CN115550259B - Flow distribution method based on white list and related equipment - Google Patents

Flow distribution method based on white list and related equipment Download PDF

Info

Publication number
CN115550259B
CN115550259B CN202211112187.5A CN202211112187A CN115550259B CN 115550259 B CN115550259 B CN 115550259B CN 202211112187 A CN202211112187 A CN 202211112187A CN 115550259 B CN115550259 B CN 115550259B
Authority
CN
China
Prior art keywords
interface
white list
score
flow
scoring
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202211112187.5A
Other languages
Chinese (zh)
Other versions
CN115550259A (en
Inventor
王旭东
王之唯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Ping An Bank Co Ltd
Original Assignee
Ping An Bank Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Ping An Bank Co Ltd filed Critical Ping An Bank Co Ltd
Priority to CN202211112187.5A priority Critical patent/CN115550259B/en
Publication of CN115550259A publication Critical patent/CN115550259A/en
Application granted granted Critical
Publication of CN115550259B publication Critical patent/CN115550259B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00—Traffic control in data switching networks
    • H04L47/10—Flow control; Congestion control
    • H04L47/29—Flow control; Congestion control using a combination of thresholds

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Data Mining & Analysis (AREA)
  • Databases & Information Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computational Linguistics (AREA)
  • Traffic Control Systems (AREA)

Abstract

The embodiment of the application provides a traffic distribution method based on a white list and related equipment. The traffic distribution method based on the white list comprises the following steps: responding to the entering of the flow, acquiring flow characteristic information, wherein the flow information comprises flow real-time characteristic information, historical characteristic information and historical record information; determining interface matching data according to the flow real-time characteristic information; determining a white list score according to the interface matching data, the history feature information and the history record information; and inquiring the white list according to the white list score, and determining the interface of the flow distribution. The technical scheme of the embodiment of the application determines whether the white list is in the white list according to the white list score, so that the white list can be flexibly and dynamically updated in real time, the maintenance pressure and cost are reduced, and the problem of high maintenance cost and poor timeliness of the white list in the prior art is solved.

