CN116307697A

CN116307697A - Business wind control method and device, storage medium and electronic equipment

Info

Publication number: CN116307697A
Application number: CN202310119410.7A
Authority: CN
Inventors: 郑行; 孙清清; 袁始股; 吴歌; 张天翼
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2023-01-17
Filing date: 2023-01-17
Publication date: 2023-06-23

Abstract

The embodiment of the specification determines each candidate wind control strategy and wind control target used in a target service scene based on a strategy adjustment request after receiving the strategy adjustment request aiming at the target service scene. And selecting the target strategy from the candidate wind control strategies based on wind control records counted when the wind control is performed on the service in the target service scene by adopting the selected wind control strategy, deploying the target strategy, and executing the service wind control through the target strategy when a service request aiming at the target service scene is received. In the method, the manpower cost is reduced and the configuration efficiency of the wind control strategy is improved by automatically selecting the wind control strategy, and the selected wind control strategy is ensured to meet the actual wind control requirement by using the historical wind control record.

Description

Business wind control method and device, storage medium and electronic equipment

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a service wind control method, a device, a storage medium, and an electronic apparatus.

Background

In the wind control business, for payment scenes such as e-commerce transactions, domestic and foreign transactions and the like, a wind control system needs to configure different wind control strategies for different business scenes so as to meet different wind control requirements.

In the prior art, a manual mode is generally adopted to set wind control strategies meeting the wind control requirements of different business scenes, however, the mode needs to consume a great deal of labor cost, the efficiency is low, and the set wind control strategies often cannot meet the actual wind control requirements.

Therefore, how to configure the wind control strategy meeting the actual wind control requirement for different business scenarios is a urgent problem to be solved under the conditions of reducing the labor cost and improving the configuration efficiency of the wind control strategy.

Disclosure of Invention

The embodiment of the specification provides a business wind control method, a device, a storage medium and electronic equipment, so as to partially solve the problems existing in the prior art.

The embodiment of the specification adopts the following technical scheme:

the service wind control method provided by the specification comprises the following steps:

Receiving a policy adjustment request for a target service scene;

based on the strategy adjustment request, determining each candidate wind control strategy used in the target service scene and a wind control target corresponding to the target service scene;

taking the selected wind control strategies as constraint conditions to meet the wind control targets when the selected wind control strategies are adopted to wind control the business in the target business scene, and selecting target strategies from the candidate wind control strategies based on wind control records counted when the wind control is carried out on the business in the target business scene by adopting the candidate wind control strategies historically;

deploying the target strategy, and executing service wind control through the target strategy when a service request aiming at the target service scene is received.

Optionally, the wind control strategy includes: risk threshold and/or matching rules;

based on the policy adjustment request, determining each candidate wind control policy used in the target service scene specifically includes:

determining a basic risk threshold and/or a basic matching rule corresponding to the target service scene based on the policy adjustment request;

determining each candidate risk threshold based on the basic risk threshold; and determining each candidate matching rule based on the basic matching rule.

Optionally, determining each candidate risk threshold based on the base risk threshold specifically includes:

if the wind control target is that the wind control strategy selected is adopted to perform wind control on the service in the target service scene, the accumulated real hit parameter counted by the wind control target is smaller than and closest to the real hit threshold value, and each candidate risk threshold value larger than the basic risk threshold value is determined based on the basic risk threshold value;

the method comprises the steps of taking the selected wind control strategy as a constraint condition when the wind control target is met when the selected wind control strategy is adopted to conduct wind control on the service in the target service scene, selecting the target strategy from the candidate wind control strategies based on wind control records counted when the wind control is conducted on the service in the target service scene through the candidate wind control strategies in history, wherein the method specifically comprises the following steps:

determining real hit parameters corresponding to each candidate risk threshold based on wind control records counted when wind control is performed on the service in the target service scene by adopting each candidate wind control strategy historically;

and selecting target candidate risk thresholds meeting the wind control target from the candidate risk thresholds based on the real hit parameters corresponding to the candidate risk thresholds.

Optionally, determining the real hit parameter corresponding to each candidate risk threshold based on the wind control record counted when the wind control is performed on the service in the target service scene by using each candidate wind control strategy historically, which specifically includes:

for each candidate risk threshold, determining a candidate risk threshold that is less than and closest to the candidate risk threshold as a matching risk threshold;

based on the wind control records counted when the wind control is performed on the service in the target service scene by adopting each candidate wind control strategy in history, determining the reduction amount of the number of the service actually hit when the wind control is performed on the service in the target service scene by adopting the risk threshold in history relative to the number of the service actually hit when the wind control is performed on the service in the target service scene by adopting the matching candidate risk threshold, and taking the reduction amount as the real hit reduction amount corresponding to the candidate risk threshold;

determining comprehensive real hit reduction amounts corresponding to all candidate risk thresholds based on the real hit reduction amounts corresponding to each candidate risk threshold;

and determining the real hit ratio corresponding to the candidate risk threshold based on the real hit reduction amount corresponding to the candidate risk threshold and the comprehensive real hit reduction amount, and taking the real hit ratio corresponding to the candidate risk threshold as a real hit parameter.

Optionally, selecting a target candidate risk threshold value meeting the wind control target from the candidate risk thresholds based on the real hit parameter and the miss parameter corresponding to each candidate risk threshold value, which specifically includes:

sequencing the candidate risk thresholds from small to large to obtain sequenced candidate risk thresholds;

sequentially traversing the sequenced candidate risk thresholds, and accumulating the real hit parameters corresponding to other candidate risk thresholds smaller than the currently traversed candidate risk threshold to obtain accumulated real hit parameters;

if the accumulated real hit parameter is less than and closest to the real hit threshold, determining a candidate risk threshold currently traversed to be a target candidate risk threshold that meets the wind control target,

optionally, determining each candidate matching rule based on the basic matching rule specifically includes:

taking the basic matching rule as each candidate matching rule;

after selecting a target candidate risk threshold value that meets the wind control target from the candidate risk threshold values, the method further includes:

based on the wind control records counted when the wind control is performed on the service in the target service scene by adopting each wind control strategy in history, determining the number of the truly hit service and the number of the mistakenly hit service through each candidate matching rule when the wind control is performed on the service in the target service scene by adopting the target candidate risk threshold in history;

For each candidate matching rule, determining a first wind control value of the candidate matching rule according to the number of the businesses truly hit by the candidate matching rule and the number of the businesses missed by the candidate matching rule, wherein the larger the first wind control value is, the larger the number of the businesses missed by the candidate matching rule is;

and selecting at least part of candidate matching rules from the candidate matching rules as target candidate matching rules based on the first wind control value of each candidate matching rule.

