WO2019232821A1

WO2019232821A1 - Method for processing risk control data, device, computer apparatus, and storage medium

Info

Publication number: WO2019232821A1
Application number: PCT/CN2018/092327
Authority: WO
Inventors: 张小敏; 李云利; 李辉; 石宇; 张文君; 朱小冬; 陈晶
Original assignee: 平安科技（深圳）有限公司
Priority date: 2018-06-08
Filing date: 2018-06-22
Publication date: 2019-12-12
Also published as: CN108985559A

Abstract

The present application relates to the technical field of computers, and provides a method for processing risk control data, a device, a computer apparatus, and a storage medium. The method comprises: acquiring risk control data items, using risk control data items having a null rule set as target data items, and using risk control data items having a non-empty rule set as basic data items; calculating an information similarity level between scenario information in the target data items and scenario information in each of the basic data items, and acquiring the basic data item that contains the scenario information corresponding to the information similarity level as a data item to be recommended; calculating an event similarity level between a scenario event in each of the target data items and a scenario event in each data item to be recommended; and acquiring a data item to be recommended corresponding to an event similarity level having the largest numerical value, and recommending a risk control rule in the data item to be recommended to a professional company corresponding to the target data items. The invention achieves, at a low cost, timely recommendation of a risk control rule effectively preventing risks to a professional company having no configured risk control rules, thereby improving risk prevention of the professional company.

Description

Risk control data processing method, device, computer equipment and storage medium

This application is based on a Chinese invention patent application filed on June 08, 2018 with application number 201810585015.7 and entitled "Risk Control Data Processing Method, Apparatus, Computer Equipment, and Storage Medium", and claims its priority.

Technical field

The present application relates to the field of computer technology, and in particular, to a method, device, computer equipment, and storage medium for risk control data processing.

Background technique

At present, in many online shopping, online transaction and other business scenarios, various loopholes, risks, or economic crimes are prone to occur. It is often necessary to configure appropriate risk control rules for various types of business scenarios to prevent high frequencies. In the case of a risky business scenario, it is more necessary to configure risk control rules to protect the security of the business scenario, prevent risks, and reduce economic losses.

In traditional technology, manual methods are usually used to analyze the various business scenarios of each professional company and develop corresponding risk control rules. However, this method has a long development cycle, high input costs, and cannot provide effective risk prevention in a timely manner. Risk control rules.

Summary of the Invention

Based on this, it is necessary to provide a risk control data processing method that can timely recommend risk control rules that effectively prevent risks to professional companies that are not equipped with risk control rules and improve the risk prevention level of professional companies in response to the above technical problems. , Devices, computer equipment and storage media.

A risk control data processing method includes:

Obtain the wind control data of each professional company in the wind control database, where the wind control data includes scene information, scene events corresponding to each of the scene information, and rules containing wind control rules corresponding to each of the scene events A set, and a wind control hit rate corresponding to each of the wind control rules;

Selecting, from the risk control data, risk control data in which the rule set is empty as target data, and using the risk control data in which the rule set is not empty as basic data;

For each of the target data, calculate an information similarity between the scene information in the target data and the scene information in each of the basic data, and if the information similarity is greater than or equal to a preset similarity threshold, Then obtain the basic data where the scene information corresponding to the information similarity is located, and use the basic data as the data to be recommended;

Calculating an event similarity between a scene event in each of the target data and a scene event in each of the to-be-recommended data;

Acquire the to-be-recommended data corresponding to the event similarity with the largest value among the event similarities, and recommend the risk control rules in the to-be-recommended data to the professional company corresponding to the target data.

A wind control data processing device includes:

A data acquisition module is configured to acquire wind control data of each professional company in the wind control database, where the wind control data includes scene information, a scene event corresponding to each of the scene information, and a corresponding event of each of the scene events. A rule set including a risk control rule, and a risk control hit rate corresponding to each of the risk control rules;

A data screening module, configured to select, from the wind control data, wind control data in which the rule set is empty as target data, and use the wind control data in which the rule set is not empty as basic data;

An information calculation module is configured to calculate, for each of the target data, information similarity between scene information in the target data and scene information in each of the basic data, and if the information similarity is greater than or equal to If the similarity threshold is set, the basic data where the scene information corresponding to the information similarity is located is used as the data to be recommended;

An event calculation module, configured to calculate an event similarity between a scene event in each of the target data and a scene event in each of the to-be-recommended data;

The rule recommendation module is configured to obtain the data to be recommended corresponding to the event similarity with the largest value among the event similarities, and recommend the risk control rule in the data to be recommended to the professional company corresponding to the target data.

A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and the processor implements the above-mentioned wind control data processing when the processor executes the computer-readable instructions Method steps.

One or more non-volatile readable storage media storing computer-readable instructions, which, when executed by one or more processors, cause the one or more processors to implement the above-mentioned Control the steps of the data processing method.

Details of one or more embodiments of the present application are set forth in the accompanying drawings and description below, and other features and advantages of the present application will become apparent from the description, the drawings, and the claims.

BRIEF DESCRIPTION OF THE DRAWINGS

In order to explain the technical solutions of the embodiments of the present application more clearly, the drawings used in the description of the embodiments of the application will be briefly introduced below. Obviously, the drawings in the following description are just some embodiments of the application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without paying creative labor.