Description

Flow distribution method based on white list and related equipment
Technical Field
The application relates to the technical field of computers and communication, in particular to a flow distribution method based on a white list and related equipment.
Background
In the field of computers, when gray level distribution is performed, a white list mode is generally adopted to distribute users to different interfaces. The method is simple and convenient, but the generation of the white list at present mostly depends on manual maintenance, and the maintenance and screening of metadata has relatively high cost. Metadata may be manually screened and confirmed from the current system, the current flow and the big data hive, and finally a white list is maintained, so that a great deal of manpower is wasted, and the white list is slow to update, low in timeliness and unable to adapt to complex and changeable environments.
Disclosure of Invention
The embodiment of the application provides a flow distribution method and related equipment based on a white list, which can further solve the problems of high maintenance cost and poor timeliness of the white list in the prior art at least to a certain extent.
Other features and advantages of the application will be apparent from the following detailed description, or may be learned by the practice of the application.
According to an aspect of the embodiment of the present application, there is provided a traffic distribution method based on a white list, including:
Responding to the entering of the flow, acquiring flow characteristic information, wherein the flow information comprises flow real-time characteristic information, historical characteristic information and historical record information;
Determining interface matching data according to the flow real-time characteristic information;
Determining a white list score according to the interface matching data, the history feature information and the history record information;
and inquiring the white list according to the white list score, and determining the interface of the flow distribution.
In one embodiment of the present application, a plurality of white list threshold intervals are stored in the white list, and the determining the interface of the traffic distribution by querying the white list according to the white list score specifically includes:
if the white list scores fall into a plurality of white list threshold intervals, distributing the flow to a first interface;
and if the white list scores do not fall into a plurality of white list threshold intervals, distributing the traffic to a second interface.
In one embodiment of the present application, before the querying a white list according to the white list score and determining the interface of the traffic distribution, the method further includes:
inquiring the first interface and the second interface to obtain interface index data;
determining the residual performance of the first interface and the residual performance of the second interface according to the interface index data
And determining the white list threshold interval according to the residual performance of the first interface and the residual performance of the second interface.
In one embodiment of the present application, the determining a white list score according to the interface matching data, the history feature information and the history record information specifically includes:
And inputting the interface matching data, the history characteristic information and the history record information into a white list scoring model, and outputting a white list score by the white list scoring model.
In one embodiment of the present application, the whitelist scoring model includes a first scoring sub-model, a second scoring sub-model, a third scoring sub-model, and a total scoring sub-model, and the inputting the interface matching data, the history feature information, and the history record information into the whitelist scoring model, where the whitelist scoring model outputs a whitelist score, specifically includes:
Inputting the interface matching data into a first scoring sub-model, and outputting a first score by the first scoring sub-model;
inputting the historical characteristic information into a second scoring sub-model, and outputting a second score by the second scoring sub-model;
inputting the history information into a third scoring sub-model, and outputting a third score by the third scoring sub-model;
obtaining a scoring vector group according to the first score, the second score and the third score;
and inputting the score component into a total score molecular model, and outputting a white list score by the total score molecular model.
In one embodiment of the present application, the inputting the interface matching data, the history feature information, and the history information into a whitelist scoring model, where the whitelist scoring model outputs a whitelist score specifically includes:
Obtaining a multidimensional scoring vector according to the interface matching data, the historical characteristic information and the historical record information;
and inputting the multidimensional scoring vector into a white list scoring model, and outputting white list scoring by the white list scoring model.
In one embodiment of the present application, the traffic real-time feature information includes the real-time user feature and the real-time non-user feature, the interface matching data includes a first interface matching value and a second interface matching value, and the determining the interface matching data according to the traffic real-time feature information specifically includes:
Determining the matching degree of the user and the first interface and the matching degree of the user and the second interface according to the real-time user characteristic information;
according to the real-time non-user characteristic information, determining the matching degree of the parameters of the flow and the first interface and the matching degree of the parameters of the flow and the second interface;
determining a first interface matching value according to the matching degree of the user and the first interface and the matching degree of the parameter of the flow and the first interface;
And determining a second interface matching value according to the matching degree of the user and the second interface and the matching degree of the parameter of the flow and the second interface.
According to an aspect of the embodiment of the present application, there is provided a traffic distribution device based on a white list, including:
The characteristic information acquisition module is used for responding to the entering of the flow and acquiring flow characteristic information, wherein the flow information comprises flow real-time characteristic information, historical characteristic information and historical record information;
the interface data matching module is used for determining interface matching data according to the flow real-time characteristic information;
The white list scoring module is used for determining white list scoring according to the interface matching data, the historical characteristic information and the historical record information;
And the interface flow distribution module is used for inquiring the white list according to the white list score and determining the flow distribution interface.
According to an aspect of the embodiments of the present application, there is provided a computer readable medium having stored thereon a computer program which, when executed by a processor, implements a whitelist based traffic distribution method as described in the above embodiments.
According to an aspect of an embodiment of the present application, there is provided an electronic apparatus including: one or more processors; and a storage means for storing one or more programs that, when executed by the one or more processors, cause the one or more processors to implement the whitelist-based traffic distribution method as described in the above embodiments.
In the technical scheme provided by some embodiments of the application, the matching degree of the flow and each interface is determined according to the flow real-time characteristic information, the preference of the user is analyzed according to the historical behaviors such as historical decision history access and the matching degree of the flow and each interface, the white list score is finally determined, and then whether the white list is in the white list is determined according to the white list score, so that the white list can be flexibly and dynamically updated in real time, the maintenance pressure and cost are reduced, and the problem of high timeliness of the white list maintenance cost in the prior art is solved.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. It is evident that the drawings in the following description are only some embodiments of the present application and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art. In the drawings:
Fig. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of an embodiment of the present application may be applied.
Fig. 2 schematically shows a flow chart of an interface traffic allocation method according to an embodiment of the application.
Fig. 3 is a flowchart showing a specific implementation of step 200 in the interface traffic allocation method according to the corresponding embodiment of fig. 2.
Fig. 4 is a flowchart of a specific implementation of step S300 in the interface traffic allocation method according to the corresponding embodiment of fig. 2.
