Abnormal data identification method and device, electronic device and storage medium

By determining business scenarios and event attributes, generating data collection rules and analysis rules, identifying abnormal behaviors in insurance companies' online customer acquisition strategies, solving the problems of unstable data quality and revenue loss, and achieving effective abnormal data identification and analyze.

CN114168632BActive Publication Date: 2024-11-26泰康保险集团股份有限公司 +1
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111483136.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-12-07
Publication Date
2024-11-26
Estimated Expiration
2041-12-07

AI Technical Summary

Technical Problem

There are fake machines, fake users and fake behaviors in the online customer acquisition strategy of insurance companies, resulting in revenue loss and lack of unified data collection and management tools, resulting in unstable data quality and difficult to support abnormal analysis.

Method used

By determining the business scenarios to be collected, generating the business events and event attributes to be collected, and establishing data collection rules, obtaining pre-configured abnormal data analysis rules, performing abnormal analysis of business data, and identifying abnormal behaviors.

Benefits of technology

It realizes unified management of data collection, improves data quality, can effectively identify abnormal behaviors, support business decisions, and improves the accuracy and timeliness of identifying abnormal data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114168632B_ABST
    Figure CN114168632B_ABST
Patent Text Reader

Abstract

The present disclosure is about an abnormal data identification method and device, an electronic device and a computer-readable storage medium, which relates to the field of computer technology and can be applied to determine whether there are scenarios of abnormal user behavior in business data. The method includes: determining the business scenario to be collected, generating business events to be collected and event attributes to be collected corresponding to the business scenario to be collected; determining the logical association relationship between the three, and generating data collection rules according to the scenario definition information, event definition information, attribute definition information and the logical association relationship; performing data collection operations according to the data collection rules to obtain business data to be analyzed; obtaining pre-configured abnormal data analysis rules, and performing abnormal analysis processing on the business data to be analyzed according to the abnormal data analysis rules to obtain abnormal analysis results. The present disclosure obtains the business data to be analyzed according to the data collection rules, and uses the abnormal data analysis rules to determine whether the business data to be analyzed is abnormal.
Need to check novelty before this filing date? Find Prior Art

Description

Background Art

[0002] As Internet technology becomes more and more popular, more and more companies are choosing to expand their customer base by combining online and offline methods. For example, a company's online customer acquisition strategy can include advertising, traffic cooperation, third-party channel cooperation and other methods.

[0003] However, there are certain problems with the above online customer acquisition strategies. For example, in the online customer acquisition strategies of insurance companies, some traffic users are driven by profit and conduct business through various arbitrage methods such as fake machines, fake users, and fake behaviors, which has a negative impact on the company's revenue. For example, an analysis of the business data of insurance companies found that some individuals repeatedly insured multiple people through the repurchase link and terminated the contract in a short period of time; it also identified that individual devices had a large number of repeated page visits in a short period of time, so companies urgently need to establish business anti-fraud capabilities to deal with similar risks.

[0004] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore may include information that does not constitute the prior art known to ordinary technicians in the field. Summary of the invention

[0005] The purpose of the present disclosure is to provide an abnormal data identification method, an abnormal data identification device, an electronic device and a computer-readable storage medium, thereby at least to a certain extent overcoming the problem of lack of a unified management tool for data collection in user abnormal behavior analysis solutions, resulting in unstable data quality and difficulty in supporting subsequent data anomaly analysis applications.

[0006] Other features and advantages of the present disclosure will become apparent from the following detailed description, or may be learned in part by the practice of the present invention.

[0007] According to a first aspect of the present disclosure, there is provided an abnormal data identification method, comprising: determining a business scenario to be collected, generating a business event to be collected and an event attribute to be collected corresponding to the business scenario to be collected; the business scenario to be collected includes scenario definition information, the business event to be collected includes event definition information, and the event attribute to be collected includes attribute definition information; determining a logical association relationship among the business scenario to be collected, the business event to be collected and the event attribute to be collected, and generating a data collection rule according to the scenario definition information, the event definition information, the attribute definition information and the logical association relationship; performing a data collection operation according to the data collection rule to obtain business data to be analyzed; obtaining a pre-configured abnormal data analysis rule, and performing abnormal analysis processing on the business data to be analyzed according to the abnormal data analysis rule to obtain an abnormal analysis result.

[0008] According to a second aspect of the present disclosure, there is provided an abnormal data identification device, comprising: a scenario event determination module, used to determine a business scenario to be collected, and generate a business event to be collected and an event attribute to be collected corresponding to the business scenario to be collected; the business scenario to be collected includes scenario definition information, the business event to be collected includes event definition information, and the event attribute to be collected includes attribute definition information; a collection rule determination module, used to determine a logical association relationship between the business scenario to be collected, the business event to be collected and the event attribute to be collected, and generate a data collection rule according to the scenario definition information, the event definition information, the attribute definition information and the logical association relationship; a data collection module, used to perform a data collection operation according to the data collection rule to obtain business data to be analyzed; an abnormal analysis module, used to obtain a pre-configured abnormal data analysis rule, and perform abnormal analysis processing on the business data to be analyzed according to the abnormal data analysis rule to obtain an abnormal analysis result.

[0009] In an exemplary embodiment of the present disclosure, the event attributes to be collected include common event attributes and private event attributes; the scenario event determination module includes a scenario event determination unit, which is used to obtain a business scenario definition template, and determine the business scenario to be collected according to the business scenario definition template and the common event attributes; obtain a business event generation template, and configure the event definition information according to the business event generation template to generate the business event to be collected; the business event to be collected includes private event attributes; obtain an event attribute generation template and an attribute verification rule, and configure private attribute definition information for the private event attributes according to the event attribute generation template and the attribute verification rule to generate the event attributes to be collected.

[0010] In an exemplary embodiment of the present disclosure, a scenario event determination unit includes a scenario determination sub-unit, which is used to determine the scenario field to be configured according to the business scenario definition template; the scenario field to be configured includes a scenario name, a scenario classification, and a business event naming rule; a configuration operation is performed on the scenario field to be configured to obtain the name of the scene to be collected, the classification of the scene to be collected, and the naming rule of the event to be collected; and the business scenario to be collected is generated according to the common event attributes, the name of the scene to be collected, the classification of the scene to be collected, and the naming rule of the event to be collected.

[0011] In an exemplary embodiment of the present disclosure, a scenario event determination unit includes an event determination subunit, which is used to determine the event field to be configured based on the business event generation template; the event field to be configured includes the scene to which it belongs, the event name, the event type, and the event identifier; a configuration operation is performed on the scene field to be configured to obtain the scene type to which it belongs, the event name to which it is collected, the event type to which it is collected, and the event identifier to which it is collected; based on the business event generation template, the associated private event attributes are filled in, and the business event to be collected is generated according to the scene type to which it belongs, the event name to which it is collected, the event type to which it is collected, the event identifier to which it is collected, and the private event attributes.