Optionally, based on the first wind control value of each candidate matching rule, selecting at least part of candidate matching rules from the candidate matching rules as target candidate matching rules, and specifically including:

determining the comprehensive business quantity truly hit by all candidate matching rules based on the business quantity truly hit by each candidate matching rule;

for each candidate matching rule, determining a real hit parameter corresponding to the candidate matching rule based on the number of services actually hit by the candidate matching rule and the comprehensive number of services;

and sequentially closing algorithm switches of each candidate matching rule according to the sequence from the high value to the low value of the first wind control, accumulating real hit parameters corresponding to the closed candidate matching rules to obtain a second accumulated real hit parameter until the second accumulated real hit parameter is smaller than and closest to the real hit threshold, and taking the candidate matching rule in an on state as a target candidate matching rule.

if the wind control target is that the wind control strategy selected is adopted to perform wind control on the service in the target service scene, the accumulated miss parameter counted by the wind control target is smaller than and closest to a miss threshold value, and based on the basic matching rule, other matching rules except the basic matching rule are used as candidate matching rules;

based on the wind control records counted when the wind control is performed on the service under the target service scene by adopting each candidate wind control strategy historically, determining the real hit service increment and the miss hit service increment when the algorithm switch of each candidate matching rule is in an on state;

for each candidate matching rule, determining a second wind control value corresponding to the candidate matching rule based on the real hit service increment and the error hit service increment when an algorithm switch of the candidate matching rule is in an on state, wherein the larger the second wind control value is, the larger the number of the real hit services through the candidate matching rule is;

Sequentially starting algorithm switches of all candidate matching rules according to the sequence from high to low of the second wind control value, accumulating miss parameters corresponding to the started candidate matching rules to obtain a first accumulated miss parameter until the first accumulated miss parameter is smaller than and closest to the miss threshold, and selecting the candidate matching rules in the starting state from all the candidate matching rules as target candidate matching rules.

Optionally, sequentially starting algorithm switches of each candidate matching rule according to the sequence from the high value to the low value of the second wind control, and accumulating miss parameters corresponding to the started candidate matching rules to obtain a first accumulated miss parameter, which specifically comprises:

for each candidate matching rule, determining a miss-hit parameter corresponding to the candidate matching rule based on the real hit business increment and the miss-hit business increment when an algorithm switch of the candidate matching rule is in an on state;

and sequentially starting algorithm switches of each candidate matching rule according to the sequence from the high value to the low value of the second wind control, and accumulating the error hit parameters corresponding to the started candidate matching rules to obtain a first accumulated error hit parameter.

Optionally, after selecting the candidate matching rule in the on state from the candidate matching rules as the target candidate matching rule, the method further includes:

determining candidate risk thresholds smaller than the basic risk threshold based on the basic risk threshold;

determining a second accumulated error hit parameter when traversing to each candidate risk threshold based on wind control records counted when wind control is performed on the service in the target service scene by adopting each candidate wind control strategy historically;

and selecting a target candidate risk threshold meeting the wind control target from the candidate risk thresholds based on a second accumulated miss parameter when traversing to each candidate risk threshold.

Optionally, determining the second accumulated miss parameter when traversing to each candidate risk threshold based on the wind control record counted when historically adopting each candidate wind control strategy to wind control the service in the target service scene specifically includes:

for each candidate risk threshold, determining a candidate risk threshold that is greater than and closest to the candidate risk threshold as a target risk threshold;

based on the wind control records counted when the wind control is performed on the service in the target service scene by adopting each candidate wind control strategy in history, determining the increase of the number of the actually hit service when the wind control is performed on the service in the target service scene by adopting the target risk threshold in history relative to the increase of the number of the actually hit service when the wind control is performed on the service in the target service scene by adopting the candidate risk threshold, as the first increase corresponding to the candidate risk threshold, and determining the increase of the number of the mistakenly hit service when the wind control is performed on the service in the target service scene by adopting the target risk threshold in history relative to the increase of the number of the mistakenly hit service when the wind control is performed on the service in the target service scene by adopting the candidate risk threshold, as the second increase corresponding to the candidate risk threshold;

Traversing each candidate risk threshold from large to small in sequence, accumulating the first increment corresponding to other candidate risk thresholds larger than the currently traversed candidate risk threshold to obtain a comprehensive first increment, and accumulating the second increment corresponding to other candidate risk thresholds larger than the currently traversed candidate risk threshold to obtain a comprehensive second increment;

determining a second accumulated miss parameter when the candidate risk threshold is currently traversed according to the comprehensive first increment and the comprehensive second increment;

selecting a target candidate risk threshold meeting the wind control target from the candidate risk thresholds based on a second accumulated miss parameter when traversing to each candidate risk threshold, wherein the target candidate risk threshold specifically comprises:

and if the second accumulated miss parameter when the currently traversed candidate risk threshold is smaller than and closest to the miss threshold, determining the currently traversed candidate risk threshold as a target candidate risk threshold meeting the wind control target.

The service wind control device provided in the specification comprises:

the receiving module is used for receiving a strategy adjustment request aiming at a target service scene;

The determining module is used for determining each candidate wind control strategy used in the target service scene and a wind control target corresponding to the target service scene based on the strategy adjustment request;

the selection module is used for selecting a target strategy from the candidate wind control strategies based on wind control records counted when the wind control is performed on the service in the target service scene by using the selected wind control strategies when the wind control target is met when the selected wind control strategies are used for performing wind control on the service in the target service scene;

the wind control module is used for deploying the target strategy and executing service wind control through the target strategy when a service request aiming at the target service scene is received.

A computer readable storage medium is provided in the present specification, where the storage medium stores a computer program, and when executed by a processor, implements the service wind control method described above.

The electronic equipment provided by the specification comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor realizes the business wind control method when executing the program.

The above-mentioned at least one technical scheme that this description embodiment adopted can reach following beneficial effect:

in the embodiment of the specification, after receiving a policy adjustment request for a target service scenario, each candidate wind control policy and wind control target used in the target service scenario are determined based on the policy adjustment request. And selecting the target strategy from the candidate wind control strategies based on wind control records counted when the wind control is performed on the service in the target service scene by adopting the selected wind control strategy, deploying the target strategy, and executing the service wind control through the target strategy when a service request aiming at the target service scene is received. In the method, the manpower cost is reduced and the configuration efficiency of the wind control strategy is improved by automatically selecting the wind control strategy, and the selected wind control strategy is ensured to meet the actual wind control requirement by using the historical wind control record.

Drawings

The accompanying drawings, which are included to provide a further understanding of the specification, illustrate and explain the exemplary embodiments of the present specification and their description, are not intended to limit the specification unduly. Attached at

In the figure:

fig. 1 is a schematic flow chart of a service wind control method according to an embodiment of the present disclosure;

fig. 2 is a schematic structural diagram of a service wind control device according to an embodiment of the present disclosure;

fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present disclosure.