Fig. 5 is a flowchart of a specific implementation of step S400 in the interface traffic allocation method according to the corresponding embodiment of fig. 2.
Fig. 6 is a flowchart of still another implementation of the interface traffic allocation method according to the corresponding embodiment of fig. 2.
Fig. 7 schematically shows a block diagram of an interface traffic distribution device according to an embodiment of the application.
Fig. 8 shows the structure of a computer system suitable for use in implementing the electronic device of the embodiment of the application.
Detailed Description
Example embodiments will now be described more fully with reference to the accompanying drawings. However, the exemplary embodiments may be embodied in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art.
Furthermore, the described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to give a thorough understanding of embodiments of the application. One skilled in the relevant art will recognize, however, that the application may be practiced without one or more of the specific details, or with other methods, components, devices, steps, etc. In other instances, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the application.
The block diagrams depicted in the figures are merely functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The flow diagrams depicted in the figures are exemplary only, and do not necessarily include all of the elements and operations/steps, nor must they be performed in the order described. For example, some operations/steps may be decomposed, and some operations/steps may be combined or partially combined, so that the order of actual execution may be changed according to actual situations.
Fig. 1 shows a schematic diagram of an exemplary system architecture to which the technical solution of an embodiment of the present application may be applied.
As shown in fig. 1, the system architecture may include a terminal device (such as one or more of the smartphone 101, tablet 102, and portable computer 103 shown in fig. 1, but of course, a desktop computer, etc.), a network 104, and a server 105. The network 104 is the medium used to provide communication links between the terminal devices and the server 105. The network 104 may include various connection types, such as wired communication links, wireless communication links, and the like.
It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation. For example, the server 105 may be a server cluster formed by a plurality of servers.
A user may interact with the server 105 via the network 104 using a terminal device to receive or send messages or the like. The server 105 may be a server providing various services. For example, the user uploads the traffic characteristic information to the server 105 by using the terminal device 103 (may also be the terminal device 101 or 102), and the server 105 may obtain the traffic characteristic information in response to the entry of the traffic, where the traffic characteristic information includes traffic real-time characteristic information, history characteristic information, and history record information; determining interface matching data according to the flow real-time characteristic information; determining a white list score according to the interface matching data, the history feature information and the history record information; and inquiring the white list according to the white list score, and determining the interface of the flow distribution.
It should be noted that, the flow allocation method based on the white list provided in the embodiment of the present application is generally executed by the server 105, and accordingly, the flow allocation device based on the white list is generally disposed in the server 105. However, in other embodiments of the present application, the terminal device may also have a similar function as the server, so as to execute the whitelist-based traffic allocation scheme provided by the embodiments of the present application.
The implementation details of the technical scheme of the embodiment of the application are described in detail below:
Fig. 2 illustrates a flow chart of a whitelist-based traffic allocation method, which may be performed by a server, which may be the server illustrated in fig. 1, according to one embodiment of the present application. Referring to fig. 2, the traffic distribution method based on the white list at least includes:
and step S100, responding to the entering of the flow, and acquiring flow characteristic information, wherein the flow information comprises flow real-time characteristic information, history characteristic information and history record information.
And step 200, determining interface matching data according to the flow real-time characteristic information.
And step S300, determining a white list score according to the interface matching data, the history characteristic information and the history record information.
Step S400, inquiring a white list according to the white list score, and determining the interface of flow distribution.
In this embodiment, in response to the entering of the flow, the flow feature information is acquired first, then, according to the real-time feature information in the flow feature information, the interface matching data of the flow, that is, the matching degree of the flow and the first interface and the second interface is determined, a white list score is given according to the interface matching data, the history feature information and the plurality of dimensions of the history record information, preferably, the white list is queried, whether the white list score is on the white list is determined, and the allocated interface is determined according to the white list score. The white list of the embodiment of the application is in a fractional form, so that the white list can be flexibly and dynamically updated in real time, the maintenance pressure and cost are reduced, and the problem of high maintenance cost and poor timeliness of the white list in the prior art is solved.
In step S100, the flow characteristic information has multiple dimensions, which may include dimensions of real-time characteristic information, history access information, and the like, and the more dimensions, the more accurate the flow distribution. Traffic characteristic information for different dimensions may be obtained from different sources, e.g. from traffic in real time, from a local database or from a network database.
The traffic real-time features comprise traffic real-time user features and traffic real-time non-user features, the traffic real-time user features can comprise user information, trusted information and the like, the traffic real-time non-user features can comprise terminal positioning data, service parameters, access page and the like, and the traffic real-time features can be directly obtained from traffic.
The historical characteristic information comprises traffic data of previous decisions, data of results of previous decisions and the like, which are generally stored locally, so that the historical characteristic information can be obtained from a local database.
The history information includes the number of accesses to each interface, the frequency of accesses, the time of accesses, etc., which are typically stored in the network, so that they can be obtained from the network database.
In step S200, the interface matching data determined according to the real-time feature in the traffic may reflect whether the traffic is suitable for being allocated to the first interface and whether it is suitable for being allocated to the second interface, and whether it is more suitable for being allocated to the first interface or the second interface. In an embodiment of the present application, the interface matching data is one of the important indicators for deciding to which interface the traffic is allocated.
Specifically, in some embodiments, the specific implementation of step S200 may refer to fig. 3. Fig. 3 is a detailed description of step S200 in the interface traffic distribution method according to the corresponding embodiment of fig. 2, where the real-time feature of the traffic includes the real-time user feature of the traffic and the real-time non-user feature of the traffic, and the interface matching data includes a first interface matching value and a second interface matching value, and step S200 may include the following steps:
Step S210, determining a matching degree between the user and the first interface and a matching degree between the user and the second interface according to the real-time user feature information.
Step S220, determining a matching degree of the parameter of the flow and the first interface and a matching degree of the parameter of the flow and the second interface according to the real-time non-user feature information.
Step S230, determining a first interface matching value according to the matching degree of the user and the first interface and the matching degree of the parameter of the flow and the first interface.
And step S240, determining a second interface matching value according to the matching degree of the user and the second interface and the matching degree of the parameter of the flow and the second interface.