[0012] In an exemplary embodiment of the present disclosure, the abnormal data identification device also includes an analysis rule generation module, which is used to determine an analysis rule name; determine multiple behavior analysis rules corresponding to the analysis rule name, and determine a rule association relationship between the multiple behavior analysis rules; and generate the abnormal data analysis rule according to the analysis rule name, the multiple behavior analysis rules and the rule association relationship.

[0013] In an exemplary embodiment of the present disclosure, the anomaly analysis module includes an anomaly analysis unit, which is used to determine the behavior category corresponding to the business data to be analyzed; perform event classification processing on the behavior category to obtain a behavior event classification result; perform the anomaly analysis processing according to the behavior event classification result and the anomaly data analysis rule to obtain the anomaly analysis result.

[0014] In an exemplary embodiment of the present disclosure, the abnormal analysis unit includes an abnormal analysis sub-unit, which is used to determine the target event attribute corresponding to the business data to be analyzed if the behavior event classification result belongs to the event category; obtain the event attribute threshold corresponding to the target event attribute, and determine the first analysis result according to the event attribute threshold; if the behavior event classification result belongs to the non-event category, determine the behavior information included in the business data to be analyzed; obtain the behavior information threshold corresponding to the behavior information, and determine the second analysis result according to the behavior information threshold; determine the abnormal analysis result according to the first analysis result and the second analysis result.

[0015] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the abnormal data identification method according to any one of the above items is implemented.

[0016] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the abnormal data identification method according to any one of the above items is implemented.

[0017] The technical solution provided by the present disclosure may include the following beneficial effects: on the one hand, data collection is performed according to the data collection rules generated by the business events to be collected and the attributes of the events to be collected corresponding to the business scenarios to be collected, as well as the association between the three, so that data collection is uniformly and effectively managed, and the quality of the collected data is also significantly improved. On the other hand, by performing abnormal analysis on the collected business data, abnormal behavior data in the business data can be effectively identified, and the obtained analysis results can be used in business decisions.

[0018] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described below are only some embodiments of the present disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0020] Figure 1 A flowchart of an abnormal data identification method according to an exemplary embodiment of the present disclosure is schematically shown;

[0021] Figure 2 The overall structure diagram of the abnormal behavior identification system according to the exemplary embodiment of the present disclosure is schematically shown;

[0022] Figure 3 A diagram schematically shows a logical association relationship between business scenarios, business events, and event attributes according to an exemplary embodiment of the present disclosure;

[0023] Figure 4 A management diagram of a business scenario according to an exemplary embodiment of the present disclosure is schematically shown;

[0024] Figure 5 A schematic diagram of managing scene events according to an exemplary embodiment of the present disclosure is schematically shown;

[0025] Figure 6 A schematic diagram of managing event attributes according to an exemplary embodiment of the present disclosure is schematically shown;

[0026] Figure 7 A flowchart of abnormal behavior identification, analysis and management according to an exemplary embodiment of the present disclosure is schematically shown;

[0027] Figure 8 Schematically shows an interface diagram of a functional design for generating abnormal data analysis rules according to an exemplary embodiment of the present disclosure;

[0028] Fig. 9 Schematically shows a block diagram of an abnormal data identification device according to an exemplary embodiment of the present disclosure;

[0029] Fig.10 A block diagram schematically shows an electronic device according to an exemplary embodiment of the present disclosure;

[0030] Fig.11 A schematic diagram of a computer-readable storage medium according to an exemplary embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0031] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, these embodiments are provided so that this disclosure will be comprehensive and complete and will fully convey the concepts of the example embodiments to those skilled in the art. The same reference numerals in the figures represent the same or similar parts, and thus their repeated description will be omitted.

[0032] In addition, the described features, structures or characteristics may be combined in one or more embodiments in any suitable manner. Many specific details are provided in the following description to provide a full understanding of the embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be adopted. In other cases, known structures, methods, devices, implementations, materials or operations are not shown or described in detail to avoid blurring the various aspects of the present disclosure.

[0033] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or these functional entities or parts of functional entities may be implemented in one or more software hardened modules, or these functional entities may be implemented in different networks and / or processor devices and / or microcontroller devices.

[0034] In the process of enterprises using online customer acquisition strategies (such as advertising and traffic cooperation channels) to acquire new customers, there is a certain lag in the discovery of users who place fake orders or take advantage of the platform. At present, the method of analyzing user behavior is mainly through monitoring renewal-related reports. Only after discovering user loss do we know that there is a problem with the quality of the channel. There is a lack of appropriate analysis tools for judging low-quality users based on user behavior. User behavior data is one of the important data sources for formulating marketing anti-fraud strategies. To accurately identify high-risk users, it is necessary to do a good job of collecting user behavior data. At present, in the data collection link, enterprises lack standardized and unified management tools, and often encounter problems such as misplaced points, missed collection, and missed statistics of behavioral events, resulting in unstable data quality and difficulty in supporting related data applications.

[0035] Based on this, in this example embodiment, firstly, a method for identifying abnormal data is provided. The method for identifying abnormal data of the present disclosure may be implemented by a server, or by a terminal device. The terminal described in the present disclosure may include mobile terminals such as mobile phones, tablet computers, laptop computers, PDAs, and fixed terminals such as desktop computers. Figure 1 The following is a schematic diagram showing the process of the abnormal data identification method according to some embodiments of the present disclosure. Figure 1 , the abnormal data identification method may include the following steps:

[0036] Step S110, determine the business scenario to be collected, generate the business events to be collected and the event attributes to be collected corresponding to the business scenario to be collected; the business scenario to be collected includes scenario definition information, the business event to be collected includes event definition information, and the event attributes to be collected include attribute definition information.

[0037] Step S120, determining the logical association relationship between the business scenarios to be collected, the business events to be collected and the event attributes to be collected, and generating data collection rules according to the scenario definition information, the event definition information, the attribute definition information and the logical association relationship.

[0038] Step S130: Perform data collection operations according to data collection rules to obtain business data to be analyzed.

[0039] Step S140, obtaining a pre-configured abnormal data analysis rule, and performing abnormal analysis processing on the business data to be analyzed according to the abnormal data analysis rule to obtain an abnormal analysis result.

[0040] According to the abnormal data identification method in this example embodiment, on the one hand, data collection is performed based on the business events to be collected and the attributes of the events to be collected corresponding to the business scenarios to be collected, as well as the data collection rules generated by the association relationship between the three, so that data collection is uniformly and effectively managed, and the quality of the collected data is also significantly improved. On the other hand, by performing abnormal analysis on the collected business data, abnormal behavior data in the business data can be effectively identified, and the obtained analysis results can be used in business decisions.