Detailed Description

For the purposes of making the objects, technical solutions and advantages of the present specification more apparent, the technical solutions of the present specification will be clearly and completely described below with reference to specific embodiments of the present specification and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, of the embodiments of the present specification. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are intended to be within the scope of the present disclosure.

The following describes in detail the technical solutions provided by the embodiments of the present specification with reference to the accompanying drawings.

Fig. 1 is a schematic flow chart of a service wind control method provided in the present specification, including:

s100: and receiving a policy adjustment request aiming at a target service scene, which is sent by a user.

In the embodiment of the present specification, a policy adjustment request sent by a user for a target service scenario may be obtained. The policy adjustment request carries the service scene identifier and the policy adjustment direction. A user may refer to a user who can configure a wind control policy under different business scenarios, such as: and (5) operating and maintaining personnel. The target service scenario may refer to a service scenario requiring adjustment of a wind control policy, where the service scenario may refer to a payment scenario, such as: payment scenario from person to person, from company to company, from person to merchant, country to country, etc.

In addition, the wind control strategy at least comprises: risk threshold and/or respective matching rules. Each matching rule corresponds to a respective algorithm switch. Adjusting the wind control strategy may refer to adjusting the risk threshold and/or adjusting the status of the algorithmic switches of each matching rule. The matching rule may be a matching rule for matching target information carried in a service request (for example, a payment request) with information in a blacklist, where the target information at least includes: name, address, etc. of the service executor. Taking the name as an example, the matching rule at least includes: converting the Chinese name into English, and matching the English name with the name of a service executor in the service request; the surname and the first name of the Chinese first name are reversed, the reversed first name is matched with the first name of the service executor in the service request, and the like.

Taking the payment scenario as an example, the wind control requirement of each payment scenario may be different for different payment scenarios, and the wind control strategy of each payment scenario may also be different. Such as: risk prevention and control for payment scenarios from person to person may be broad and risk prevention and control for payment scenarios from company to company may be strict.

Thus, a policy adjustment direction needs to be determined for each traffic scenario. The policy adjustment direction may include: the business disturbance is reduced, and the wind control coverage area is increased.

The reduction of the service disturbance is actually to reduce the probability of the error hit of the wind control by increasing the risk threshold and/or reducing the matching rule, thereby achieving the purpose of reducing the service disturbance. Traffic disruption may refer to blocking a certain traffic when it is determined to be risky. A miss refers to a payment request that is otherwise not at risk being mismatched as being at risk.

Increasing the wind control coverage is actually by lowering the risk threshold and/or increasing the matching rules to increase the probability of a true hit of the wind control, i.e. to increase the accuracy of the wind control. A true hit means that an otherwise risky payment request is matched as risky.

S102: and determining each candidate wind control strategy used under the target service scene and a wind control target corresponding to the target service scene based on the strategy adjustment request.

In the embodiment of the present disclosure, after the policy adjustment request is obtained, a service scenario that needs to be subjected to wind control policy adjustment may be determined as a target service scenario according to a service scenario identifier carried in the policy adjustment request. And then, determining the current wind control strategy of the target service scene as a basic wind control strategy. The basic wind control strategy may include: a base risk threshold and/or a base matching rule.

And simultaneously, according to the strategy adjustment direction carried in the strategy adjustment request, determining each candidate wind control strategy used in the target service scene and the wind control target corresponding to the target service scene. The candidate wind control strategy may include: a candidate risk threshold and/or a candidate matching rule.

If the policy adjustment direction is to reduce the business disturbance, the probability of the wind control miss is required to be reduced, and meanwhile, the probability of the real hit of too much wind control cannot be reduced. Therefore, the wind control target corresponding to the target service scene is that the accumulated real hit parameter counted after wind control is performed on the service in the target service scene by adopting the selected wind control strategy is smaller than and closest to the real hit threshold value.

When determining each candidate wind control policy used in the target service scenario, a risk threshold greater than the base risk threshold may be used as each candidate risk threshold, and/or a base matching rule may be used as each candidate matching rule. Wherein the basic matching rule may be plural.

If the policy adjustment direction is to increase the wind control coverage, the probability of the actual hit of the wind control needs to be increased, and meanwhile, the probability of the miss of too many wind controls cannot be increased. Therefore, the wind control target corresponding to the target service scene is that the accumulated miss parameter counted after wind control is carried out on the service in the target service scene by adopting the selected wind control strategy is smaller than and closest to the miss threshold.

When determining each candidate wind control policy used in the target service scenario, a risk threshold smaller than the basic risk threshold may be used as each candidate risk threshold, and/or other matching rules than the basic matching rule may be selected from the matching rule library as each candidate matching rule.

It should be noted that, since the wind control policy may include the risk threshold and/or each matching rule, only the risk threshold may be adjusted or reselected, only each matching rule may be adjusted or reselected, and also the risk threshold and each matching rule may be adjusted or reselected.

S104: and taking the selected wind control strategies as constraint conditions when the wind control targets are met when the selected wind control strategies are adopted to wind control the business in the target business scene, and selecting the target strategies from the candidate wind control strategies based on wind control records counted when the wind control is carried out on the business in the target business scene by adopting the candidate wind control strategies historically.

S106: deploying the target strategy, and executing service wind control through the target strategy when a service request aiming at the target service scene is received.

In the embodiment of the present disclosure, after determining each candidate wind control policy and the wind control target used in the target service scenario, the selected wind control policy may be adopted to satisfy the wind control target as a constraint condition when the wind control is performed on the service in the target service scenario, and the target policy may be selected from the candidate wind control policies based on the wind control record counted when the wind control is performed on the service in the target service scenario by historically adopting each candidate wind control policy. Then, the target strategy is deployed, and when a service request aiming at a target service scene is received, service wind control is executed through the target strategy. The selected target strategy may include: a target candidate risk threshold and/or a target candidate matching rule.

Next, a method for determining the target policy will be described with respect to different policy adjustment directions.

If the strategy adjustment direction is to reduce the business disturbance, the wind control target is that the accumulated real hit parameter counted after wind control is carried out on the business in the target business scene by adopting the selected wind control strategy is smaller than and closest to the real hit threshold value.

Adjustment of risk threshold in wind control strategy:

firstly, determining each candidate risk threshold value larger than a basic risk threshold value based on the basic risk threshold value corresponding to the target business scene currently. And then, determining the real hit parameters corresponding to the candidate risk thresholds based on wind control records counted when the wind control is performed on the service in the target service scene by adopting each candidate wind control strategy in history. And then, selecting a target candidate risk threshold meeting the wind control target from the candidate risk thresholds based on the real hit parameters corresponding to the candidate risk thresholds.

