0217] Obtain the request processing time corresponding to the information recommendation request processed by the information recommendation service within the unit time window, sort the request processing time based on the length of the request processing time, obtain the time ranking, determine the target request processing time at a preset proportion position in the time ranking, and determine the information recommendation request processing time based on the target request processing time;

[0218] When the processor 901 executes the process of obtaining the service concurrent parameter amount and concurrent parameter amount threshold of the information recommendation service, the processor 901 specifically executes the following steps:

[0219] Obtain the number of information recommendation requests received and not yet processed by the information recommendation service, and determine the service concurrency parameter quantity based on the number of information recommendation requests;

[0220] Determine, in at least two adjacent cycles, a maximum number of information recommendation requests processed by the information recommendation service within a unit time window of each cycle;

[0221] Determine time series information of at least two adjacent periods, determine a weighted parameter corresponding to the maximum quantity of each period based on the time series information, and determine a concurrent parameter quantity threshold based on the maximum quantity of each period and the weighted parameter corresponding to the maximum quantity.

[0222] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another service, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0223] The modules described as separate components may or may not be physically separated, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed on multiple network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0224] In addition, each functional module in each embodiment of the present application can be integrated into a processing module, or each module can exist physically separately, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software functional modules.

[0225] If the integrated module is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.

[0226] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present application are not limited by the described order of actions, because according to the embodiments of the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of the present application.

[0227] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0228] The above is a description of an information recommendation processing method, device, terminal and computer-readable storage medium provided in an embodiment of the present application. For technicians in this field, according to the ideas of the embodiments of the present application, there may be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the embodiments of the present application.

Claims

1. A method for information recommendation processing, wherein: The method comprises: Acquire a performance indicator value and a performance indicator threshold of the information recommendation service, and determine a performance indicator detection result based on the performance indicator value and the performance indicator threshold; The service operation status of the information recommendation service is determined based on the performance indicator detection result, and the service processing strategy for the information recommendation service is determined based on the service operation status.

2. The method according to claim 1, wherein: The obtaining of a performance indicator value and a performance indicator threshold of the information recommendation service, and determining a performance indicator detection result based on the performance indicator value and the performance indicator threshold, includes: Obtain the information recommendation request processing time and the request processing time threshold of the information recommendation service, and determine the first performance indicator detection result based on the information recommendation request processing time and the request processing time threshold; and / or, obtain the service module request processing time and the module processing time threshold of the information recommendation service, and determine the second performance indicator detection result based on the service module request processing time and the module processing time threshold; and / or, obtain the service concurrency parameter amount and the concurrency parameter amount threshold of the information recommendation service, and determine the third performance indicator detection result based on the service concurrency parameter amount and the concurrency parameter amount threshold; A performance indicator detection result is generated based on at least one of the first performance indicator detection result, the second performance indicator detection result, and the third performance indicator detection result.

3. The method according to claim 2, wherein: The performance indicator detection results include a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result, The determining the service operation status of the information recommendation service based on the performance indicator detection result includes: When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is greater than the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is less than or equal to the concurrency parameter amount threshold, it is determined that the service operation status of the information recommendation service is an abnormal module operation state.

4. The method according to claim 3, wherein: The determining of a service processing strategy for the information recommendation service based on the service running state includes: If the service operation state is a module operation abnormal state, determining a target operation abnormal module from the information recommendation service, the target operation abnormal module being a module whose service module request processing time is longer than the module processing time threshold; The module computing amount is downgraded for the target abnormal operation module in the information recommendation service.

5. The method according to claim 2, wherein: The performance indicator detection results include a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result, The determining of a service processing strategy for the information recommendation service based on the service running state includes: When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is less than or equal to the concurrency parameter amount threshold, it is determined that the service operation status of the information recommendation service is an overloaded computing state.

6. The method according to claim 5, wherein: The determining of a service processing strategy for the information recommendation service based on the service running state includes: If the service operation state is an overloaded computing state, the information recommendation service is subjected to a system computing capacity degradation process.

7. The method according to claim 2, wherein: The performance indicator detection results include a first performance indicator detection result, a second performance indicator detection result and a third performance indicator detection result, The determining the service operation status of the information recommendation service based on the performance indicator detection result includes: When the first performance indicator detection result is that the information recommendation request processing time is greater than the request processing time threshold, the second performance indicator detection result is that the service module request processing time is less than or equal to the module processing time threshold, and the third performance indicator detection result is that the service concurrency parameter amount is greater than the concurrency parameter amount threshold, it is determined that the service operation status of the information recommendation service is a concurrent overload state.

8. An information recommendation processing platform, wherein: The platform includes: An acquisition module, adapted to acquire a performance indicator value and a performance indicator threshold of an information recommendation service, and determine a performance indicator detection result based on the performance indicator value and the performance indicator threshold; The processing module is adapted to determine a service operation status of the information recommendation service based on the performance indicator detection result, and determine a service processing strategy for the information recommendation service based on the service operation status.

9. A terminal, wherein: The terminal includes: Processor; and A memory arranged to store computer executable instructions which, when executed, cause the processor to perform a method according to any one of claims 1 to 7.

10. A computer-readable storage medium, wherein: The computer-readable storage medium stores one or more programs, which, when executed by a processor, implement the method of any one of claims 1 to 7.

Images