[0041] Next, the abnormal data identification method in this example embodiment will be further described.

[0042] In step S110, the business scenario to be collected is determined, and the business events to be collected and the event attributes to be collected corresponding to the business scenario to be collected are generated; the business scenario to be collected includes scenario definition information, the business event to be collected includes event definition information, and the event attributes to be collected include attribute definition information.

[0043] In some exemplary embodiments of the present disclosure, the business scenario to be collected may be a related business scenario to be collected during the data collection process. For example, the business scenario to be collected may include a scenario where a user purchases an item, a scenario where a user browses an item, etc. The business event to be collected may be a related business event contained in the business scenario to be collected. For example, the business events to be collected in the scenario where a user purchases an item may include an event where a user submits an order and an event where a user clicks to pay, etc. The event attributes to be collected may be related attributes contained in the business event to be collected. For example, for a business event where a user clicks to pay, the event attributes to be collected may include the control type, control style, and user information of the "payment" button, etc. The scenario definition information may be relevant information representing the specific content of the business scenario to be collected. The event definition information may be relevant information representing the specific content of the business event. The attribute definition information may be relevant information representing the specific content of the event attribute.

[0044] Before data collection, the business scenarios to be collected can be determined based on specific business analysis requirements and relevant configuration rules. After determining the business scenarios to be collected, the relevant business events and event attributes corresponding to the business scenarios to be collected can be further determined, and relevant configuration rules can be used to generate corresponding business events to be collected and event attributes to be collected. The generated business events to be collected contain event definition information. For example, the event definition information can be the business scenario corresponding to the business event to be collected and the event name of the event. The event attributes to be collected contain attribute definition information. The attribute definition information can be the attribute names of multiple event attributes and specific format requirements.

[0045] In an exemplary embodiment of the present disclosure, a business scenario definition template is obtained, and a business scenario to be collected is determined based on the business scenario definition template and common event attributes; a business event generation template is obtained, and event definition information is configured based on the business event generation template to generate business events to be collected; the business events to be collected include private event attributes; an event attribute generation template and attribute verification rules are obtained, and private attribute definition information is configured for private event attributes based on the event attribute generation template and the attribute verification rules to generate event attributes to be collected.

[0046] Among them, common event attributes may be event attributes possessed by all business events in a certain business scenario. Private event attributes may be other event attributes in each business event except common event attributes. A business scenario definition template may be a template used to generate a business scenario to be collected, and the business scenario definition template may include specific definition rules for generating the business scenario to be collected. A business event generation template may be a template used to generate business events to be collected. An event attribute generation template may be a template used to generate event attributes to be collected. Attribute verification rules may be specific rules used to perform data verification processing on event attributes. Private attribute definition information may be private event attributes.

[0047] refer to Figure 2 , Figure 2 The overall structure of the abnormal behavior identification system according to an exemplary embodiment of the present disclosure is schematically shown. Figure 2 The overall architecture of the anomaly identification system can be divided into software layer and hardware layer; among them, the main functional modules of the software layer can include point-of-care acquisition module, indicator management module, statistical analysis module, anti-fraud strategy management module and risk disposal module, etc.; the hardware layer mainly includes three parts: data collection cluster, big data platform and risk control decision engine. First, the operator can enter the corresponding data collection rules through the point-of-care acquisition module, and automatically synchronize the determined data collection rules to the data collection cluster, which will perform data collection operations.

[0048] Before generating data collection rules, you can determine the business scenarios to be collected, and generate the corresponding business events and event attributes to be collected. The tracking point collection module at the software layer can provide three core functions, namely managing "business scenarios", "business events" and "event attributes". Figure 3 , Figure 3 The following schematically shows the logical association relationship diagram among business scenarios, business events and event attributes according to an exemplary embodiment of the present disclosure. Specifically, a "business scenario" may include multiple "business events", and a "business event" may have multiple "event attributes".

[0049] When determining the business scenario to be collected, you can obtain a business scenario definition template. The business scenario definition template can define the filling specifications of the corresponding information of the business scenario. According to the business scenario definition template, configure the relevant information required for this data collection to generate the corresponding business scenario to be collected. In addition, when determining the business scenario to be collected, you can determine the common event attributes corresponding to the business scenario to be collected, that is, the event attributes that all business events in the business scenario to be collected have. After defining the common event attributes, you can determine the business scenario to be collected based on the business scenario definition template and the common event attributes. When defining the common event attributes, you can determine the attribute verification rules corresponding to the common event attributes so as to perform data verification on the collected business data.

[0050] After determining the business scenario to be collected, obtain a business event generation template, which may include relevant fields of event definition information required to be configured for the business event. Configure the event definition information according to the business event generation template to generate the corresponding business event to be collected. If a business scenario to be collected contains multiple business events to be collected, the above configuration method is used for each business event to be collected to generate the corresponding business event to be collected.

[0051] For the business events to be collected, the business events to be collected may contain private event attributes, that is, specific attributes that only this business event has. After determining the private event attributes, you can obtain an event attribute generation template, which can contain all the information fields required to configure a certain event attribute; in addition, to ensure the data quality of the business data collected during the data collection process, you can obtain pre-defined attribute verification rules, and configure the private attribute definition information according to the event attribute generation template, attribute verification rules, etc. to generate the corresponding event attributes to be collected. Similarly, if a business event to be collected contains multiple event attributes, the configuration method used will generate the corresponding event attributes to be collected.

[0052] In an exemplary embodiment of the present disclosure, the scene fields to be configured are determined according to a business scenario definition template; the scene fields to be configured include a scene name, a scene classification, and a business event naming rule; a configuration operation is performed on the scene fields to be configured to obtain the scene name to be collected, the scene classification to be collected, and the event naming rule to be collected; the business scene to be collected is generated according to the common event attributes, the scene name to be collected, the scene classification to be collected, and the event naming rule to be collected.

[0053] The scene to be configured field may be a field based on which the scene definition information is configured. The business event naming rule may be a naming specification for business event identifiers contained in the business scene. The scene name to be collected may be the name of a specific business scene to be collected. The scene classification to be collected may be a category to which a specific business scene to be collected belongs. The event naming rule to be collected may be a naming specification used for naming the business events to be collected.

[0054] refer to Figure 4 , Figure 4 A schematic diagram of the management of business scenarios according to an exemplary embodiment of the present disclosure is schematically shown. When determining the business scenario to be collected, a business scenario definition template 410 can be obtained, and the business scenario definition template 410 can include the scene fields to be configured contained in generating a certain business scenario to be collected, such as scene classification, scene name, business event naming rules, scene common attributes, etc.

[0055] In step S410, define the business scenario name. Fill in the corresponding scenario name based on the business scenario definition template 410 to configure the business scenario name. For example, in the insurance scenario, if you need to collect relevant business data under the auto insurance underwriting process, you can fill in "Auto Insurance Underwriting Process" in the input box corresponding to the business scenario name. In step S420, define the event identifier naming rules. According to Figure 4 It can be seen that the business scenario definition template 410 includes an "event naming rule" field. By filling in the specific rule content in the input box corresponding to the "event naming rule" field, the corresponding event naming rule to be collected can be generated. In step S430, the public event attributes are set. Since multiple business events included in a business scenario to be collected may have the same event attributes, the corresponding scenario common attributes are filled in the business scenario definition template 410.

[0056] according to Figure 4 It can be seen that the business scenario definition template 410 can restrict the relevant filling requirements of the scenario fields to be configured. For example, the business scenario definition template 410 limits the character length of the scenario name, event naming rules, and remarks fields. The operator can also define other specific field configuration requirements in the business scenario definition template 410 according to specific business needs.

[0057] In an exemplary embodiment of the present disclosure, the event field to be configured is determined based on a business event generation template; the event field to be configured includes the scene to which it belongs, the event name, the event type, and the event identifier; a configuration operation is performed on the scene field to be configured to obtain the scene type to which it belongs, the event name to which it is collected, the event type to which it is collected, and the event identifier to which it is collected; the associated private event attributes are filled in based on the business event generation template, and the business event to be collected is generated according to the scene type to which it belongs, the event name to which it is collected, the event type to which it is collected, the event identifier to which it is collected, and the private event attributes.

[0058] Among them, the event field to be configured may be a field that needs to be configured when configuring the business event to be collected. The scenario to which it belongs may be a specific business scenario to which the business event to be collected belongs. The private event attribute may be an event attribute that a specific business event to be collected has alone. The scenario type to which it belongs may be a specific type of business scenario to which a specific business event to be collected belongs. The event name to be collected may be the specific name of a specific business event to be collected. The event type to be collected may be a specific type corresponding to a specific business event to be collected. The event identifier to be collected may be a unique identifier (Identity document, ID) corresponding to a specific business event to be collected.

[0059] refer to Figure 5 , Figure 5 The schematic diagram of the management of scene events according to the exemplary embodiment of the present disclosure is schematically shown. When generating a business event to be collected, the business event generation template 510 can be obtained first. The business event generation template 510 can include the event fields to be configured for generating the business event to be collected, such as (belonging to) business scene, event name, event type, event ID, etc.; in addition, private event attributes can also be configured in the business event generation template 510, for example, the name of the private event attribute contained in the business event to be collected is filled in.

[0060] In step S510, select the business scenario. For example, the event of a user submitting a car insurance policy, the business scenario to which the business event belongs is "car insurance application process", so "car insurance application process" can be filled in the input box corresponding to the business scenario label. In step S520, define the event name. The name of the event to be collected can be configured as "submit car insurance policy". In step S530, define the event identifier. Before defining the specific event identifier to be collected, you can first obtain the pre-configured event identifier configuration rules. For example, in the car insurance application process, the business event configuration rule under "car insurance application process" is: "car insurance application process" has a unified prefix, which can be "car", and then use a connector to connect the fixed prefix with the corresponding event abbreviation to obtain the corresponding event ID name, such as "submit car insurance policy" The event identifier can be "car_submittable". In step S540, define the event type. Determine the specific type of the business event to be collected and fill it in the corresponding input box. For example, the event type of "submit car insurance policy" can be filled in the front-end event. In step S550, private event attributes are determined. The private event attributes of "submitting a car insurance policy" may include policy submission time, policy ID, and the like.

[0061] Specifically, the configuration process of private event attributes is as follows Figure 6 As shown, Figure 6 The schematic diagram of event attribute management according to an exemplary embodiment of the present disclosure is schematically shown. Before configuring the event attributes to be collected, an event attribute generation template 610 may be obtained first. The event attribute generation template 610 may include attribute fields for generating the event attributes to be collected. For example, the event attribute generation template may include: event attribute identifier (Key), event attribute name, event attribute type, etc.

[0062] The specific configuration process can be as follows: in step S610, define the event attribute name. For example, "policy submission time" in "submit auto insurance policy" is the Chinese name of the event attribute. In step S620, define the event attribute identifier. The attribute identifier corresponding to the policy submission time in "submit auto insurance policy" can be "submit_time". In step S630, define the event attribute category. For example, the event attribute category can include dictionary type and string type. The dictionary type can be an event attribute that can be enumerated, and the string type can be an event attribute that cannot be represented by enumeration. In step S640, define the data verification rule. The data verification rule can be a specific rule defined for each field, and the data verification rule can be used to improve the data quality of the collected business data. Taking the event attribute "member ID" as an example, the data format of "member ID" can be defined as 12-digit letters. In the actual processing process, the transmitted data can be judged according to the defined attribute verification rule to determine whether it meets the requirements, so as to avoid the big data platform receiving dirty data.

[0063] It is easy for those skilled in the art to understand that both the common event attributes and the private event attributes of the present disclosure can be configured using the above steps, and the present disclosure will not elaborate on the configuration process of the common event attributes.

[0064] In step S120, the logical association relationship among the business scenarios to be collected, the business events to be collected and the event attributes to be collected is determined, and data collection rules are generated according to the scenario definition information, the event definition information, the attribute definition information and the logical association relationship.

[0065] In some exemplary embodiments of the present disclosure, the logical association relationship may be the relationship between the business scenario to be collected, the business event to be collected, and the event attribute to be collected. For example, the logical relationship between the three may include one or more business events to be collected corresponding to a business scenario to be collected, and a business event to be collected may include one or more event attributes to be collected corresponding to it. The data collection rule may be a rule used for data collection when performing data embedding.

[0066] refer to Figure 3 , Figure 3 The following schematically shows the logical association relationship between business scenarios, business events and event attributes according to an exemplary embodiment of the present disclosure. Figure 3It can be seen that a business scenario can correspond to one or more business events, and one or more common event attributes can be defined in a business scenario; one business event can correspond to one or more event attributes. The business scenario to be collected can include configuration fields such as the scenario name and event ID naming rules; the business event to be collected can include fields such as event ID, event name and event type; the event attributes to be collected can include fields such as event attribute ID, event attribute name, event attribute type and event attribute verification rules.

[0067] After determining the scene definition information, event definition information, attribute definition information and the logical relationship between the three through the above steps, data collection rules can be generated according to the above information and sent to Figure 2 The data collection cluster in is used for data collection and processing.

[0068] In step S130, data collection operations are performed according to data collection rules to obtain business data to be analyzed.

[0069] In some exemplary embodiments of the present disclosure, the data collection operation may be an operation process of performing data collection by performing data embedding based on data collection rules. The business data to be analyzed may be the business data determined by this data collection operation. The business data to be analyzed may include data generated by users performing related operations in a certain application (Application, APP).

[0070] After the data collection rules are sent to the data collection cluster, the data collection cluster will perform data collection operations according to the data collection rules, obtain the corresponding business data to be analyzed, and send the collected business data to be analyzed to the big data platform through data synchronization operations.

[0071] In step S140, a pre-configured abnormal data analysis rule is obtained, and abnormal analysis processing is performed on the business data to be analyzed according to the abnormal data analysis rule to obtain an abnormal analysis result.

[0072] In some exemplary embodiments of the present disclosure, the abnormal data analysis rule may be a rule used when performing abnormal analysis processing on user behavior in the business data to be analyzed. The abnormal analysis processing may be an analysis process for determining whether the user behavior is abnormal. The abnormal analysis result may be a result obtained after performing abnormal analysis processing on the user behavior in the business data to be analyzed.

[0073] Continue to refer Figure 2 The indicator management module can be used to define the calculation rules of monitoring indicators and manage monitoring indicators; the statistical analysis module can provide operators with a visual tool to analyze monitoring indicators. Figure 2The abnormal data analysis rules are configured in the anti-fraud policy management module in the anti-fraud policy management module, which can include functions such as adding new policies, editing policies, and policy set management. After the corresponding abnormal data analysis rules are generated through the anti-fraud policy management module configuration, the abnormal data analysis rules can be synchronized to the risk control engine cluster at the hardware layer through the rule synchronization operation. In other words, the risk control engine cluster can obtain the pre-configured abnormal data analysis rules and perform abnormal analysis on the business data to be analyzed according to the abnormal data analysis rules.

[0074] In an exemplary embodiment of the present disclosure, before obtaining the pre-configured abnormal data analysis rules, the method also includes: determining the analysis rule name; determining multiple behavior analysis rules corresponding to the analysis rule name, and determining the rule association relationship between the multiple behavior analysis rules; generating the abnormal data analysis rules according to the analysis rule name, the multiple behavior analysis rules and the rule association relationship.

[0075] The analysis rule name may be a specific name corresponding to the abnormal data analysis rule. The behavior analysis rule may be a rule used to perform abnormal identification analysis on the user behavior contained in the business data to be analyzed. The rule association relationship may be an association relationship between multiple behavior analysis rules, for example, the rule association relationship may be a parallel relationship.

[0076] refer to Figure 7 , Figure 7 The flowchart of abnormal behavior identification and analysis management according to an exemplary embodiment of the present disclosure is schematically shown. In step S710, the analysis rule name is defined. Taking the user anti-fraud behavior management in the insurance scenario as an example, the operation personnel can configure the abnormal data analysis rules according to the actual business needs, such as anti-fraud strategy. First, the analysis rule name corresponding to a certain abnormal data analysis rule can be determined. Reference Figure 8 ,refer to Figure 8 , Figure 8 The following schematically shows the interface diagram of the functional design of generating abnormal data analysis rules according to an exemplary embodiment of the present disclosure. For example, in the "Policy Name" configuration part 810 in the page, enter the corresponding policy name through the input box corresponding to "Policy Name" to determine the analysis rule name. In step S720, define the behavior analysis rules. For example, in Figure 8 In the "User Behavior Definition" section 820 of the page, the behavior analysis rule configuration operation is performed. After the behavior analysis rule is defined, the subsequent steps are continued. In step S730, the rule is calculated. Since the above processing process has defined the behavior analysis rule, the rule calculation can be performed on the defined abnormal data analysis rule. Figure 8, the trigger event in behavior rule 1, the corresponding time scenario is "property insurance application process", the event ID is "page loading event", the event attributes include "member ID" and "sales plan number", and the rule threshold is "trigger frequency is greater than 3 times per hour". In step S740, the rule is published. After the rule calculation is completed, the rule can be published to determine the corresponding abnormal analysis results according to the rule.

[0077] In an exemplary embodiment of the present disclosure, the behavior category corresponding to the business data to be analyzed is determined; event classification processing is performed on the behavior category to obtain a behavior event classification result; and an exception analysis processing is performed based on the behavior event classification result and an exception data analysis rule to obtain an exception analysis result.

[0078] The behavior category may be a specific category of user behavior included in the business data to be analyzed. The event classification process may be a process of classifying the behavior category into event categories. The behavior event classification result may be a result obtained after event classification process is performed on the behavior category. The abnormal analysis result may be a result obtained after abnormal analysis process is performed on the business data to be analyzed.

[0079] Continue to refer Figure 7 , after entering the step of defining behavior analysis rules, in step S7201, select a behavior category. Selecting a behavior category determines the behavior category corresponding to the business data to be analyzed this time. In step S7202, determine whether it is an event. Determine whether the behavior category to be analyzed is the business event to be collected that was previously configured in the data collection rules. In this judgment step, the event classification results obtained include belonging to the event category and not belonging to the event category. After obtaining the specific event classification results, the business data to be analyzed can be combined with the abnormal data analysis rules to perform subsequent abnormal analysis processing to obtain abnormal analysis results.

[0080] In an exemplary embodiment of the present disclosure, if the behavioral event classification result is that it belongs to the event category, then determine the target event attribute corresponding to the business data to be analyzed; obtain the event attribute threshold corresponding to the target event attribute, and determine the first analysis result based on the event attribute threshold; if the behavioral event classification result is that it belongs to the non-event category, then determine the behavioral information included in the business data to be analyzed; obtain the behavior information threshold corresponding to the behavior information, and determine the second analysis result based on the behavior information threshold; determine the abnormal analysis result based on the first analysis result and the second analysis result.

[0081] Among them, belonging to the event category may mean that the relevant user behavior in the business data to be analyzed belongs to a specific business event to be collected. The target event attribute may be the event attribute contained in the event when it is determined that the behavior category in the business data to be analyzed belongs to a specific event. The event attribute threshold may be a specific value used for comparison with the event attribute. The first analysis result may be the analysis result obtained after comparing the target event attribute with the event threshold. Belonging to the non-event category may mean that the relevant user behavior in the business data to be analyzed does not belong to any business event to be collected. The behavior information may be the specific information of the user behavior contained in the business data to be analyzed. The behavior information threshold may be the specific value used for comparison with the behavior information. The second analysis result may be the analysis result obtained after comparing the behavior information with the behavior information threshold.

[0082] Continue to refer Figure 2 After configuring the abnormal data analysis rules, the risk control engine cluster can determine the abnormal analysis results of the business data to be analyzed based on the abnormal data analysis rules, and synchronize the abnormal analysis results to the risk disposal module so that the operation personnel can handle the abnormal behavior data. Figure 7 In step S7203, if the behavior event classification result is that it belongs to the event category, then select the event. That is, select the corresponding business event to be collected. And in step S7204, determine the event attribute. Determine the event attribute required for this business analysis data, that is, the target event attribute. In step S7205, define the rule threshold. Obtain the event attribute threshold corresponding to the target event attribute. Then determine the first analysis result based on the event attribute threshold.

[0083] Specifically, refer to Figure 8 , Figure 8 In the user behavior definition area 821, for example, the behavior category selected this time is "trigger event", the event scenario corresponds to "property insurance underwriting process", and the event type is "core event"; and the corresponding event attributes are added in the add attribute part. Figure 8 Two event attributes, "sales plan number" and "channel ID", are added. In this behavior analysis rule, the rule threshold can be the trigger frequency, and operators can add the trigger frequency according to specific business needs. For example, the trigger frequency can be configured to 3 times per minute.

[0084] In addition, in the step of defining the behavior analysis rules, if it is determined that the behavior event classification result does not belong to the non-event category. Then determine the behavior information included in the business data to be analyzed. For example, in a certain business data analysis process, the user's access time to the target page can be detected. Then in step S7206, enter the Uniform Resource Locator (URL) address. In this step, the page address of the target page to be monitored can be determined. In step S7207, select / enter the URL parameters. Enter the relevant page parameters corresponding to the page address. In step S7208, define the rule threshold. The rule threshold can be a specific value used to compare with the behavior information of the non-event category. By comparing the user's behavior information with the behavior information threshold, a second analysis result can be determined. According to Figure 7 As can be seen from the user behavior definition part, since the two behavior analysis rules are connected by the conjunction "AND", as shown in control 823, the abnormal data analysis rule can be determined by the two behavior analysis rules. The first analysis result and the second analysis result are combined to determine the corresponding abnormal analysis result.

[0085] Specifically, refer to Figure 8 In the user behavior definition area 822, the behavior category selected this time is "page visit". The operator can enter the page address to be monitored this time in the input box corresponding to the page address; and add the corresponding event attributes in the add attribute part. For example, two event attributes "channel ID" and "custom parameter" are added in area 822. In this behavior analysis rule, the rule threshold can be the visit frequency and the length of stay. The operator can add the corresponding visit frequency and length of stay according to specific business needs.

[0086] In other embodiments of the present disclosure, new behavior analysis rules can be added based on the currently defined behavior analysis rules to obtain corresponding abnormal data analysis rules. The specific process is as follows: in step S7209, determine whether to continue adding behavior. If you want to continue adding behavior analysis rules, you can do so through page control 824, that is, the "+ Add Behavior" control, to add new behavior analysis rules. In step S7210, if the judgment result is yes, continue to define rule thresholds for the most recently added behavior. That is, if the operator adds a new behavior analysis rule through page control 824, the rule threshold corresponding to the behavior analysis rule can be added; otherwise, the rule definition process ends.

[0087] The following uses a business data analysis process in the actual business processing process as an example to illustrate the beneficial effects of the present disclosure. Taking a special analysis of channel quality of a certain enterprise in April 2021 as an example, the abnormal data identification method in the present disclosure was used to discover the order-brushing behavior by analyzing the user behavior data of the channel. The data in Table 1 is used as an example of the application of user behavior data:

[0088] Table 1

[0089]

[0090] As can be seen from Table 1, there are two customer acquisition methods in the above business data: A channel and B channel. Among them, the user behavior characteristics of A channel and B channel are obviously different, which are specifically manifested in:

[0091] 1) The “Enter mobile phone number” event in the landing page was triggered 1.5 times per person in channel A and 5.5 times per person in channel B, with a maximum of 240 times for a single device (not shown in Table 1);

[0092] 2) The average number of triggers for the “Get it now” event on the landing page was 2.2 times in channel A and 7.5 times in channel B, with a maximum of 249 times for a single device (not shown in Table 1);

[0093] 3) The “Who is insured for” button on the short-term insurance page was triggered 0.5 times per person in channel A and 5.5 times per person in channel B, with a maximum of 173 times for a single device (not shown in Table 1);

[0094] In addition, there are abnormal user behaviors in Category B channels, which are as follows:

[0095] 1) The “Who is insured for” event was triggered 5.5 times per person, but the event of filling in “Name of the insured person” was 0.06. The ratio of the two events “Who is insured for” / “Name of the insured person” was 91.6, and the ratio within the site was 16.6;

[0096] 2) The triggering frequency of "confirming insurance" for short-term insurance is abnormal for some devices, with 3-4 times being triggered within 1ms.

[0097] By analyzing the above data, it is obvious that the user behavior of Category B channels is obviously abnormal. If the "anti-fraud strategy management" module is further implemented, it can effectively monitor and warn low-quality channels in real time, intercept high-risk users from insurance, and reduce losses for corporate operations in a timely manner.

[0098] It should be noted that the terms “first”, “second”, etc. used in the present disclosure are only used to distinguish different analysis results and should not impose any limitations on the present disclosure.

[0099] In summary, the abnormal data identification method disclosed in the present invention determines the business scenario to be collected, generates the business events to be collected and the event attributes to be collected corresponding to the business scenario to be collected; the business scenario to be collected includes the scenario definition information, the business event to be collected includes the event definition information, and the event attributes to be collected include the attribute definition information; determines the logical association relationship between the business scenario to be collected, the business event to be collected and the event attributes to be collected, and generates data collection rules according to the scenario definition information, the event definition information, the attribute definition information and the logical association relationship; performs data collection operations according to the data collection rules to obtain the business data to be analyzed; obtains the pre-configured abnormal data analysis rules, and performs abnormal analysis processing on the business data to be analyzed according to the abnormal data analysis rules to obtain abnormal analysis results. On the one hand, data collection is performed according to the business events to be collected and the event attributes to be collected corresponding to the business scenario to be collected, and the data collection rules generated by the association relationship between the three, so that data collection is uniformly and effectively managed, and the quality of the collected data is also significantly improved. On the other hand, by performing abnormal analysis processing on the collected business data, abnormal behavior data in the business data can be effectively identified, and the obtained analysis results can be applied to business decisions. On the other hand, since the behavior analysis rules can be configured by themselves, the parameters of event attributes can be configured through the behavior analysis rules, which can effectively improve the timeliness of the identification process and determine the abnormal analysis results more quickly. On the other hand, since the abnormal analysis process can be combined with user behavior data for judgment, the data dimensions for judgment are richer and the abnormal analysis results obtained are more accurate.

[0100] It should be noted that, although the steps of the method of the present invention are described in a specific order in the drawings, this does not require or imply that the steps must be performed in this specific order, or that all the steps shown must be performed to achieve the desired results. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step, and / or one step may be decomposed into multiple steps, etc.

[0101] In addition, in this exemplary embodiment, an abnormal data identification device is also provided. Fig. 9 The abnormal data identification device 900 may include: a scene event determination module 910, a collection rule determination module 920, a data collection module 930 and an abnormality analysis module 940.

[0102] Specifically, the scenario event determination module 910 is used to determine the business scenario to be collected, and generate the business events to be collected and the event attributes to be collected corresponding to the business scenario to be collected; the business scenario to be collected includes scenario definition information, the business event to be collected includes event definition information, and the event attributes to be collected include attribute definition information; the collection rule determination module 920 is used to determine the logical association relationship between the business scenario to be collected, the business event to be collected and the event attributes to be collected, and generate data collection rules according to the scenario definition information, event definition information, attribute definition information and the logical association relationship; the data collection module 930 is used to perform data collection operations according to the data collection rules to obtain the business data to be analyzed; the exception analysis module 940 is used to obtain pre-configured exception data analysis rules, and perform exception analysis processing on the business data to be analyzed according to the exception data analysis rules to obtain exception analysis results.

[0103] In an exemplary embodiment of the present disclosure, the event attributes to be collected include common event attributes and private event attributes; the scenario event determination module includes a scenario event determination unit, which is used to obtain a business scenario definition template, and determine the business scenario to be collected according to the business scenario definition template and the common event attributes; obtain a business event generation template, and configure event definition information according to the business event generation template to generate business events to be collected; the business events to be collected include private event attributes; obtain an event attribute generation template and attribute verification rules, and configure private attribute definition information for private event attributes according to the event attribute generation template and the attribute verification rules to generate event attributes to be collected.

[0104] In an exemplary embodiment of the present disclosure, a scenario event determination unit includes a scenario determination sub-unit, which is used to determine the scenario fields to be configured according to a business scenario definition template; the scenario fields to be configured include a scenario name, a scenario classification, and a business event naming rule; a configuration operation is performed on the scenario fields to be configured to obtain the scene name to be collected, the scene classification to be collected, and the event naming rule to be collected; and the business scenario to be collected is generated according to the common event attributes, the scene name to be collected, the scene classification to be collected, and the event naming rule to be collected.

[0105] In an exemplary embodiment of the present disclosure, a scenario event determination unit includes an event determination subunit, which is used to determine the event field to be configured based on a business event generation template; the event field to be configured includes the scenario to which it belongs, the event name, the event type, and the event identifier; a configuration operation is performed on the scenario field to which it belongs to obtain the scenario type, the event name to be collected, the event type to be collected, and the event identifier to be collected; the associated private event attributes are filled in based on the business event generation template, and the business event to be collected is generated according to the scenario type, the event name to be collected, the event type to be collected, the event identifier to be collected, and the private event attributes.

[0106] In an exemplary embodiment of the present disclosure, the abnormal data identification device also includes an analysis rule generation module, which is used to determine the analysis rule name; determine multiple behavior analysis rules corresponding to the analysis rule name, and determine the rule association relationship between the multiple behavior analysis rules; and generate abnormal data analysis rules based on the analysis rule name, the multiple behavior analysis rules and the rule association relationship.

[0107] In an exemplary embodiment of the present disclosure, the anomaly analysis module includes an anomaly analysis unit for determining the behavior category corresponding to the business data to be analyzed; performing event classification processing on the behavior category to obtain a behavior event classification result; performing anomaly analysis processing based on the behavior event classification result and the anomaly data analysis rule to obtain an anomaly analysis result.

[0108] In an exemplary embodiment of the present disclosure, the abnormal analysis unit includes an abnormal analysis sub-unit, which is used to determine the target event attribute corresponding to the business data to be analyzed if the behavior event classification result belongs to the event category; obtain the event attribute threshold corresponding to the target event attribute, and determine the first analysis result according to the event attribute threshold; if the behavior event classification result belongs to the non-event category, determine the behavior information included in the business data to be analyzed; obtain the behavior information threshold corresponding to the behavior information, and determine the second analysis result according to the behavior information threshold; determine the abnormal analysis result according to the first analysis result and the second analysis result.

[0109] The specific details of the virtual modules of each abnormal data identification device mentioned above have been described in detail in the corresponding abnormal data identification method, so they will not be repeated here.

[0110] It should be noted that, although several modules or units of the abnormal data identification device are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more modules or units described above can be concretized in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided into multiple modules or units to be concretized.

[0111] In addition, in an exemplary embodiment of the present disclosure, an electronic device capable of implementing the above method is also provided.

[0112] It will be appreciated by those skilled in the art that various aspects of the present invention may be implemented as systems, methods or program products. Therefore, various aspects of the present invention may be specifically implemented in the following forms, namely: complete hardware embodiments, complete software embodiments (including firmware, microcode, etc.), or embodiments combining hardware and software aspects, which may be collectively referred to herein as "circuits", "modules" or "systems".

[0113] Refer to the following Fig.10 hereinafter describes the electronic device 1000 according to such an embodiment of the present disclosure. Fig.10 The electronic device 1000 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0114] like Fig.10 As shown, the electronic device 1000 is in the form of a general computing device. The components of the electronic device 1000 may include but are not limited to: the at least one processing unit 1010, the at least one storage unit 1020, a bus 1030 connecting different system components (including the storage unit 1020 and the processing unit 1010), and a display unit 1040.

[0115] The storage unit stores program codes, which can be executed by the processing unit 1010, so that the processing unit 1010 executes the steps according to various exemplary embodiments of the present disclosure described in the above “Exemplary Method” section of this specification.

[0116] The storage unit 1020 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 1021 and / or a cache memory unit 1022 , and may further include a read-only memory unit (ROM) 1023 .

[0117] The storage unit 1020 may also include a program / utility 1024 having a set (at least one) of program modules 1025, such program modules 1025 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0118] Bus 1030 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0119] The electronic device 1000 may also communicate with one or more external devices 1070 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 1000, and / or communicate with any device that enables the electronic device 1000 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 1050. Furthermore, the electronic device 1000 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 1060. As shown, the network adapter 1060 communicates with other modules of the electronic device 1000 via a bus 1030. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 1000, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0120] Through the description of the above embodiments, it is easy for those skilled in the art to understand that the example embodiments described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the embodiment of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, and includes several instructions to enable a computing device (which can be a personal computer, a server, a terminal device, or a network device, etc.) to execute the method according to the embodiment of the present disclosure.

[0121] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the above method of the present specification is stored. In some possible embodiments, various aspects of the present invention can also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to enable the terminal device to perform the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of the present specification.

[0122] refer to Fig.11 As shown, a program product 1100 for implementing the above method according to an embodiment of the present invention is described, which can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0123] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0124] Computer readable signal media may include data signals propagated in baseband or as part of a carrier wave, in which readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0125] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0126] Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0127] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to an exemplary embodiment of the present invention, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously, for example, in multiple modules.

[0128] Those skilled in the art will readily appreciate other embodiments of the present disclosure after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary technical means in the art that are not disclosed in the present disclosure. The specification and examples are to be considered as exemplary only, and the true scope and spirit of the present disclosure are indicated by the claims.

[0129] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes may be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.

Claims

1. A method for identifying abnormal data, characterized in that: include: Determine the business scenario to be collected, and generate the business events to be collected and the event attributes to be collected corresponding to the business scenario to be collected; The business scenario to be collected includes scenario definition information, the business event to be collected includes event definition information, and the event attribute to be collected includes attribute definition information. The scenario definition information is relevant information indicating the specific content of the business scenario to be collected, the event definition information is relevant information indicating the specific content of the business event to be collected, and the attribute definition information is relevant information indicating the specific content of the event attribute to be collected; Determine the logical association relationship between the business scenario to be collected, the business event to be collected and the event attribute to be collected, and generate a data collection rule according to the scenario definition information, the event definition information, the attribute definition information and the logical association relationship; Perform data collection operations according to the data collection rules to obtain business data to be analyzed; Acquire a pre-configured abnormal data analysis rule, and perform abnormal analysis processing on the business data to be analyzed according to the abnormal data analysis rule to obtain an abnormal analysis result; The performing abnormal analysis processing on the business data to be analyzed according to the abnormal data analysis rule to obtain an abnormal analysis result includes: Determine the behavior event classification result of the business data to be analyzed; If the behavior event classification result is that it belongs to the event category, determining the target event attribute corresponding to the business data to be analyzed; Acquire an event attribute threshold corresponding to the target event attribute, and determine a first analysis result according to the event attribute threshold; If the behavior event classification result is that it belongs to the non-event category, determining the behavior information included in the business data to be analyzed; Acquire a behavior information threshold corresponding to the behavior information, and determine a second analysis result according to the behavior information threshold; The abnormal analysis result is determined according to the first analysis result and the second analysis result.

2. The method according to claim 1, characterized in that The event attributes to be collected include common event attributes and private event attributes; Determining a business scenario to be collected, and generating business events to be collected and event attributes to be collected corresponding to the business scenario to be collected, including: Acquire a business scenario definition template, and determine the business scenario to be collected according to the business scenario definition template and the common event attribute; Acquire a business event generation template, and configure the event definition information according to the business event generation template to generate the business event to be collected; the business event to be collected includes private event attributes; An event attribute generation template and an attribute verification rule are obtained, and private attribute definition information is configured for the private event attribute according to the event attribute generation template and the attribute verification rule to generate the event attribute to be collected.

3. The method according to claim 2, characterized in that Determining the business scenario to be collected according to the business scenario definition template and the common event attributes includes: Determine the scene field to be configured according to the business scene definition template; the scene field to be configured includes the scene name, scene classification, and business event naming rules; Performing configuration operations on the scene field to be configured to obtain the name of the scene to be collected, the classification of the scene to be collected, and the naming rules of the events to be collected; The business scenario to be collected is generated according to the common event attributes, the name of the scenario to be collected, the classification of the scenario to be collected and the naming rule of the event to be collected.

4. The method according to claim 2, characterized in that: Configuring the event definition information according to the business event generation template to generate the business event to be collected includes: Determine the event field to be configured based on the business event generation template; the event field to be configured includes the scene to which it belongs, the event name, the event type, and the event identifier; Perform configuration operations on the scene field to be configured to obtain the scene type, the name of the event to be collected, the type of the event to be collected, and the identifier of the event to be collected; The associated private event attributes are filled in based on the business event generation template, and the business event to be collected is generated according to the scene type, the name of the event to be collected, the type of the event to be collected, the identifier of the event to be collected and the private event attributes.

5. The method according to claim 1, characterized in that Before obtaining the pre-configured abnormal data analysis rule, the method further includes: Determine the name of the analysis rule; Determine a plurality of behavior analysis rules corresponding to the analysis rule name, and determine a rule association relationship between the plurality of behavior analysis rules; The abnormal data analysis rule is generated according to the analysis rule name, the plurality of behavior analysis rules and the rule association relationship.

6. The method according to claim 1, characterized in that Performing abnormal analysis processing on the business data to be analyzed according to the abnormal data analysis rule to obtain an abnormal analysis result, further comprising: Determining the behavior category corresponding to the business data to be analyzed; Perform event classification processing on the behavior category to obtain the behavior event classification result.

7. An abnormal data identification device, characterized in that: include: A scenario event determination module, used to determine the business scenario to be collected, and generate the business events to be collected and the attributes of the events to be collected corresponding to the business scenario to be collected; The business scenario to be collected includes scenario definition information, the business event to be collected includes event definition information, and the event attribute to be collected includes attribute definition information. The scenario definition information is relevant information indicating the specific content of the business scenario to be collected, the event definition information is relevant information indicating the specific content of the business event to be collected, and the attribute definition information is relevant information indicating the specific content of the event attribute to be collected; A collection rule determination module, used to determine the logical association relationship between the business scenario to be collected, the business event to be collected and the event attribute to be collected, and generate a data collection rule according to the scenario definition information, the event definition information, the attribute definition information and the logical association relationship; A data collection module, used to perform data collection operations according to the data collection rules to obtain business data to be analyzed; The abnormality analysis module is used to obtain a pre-configured abnormal data analysis rule, and perform abnormality analysis processing on the business data to be analyzed according to the abnormal data analysis rule to obtain an abnormality analysis result; The abnormality analysis module is further used to determine the behavior event classification result of the business data to be analyzed; If the behavior event classification result is that it belongs to the event category, determining the target event attribute corresponding to the business data to be analyzed; Acquire an event attribute threshold corresponding to the target event attribute, and determine a first analysis result according to the event attribute threshold; If the behavior event classification result is that it belongs to the non-event category, determining the behavior information included in the business data to be analyzed; Acquire a behavior information threshold corresponding to the behavior information, and determine a second analysis result according to the behavior information threshold; The abnormal analysis result is determined according to the first analysis result and the second analysis result.

8. An electronic device, characterized in that: include: processor; as well as A memory having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by the processor, implement the abnormal data identification method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the abnormal data identification method according to any one of claims 1 to 6.