In this embodiment, the real-time features of the flow include a real-time user feature and a real-time non-user feature, where the real-time user feature may be used to determine a degree of matching between a user and each interface, the real-time non-user feature may determine a degree of matching between a parameter of the current flow and each interface, and may determine a degree of matching between the current flow and each interface, that is, interface matching data, according to the degree of matching between the user and each interface and the degree of matching between the parameter of the current flow and each interface.
In step S210, the real-time user characteristics may be used to determine the degree of matching of the user with the interfaces.
Specifically, in some embodiments, the method for determining the matching degree of the user and each interface may be to perform user portrait according to the real-time user characteristic information in the traffic, and then determine the matching degree of the user and the first interface and the matching degree of the user and the second interface according to the user portrait.
In other embodiments, determining the degree of matching between the user and each interface may also rely on a scoring model, where real-time user characteristic information is input into a user-interface scoring model, which outputs the degree of matching between the user and the first interface and the degree of matching between the user and the second interface.
Specifically, the training method of the user-interface scoring model specifically includes: acquiring a real-time user characteristic information sample set, wherein each real-time user characteristic information sample is calibrated in advance to match the corresponding user with the first interface and match the corresponding user with the second interface; respectively inputting the data of each real-time user characteristic information sample into a user-interface scoring model to obtain the matching degree of the user and the first interface and the matching degree of the user and the second interface output by the flow strategy; if the matching degree of the user and the first interface and the matching degree of the user and the second interface, which are obtained after the data of the real-time user characteristic information sample are input into the user-interface scoring model, are inconsistent with the matching degree of the user and the first interface and the matching degree of the user and the second interface, which are calibrated in advance for the real-time user characteristic information sample, the coefficients of the flow strategy are adjusted until the coefficients are consistent; after the data of all the real-time user characteristic information samples are input into a user-interface scoring model, the obtained matching degree of the user and the first interface and the matching degree of the user and the second interface are consistent with the matching degree of the user and the first interface and the matching degree of the user and the second interface which are calibrated in advance for the real-time user characteristic information samples, and training is finished.
In step S220, the real-time non-user feature may determine the degree of matching of the parameters of the current flow with the interfaces.
Specifically, in some embodiments, the manner of determining the matching degree of the user and each interface may be to determine the behavior preference and the data format according to the real-time non-user feature information in the traffic, and then determine the matching degree of the parameter of the traffic and the first interface and the matching degree of the parameter of the traffic and the second interface according to the behavior preference and the data format.
In other embodiments, determining the matching degree of the flow parameter and each interface may also rely on a scoring model, where real-time non-user feature information is input into a flow parameter-interface scoring model, where the flow parameter-interface scoring model outputs the matching degree of the flow parameter and the first interface and the matching degree of the flow parameter and the second interface.
Specifically, the training method of the flow parameter-interface scoring model specifically includes: acquiring a real-time non-user characteristic information sample set, wherein each real-time non-user characteristic information sample is calibrated in advance to match the corresponding flow parameter with the first interface and to match the flow parameter with the second interface; inputting the data of each real-time non-user characteristic information sample into a flow parameter-interface scoring model respectively to obtain the matching degree of the flow parameter output by the flow strategy and the first interface and the matching degree of the flow parameter and the second interface; if the data of the real-time non-user characteristic information sample is input into a flow parameter-interface scoring model, the obtained matching degree of the flow parameter and the first interface and the matching degree of the flow parameter and the second interface are inconsistent with the matching degree of the flow parameter and the first interface and the matching degree of the flow parameter and the second interface which are calibrated in advance for the real-time non-user characteristic information sample, and then the coefficients of the flow strategy are adjusted until the parameters are consistent; after the data of all the real-time non-user characteristic information samples are input into a flow parameter-interface scoring model, the obtained matching degree of the flow parameter and the first interface and the matching degree of the flow parameter and the second interface are consistent, and training is finished.
In step S230, the matching degree of the current flow and the first interface is reflected by the first interface matching value, and the manner of determining the first interface matching value may be to sum, average, weight sum and weight average the matching degree of the user and the first interface and the matching degree of the parameter of the flow and the first interface, and take the calculation result as the first interface matching value; or, by comparing the matching degree of the user and the first interface with the matching degree of the parameter of the flow and the first interface, selecting one of them as the matching value of the first interface; and the first interface matching value can be obtained by assigning the matching degree of the user and the first interface and the matching degree of the parameter of the flow and the first interface.
In step S240, the second interface matching value reflects the matching degree of the current flow and the second interface, and the manner of determining the second interface matching value may be to sum, average, weight sum and weight average the matching degree of the user and the second interface and the matching degree of the parameter of the flow and the second interface, and take the calculation result as the second interface matching value; or, by comparing the matching degree of the user and the second interface with the matching degree of the parameter of the flow and the second interface, selecting one of them as the matching value of the second interface; and the second interface matching value can be obtained by assigning the matching degree of the user and the second interface and the matching degree of the parameter of the flow and the second interface.
Specifically, in other embodiments, the following embodiments may be referred to for specific implementation of step S200. The embodiment is a detailed description of step S200 in the interface traffic distribution method according to the corresponding embodiment shown in fig. 2, where step S200 may include the following steps:
and inputting the real-time characteristics of the flow into an interface matching model, and outputting interface matching data by the interface matching model.
Specifically, the implementation steps may be that a multi-dimensional real-time feature vector is generated according to the real-time feature of the flow, and then the multi-dimensional real-time feature vector is input into an interface matching model, and the interface matching model outputs interface matching data.
Specifically, the training method of the interface matching model specifically includes: acquiring a real-time feature vector sample set, wherein each real-time feature vector sample is calibrated with corresponding interface matching data in advance; respectively inputting the data of each real-time feature vector sample into an interface matching model to obtain interface matching data output by the flow strategy; if the interface matching data obtained after the data of the real-time feature vector sample is input into the interface matching model is inconsistent with the interface matching data calibrated in advance for the real-time feature vector sample, adjusting the coefficient of the flow strategy until the coefficients are consistent; after the data of all the real-time feature vector samples are input into the interface matching model, the obtained interface matching data are consistent with the interface matching data calibrated in advance for the real-time feature vector samples, and training is finished.
In step S300, the white list score may be obtained in various manners, and may be obtained through a machine school model, or the history feature information and the history record information may be preprocessed to obtain history parameters, and then the history parameters and the interface matching data may be calculated to obtain the white list score.
In some embodiments, the specific real-time manner of step S300 may include:
And inputting the interface matching data, the history characteristic information and the history record information into a white list scoring model, and outputting a white list score by the white list scoring model.
In this embodiment, the white list score is obtained through a white list score model, and the specific real-time manner may be referred to the following embodiments.
Specifically, in some embodiments, the specific implementation of step S300 may refer to fig. 4. Fig. 4 is a detailed description of step S300 in the flow allocation method based on the white list according to the corresponding embodiment of fig. 2, where the white list scoring model includes a first scoring sub-model, a second scoring sub-model, a third scoring sub-model, and a total scoring sub-model, and step S300 may include the following steps:
step S310, inputting the interface matching data into a first scoring sub-model, and outputting a first score by the first scoring sub-model.
Step S320, inputting the history feature information into a second scoring sub-model, and outputting a second score by the second scoring sub-model.
Step S330, inputting the history information into a third scoring sub-model, and outputting a third score by the third scoring sub-model.
And step 340, obtaining a scoring vector group according to the first score, the second score and the third score.
And step S350, inputting the score group into a total score sub-model, and outputting a white list score by the total score sub-model.
In this embodiment, the above-mentioned white list scoring model includes a plurality of scoring sub-models, which are a first scoring sub-model, a second scoring sub-model, a third scoring sub-model, and a total scoring sub-model, respectively. In the embodiment, the scores are scored according to the data of different dimensionalities through a plurality of scoring sub-models, and then the scores of the different scoring sub-models are collected in an arrangement mode to obtain the white list score.
In step S310, a first score is derived based on the interface matching data, which may generally characterize the matching of the current traffic to both interfaces.
In step S320, a second score is derived based on the historical characteristic information, which may be used to characterize the historical decision preference level.
In step S330, a third score is derived based on the history information, which may characterize the degree of preference for both interfaces.
In step S340, the first score, the second score, and the third score are packaged into a score vector set, which may be in a form including a score value and a corresponding dimension marker, and in step S350, the total score model may determine a dimension from which the score value is derived according to the corresponding dimension marker.
The training method of the first scoring model specifically comprises the following steps: acquiring an interface matching data set, wherein each interface matching data is calibrated with a corresponding first score in advance; respectively inputting the data of each interface matching data into a first scoring model to obtain a first score of the screening output; if the data of the interface matching data are input into a first scoring model, the obtained first scoring is inconsistent with the first scoring calibrated in advance for the interface matching data, and the coefficients of the first scoring model are adjusted until the first scoring is consistent with the first scoring; after the data of all the interface matching data are input into the first scoring model, the obtained first score is consistent with the first score calibrated in advance for the interface matching data, and training is finished.
The training method of the second scoring model specifically comprises the following steps: acquiring a historical characteristic information sample set, wherein each historical characteristic information sample is calibrated with a corresponding second score in advance; respectively inputting the data of each historical characteristic information sample into a second scoring model to obtain a second score of the screening output; if the data of the historical characteristic information sample are input into a second scoring model, the obtained second score is inconsistent with a second score calibrated in advance for the historical characteristic information sample, and the coefficients of the second scoring model are adjusted until the second score is consistent with the second score; and after the data of all the historical characteristic information samples are input into a second scoring model, the obtained second score is consistent with the second score calibrated in advance for the historical characteristic information samples, and training is finished.
The training method of the third scoring sub-model specifically comprises the following steps: acquiring a history information sample set, wherein each history information sample is calibrated with a corresponding third score in advance; respectively inputting the data of each history information sample into a third scoring sub-model to obtain a third score of the screening output; if the data of the historical record information sample are input into a third scoring sub-model, and the obtained third score is inconsistent with a third score calibrated in advance for the historical record information sample, adjusting the coefficient of the third scoring sub-model until the third score is consistent with the third score; and after the data of all the historical record information samples are input into a third scoring sub-model, the obtained third score is consistent with the third score calibrated in advance for the historical record information samples, and training is finished.
The training method of the general evaluation molecular model specifically comprises the following steps: obtaining a scoring vector group sample set, wherein each scoring vector group sample is calibrated with a corresponding white list score in advance; respectively inputting the data of each score group sample into a total score model to obtain the white list scores of the screening output; if the obtained white list score is inconsistent with the white list score calibrated in advance for the score vector group sample after the data of the score vector group sample are input into the total score sub-model, adjusting the coefficient of the total score sub-model until the obtained white list score is consistent with the white list score calibrated in advance for the score vector group sample; and after the data of all the score group samples are input into the total score molecular model, the obtained white list score is consistent with the white list score calibrated in advance for the score group samples, and the training is finished.
Specifically, in other embodiments, the following embodiments may be referred to for specific implementation of step S300. The present embodiment is a detailed description of step S300 in the traffic distribution method based on the white list according to the corresponding embodiment of fig. 2, where step S300 may include the following steps:
And obtaining a multidimensional scoring vector according to the interface matching data, the historical characteristic information and the historical record information.
And inputting the multidimensional scoring vector into a white list scoring model, and outputting white list scoring by the white list scoring model.
In this embodiment, the information including the interface matching data, the history feature information and the history record information in multiple dimensions is integrated and carded to obtain a multidimensional scoring vector, where the multidimensional scoring vector is a multidimensional vector, and each vector dimension includes information of one dimension. And then inputting the multidimensional grading vector into a white list grading model, and comprehensively grading the white list grading model through each vector dimension in the white list grading vector to obtain the white list grading. The white list score may characterize how well the current traffic matches the two interfaces when the white list is being used for allocation and how well the current traffic matches the white list.
The training method of the white list scoring model specifically comprises the following steps: and acquiring a multi-dimensional scoring vector sample set, wherein each multi-dimensional scoring vector sample is calibrated with a corresponding white list score in advance. And respectively inputting the data of each multidimensional scoring vector sample into a white list scoring model to obtain the white list scoring output by screening. And if the obtained white list score is inconsistent with the white list score calibrated in advance for the multidimensional scoring vector sample after the data of the multidimensional scoring vector sample are input into the white list scoring model, adjusting the coefficient of the white list scoring model until the obtained white list score is consistent with the white list score calibrated in advance for the multidimensional scoring vector sample. And after the data of all the multidimensional grading vector samples are input into a white list grading model, the obtained white list grading is consistent with the white list grading calibrated in advance for the multidimensional grading vector samples, and the training is finished.
In step S400, after obtaining the score of the white list, the white list may be queried to determine whether the score is in the white list, and based on the score, the traffic is distributed to the first interface or the second interface.