FIG. 1 is a schematic diagram of an application environment of a wind control data processing method according to an embodiment of the present application;

2 is a flowchart of a wind control data processing method according to an embodiment of the present application;

3 is a flowchart of acquiring wind control data in a wind control data processing method according to an embodiment of the present application;

4 is an implementation flowchart of step S5 in the wind control data processing method according to an embodiment of the present application;

5 is a flowchart of updating a wind control database in a wind control data processing method according to an embodiment of the present application;

6 is a schematic diagram of a wind control data processing device according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a computer device in an embodiment of the present application.

Detailed ways

In the following, the technical solutions in the embodiments of the present application will be clearly and completely described with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, but not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by a person of ordinary skill in the art without creative efforts shall fall within the protection scope of this application.

FIG. 1 shows an application environment provided by an embodiment of the present application. The application environment includes a server and a client. The server and the client are connected through a network, and the client is used to receive a recommendation request sent by a professional company. And send the received recommendation request from the professional company to the server. The client can specifically but not limited to various personal computers, laptops, smartphones, tablets and portable wearable devices; the server is used to carry out risk control data. For processing, the server can be implemented by an independent server or a server cluster composed of multiple servers. The risk control data processing method provided in the embodiment of the present application is applied to a server.

Please refer to FIG. 2, which illustrates an implementation process of a risk control data processing method provided by this embodiment. Details are as follows:

S1: Obtain the wind control data of each professional company in the wind control database, where the wind control data includes scene information, scene events corresponding to each scene information, a rule set containing wind control rules corresponding to each scene event, and each The risk control hit rate corresponding to each risk control rule.

In this embodiment, the method for obtaining the wind control data may be specifically obtained from the wind control database in real time, or may be obtained from the wind control database at predetermined intervals, and may be specifically set according to actual application requirements. Here, No restrictions.

Specifically, the wind control data includes scene information, scene events, rule sets, and wind control hit ratios. The correspondence between the scene information and the scene events can be a one-to-one correspondence or a one-to-many relationship. The rule set is a one-to-one relationship; the rule set can be empty or it can contain one or more risk control rules; each risk control rule has a one-to-one correspondence with the risk control hit rate, and the risk control hit rate is The number of times a scene event hits its corresponding risk control rule as a percentage of the total number of occurrences of the scene event is used to indicate the hit degree of each scene event.

For example, in the risk control data of professional company A, there is scene information "login", and the scene information "login" corresponds to a scene event "login transaction interface of user IP", and a rule set corresponding to this scene event has a wind The control rule is "the number of consecutive logins of a user IP at the same time, less than or equal to the preset number, otherwise the user IP login is restricted."

S2: The risk control data with the empty rule set is selected from the risk control data as the target data, and the wind control data with the non-empty rule set is used as the basic data.

In this embodiment, the target data is wind control data without a wind control rule configured, and the basic data is wind control data with a wind control rule configured.

Specifically, the rule set in the wind control data obtained in step S1 is traversed. If the rule set is retrieved as empty, the risk control data in which the rule set is located is marked as the target data. If the rule set retrieved is not empty, then The risk control data where the rule set is located is marked as the basic data.

From the obtained large amount of risk control data, it is clearly distinguished between target data that has not been configured with risk control rules, and basic data that has been configured with risk control rules, which is conducive to the subsequent search of target data to adapt to the risk control rules in the basic data.

S3: For each target data, calculate the information similarity between the scene information in the target data and the scene information in each basic data. If the information similarity is greater than or equal to a preset similarity threshold, obtain the information The basic data where the scene information corresponding to the similarity is located, and the basic data is used as the data to be recommended.

In this embodiment, the information similarity can be specifically obtained by calculating a ratio between the number of times the words in the scene information in the base data appear in the scene information in the target data and the total number of words in the scene information in the target data. The process of calculating information similarity is detailed as follows:

Perform segmentation processing on the scene information in the target data and the scene information in each basic data to obtain the target scene information vocabulary set and each basic scene information vocabulary set. If the words in the basic scene information vocabulary set are in the target scene information vocabulary If it appears once in the set, it will be marked as "1", if it appears twice, it will be marked as "2". Similarly, if it appears N times, it will be marked as "N". If it does not appear, it will be marked as "0". The total number of times a word in the scene information vocabulary appears in the target scene information vocabulary set, and the ratio of each total number of times to the total number of words in the target scene information vocabulary set is calculated. Examples are as follows:

Assume that the scene information of a basic data is "discount offer", and the vocabulary set of the basic scene information obtained by segmenting this scene information is unit1: discount / offer / activity, and the scene information in a target data is "promotional big reward event" ", The target scene information vocabulary set after segmenting the scene information in the target data is unit2: promotion / discount / big reward / activity, then the total number of times the word in unit1 appears in unit2 is 2, and the target scene information vocabulary set The total number of words is 4, and the ratio of the total number of times to the total number of words in the target scene information vocabulary set is 50%, that is, the information similarity between the scene information and the scene information of the target data is 50%.

Specifically, if the calculated information similarity is greater than or equal to a preset similarity threshold, the basic data where the scene information corresponding to the information similarity is located is used as the data to be recommended.