When determining the real hit parameters corresponding to the candidate risk thresholds, for each candidate risk threshold, a candidate risk threshold smaller than and closest to the candidate risk threshold can be determined as a matching risk threshold. And then, determining the reduction amount of the number of the businesses actually hit when the business in the target business scene is subjected to wind control by adopting the risk threshold in history relative to the number of the businesses actually hit when the business in the target business scene is subjected to wind control by adopting the matched candidate risk threshold based on the wind control record counted when the business in the target business scene is subjected to wind control by adopting each candidate wind control strategy, and taking the reduction amount as the actual hit reduction amount corresponding to the candidate risk threshold.

And then, determining the comprehensive real hit reduction amount corresponding to all the candidate risk thresholds based on the real hit reduction amount corresponding to each candidate risk threshold, namely accumulating the real hit reduction amounts corresponding to each candidate risk threshold to obtain the comprehensive real hit reduction amount.

And finally, determining the real hit ratio corresponding to the candidate risk threshold based on the real hit reduction amount corresponding to the candidate risk threshold and the comprehensive real hit reduction amount, and taking the real hit ratio corresponding to the candidate risk threshold as a real hit parameter corresponding to the candidate risk threshold. The real hit parameter corresponding to the candidate risk threshold may refer to a ratio of the real hit reduction amount corresponding to the candidate risk threshold in the integrated real hit reduction amount. As shown in table 1.

When selecting a target candidate risk threshold meeting the wind control target from the candidate risk thresholds, sorting the candidate risk thresholds from small to large to obtain sorted candidate risk thresholds. And then sequentially traversing the sequenced candidate risk thresholds, and accumulating the real hit parameters corresponding to other candidate risk thresholds smaller than the currently traversed candidate risk threshold to obtain a first accumulated real hit parameter. As shown in table 2. And if the first accumulated real hit parameter is smaller than and closest to the real hit threshold, determining the candidate risk threshold traversed currently as a target candidate risk threshold meeting the wind control target.

In addition, based on the wind control record counted when the wind control is performed on the service in the target service scene by using each candidate wind control strategy in history, the reduction amount of the number of the missed services when the wind control is performed on the service in the target service scene by using the risk threshold in history relative to the number of the missed services when the wind control is performed on the service in the target service scene by using the matching candidate risk threshold can be determined as the miss reduction amount corresponding to the candidate risk threshold. And then, determining the comprehensive miss reduction amount corresponding to all the candidate risk thresholds based on the miss reduction amount corresponding to each candidate risk threshold, namely accumulating the miss reduction amounts corresponding to each candidate risk threshold to obtain the comprehensive miss reduction amount. And determining the miss ratio corresponding to the candidate risk threshold based on the miss reduction amount corresponding to the candidate risk threshold and the comprehensive miss reduction amount, and taking the miss ratio corresponding to the candidate risk threshold as a miss parameter corresponding to the candidate risk threshold. The miss parameter corresponding to the candidate risk threshold may refer to a ratio of the miss reduction amount corresponding to the candidate risk threshold in the integrated miss reduction amount.

And finally, sorting the candidate risk thresholds from small to large to obtain sorted candidate risk thresholds. And then sequentially traversing the sequenced candidate risk thresholds, and accumulating the miss parameters corresponding to other candidate risk thresholds smaller than the currently traversed candidate risk threshold to obtain a first comprehensive miss parameter.

Table 1 is a statistical table of the real hit parameters corresponding to each candidate risk threshold.

TABLE 1

In table 1, if the true hit threshold is 0.5% and the base risk threshold is 96, there are four candidate risk thresholds, 97, 98, 99, 100, respectively. When the traversed candidate risk threshold is 97, the candidate risk threshold is 0% relative to 96, and the first integrated miss parameter is 16.89%; when the traversed candidate risk threshold is 98, the candidate risk threshold is 0.19% relative to 96, and the first integrated miss parameter is 68.24%; when the traversed candidate risk threshold is 99, the candidate risk threshold is 3.92% for the first cumulative true hit parameter and 83.78% for the first composite miss parameter relative to 96. It can be seen that the first cumulative actual hit parameter is less than and closest to the actual hit threshold when the candidate risk threshold is 98.

Based on the above traversal of the wind control threshold, table 2 is a table of variation of the first accumulated real hit parameter and the first integrated miss parameter for traversing each candidate risk threshold.

TABLE 2

And turning off an algorithm switch of at least part of candidate matching rules aiming at each candidate matching rule, and taking the matching rule which is not turned off in each candidate matching rule as a target candidate matching rule.

In the embodiment of the present disclosure, a method for adjusting a matching rule after adjusting a risk threshold in a target service scenario is mainly described. However, the matching rule may be adjusted only, and the risk threshold may not be adjusted.

Specifically, the basic matching rule may be first used as each candidate matching rule. Then, based on the wind control records counted when the wind control strategy is adopted historically to wind control the service in the target service scene, the number of the service truly hit and the number of the service mistakenly hit by each candidate matching rule when the target candidate risk threshold is adopted historically to wind control the service in the target service scene can be determined. Then, for each candidate matching rule, determining a first wind control value of the candidate matching rule according to the number of the true hit business and the number of the miss business through the candidate matching rule, wherein the larger the first wind control value is, the larger the number of the miss business through the candidate matching rule is. Finally, based on the first wind control value of each candidate matching rule, at least part of candidate matching rules are selected from the candidate matching rules to serve as target candidate matching rules.

And when the first wind control value of the candidate matching rule is determined, taking the ratio between the number of the missed services and the number of the true hit services as the first wind control value of the candidate matching rule.

When at least a portion of candidate matching rules are selected from the candidate matching rules, a total number of traffic hit by all candidate matching rules may be determined based on the number of traffic hit by each candidate matching rule. And accumulating the number of the services truly hit by each candidate matching rule to obtain the comprehensive number of the services.

Then, for each candidate matching rule, determining the real hit ratio corresponding to the candidate matching rule based on the real hit service number and the real hit comprehensive service number of the candidate matching rule, and taking the real hit ratio as the real hit parameter corresponding to the candidate matching rule. As shown in table 3. The actual hit parameter corresponding to the candidate matching rule may refer to a duty ratio of the number of services actually hit by the candidate matching rule in the number of comprehensive services actually hit.

And finally, sequentially closing algorithm switches of each candidate matching rule according to the sequence from the high value to the low value of the first wind control, accumulating real hit parameters corresponding to the closed candidate matching rules to obtain second accumulated real hit parameters, and taking the candidate matching rule in an on state as a target candidate matching rule until the second accumulated real hit parameters are smaller than and closest to the real hit threshold. As shown in table 4.

In addition, the comprehensive business quantity of the missed hits of all the candidate matching rules can be determined based on the business quantity of the true hits of each candidate matching rule, and then, for each candidate matching rule, the miss ratio corresponding to the candidate matching rule is determined based on the business quantity of the missed hits of the candidate matching rules and the comprehensive business quantity of the missed hits, and is used as the miss parameter corresponding to the candidate matching rule. And finally, sequentially closing algorithm switches of each candidate matching rule according to the sequence from the high value to the low value of the first wind control, and accumulating the error hit parameters corresponding to the closed candidate matching rules to obtain a second comprehensive error hit parameter. The miss parameter corresponding to the candidate matching rule may refer to a duty ratio of the number of missed services of the candidate matching rule in the number of missed integrated services.