Specifically, in some embodiments, the specific implementation of step S400 may refer to fig. 5. Fig. 5 is a detailed description of step S400 in the traffic distribution method based on the white list according to the corresponding embodiment of fig. 2, where a plurality of white list threshold intervals are stored in the white list, step S400 may include the following steps:
Step S410, if the white list score falls into a plurality of white list threshold intervals, the traffic is allocated to the first interface.
Step S420, if the white list score does not fall into a plurality of white list threshold intervals, the traffic is distributed to a second interface.
In this embodiment, a plurality of white list threshold intervals are stored in the white list, and when the white list score falls into the threshold intervals, it is proved that the flow corresponding to the white list score can be distributed to the first interface of the updated environment; when the white list score does not fall into the threshold intervals, the traffic corresponding to the white list score is proved to be not distributed to the first interface flowing to the updated environment and only distributed to the second interface flowing to the pre-updated environment.
Referring to fig. 6, in some embodiments, before step S400, the method further includes:
step S500, inquiring the first interface and the second interface to obtain interface index data.
And step S600, determining the residual performance of the first interface and the residual performance of the second interface according to the interface index data.
Step S700, determining the white list threshold interval according to the remaining performance of the first interface and the remaining performance of the second interface.
In this embodiment, a plurality of whitelist threshold intervals stored in the whitelist may be flexibly adjusted according to the performance of each interface, so as to determine the whitelist threshold interval, realize the regulation and control of the traffic of the interfaces in a complex environment, and avoid traffic congestion into a single interface, which results in interface blockage and affects the data processing efficiency.
The following describes an embodiment of the apparatus of the present application, which may be used to perform the whitelist-based traffic allocation method in the above embodiment of the present application. For details not disclosed in the embodiment of the apparatus of the present application, please refer to the embodiment of the flow distribution method based on the white list.
Fig. 7 shows a block diagram of a whitelist-based flow distribution device according to one embodiment of the application.
Referring to fig. 7, a whitelist-based traffic distribution apparatus 900 according to an embodiment of the present application includes:
A feature information obtaining module 910, configured to obtain flow feature information in response to an entry of a flow, where the flow feature information includes flow real-time feature information, history feature information, and history record information;
an interface data matching module 920, configured to determine interface matching data according to the flow real-time feature information;
A whitelist scoring module 930 configured to determine a whitelist score according to the interface matching data, the history feature information, and the history record information;
and the interface flow distribution module 940 is configured to query a white list according to the score of the white list and determine the interface of the flow distribution.
The implementation process of the functions and roles of each module in the above device is specifically detailed in the implementation process of the corresponding steps in the flow distribution method based on the white list, and will not be described herein again.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functionality of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the present disclosure. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
Furthermore, although the steps of the methods in the present disclosure are depicted in a particular order in the drawings, this does not require or imply that the steps must be performed in that particular order, or that all illustrated steps be performed, to achieve desirable results. Additionally or alternatively, certain steps may be omitted, multiple steps combined into one step to perform, and/or one step decomposed into multiple steps to perform, etc.
Fig. 8 shows a schematic diagram of a computer system suitable for use in implementing an embodiment of the application.
It should be noted that, the computer system of the electronic device shown in fig. 8 is only an example, and should not impose any limitation on the functions and the application scope of the embodiments of the present application.
As shown in fig. 8, the computer system includes a central processing unit (Central Processing Unit, CPU) 1801, which can perform various appropriate actions and processes, such as performing the methods described in the above embodiments, according to a program stored in a Read-Only Memory (ROM) 1802 or a program loaded from a storage portion 1808 into a random access Memory (Random Access Memory, RAM) 1803. In the RAM 1803, various programs and data required for system operation are also stored. The CPU 1801, ROM 1802, and RAM 1803 are connected to each other via a bus 1804. An Input/Output (I/O) interface 1805 is also connected to the bus 1804.
The following components are connected to the I/O interface 1805: an input section 1806 including a keyboard, a mouse, and the like; an output portion 1807 including a Cathode Ray Tube (CRT), a Liquid crystal display (Liquid CRYSTAL DISPLAY, LCD), and a speaker, etc.; a storage section 1808 including a hard disk or the like; and a communication section 1809 including a network interface card such as a LAN (Local Area Network ) card, a modem, or the like. The communication section 1809 performs communication processing via a network such as the internet. The drive 1810 is also connected to the I/O interface 1805 as needed. Removable media 1811, such as magnetic disks, optical disks, magneto-optical disks, semiconductor memory, and the like, is installed as needed on drive 1810 so that a computer program read therefrom is installed as needed into storage portion 1808.
In particular, according to embodiments of the present application, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present application include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising a computer program for performing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from a network via the communication portion 1809, and/or installed from the removable medium 1811. When executed by a Central Processing Unit (CPU) 1801, performs various functions defined in the system of the present application.
It should be noted that, the computer readable medium shown in the embodiments of the present application may be a computer readable signal medium or a computer readable storage medium, or any combination of the two. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-Only Memory (ROM), an erasable programmable read-Only Memory (Erasable Programmable Read Only Memory, EPROM), a flash Memory, an optical fiber, a portable compact disc read-Only Memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with a computer-readable computer program embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. A computer program embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. Where each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
The units involved in the embodiments of the present application may be implemented by software, or may be implemented by hardware, and the described units may also be provided in a processor. Wherein the names of the units do not constitute a limitation of the units themselves in some cases.
As another aspect, the present application also provides a computer-readable medium that may be contained in the electronic device described in the above embodiment; or may exist alone without being incorporated into the electronic device. The computer-readable medium carries one or more programs which, when executed by the electronic device, cause the electronic device to implement the methods described in the above embodiments.
It should be noted that although in the above detailed description several modules or units of a device for action execution are mentioned, such a division is not mandatory. Indeed, the features and functions of two or more modules or units described above may be embodied in one module or unit in accordance with embodiments of the application. Conversely, the features and functions of one module or unit described above may be further divided into a plurality of modules or units to be embodied.
From the above description of embodiments, those skilled in the art will readily appreciate that the example embodiments described herein may be implemented in software, or may be implemented in software in combination with the necessary hardware. Thus, the technical solution according to the embodiments of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.) or on a network, and includes several instructions to cause a computing device (may be a personal computer, a server, a touch terminal, or a network device, etc.) to perform the method according to the embodiments of the present application.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.