For example, suppose the preset similarity threshold is 50%. Following the above example, the similarity between the information of the basic data's scene information is "discount offers" and the target data's scene information is "promotional offers and big reward events". If the similarity of the information is equal to a preset similarity threshold, the basic data where the scene information is located is obtained, and the basic data is used as the data to be recommended.

It should be noted that the word segmentation processing can use a tool with a word segmentation function, which is not limited here. The preset similarity threshold may be specifically set according to actual service requirements, and is not limited here. Calculating information similarity can also be calculated using Jaccard's similarity formula, or other similarity calculation methods, which are not limited here.

S4: Calculate the event similarity between the scene event in each target data and the scene event in each to-be-recommended data.

In this embodiment, the process of calculating the event similarity is detailed as follows:

Perform word segmentation on the scene events in the target data and the scene events in each basic data to obtain the target scene event vocabulary set and each basic scene event vocabulary set;

The target scene event vocabulary set is deduplicated and merged with each basic scene event vocabulary set to obtain the scene event in the target data and the total event vocabulary set after each basic scene event is merged. For example, suppose the target data A contains 1 10 scene events, according to the target data A obtained in step S3, there are a total of 10 scene events to be recommended, and then 10 total event vocabulary sets can be obtained;

Calculate each word in the target scene event vocabulary set, the word frequency in each total event vocabulary set, get the word frequency vector of the target scene event vocabulary set in each total event vocabulary set, and calculate the basic scene event vocabulary set For each word in the set, the word frequency in its corresponding total event vocabulary set is used to obtain the word frequency vector of each basic scene event vocabulary set;

Calculate the cosine similarity between the word frequency vector of the target scene event vocabulary set and the word frequency vector of each base scene event vocabulary set. The larger the value of the cosine similarity, the more the scene event corresponding to the value and the scene event in the target data are. Similar, the cosine similarity is the event similarity.

To better understand this step, here is an example:

Assume that a basic scenario event is "login transaction interface of user IP", and the basic scenario event vocabulary set obtained by segmenting this basic scenario event is unit3: user / IP // login / transaction / interface, a scenario in the target data The event is "users use the account and password to log in to the trading interface", and the target event event vocabulary set after segmenting the scene events in the target data is unit4: user / use / account / password / login / transaction / interface, go to unit3 and unit4 Repeat the merge to get the target scene event vocabulary set and the basic scene event vocabulary set, and the combined total event vocabulary set unit5: user / IP // login / transaction / interface / use / account / password / login, calculate the words in unit3 Word frequency in unit5: User 1, IP1, 1, Login 1, Transaction 1, Interface 1, Use 0, Account 0, Password 0, Login 0, Calculate the word frequency of words in unit4 in unit5: User 1, IP0, 0, login 0, transaction 1, interface 1, use 1, account 1, password 1, login 1, the word frequency vector of the basic scene event vocabulary set is (1,1,1,1,1,1,0, 0,0,0), the word frequency vector of the target scene event vocabulary set is (1,0,0,0,1,1,1,1,1,1), and the target scene event vocabulary set is calculated according to the cosine similarity formula The cosine similarity between the word frequency vector of the vector and the word frequency vector of the base scene event vocabulary set, and the cosine value obtained is 0.463, that is, the event similarity between the scene event and the scene event in the target data is 0.463.

It should be noted that the cosine similarity formula is

Among them, x _i represents the component of the word frequency vector of the basic scene event vocabulary set in its corresponding total event vocabulary set, y _i represents the component of the word frequency vector of the target scene event vocabulary set in each total event vocabulary set, and p represents the cosine Similarity value, n represents the total number of words in the total event vocabulary set. To calculate the event similarity, you can also use the simhash mass similarity algorithm to calculate, or other similarity calculation methods, which are not limited here.

S5: Obtain the data to be recommended corresponding to the event similarity with the largest value in the event similarity, and recommend the risk control rules in the data to be recommended to the professional company corresponding to the target data.

Specifically, from the event similarity between the scene event in the target data and the scene event of each to-be-recommended data calculated in step S4, the event similarity with the largest value is selected to obtain the to-be-recommended data corresponding to the event similarity And recommend the risk control rules in the data to be recommended to the professional company corresponding to the target data.

It should be noted that the recommended method may specifically be email or instant messaging, or other methods, and the specific method may be set according to actual application requirements, and is not limited here.

In this embodiment, by acquiring the wind control data of each professional company in the wind control database, the wind control data with an empty rule set is selected, and the target data without the risk control rule is determined, and the rule set is not empty. The risk control data is used as the basic data, which is beneficial to the subsequent targeted search for an adapted risk control rule for the target data. At the same time, for each target data, the scene information in each target data and each basic data are calculated. The information similarity between the scene information of the. If the information similarity is greater than or equal to a preset similarity threshold, the basic data where the scene information corresponding to the information similarity is located is used as the data to be recommended. The data to be recommended can find the scope and direction of the risk control rules adapted to the target data, which is conducive to subsequent selection of the best recommendation results from the data to be recommended. The method of calculating similarity is simple, fast, and easy to operate. Further, Calculate the event similarity between the scene events in each target data and the scene events in each to-be-recommended data to obtain the number The data to be recommended corresponding to the event similarity with the largest value, and the risk control rules in the data to be recommended are recommended to the professional company corresponding to the target data. For the scene events in the target data, find the risk control rules applicable to the scene events It is a low-cost implementation for professional companies corresponding to target data that has not been equipped with risk control rules to recommend adapted risk control rules in a timely manner, which is conducive to improving the risk prevention level of professional companies.