Table 3 is a statistical table of the actual hit parameters and miss parameters corresponding to each candidate matching rule.

TABLE 3 Table 3

In table 3, if the true hit threshold is 0.5%, there are A, B, C, D, E matching rules in table 3. As can be seen, the first wind control value of C, E, B is relatively large, the algorithm switch is turned off from C, if C is turned off, the second cumulative real hit parameter is 0.08%, and the second integrated miss parameter is 24.44%; if E is closed again, the second accumulated real hit parameter is 0.31%, and the second comprehensive miss parameter is 62.22%; if B is closed again, the second cumulative true hit parameter is 8.9%, and the second integrated miss parameter is 75.55%. At turn-off E, the second cumulative actual hit parameter is less than and closest to the actual hit threshold, so turn-off C, E, algorithm switch A, B, D in on state is the selected target candidate matching rule.

Based on the above adjustment of the algorithm switch state of the candidate matching rules, table 4 is a table of changes in the algorithm switch that adjusts each candidate matching rule in turn.

TABLE 4 Table 4

When the risk threshold is adjusted and the algorithm switch of at least part of the matching rules is closed, the strategy adjustment direction is used for reducing the probability of miss, so that the risk threshold larger than the basic risk threshold can be selected first, and then the algorithm switch of at least part of the matching rules is closed.

It should be noted that, when only the matching rule is adjusted, the method is similar to the above method, but when the number of services actually hit and missed are determined, the number of services actually hit and the number of services missed by each candidate matching rule when the service in the target service scene is wind-controlled by using the basic risk threshold historically can be determined based on the wind-control record counted when the service in the target service scene is wind-controlled by using each wind-control policy, and other steps are completed the same.

Next, a description will be given of selecting a target policy with respect to another policy adjustment direction.

If the strategy adjustment direction is to increase the wind control coverage, the wind control target is that the accumulated miss parameter counted after wind control is performed on the service in the target service scene by adopting the selected wind control strategy is smaller than and closest to the miss threshold.

Because more business quantity possibly at risk needs to be acquired by increasing the wind control coverage, the matching rule can be adjusted first, and then the risk threshold can be adjusted.

Adjusting matching rules in the wind control strategy:

other matching rules than the basic matching rule can be selected from the matching rule base as candidate matching rules based on the basic matching rule. And determining the actual hit service increment and the error hit service increment when the algorithm switch of each candidate matching rule is in an on state based on the wind control record counted when the wind control is performed on the service in the target service scene by adopting each candidate wind control strategy historically.

Then, for each candidate matching rule, a second air control value corresponding to the candidate matching rule is determined based on the actual hit traffic increase and the miss traffic increase when the algorithm switch of the candidate matching rule is in the on state, as shown in table 5. The larger the second wind control value is, the larger the number of services actually hit through the candidate matching rule is.

And when the second wind control value corresponding to the candidate matching rule is determined, the ratio of the actual hit business increment to the false hit business increment when the algorithm switch of the candidate matching rule is in an on state can be used as the second wind control value corresponding to the candidate matching rule.

And finally, sequentially starting algorithm switches of all candidate matching rules according to the sequence from the high value to the low value of the second wind control, accumulating the miss parameters corresponding to the started candidate matching rules to obtain a first accumulated miss parameter until the first accumulated miss parameter is smaller than and closest to a miss threshold value, and selecting the candidate matching rule in the on state from all the candidate matching rules as a target candidate matching rule. As shown in table 6.

When determining the miss parameter corresponding to each candidate matching rule, for each candidate matching rule, the miss parameter corresponding to the candidate matching rule can be determined based on the actual hit business increment and the miss business increment when the algorithm switch of the candidate matching rule is in an on state. The ratio of the increase of the missed service to the increase of the true hit service when the algorithm switch of the candidate matching rule is in the on state can be used as the miss parameter corresponding to the candidate matching rule. The larger the increase of the mishit business when the algorithm switch of the candidate matching rule is in the on state, the larger the mishit parameter corresponding to the candidate matching rule.

In addition, algorithm switches of each candidate matching rule can be sequentially started according to the sequence from the high value to the low value of the second wind control value, and real hit parameters corresponding to the started candidate matching rules are accumulated to obtain comprehensive real hit parameters. The ratio of the increase of the real hit service to the increase of the miss service when the algorithm switch of the candidate matching rule is in the on state can be used as the real hit parameter corresponding to the candidate matching rule for each matching rule. The larger the service increment of the real hit when the algorithm switch of the candidate matching rule is in an on state, the larger the real hit parameter corresponding to the candidate matching rule.

Table 5 is a statistical table of the actual hit traffic increase and miss traffic increase at each match rule on.

/>

TABLE 5

In table 5, if the basic matching rule is A, B, C, D, E, the miss threshold is 2%, and there are five candidate matching rules F, G, H, I, J in table 5. As can be seen, the second pneumatic control value of G, F, J is relatively large, the algorithm switch is turned on from G, if G is turned on, the accumulated traffic increase of real hits is 26, the accumulated traffic increase of false hits is 19, and the first accumulated false hit parameter is 0.731; if F is started again, the accumulated service increment of the true hit is 106, the accumulated service increment of the miss is 145, and the first accumulated miss parameter is 1.381; if J is turned on again, the accumulated traffic increase for a real hit is 141, the accumulated traffic increase for a miss is 369, and the first accumulated miss parameter is 2.617. At turn-on F, the first cumulative miss parameter is less than and closest to the miss threshold, so turn-on G, F is the selected target candidate matching rule.

Based on the above adjustment of the matching rule, table 6 is a table of variation of the first cumulative miss parameter.

TABLE 6

For the risk threshold, a target candidate risk threshold may be selected from the candidate risk thresholds.

Specifically, based on the base risk threshold, candidate risk thresholds that are less than the base risk threshold are determined. And determining a second accumulated error hit parameter when traversing to each candidate risk threshold based on the wind control record counted when the wind control is performed on the service in the target service scene by adopting each candidate wind control strategy historically. And selecting a target candidate risk threshold meeting the wind control target from the candidate risk thresholds based on the second accumulated miss parameters when traversing to each candidate risk threshold.