Claims (9)

1. The traffic distribution method based on the white list is characterized by comprising the following steps:
Responding to the entering of the flow, acquiring flow characteristic information, wherein the flow characteristic information comprises flow real-time characteristic information, historical characteristic information and historical record information, and the flow real-time characteristic information comprises real-time user characteristics and real-time non-user characteristics;
Determining the matching degree of the user and the first interface and the matching degree of the user and the second interface according to the real-time user characteristic information;
according to the real-time non-user characteristic information, determining the matching degree of the parameters of the flow and the first interface and the matching degree of the parameters of the flow and the second interface;
determining a first interface matching value according to the matching degree of the user and the first interface and the matching degree of the parameter of the flow and the first interface;
Determining a second interface matching value according to the matching degree of the user and the second interface and the matching degree of the parameter of the flow and the second interface, wherein interface matching data comprise the first interface matching value and the second interface matching value;
Determining a white list score according to the interface matching data, the history feature information and the history record information;
and inquiring the white list according to the white list score, and determining the interface of the flow distribution.
2. The traffic distribution method based on the white list as recited in claim 1, wherein a plurality of white list threshold intervals are stored in the white list, and the interface for traffic distribution is determined by querying the white list according to the white list score, which specifically includes:
if the white list scores fall into a plurality of white list threshold intervals, distributing the flow to a first interface;
and if the white list scores do not fall into a plurality of white list threshold intervals, distributing the traffic to a second interface.
3. The whitelist-based traffic distribution method of claim 2, wherein prior to said querying a whitelist for said traffic distribution interface based on said whitelist score, said method further comprises:
inquiring the first interface and the second interface to obtain interface index data;
determining the residual performance of the first interface and the residual performance of the second interface according to the interface index data;
And determining the white list threshold interval according to the residual performance of the first interface and the residual performance of the second interface.
4. The traffic distribution method according to claim 1, wherein determining a white list score according to the interface matching data, the history feature information, and the history record information specifically includes:
And inputting the interface matching data, the history characteristic information and the history record information into a white list scoring model, and outputting a white list score by the white list scoring model.
5. The traffic distribution method according to claim 4, wherein the whitelist scoring model includes a first scoring sub-model, a second scoring sub-model, a third scoring sub-model, and a total scoring sub-model, the inputting the interface matching data, the history feature information, and the history record information into the whitelist scoring model, the whitelist scoring model outputting a whitelist score, specifically comprising:
Inputting the interface matching data into a first scoring sub-model, and outputting a first score by the first scoring sub-model;
inputting the historical characteristic information into a second scoring sub-model, and outputting a second score by the second scoring sub-model;
inputting the history information into a third scoring sub-model, and outputting a third score by the third scoring sub-model;
obtaining a scoring vector group according to the first score, the second score and the third score;
and inputting the score component into a total score molecular model, and outputting a white list score by the total score molecular model.
6. The traffic distribution method according to claim 4, wherein the inputting the interface matching data, the history feature information, and the history information into a whitelist scoring model, the whitelist scoring model outputting a whitelist score, specifically comprises:
Obtaining a multidimensional scoring vector according to the interface matching data, the historical characteristic information and the historical record information;
and inputting the multidimensional scoring vector into a white list scoring model, and outputting white list scoring by the white list scoring model.
7. A whitelist-based traffic distribution device, the whitelist-based traffic distribution device comprising:
The system comprises a characteristic information acquisition module, a characteristic information processing module and a traffic information processing module, wherein the characteristic information acquisition module is used for responding to the entering of traffic and acquiring traffic characteristic information, the traffic characteristic information comprises traffic real-time characteristic information, historical characteristic information and historical record information, and the traffic real-time characteristic information comprises real-time user characteristics and real-time non-user characteristics;
The interface data matching module is used for determining the matching degree of the user and the first interface and the matching degree of the user and the second interface according to the real-time user characteristic information;
according to the real-time non-user characteristic information, determining the matching degree of the parameters of the flow and the first interface and the matching degree of the parameters of the flow and the second interface;
determining a first interface matching value according to the matching degree of the user and the first interface and the matching degree of the parameter of the flow and the first interface;
Determining a second interface matching value according to the matching degree of the user and the second interface and the matching degree of the parameter of the flow and the second interface, wherein interface matching data comprise the first interface matching value and the second interface matching value;
The white list scoring module is used for determining white list scoring according to the interface matching data, the historical characteristic information and the historical record information;
And the interface flow distribution module is used for inquiring the white list according to the white list score and determining the flow distribution interface.
8. A computer readable medium on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the whitelist based traffic distribution method according to any of claims 1 to 6.
9. An electronic device, comprising:
one or more processors;
Storage means for storing one or more programs which when executed by the one or more processors cause the one or more processors to implement the whitelist-based traffic allocation method of any one of claims 1 to 6.
CN202211112187.5A 2022-09-13 2022-09-13 Flow distribution method based on white list and related equipment Active CN115550259B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211112187.5A CN115550259B (en) 2022-09-13 2022-09-13 Flow distribution method based on white list and related equipment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211112187.5A CN115550259B (en) 2022-09-13 2022-09-13 Flow distribution method based on white list and related equipment