In an embodiment, after step S2 and before step S3, the risk control data processing method further includes the following steps:

S6: If a risk control recommendation request from a professional company is received, the target data is updated according to the risk control recommendation request.

Specifically, it receives a risk control recommendation request from a professional company whose risk control data is not included in the risk control database, obtains the risk control data of the professional company, and saves the risk control data as updated target data to the risk control. Database.

In this embodiment, a risk control recommendation request is received from a professional company whose risk control data is not included in the risk control database. According to the risk control recommendation request, an adapted company can be found in the risk control database for the professional company. Risk control rules, and recommend the adapted risk control rules to the professional company, reflecting practicality and broad applicability.

In an embodiment, as shown in FIG. 3, before step S1, the method for processing wind control data further includes the following steps:

S7: Monitor each scene event of each professional company. If it is detected that the scene event is triggered and the risk control rule in the rule set corresponding to the scene event is detected, then the hit information of the scene event is recorded, where the hit information includes the The time when a scene event occurs and the risk control rules that the scene event hits.

In this embodiment, a scenario event hits a risk control rule in a rule set corresponding to the scenario event, which means that a situation occurring in the scenario event violates a constraint condition in the configured risk control rule, or exceeds a constraint condition in the risk control rule. Restrictions.

For example, suppose a scenario event is "Users can receive merchant coupons during coupon discount activities" and the configured risk control rule is "A user IP can only receive coupons once, otherwise, the use of that IP is restricted". The specific process of the event is that the user logs in the merchant software and clicks the button to receive the coupon. If it is detected that the same user IP has clicked to receive the coupon 100 times at the same time, it may be that the user used the fraud software to conduct a coupon to the merchant. Unreasonable possession, confirm that it violates the risk control rules configured for this scenario event, and will limit the use of the user IP in the merchant software, that is, the scenario event hits the risk control rule in the rule set corresponding to the scenario event.

Specifically, monitor each scene event of each professional company, record the occurrence time of the detected scene event when it is triggered, and when the scene event is triggered, whether to hit the risk control rule in the rule set corresponding to the scene event, and record The wind control log in the wind control database can directly reflect the hit situation of each scene event, which is beneficial to the subsequent analysis and calculation of wind control data.

S8: Count the data amount of each scene event in a preset time period according to the hit information every predetermined time interval, where the data amount includes the number of scene event occurrences and each risk control in the rule set corresponding to the scene event The number of times the rule was hit.

Specifically, every predetermined time interval, according to the hit information recorded in the wind control log in step S7, the number of occurrences of each scene event within a preset period of time and a rule set corresponding to the scene event are counted. The number of times each risk control rule was hit.

For example, assuming that the preset time period is "1st to 15th in January", continue to use the example in step S7. For example, if the statistics are obtained from "1st to 15th in January", the scenario event "Users can pick up coupons" In the discount campaign, the number of times of "Get Merchant Coupon" occurred 500 times, and the number of hits to the corresponding risk control rules was 5 times.

It should be noted that the predetermined time interval and the preset time period may be specifically set according to actual service requirements, and are not limited here.

S9: Calculate the wind control hit rate of each scene event according to the amount of data.

In this embodiment, the wind control hit rate of each scene event is the number of times each wind control rule is hit in the rule set corresponding to the scene event within a preset time period of each scene event and the occurrence of the scene event. The ratio of the number of times, the higher the hit rate, it means that the scene event is more prone to risk.

Continue to use the example in step S8, for example, the scenario event "users can collect merchant coupons during coupon collection discounts" has a risk control hit rate of 1% during the period of "1st to 15th of January".

In this embodiment, each scene event of each professional company is monitored, the time when the detected scene event is triggered, and when the scene event is triggered, whether the risk control rule in the rule set corresponding to the scene event is hit. The wind control log recorded in the wind control database can intuitively reflect the hit situation of each scene event, which is conducive to subsequent analysis and calculation of wind control data, so as to count the scene of each scene event within a preset time period. The number of event occurrences and the number of times each risk control rule in the rule set corresponding to the scenario event is calculated can calculate the risk control hit rate of each scenario event, which can fully reflect the degree of risk of each scenario event.

In an embodiment, as shown in FIG. 4, in step S5, the data to be recommended corresponding to the event similarity with the largest value in the event similarity is obtained, and the risk control rule in the data to be recommended is recommended to the target data. The corresponding professional company includes the following steps:

S501: Acquire to-be-recommended data corresponding to the event similarity with the largest numerical value in the event similarity as standard data.

Specifically, from the event similarity between the scene event of each target data and the scene event of each to-be-recommended data obtained in step S4, the event similarity with the largest numerical value is selected, and the wind corresponding to the event similarity corresponds to the wind. Control data is used as standard data to be recommended to professional companies.

S502: From the standard data, filter out the wind control hit ratio with the largest value, and recommend the wind control rule corresponding to the wind control hit ratio to the professional company corresponding to the target data.

Specifically, according to the wind control hit rate of each scene event calculated and calculated in step S9, in the standard data, the wind control hit rate with the largest value is selected, and the wind control rule corresponding to the wind control hit rate is selected. As a risk control rule most suitable for the target data, it is recommended to the professional company corresponding to the target data.

For example, in the standard data, there is a scenario event "On a shopping platform, a shopping transaction is performed." This scenario event corresponds to the risk control rule-"The amount of each transaction cannot exceed 20,000 yuan, otherwise, the transaction is stopped." The rate is 5%. There is risk control rule two. “The number of transactions per day must not exceed 20, otherwise, the transaction is stopped.” If the risk control hit rate is 2%, then the risk control rule 1 corresponding to the risk control hit rate of 5% is selected. , Recommended to the professional company corresponding to the target data.

In this embodiment, by selecting the event similarity with the largest value and using the risk control data corresponding to the event similarity as the standard data to be recommended to a professional company, at the same time, the risk control with the largest value is selected from the standard data. Hit rate, and the risk control rule corresponding to the risk control hit rate is used as the risk control rule most suitable for the target data. It is recommended to the professional company corresponding to the target data. The risk control hit rate can intuitively reflect its corresponding scene events. The degree of risk occurrence is conducive to improving the level of risk prevention of scene events of the target data.

In an embodiment, as shown in FIG. 5, after step S5, the method for processing wind control data further includes the following steps:

S10: Obtain the target risk control rule confirmed by the professional company in the confirmation information according to the confirmation information fed back by the professional company corresponding to the target data.

Specifically, the confirmation information fed back by the professional company corresponding to the target data is received, and the confirmation information includes the recommended risk control rule confirmed for use by the professional company, and the confirmed risk control rule is used as the target risk control rule.

S11: In the risk control database, configure the target risk control rule into a rule set corresponding to the target data.

Specifically, according to the target wind control rule obtained in step S10, the wind control data in the wind control database is updated, that is, the target wind control rule is configured into a rule set corresponding to the target data.

In this embodiment, according to the confirmation information fed back by the professional company corresponding to the target data, the target risk control rule confirmed by the professional company in the confirmation information is obtained, and the target risk control rule is configured in the risk control database to the target data In the rule set, updating the wind control data can fully reflect the hit situation of the target data configured with the wind control rules. On the other hand, the wind control data can be used to have similar or same scenarios with the target data. For other professional companies that do not have risk control rules, recommending risk control rules will help improve the level of risk prevention of each professional company.

It should be understood that the size of the sequence numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

In one embodiment, a wind control data processing device is provided. The wind control data processing device corresponds to the wind control data processing method in the above embodiment in a one-to-one correspondence. As shown in FIG. 6, the risk control data processing device includes a data acquisition module 601, a data screening module 602, an information calculation module 603, an event calculation module 604, and a rule recommendation module 605. The detailed description of each function module is as follows:

A data acquisition module 601 is used to acquire wind control data of each professional company in the wind control database, where the wind control data includes scene information, scene events corresponding to each scene information, and each scene event corresponding to a wind control rule. Rule set, and the risk control hit rate corresponding to each risk control rule;

The data screening module 602 is configured to screen out wind control data from which the rule set is empty as target data, and use the wind control data whose rule set is not empty as basic data;

An information calculation module 603 is configured to calculate, for each target data, the information similarity between the scene information in the target data and the scene information in each basic data, if the information similarity is greater than or equal to a preset similarity threshold , Obtain the basic data where the scene information corresponding to the information similarity is located, and use the basic data as the data to be recommended;

An event calculation module 604, configured to calculate an event similarity between a scene event in each target data and a scene event in each to-be-recommended data;

The rule recommendation module 605 is configured to obtain the data to be recommended corresponding to the event similarity with the largest value in the event similarity, and recommend the risk control rule in the data to be recommended to the professional company corresponding to the target data.

Further, the risk control data processing device further includes:

The request receiving module 606 is configured to update the target data according to the risk control recommendation request if a risk control recommendation request from a professional company is received.

Further, the risk control data processing device further includes:

A hit recording module 607 is used to monitor each scene event of each professional company. If it is detected that a scene event is triggered and the risk control rule in the rule set corresponding to the scene event is detected, the hit information of the scene event is recorded, where The hit information includes the occurrence time of the scene event and the risk control rule of the scene event hit;

A data statistics module 608 is configured to count the data amount of each scene event in a preset time period according to the hit information at a predetermined time interval, where the data amount includes the number of scene event occurrences and a rule set corresponding to the scene event The number of times each risk control rule was hit;

The hit calculation module 609 is configured to calculate a wind control hit rate of each scene event according to the amount of data.

Further, the rule recommendation module 605 includes:

A data obtaining unit 6051 is configured to obtain data to be recommended corresponding to the event similarity with the largest numerical value among the event similarities as standard data;

A rule recommending unit 6052 is used to filter out the wind control hit ratio with the largest value from the standard data, and recommend the wind control rule corresponding to the wind control hit ratio to the professional company corresponding to the target data.

Further, the risk control data processing device further includes:

An information feedback module 610 is configured to obtain the target risk control rule confirmed by the professional company in the confirmation information according to the confirmation information fed back by the professional company corresponding to the target data;

A rule configuration module 611 is configured to configure a target risk control rule in a risk control database to a rule set corresponding to the target data.

For the specific limitation of the wind control data processing device, refer to the foregoing limitation on the wind control data processing method, which will not be repeated here. Each module in the above-mentioned wind control data processing device may be implemented in whole or in part by software, hardware, and a combination thereof. The above-mentioned modules may be embedded in the hardware in or independent of the processor in the computer device, or may be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. 7. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer-readable instructions, and a database. The internal memory provides an environment for the operation of the operating system and computer-readable instructions in a non-volatile storage medium. The database of the computer equipment is used to store risk control data. The network interface of the computer device is used to communicate with an external terminal through a network connection. The computer-readable instructions are executed by a processor to implement a method for processing wind control data.

In one embodiment, a computer device is provided, including a memory, a processor, and computer-readable instructions stored on the memory and executable on the processor. When the processor executes the computer-readable instructions, the wind control of the foregoing embodiment is implemented. The steps of the data processing method are, for example, steps S1 to S5 shown in FIG. 2. Alternatively, when the processor executes the computer-readable instructions, the functions of the modules / units of the wind control data processing device in the foregoing embodiment are implemented, for example, the functions of modules 601 to 605 shown in FIG. 6. To avoid repetition, we will not repeat them here.

In one embodiment, a non-volatile storage medium is provided, on which computer-readable instructions are stored, and when the computer-readable instructions are executed by a processor, the wind control data processing method in the foregoing method embodiment is implemented, or the computer When the readable instructions are executed by the processor, the functions of each module / unit in the wind control data processing device in the above device embodiment are realized. To avoid repetition, we will not repeat them here.

A person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by using computer-readable instructions to instruct related hardware. The computer-readable instructions can be stored in a non-volatile computer. In the readable storage medium, the computer-readable instructions, when executed, may include the processes of the embodiments of the methods described above. Wherein, any reference to the storage, storage, database, or other media used in the embodiments provided in this application may include non-volatile and / or volatile storage. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain (Synchlink), DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

Those skilled in the art can clearly understand that, for the convenience and brevity of the description, only the above-mentioned division of functional units and modules is used as an example. In practical applications, the above functions can be assigned by different functional units, Module completion, that is, dividing the internal structure of the device into different functional units or modules to complete all or part of the functions described above.

The above-mentioned embodiments are only used to describe the technical solution of the present application, but are not limited thereto. Although the present application is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still implement the foregoing implementations. The technical solutions described in the examples are modified, or some of the technical features are equivalently replaced; and these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the application, and should be included in Within the scope of this application.

Claims

A wind control data processing method, characterized in that the wind control data processing method includes:

Obtain the wind control data of each professional company in the wind control database, where the wind control data includes scene information, scene events corresponding to each of the scene information, and rules containing wind control rules corresponding to each of the scene events A set, and a wind control hit rate corresponding to each of the wind control rules;

Selecting, from the risk control data, risk control data in which the rule set is empty as target data, and using the risk control data in which the rule set is not empty as basic data;

For each of the target data, calculate an information similarity between the scene information in the target data and the scene information in each of the basic data, and if the information similarity is greater than or equal to a preset similarity threshold, Then obtain the basic data where the scene information corresponding to the information similarity is located, and use the basic data as the data to be recommended;

Calculating an event similarity between a scene event in each of the target data and a scene event in each of the to-be-recommended data;

Acquire the to-be-recommended data corresponding to the event similarity with the largest value among the event similarities, and recommend the risk control rules in the to-be-recommended data to the professional company corresponding to the target data.
The method for processing risk control data according to claim 1, wherein the risk control data in which the rule set is empty is selected from the risk control data as target data, and the rule set is not After the empty wind control data is used as the basic data, and for each of the target data, the information similarity between the scene information in the target data and the scene information in each of the basic data is calculated. Before the information similarity is greater than or equal to a preset similarity threshold, the basic data where the scene information corresponding to the information similarity is located and before the basic data is used as the data to be recommended, the method for processing wind control data further includes:

If a risk control recommendation request from a professional company is received, the target data is updated according to the risk control recommendation request.
The wind control data processing method according to claim 1 or 2, wherein before the acquiring wind control data of each professional company in the wind control database, the wind control data processing method further comprises:

Monitoring each of the scene events of each of the professional companies, and if it is detected that the scene event is triggered and hits a wind control rule in a rule set corresponding to the scene event, then the hit information of the scene event is recorded, wherein, The hit information includes the occurrence time of the scene event and the risk control rule of the scene event hit;

Every predetermined time interval, according to the hit information, the data amount of each scene event in a preset time period is counted, wherein the data amount includes the number of times the scene event occurs and a rule corresponding to the scene event The number of times each risk control rule in the set was hit;

According to the amount of data, a wind control hit rate of each of the scene events is calculated.
The method for processing risk control data according to claim 1 or 2, wherein the to-be-recommended data corresponding to the event similarity with the largest value among the event similarities is obtained, and the risk control in the to-be-recommended data is The rules recommended to the professional company corresponding to the target data include:

Acquiring to-be-recommended data corresponding to the event similarity with the largest value among the event similarities as standard data;

From the standard data, the wind control hit ratio with the largest value is selected, and the wind control rule corresponding to the wind control hit ratio is recommended to the professional company corresponding to the target data.
The method for processing risk control data according to claim 1 or 2, characterized in that: the to-be-recommended data corresponding to the event similarity with the largest value among the event similarities is obtained, and the risk in the to-be-recommended data is obtained. After the control rules are recommended to the professional company corresponding to the target data, the method for processing risk control data further includes:

Obtaining the target risk control rule confirmed by the professional company in the confirmation information according to the confirmation information fed back by the professional company corresponding to the target data;

In the risk control database, the target risk control rule is configured into a rule set corresponding to the target data.
A wind control data processing device, characterized in that the wind control data processing device includes:

A data acquisition module is configured to acquire wind control data of each professional company in the wind control database, where the wind control data includes scene information, a scene event corresponding to each of the scene information, and a corresponding event of each of the scene events. A rule set including a risk control rule, and a risk control hit rate corresponding to each of the risk control rules;

A data screening module, configured to select, from the wind control data, wind control data in which the rule set is empty as target data, and use the wind control data in which the rule set is not empty as basic data;

An information calculation module is configured to calculate, for each of the target data, information similarity between scene information in the target data and scene information in each of the basic data, and if the information similarity is greater than or equal to If the similarity threshold is set, the basic data where the scene information corresponding to the information similarity is located is used as the data to be recommended;

An event calculation module, configured to calculate an event similarity between a scene event in each of the target data and a scene event in each of the to-be-recommended data;

The rule recommendation module is configured to obtain the data to be recommended corresponding to the event similarity with the largest value among the event similarities, and recommend the risk control rule in the data to be recommended to the professional company corresponding to the target data.
The wind control data processing device according to claim 6, wherein the wind control data processing device further comprises:

The request receiving module is configured to update the target data according to the risk control recommendation request if a risk control recommendation request from a professional company is received.
The wind control data processing device according to claim 6 or 7, wherein the wind control data processing device further comprises:

The hit recording module is configured to monitor each of the scene events of each of the professional companies, and if it is detected that the scene event is triggered and hits a wind control rule in a rule set corresponding to the scene event, the scene event is recorded The hit information, wherein the hit information includes a time of occurrence of the scene event and a risk control rule of the scene event hit;

A data statistics module is configured to count a data amount of each scene event in a preset time period according to the hit information at a predetermined time interval, where the data amount includes the number of times the scene event occurs and The number of times each risk control rule in the rule set corresponding to the scenario event is hit;

A hit calculation module is configured to calculate a wind control hit rate of each of the scene events according to the data amount.
The wind control data processing device according to claim 6 or 7, wherein the rule recommendation module comprises:

A data obtaining unit, configured to obtain data to be recommended corresponding to the event similarity with the largest numerical value among the event similarities as standard data;

A rule recommendation unit is configured to select the wind control hit ratio with the largest value from the standard data, and recommend the wind control rule corresponding to the wind control hit ratio to a professional company corresponding to the target data .
The wind control data processing device according to claim 6 or 7, wherein the wind control data processing device further comprises:

An information feedback module, configured to obtain target risk control rules confirmed by the professional company in the confirmation information according to the confirmation information fed back by the professional company corresponding to the target data;

A rule configuration module is configured to configure the target risk control rule in the risk control database to a rule set corresponding to the target data.
A computer device includes a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor, and is characterized in that the processor implements the computer-readable instructions as follows step:

Obtain the wind control data of each professional company in the wind control database, where the wind control data includes scene information, scene events corresponding to each of the scene information, and rules containing wind control rules corresponding to each of the scene events A set, and a wind control hit rate corresponding to each of the wind control rules;

Selecting, from the risk control data, risk control data in which the rule set is empty as target data, and using the risk control data in which the rule set is not empty as basic data;

For each of the target data, calculate an information similarity between the scene information in the target data and the scene information in each of the basic data, and if the information similarity is greater than or equal to a preset similarity threshold, Then obtain the basic data where the scene information corresponding to the information similarity is located, and use the basic data as the data to be recommended;

Calculating an event similarity between a scene event in each of the target data and a scene event in each of the to-be-recommended data;

Acquire the to-be-recommended data corresponding to the event similarity with the largest value among the event similarities, and recommend the risk control rules in the to-be-recommended data to the professional company corresponding to the target data.
The computer device according to claim 11, wherein the wind control data in which the rule set is empty is selected from the wind control data as target data, and the wind in which the rule set is not empty is selected. After controlling data as basic data, and for each of the target data, calculating information similarity between scene information in the target data and scene information in each of the basic data, if the information is similar If the degree is greater than or equal to a preset similarity threshold, the basic data where the scene information corresponding to the similarity of the information is located, and before the basic data is used as the data to be recommended, the processor also executes the computer-readable instructions. To achieve the following steps:

If a risk control recommendation request from a professional company is received, the target data is updated according to the risk control recommendation request.
The computer device according to claim 11 or 12, wherein before the acquiring the wind control data of each professional company in the wind control database, the processor further implements the following steps when executing the computer-readable instructions :

Monitoring each of the scene events of each of the professional companies, and if it is detected that the scene event is triggered and hits a wind control rule in a rule set corresponding to the scene event, then the hit information of the scene event is recorded, wherein, The hit information includes the occurrence time of the scene event and the risk control rule of the scene event hit;

Every predetermined time interval, according to the hit information, the data amount of each scene event in a preset time period is counted, wherein the data amount includes the number of times the scene event occurs and a rule corresponding to the scene event The number of times each risk control rule in the set was hit;

According to the amount of data, a wind control hit rate of each of the scene events is calculated.
The computer device according to claim 11 or 12, wherein the to-be-recommended data corresponding to the event similarity with the largest numerical value in the event similarity is obtained, and the risk control rule in the to-be-recommended data is recommended. The professional company corresponding to the target data includes:

Acquiring to-be-recommended data corresponding to the event similarity with the largest value among the event similarities as standard data;

From the standard data, the wind control hit ratio with the largest value is selected, and the wind control rule corresponding to the wind control hit ratio is recommended to the professional company corresponding to the target data.
The computer device according to claim 11 or 12, wherein, in the step of acquiring the data to be recommended corresponding to the event similarity having the largest value among the event similarities, the risk control rules in the data to be recommended are obtained, After recommending to the professional company corresponding to the target data, the processor further implements the following steps when executing the computer-readable instructions:

Obtaining the target risk control rule confirmed by the professional company in the confirmation information according to the confirmation information fed back by the professional company corresponding to the target data;

In the risk control database, the target risk control rule is configured into a rule set corresponding to the target data.
One or more non-volatile readable storage media storing computer readable instructions, characterized in that when the computer readable instructions are executed by one or more processors, the one or more processors are caused to execute The following steps:

Obtain the wind control data of each professional company in the wind control database, where the wind control data includes scene information, scene events corresponding to each of the scene information, and rules containing wind control rules corresponding to each of the scene events A set, and a wind control hit rate corresponding to each of the wind control rules;

Selecting, from the risk control data, risk control data in which the rule set is empty as target data, and using the risk control data in which the rule set is not empty as basic data;

For each of the target data, calculate an information similarity between the scene information in the target data and the scene information in each of the basic data, and if the information similarity is greater than or equal to a preset similarity threshold, Then obtain the basic data where the scene information corresponding to the information similarity is located, and use the basic data as the data to be recommended;

Calculating an event similarity between a scene event in each of the target data and a scene event in each of the to-be-recommended data;

Acquire the to-be-recommended data corresponding to the event similarity with the largest value among the event similarities, and recommend the risk control rules in the to-be-recommended data to the professional company corresponding to the target data.
The non-volatile readable storage medium according to claim 16, wherein the wind control data with the rule set empty is selected from the wind control data as target data, and the rule is After collecting non-empty risk control data as basic data, and for each of the target data, calculating information similarity between scene information in the target data and scene information in each of the basic data If the similarity of the information is greater than or equal to a preset similarity threshold, then obtain the basic data where the scene information corresponding to the information similarity is located, and before using the basic data as the data to be recommended, the computer-readable instructions are When the one or more processors execute, the one or more processors further perform the following steps:

If a risk control recommendation request from a professional company is received, the target data is updated according to the risk control recommendation request.
The non-volatile readable storage medium according to claim 16 or 17, wherein before the obtaining wind control data of each professional company in the wind control database, the computer-readable instructions are read by one or more When the two processors execute, the one or more processors further perform the following steps:

Monitoring each of the scene events of each of the professional companies, and if it is detected that the scene event is triggered and hits a wind control rule in a rule set corresponding to the scene event, then the hit information of the scene event is recorded, wherein, The hit information includes the occurrence time of the scene event and the risk control rule of the scene event hit;

Every predetermined time interval, according to the hit information, the data amount of each scene event in a preset time period is counted, wherein the data amount includes the number of times the scene event occurs and a rule corresponding to the scene event The number of times each risk control rule in the set was hit;

According to the amount of data, a wind control hit rate of each of the scene events is calculated.
The non-volatile readable storage medium according to claim 16 or 17, characterized in that, the to-be-recommended data corresponding to the event similarity with the largest value among the event similarities is obtained, and the to-be-recommended data is Risk control rules recommended to professional companies corresponding to the target data include:

Acquiring to-be-recommended data corresponding to the event similarity with the largest value among the event similarities as standard data;

From the standard data, the wind control hit ratio with the largest value is selected, and the wind control rule corresponding to the wind control hit ratio is recommended to the professional company corresponding to the target data.
The non-volatile readable storage medium according to claim 16 or 17, wherein in the step of acquiring the data to be recommended corresponding to the event similarity having the largest value among the event similarities, the data to be recommended After the risk control rules in the recommendation are recommended to the professional company corresponding to the target data, when the computer-readable instructions are executed by one or more processors, the one or more processors further perform the following steps:

Obtaining the target risk control rule confirmed by the professional company in the confirmation information according to the confirmation information fed back by the professional company corresponding to the target data;

In the risk control database, the target risk control rule is configured into a rule set corresponding to the target data.