Upon determining the second accumulated miss parameter when traversing to each candidate risk threshold, a candidate risk threshold that is greater than and closest to the candidate risk threshold may be determined for each candidate risk threshold as the target risk threshold. Then, based on the wind control records counted when the wind control strategy is adopted for the wind control of the service in the target service scene in the history, determining the increment of the actual hit service quantity when the wind control is carried out on the service in the target service scene by adopting the target risk threshold value in the history relative to the actual hit service quantity when the wind control is carried out on the service in the target service scene by adopting the candidate risk threshold value, as the first increment corresponding to the candidate risk threshold value, and determining the increment of the error hit service quantity when the wind control is carried out on the service in the target service scene by adopting the target risk threshold value in the history relative to the error hit service quantity when the wind control is carried out on the service in the target service scene by adopting the candidate risk threshold value, as the second increment corresponding to the candidate risk threshold value.

When only the risk threshold is adjusted, based on the wind control record counted when each candidate wind control strategy is historically adopted to wind control the service in the target service scene, determining the increase of the number of the services actually hit when the target risk threshold is historically adopted to wind control the service in the target service scene under the basic matching rule relative to the increase of the number of the services actually hit when the candidate risk threshold is adopted to wind control the service in the target service scene, as a first increase corresponding to the candidate risk threshold, and determining the increase of the number of the services mistakenly hit when the target risk threshold is historically adopted to wind control the service in the target service scene relative to the increase of the number of the services mistakenly hit when the candidate risk threshold is adopted to wind control the service in the target service scene, as a second increase corresponding to the candidate risk threshold.

When the basic matching rule is adjusted first and then the risk threshold is adjusted, based on the wind control record counted when the wind control is performed on the service under the target service scene by adopting each candidate wind control strategy in history, the increase of the number of the services actually hit when the wind control is performed on the service under the target service scene by adopting the target risk threshold under the target candidate matching rule in history is determined, the increase of the number of the services actually hit when the wind control is performed on the service under the target service scene by adopting the candidate risk threshold is used as the first increase corresponding to the candidate risk threshold, and the increase of the number of the services mistakenly hit when the wind control is performed on the service under the target service scene by adopting the target risk threshold in history is determined, and the increase of the number of the services mistakenly hit when the wind control is performed on the service under the target service scene by adopting the candidate risk threshold is used as the second increase corresponding to the candidate risk threshold.

And traversing each candidate risk threshold from large to small in sequence, accumulating the first increment corresponding to other candidate risk thresholds larger than the currently traversed candidate risk threshold to obtain a comprehensive first increment, and accumulating the second increment corresponding to other candidate risk thresholds larger than the currently traversed candidate risk threshold to obtain a comprehensive second increment.

And finally, determining a second accumulated miss parameter when the candidate risk threshold value is currently traversed according to the comprehensive first increment and the comprehensive second increment. Specifically, the ratio between the integrated second increment and the integrated first increment may be used as the second cumulative miss parameter. The larger the second accumulated miss parameter is, the more the number of the missed services is when the wind control is carried out through the candidate risk threshold value traversed currently. As shown in table 7.

And if the second accumulated false hit parameter when the currently traversed candidate risk threshold is smaller than and closest to the false hit threshold, determining the currently traversed candidate risk threshold as a target candidate risk threshold meeting the wind control target.

Table 7 is a statistical table of the second cumulative miss parameters traversed to correspond to each candidate risk threshold.

TABLE 7

In table 7, if the base risk threshold is 96 and the miss threshold is 7%, the candidate risk thresholds smaller than the base risk threshold are: 95. 94, 93, 92, 91, 90. When the traversed candidate risk threshold is 95, the candidate risk threshold is 12 in the comprehensive first increment, 8 in the comprehensive second increment and 0.67 in the second accumulated miss parameter relative to 96; when the traversed candidate risk threshold is 94, the candidate risk threshold is 25 in a comprehensive first increment, 33 in a comprehensive second increment and 1.32 in a second cumulative miss parameter relative to 96; when the traversed candidate risk threshold is 93, the candidate risk threshold is 36 for the first integrated increment, 271 for the second integrated increment, and 7.53 for the second cumulative miss parameter, relative to 96. It can be seen that when the traversed candidate risk threshold is 94, the second cumulative miss parameter is less than and closest to the miss threshold, i.e., the target candidate risk threshold should be 94.

It should be noted that, the basic risk threshold may be adjusted only or an algorithm switch for opening at least part of the matching rules may be newly added, or the basic risk threshold may be adjusted and an algorithm switch for opening at least part of the matching rules may be newly added.

When the basic risk threshold is adjusted and the algorithm switch of at least part of the matching rules is newly added, the algorithm switch of at least part of the matching rules can be newly added and started, and then the target candidate risk threshold can be selected from the candidate risk thresholds because the aim of the strategy adjustment direction is to increase the probability of real hit.

After selecting the target policy or the target wind control policy, the target policy may be deployed, and when a service request for a target service scenario is received, service wind control is performed through the target policy. Wherein the target candidate risk threshold and/or the target candidate matching rule may be used as the target policy.

Specifically, for each service in the target service scene, matching the information related to the service with the information in the blacklist through each matching rule in the target strategy to obtain a matching result, and then judging whether the service has risks according to the matching result and a risk threshold in the target strategy, if so, blocking the service, and if not, normally executing the service.

Further, for each matching rule, matching the information related to the service with the information in the blacklist to obtain a risk value of the information related to the service hitting the information in the blacklist, and obtaining a risk value corresponding to the matching rule. And selecting the maximum risk value from the risk values corresponding to the matching rules as a target risk value. And comparing the target risk value with a risk threshold value, and judging whether the business has risk or not.

As can be seen from the method shown in fig. 1, after receiving a policy adjustment request for a target service scenario, the present disclosure determines, based on the policy adjustment request, each candidate wind control policy and wind control target used in the target service scenario. And selecting the target strategy from the candidate wind control strategies based on wind control records counted when the wind control is performed on the service in the target service scene by adopting the selected wind control strategy, deploying the target strategy, and executing the service wind control through the target strategy when a service request aiming at the target service scene is received. In the method, the manpower cost is reduced and the configuration efficiency of the wind control strategy is improved by automatically selecting the wind control strategy, and the selected wind control strategy is ensured to meet the actual wind control requirement by using the historical wind control record.

The business wind control method provided by the embodiment of the specification also provides a corresponding device, a storage medium and electronic equipment based on the same thought.

Fig. 2 is a schematic structural diagram of a service wind control device according to an embodiment of the present disclosure, where the device includes:

A receiving module 201, configured to receive a policy adjustment request for a target service scenario;

a determining module 202, configured to determine, based on the policy adjustment request, each candidate wind control policy used in the target service scenario and a wind control target corresponding to the target service scenario;

the selection module 203 is configured to select a target policy from the candidate wind control policies based on a wind control record counted when the wind control is performed on the service in the target service scene by using the selected wind control policy, where the wind control target is satisfied when the selected wind control policy is used to wind control the service in the target service scene;

the wind control module 204 is configured to deploy the target policy, and execute a service wind control through the target policy when a service request for the target service scenario is received.

optionally, the determining module 202 is specifically configured to determine, based on the policy adjustment request, a base risk threshold and/or a base matching rule corresponding to the target service scenario; determining each candidate risk threshold based on the basic risk threshold; and determining each candidate matching rule based on the basic matching rule.

Optionally, the determining module 202 is specifically configured to determine, if the wind control target is a cumulative real hit parameter that is counted after wind control is performed on the service in the target service scene by using the selected wind control policy, to be smaller than and closest to a real hit threshold, and determine, based on the base risk threshold, each candidate risk threshold that is greater than the base risk threshold; and taking the basic matching rule as each candidate matching rule.

Optionally, the determining module 202 is specifically configured to, if the wind control target is that the accumulated miss parameter counted after wind control is performed on the service in the target service scenario by using the selected wind control policy is smaller than and closest to the miss threshold, use, based on the basic matching rule, other matching rules except the basic matching rule as each candidate matching rule.

Optionally, the selecting module 203 is specifically configured to determine a real hit parameter corresponding to each candidate risk threshold based on a wind control record counted when the wind control is performed on the service in the target service scene by using each candidate wind control policy historically; and selecting target candidate risk thresholds meeting the wind control target from the candidate risk thresholds based on the real hit parameters corresponding to the candidate risk thresholds.

Optionally, the selecting module 203 is specifically configured to determine, for each candidate risk threshold, a candidate risk threshold that is smaller than and closest to the candidate risk threshold, as a matching risk threshold; based on the wind control records counted when the wind control is performed on the service in the target service scene by adopting each candidate wind control strategy in history, determining the reduction amount of the number of the service actually hit when the wind control is performed on the service in the target service scene by adopting the risk threshold in history relative to the number of the service actually hit when the wind control is performed on the service in the target service scene by adopting the matching candidate risk threshold, and taking the reduction amount as the real hit reduction amount corresponding to the candidate risk threshold; determining comprehensive real hit reduction amounts corresponding to all candidate risk thresholds based on the real hit reduction amounts corresponding to each candidate risk threshold; and determining the real hit ratio corresponding to the candidate risk threshold based on the real hit reduction amount corresponding to the candidate risk threshold and the comprehensive real hit reduction amount, and taking the real hit ratio corresponding to the candidate risk threshold as a real hit parameter.

Optionally, the selecting module 203 is specifically configured to sort the candidate risk thresholds from small to large, so as to obtain sorted candidate risk thresholds; sequentially traversing the sequenced candidate risk thresholds, and accumulating the real hit parameters corresponding to other candidate risk thresholds smaller than the currently traversed candidate risk threshold to obtain a first accumulated real hit parameter; and if the first accumulated real hit parameter is smaller than and closest to the real hit threshold, determining the candidate risk threshold currently traversed to be a target candidate risk threshold meeting the wind control target.

Optionally, after selecting a target candidate risk threshold that meets the wind control target from the candidate risk thresholds, the selecting module 203 is further configured to determine, based on a wind control record counted when historically using each wind control policy to wind control the service in the target service scenario, a number of services actually hit by each candidate matching rule and a number of services that are missed when historically using the target candidate risk threshold to wind control the service in the target service scenario; for each candidate matching rule, determining a first wind control value of the candidate matching rule according to the number of the businesses truly hit by the candidate matching rule and the number of the businesses missed by the candidate matching rule, wherein the larger the first wind control value is, the larger the number of the businesses missed by the candidate matching rule is; and selecting at least part of candidate matching rules from the candidate matching rules as target candidate matching rules based on the first wind control value of each candidate matching rule.

Optionally, the selecting module 203 is further configured to determine, based on the number of services actually hit by each candidate matching rule, a total number of services actually hit by all candidate matching rules; for each candidate matching rule, determining a real hit parameter corresponding to the candidate matching rule based on the number of services actually hit by the candidate matching rule and the comprehensive number of services; and sequentially closing algorithm switches of each candidate matching rule according to the sequence from the high value to the low value of the first wind control, accumulating real hit parameters corresponding to the closed candidate matching rules to obtain a second accumulated real hit parameter until the second accumulated real hit parameter is smaller than and closest to the real hit threshold, and taking the candidate matching rule in an on state as a target candidate matching rule.

Optionally, the selecting module 203 is specifically configured to determine, based on the wind control record counted when the wind control is performed on the service in the target service scene by using each candidate wind control policy historically, a real hit service increment and a false hit service increment when the algorithm switch of each candidate matching rule is in an on state; for each candidate matching rule, determining a second wind control value corresponding to the candidate matching rule based on the real hit service increment and the error hit service increment when an algorithm switch of the candidate matching rule is in an on state, wherein the larger the second wind control value is, the larger the number of the real hit services through the candidate matching rule is; sequentially starting algorithm switches of all candidate matching rules according to the sequence from high to low of the second wind control value, accumulating miss parameters corresponding to the started candidate matching rules to obtain a first accumulated miss parameter until the first accumulated miss parameter is smaller than and closest to the miss threshold, and selecting the candidate matching rules in the starting state from all the candidate matching rules as target candidate matching rules.

Optionally, the selecting module 203 is specifically configured to determine, for each candidate matching rule, a miss parameter corresponding to the candidate matching rule based on an increase of a service actually hit and an increase of a service missed when an algorithm switch of the candidate matching rule is in an on state; and sequentially starting algorithm switches of each candidate matching rule according to the sequence from the high value to the low value of the second wind control, and accumulating the error hit parameters corresponding to the started candidate matching rules to obtain a first accumulated error hit parameter.

Optionally, after selecting the candidate matching rule in the on state from the candidate matching rules as the target candidate matching rule, the selecting module 203 is further configured to determine, based on the base risk threshold, each candidate risk threshold that is smaller than the base risk threshold; determining a second accumulated error hit parameter when traversing to each candidate risk threshold based on wind control records counted when wind control is performed on the service in the target service scene by adopting each candidate wind control strategy historically; and selecting a target candidate risk threshold meeting the wind control target from the candidate risk thresholds based on a second accumulated miss parameter when traversing to each candidate risk threshold.

Optionally, the selecting module 203 is further configured to determine, for each candidate risk threshold, a candidate risk threshold that is greater than and closest to the candidate risk threshold as a target risk threshold; based on the wind control records counted when the wind control is performed on the service in the target service scene by adopting each candidate wind control strategy in history, determining the increase of the number of the actually hit service when the wind control is performed on the service in the target service scene by adopting the target risk threshold in history relative to the increase of the number of the actually hit service when the wind control is performed on the service in the target service scene by adopting the candidate risk threshold, as the first increase corresponding to the candidate risk threshold, and determining the increase of the number of the mistakenly hit service when the wind control is performed on the service in the target service scene by adopting the target risk threshold in history relative to the increase of the number of the mistakenly hit service when the wind control is performed on the service in the target service scene by adopting the candidate risk threshold, as the second increase corresponding to the candidate risk threshold; traversing each candidate risk threshold from large to small in sequence, accumulating the first increment corresponding to other candidate risk thresholds larger than the currently traversed candidate risk threshold to obtain a comprehensive first increment, and accumulating the second increment corresponding to other candidate risk thresholds larger than the currently traversed candidate risk threshold to obtain a comprehensive second increment; determining a second accumulated miss parameter when the candidate risk threshold is currently traversed according to the comprehensive first increment and the comprehensive second increment; and if the second accumulated miss parameter when the currently traversed candidate risk threshold is smaller than and closest to the miss threshold, determining the currently traversed candidate risk threshold as a target candidate risk threshold meeting the wind control target.

The present specification also provides a computer readable storage medium storing a computer program which when executed by a processor is operable to perform the business air control method provided in fig. 1 above.

Based on the service wind control method shown in fig. 1, the embodiment of the present disclosure further provides a schematic structural diagram of the unmanned device shown in fig. 3. At the hardware level, as in fig. 3, the unmanned device comprises a processor, an internal bus, a network interface, a memory and a non-volatile storage, but may also comprise hardware required by other services. The processor reads the corresponding computer program from the nonvolatile memory to the memory and then runs the computer program to realize the business wind control method shown in the figure 1.

Of course, other implementations, such as logic devices or combinations of hardware and software, are not excluded from the present description, that is, the execution subject of the following processing flows is not limited to each logic unit, but may be hardware or logic devices.

In the 90 s of the 20 th century, improvements to one technology could clearly be distinguished as improvements in hardware (e.g., improvements to circuit structures such as diodes, transistors, switches, etc.) or software (improvements to the process flow). However, with the development of technology, many improvements of the current method flows can be regarded as direct improvements of hardware circuit structures. Designers almost always obtain corresponding hardware circuit structures by programming improved method flows into hardware circuits. Therefore, an improvement of a method flow cannot be said to be realized by a hardware entity module. For example, a programmable logic device (Programmable Logic Device, PLD) (e.g., field programmable gate array (Field Programmable Gate Array, FPGA)) is an integrated circuit whose logic function is determined by the programming of the device by a user. A designer programs to "integrate" a digital system onto a PLD without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Moreover, nowadays, instead of manually manufacturing integrated circuit chips, such programming is mostly implemented by using "logic compiler" software, which is similar to the software compiler used in program development and writing, and the original code before the compiling is also written in a specific programming language, which is called hardware description language (Hardware Description Language, HDL), but not just one of the hdds, but a plurality of kinds, such as ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), lava, lola, myHDL, PALASM, RHDL (Ruby Hardware Description Language), etc., VHDL (Very-High-Speed Integrated Circuit Hardware Description Language) and Verilog are currently most commonly used. It will also be apparent to those skilled in the art that a hardware circuit implementing the logic method flow can be readily obtained by merely slightly programming the method flow into an integrated circuit using several of the hardware description languages described above.

The controller may be implemented in any suitable manner, for example, the controller may take the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable logic controllers, and embedded microcontrollers, examples of which include, but are not limited to, the following microcontrollers: ARC625D, atmel AT91SAM, microchip PIC18F26K20, and Silicone Labs C8051F320, the memory controller may also be implemented as part of the control logic of the memory. Those skilled in the art will also appreciate that, in addition to implementing the controller in a pure computer readable program code, it is well possible to implement the same functionality by logically programming the method steps such that the controller is in the form of logic gates, switches, application specific integrated circuits, programmable logic controllers, embedded microcontrollers, etc. Such a controller may thus be regarded as a kind of hardware component, and means for performing various functions included therein may also be regarded as structures within the hardware component. Or even means for achieving the various functions may be regarded as either software modules implementing the methods or structures within hardware components.

The system, apparatus, module or unit set forth in the above embodiments may be implemented in particular by a computer chip or entity, or by a product having a certain function. One typical implementation is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being functionally divided into various units, respectively. Of course, the functions of each element may be implemented in one or more software and/or hardware elements when implemented in the present specification.

It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present description is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the specification. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.

It will be appreciated by those skilled in the art that embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, the present specification may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present description can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The description may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.

In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. In particular, for system embodiments, since they are substantially similar to method embodiments, the description is relatively simple, as relevant to see a section of the description of method embodiments.

The foregoing is merely exemplary of the present disclosure and is not intended to limit the disclosure. Various modifications and alterations to this specification will become apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, or the like, which are within the spirit and principles of the present description, are intended to be included within the scope of the claims of the present description.

Claims

1. A business air control method, the method comprising:

receiving a policy adjustment request for a target service scene;

2. The method of claim 1, the wind control strategy comprising: risk threshold and/or matching rules;

3. The method of claim 2, determining candidate risk thresholds based on the base risk threshold, comprising:

4. The method of claim 3, wherein determining the real hit parameter corresponding to each candidate risk threshold based on the wind control record counted when the wind control is performed on the service in the target service scene by using each candidate wind control policy historically comprises:

5. The method of claim 3, selecting a target candidate risk threshold that meets the wind control target from the candidate risk thresholds based on the true hit parameter and the false hit parameter corresponding to the candidate risk thresholds, specifically comprising:

sequentially traversing the sequenced candidate risk thresholds, and accumulating the real hit parameters corresponding to other candidate risk thresholds smaller than the currently traversed candidate risk threshold to obtain a first accumulated real hit parameter;

and if the first accumulated real hit parameter is smaller than and closest to the real hit threshold, determining the candidate risk threshold currently traversed to be a target candidate risk threshold meeting the wind control target.

6. The method of claim 3, determining candidate matching rules based on the base matching rules, specifically comprising:

taking the basic matching rule as each candidate matching rule;

7. The method of claim 6, selecting at least some candidate matching rules from the candidate matching rules as target candidate matching rules based on the first pneumatic control value of each candidate matching rule, specifically comprising:

8. The method of claim 2, determining candidate matching rules based on the base matching rules, specifically comprising:

9. The method of claim 8, wherein algorithm switches of each candidate matching rule are sequentially turned on according to the order of the second wind control value from the high value to the low value, and the miss parameters corresponding to the turned-on candidate matching rules are accumulated to obtain a first accumulated miss parameter, and specifically comprises:

10. The method of claim 8, after selecting the candidate matching rule in the on state from the candidate matching rules as the target candidate matching rule, the method further comprising:

11. The method of claim 10, wherein determining the second cumulative miss parameter when traversing to each candidate risk threshold based on the wind control record counted when historically using the candidate wind control policies to wind control the traffic in the target traffic scenario, specifically comprises:

12. A business air control device, comprising:

13. A computer readable storage medium storing a computer program which, when executed by a processor, implements the method of any of the preceding claims 1-11.

14. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any of the preceding claims 1-11 when the program is executed.