Publications (2)

Publication Number Publication Date
CN115550259A CN115550259A (en) 2022-12-30
CN115550259B true CN115550259B (en) 2024-05-14

Family

ID=84727387

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211112187.5A Active CN115550259B (en) 2022-09-13 2022-09-13 Flow distribution method based on white list and related equipment

Country Status (1)

Country Link
CN (1) CN115550259B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108243271A (en) * 2016-12-23 2018-07-03 北京安云世纪科技有限公司 A kind of method, apparatus for carrying out flow control and mobile equipment
CN110049022A (en) * 2019-03-27 2019-07-23 深圳市腾讯计算机系统有限公司 A kind of domain name access control method, device and computer readable storage medium
CN112966968A (en) * 2021-03-26 2021-06-15 平安科技（深圳）有限公司 List distribution method based on artificial intelligence and related equipment
CN113992525A (en) * 2021-10-12 2022-01-28 支付宝(杭州)信息技术有限公司 Method and device for adjusting number of applied containers

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108243271A (en) * 2016-12-23 2018-07-03 北京安云世纪科技有限公司 A kind of method, apparatus for carrying out flow control and mobile equipment
CN110049022A (en) * 2019-03-27 2019-07-23 深圳市腾讯计算机系统有限公司 A kind of domain name access control method, device and computer readable storage medium
CN112966968A (en) * 2021-03-26 2021-06-15 平安科技（深圳）有限公司 List distribution method based on artificial intelligence and related equipment
CN113992525A (en) * 2021-10-12 2022-01-28 支付宝(杭州)信息技术有限公司 Method and device for adjusting number of applied containers

Also Published As

Publication number Publication date
CN115550259A (en) 2022-12-30

Similar Documents

Publication Publication Date Title
CN110309142B (en) Method and device for rule management
CN107291835B (en) Search term recommendation method and device
CN104573127B (en) Assess the method and system of data variance
CN112231299B (en) Method and device for dynamically adjusting feature library
CN115550259B (en) Flow distribution method based on white list and related equipment
CN116485019A (en) Data processing method and device
CN115545753A (en) Partner prediction method based on Bayesian algorithm and related equipment
CN115543428A (en) Simulated data generation method and device based on strategy template
CN115147183A (en) Chip resource management method, device, equipment and storage medium based on cloud platform
CN116933189A (en) Data detection method and device
CN116703046A (en) Control method and system for real-time dispatching sequence, electronic equipment and storage medium
CN113554307A (en) RFM (recursive filter) model-based user grouping method and device and readable medium
CN112906723A (en) Feature selection method and device
CN111768220A (en) Method and apparatus for generating vehicle pricing models
CN113362097B (en) User determination method and device
CN114722061B (en) Data processing method and device, equipment and computer readable storage medium
CN113762521B (en) Method and system for determining target object
CN115329280A (en) Data screening method, device, equipment and medium
CN115529281A (en) Flow distribution method and related equipment
CN115567406A (en) Method, device and system for managing network nodes
CN115543651A (en) Stream message interface distribution method and related equipment
CN115550270A (en) Interface flow distribution method and related equipment
CN117271126A (en) Task request distribution method and device and electronic equipment
CN114998029A (en) Model calibration method and device, electronic equipment and computer readable medium
CN111985511A (en) Method and device for realizing task classification

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant