CN112862322A - Universal interactive wind control method and device - Google Patents
Universal interactive wind control method and device Download PDFInfo
- Publication number
- CN112862322A CN112862322A CN202110184105.7A CN202110184105A CN112862322A CN 112862322 A CN112862322 A CN 112862322A CN 202110184105 A CN202110184105 A CN 202110184105A CN 112862322 A CN112862322 A CN 112862322A
- Authority
- CN
- China
- Prior art keywords
- user
- interactive
- risk
- grained
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q20/00—Payment architectures, schemes or protocols
- G06Q20/38—Payment protocols; Details thereof
- G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
- G06Q20/401—Transaction verification
- G06Q20/4016—Transaction verification involving fraud or risk level assessment in transaction processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/04—Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Human Resources & Organizations (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Computer Security & Cryptography (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present disclosure provides a general interactive wind control method, comprising: receiving an operation of a user and preliminarily judging that the operation is risky; acquiring coarse-grained multi-dimensional information related to the operation based on the scene of the operation; presenting a corresponding interactive wind control component to the user based on the coarse-grained multi-dimensional information; performing a plurality of rounds of interaction with the user using the corresponding interactive wind control assembly to collect updated multidimensional information; analyzing the updated multidimensional information to obtain fine-grained multidimensional information; and disclosing whether the risk exists or not to the user according to the fine-grained multi-dimensional information.
Description
Technical Field
The present disclosure relates generally to risk prevention and control, and more particularly to risk prevention and control in complex trading scenarios.
Background
In the current risk control of each financial company, the safety of the account and the transaction of the user is guaranteed. When a user performs each operation (such as login, payment, and the like), data of the environment, scene, behavior, and the like of the current operation of the user is collected, and then a safe identification and decision is performed. For some high-risk scenes, the risk wind control system is identified to intercept transactions and failure operations, and in some high-risk scenes, failure risks are prompted through various personalized pictures and documents, so that the risks are disclosed to users.
The main idea of the risk identification and control means is to use the capability of the wind control engine to judge whether the environment of the user is abnormal, whether the behavior is abnormal, whether each party of the transaction is credible, and the like. However, in some complex scenes, the situation that the approach to risk is complicated and variable and difficult to control is met. The traditional wind control product reminding is not suitable for the complex transaction scenes, the user is deceived deeply, the subjective will urgently needs transaction operation, only the risk user is reminded of being unconscious, the user operates to pay funds, the identity of the user is verified to be invalid, and the deceived user is difficult to wake up.
Therefore, there is a need in the art for a method and system for effectively waking up a user, really reaching the user in combination with the mind of the user, and revealing a risk in a complex transaction scenario in which the user participates himself.
Disclosure of Invention
In order to solve the technical problem, the present disclosure provides a general interactive wind control scheme, which can recommend different interactive products for different users, thereby revealing risks in a targeted manner.
In an embodiment of the present disclosure, a general interactive wind control method is provided, including: receiving an operation of a user and preliminarily judging that the operation is risky; acquiring coarse-grained multi-dimensional information related to the operation based on the scene of the operation; presenting a corresponding interactive wind control component to the user based on the coarse-grained multi-dimensional information; performing a plurality of rounds of interaction with the user using the corresponding interactive wind control assembly to collect updated multidimensional information; analyzing the updated multidimensional information to obtain fine-grained multidimensional information; and disclosing whether the risk exists or not to the user according to the fine-grained multi-dimensional information.
In another embodiment of the present disclosure, the coarse-grained multi-dimensional information includes categories of people to which the user belongs, user intent, and risk.
In yet another embodiment of the present disclosure, the fine-grained multi-dimensional information includes actual intent of the user, scene risk probability, risk probability of the operation, and anomaly data of participants of the operation.
In another embodiment of the present disclosure, analyzing the updated multidimensional information to obtain fine-grained multidimensional information is performed based on rules or models.
In yet another embodiment of the present disclosure, the corresponding interactive wind control component is one of an intelligent voice outbound product, an in-system electronic interactive product, and the like.
In another embodiment of the present disclosure, the electronic interactive products in the system include intelligent interactive reporting products, intelligent interactive examination paper products and the like.
In yet another embodiment of the present disclosure, the corresponding interactive wind control component is subdivided according to the scene.
In an embodiment of the present disclosure, a universal interactive wind control system is provided, including: the policy engine module is used for receiving the operation of a user, preliminarily judging that the operation is risky, and acquiring coarse-grained multi-dimensional information related to the operation based on the scene of the operation; the product recommendation module is used for presenting the corresponding interactive wind control component to the user based on the coarse-grained multi-dimensional information; the interaction module is used for carrying out multi-round interaction with the user by using the corresponding interactive wind control assembly so as to collect updated multi-dimensional information; wherein the policy engine module further analyzes the updated multidimensional information to obtain fine-grained multidimensional information; and the interaction module further reveals whether the risk exists or not to the user according to the fine-grained multi-dimensional information.
In another embodiment of the present disclosure, the coarse-grained multi-dimensional information includes categories of people to which the user belongs, user intent, and risk.
In yet another embodiment of the present disclosure, the fine-grained multi-dimensional information includes actual intent of the user, scene risk probability, risk probability of the operation, and anomaly data of participants of the operation.
In another embodiment of the present disclosure, the policy engine module further analyzes the updated multidimensional information to obtain fine-grained multidimensional information is based on rules or models.
In another embodiment of the present disclosure, the corresponding interactive wind control component is one of an intelligent voice outbound product, an in-system electronic interactive product, and the like.
In another embodiment of the present disclosure, the electronic interactive products in the system include intelligent interactive reporting products, intelligent interactive examination paper products and the like.
In another embodiment of the present disclosure, the corresponding interactive wind control component is subdivided according to the scene.
In another embodiment of the present disclosure, the policy engine module is extensible according to a scenario.
In another embodiment of the present disclosure, the data structure of the policy engine module is a tree structure.
In an embodiment of the disclosure, a computer-readable storage medium is provided that stores instructions that, when executed, cause a machine to perform the method as previously described.
This summary is provided to introduce a selection of concepts in a simplified form that are further described below in the detailed description. This summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter.
Drawings
The foregoing summary, as well as the following detailed description of the present disclosure, will be better understood when read in conjunction with the appended drawings. It is to be noted that the appended drawings are intended as examples of the claimed invention. In the drawings, like reference characters designate the same or similar elements.
FIG. 1 is a flow chart illustrating a general interactive wind control method according to an embodiment of the present disclosure;
FIG. 2 is a timing diagram illustrating an interactive wind control assembly according to an embodiment of the present disclosure;
FIG. 3 is a block diagram illustrating a generic interactive wind control system according to an embodiment of the present disclosure;
FIG. 4 is a diagram illustrating a layered architecture of a universal interactive wind control system according to an embodiment of the present disclosure;
FIG. 5 is a diagram illustrating a policy engine data structure in a generic interactive wind control system according to an embodiment of the present disclosure.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, embodiments accompanying the present disclosure are described in detail below.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure may be practiced in other ways than those described herein, and thus the present disclosure is not limited to the specific embodiments disclosed below.
In the current risk control of each financial company, risk identification and control are carried out on the safety of the account and the transaction of a user. The main idea is to use the ability of the wind control engine to judge whether the environment of the user is abnormal, whether the behavior is abnormal, whether each party of the transaction is credible, etc. However, for some complex scenes, risk prevention and control face the situation that the risk technique is complex and changeable and difficult to control. Mainly relates to: some information of the user before the transaction cannot be obtained, for example, the user may have a certain social contact with a cheater before the transaction, and the lack of some necessary background information may cause inaccurate risk identification; the traditional safety product verification and management and control reminding is not suitable for complex scenes, the user is deeply cheated, the subjective intention of the user urgently needs transaction operation, only the risk user is reminded of noninductivity, at the moment, capital expenditure is usually carried out for the user operation, the identity of the user is verified to be invalid, and the cheated user is difficult to awaken; further, the governance output in such scenarios is not understood by the user, resulting in complaints that the user thinks it is disturbing.
According to the method and the system, the user is contacted through various interactive products in an interactive service form, transaction risk information is deeply communicated with the user, the user is helped to discriminate and reveal fraud risks, and finally the purpose of helping the user stop payment is achieved. Under the condition that necessary background information is missing, in the process of interacting with a user in various forms, effective information is continuously acquired, risk identification is carried out in real time based on historical information and latest interaction information, intention identification is carried out by using a model, and rule intervention is carried out by using a strategy engine, so that the risk identification preparation rate is improved.
Furthermore, in order to wake up a deeply deceived user and improve user experience, different interactive products are recommended for different users, information is continuously confirmed with the user in a targeted manner in the process of multi-round interaction, risk information is revealed, and the ability of really combining the mind of the user to reach the user risk revealing capability is achieved. Through data comparison, after the user is actively touched in an interactive mode, the risk is confirmed, the transaction payment stopping rate of the user is improved, and the risk revealing efficiency in one-time interaction is greatly improved.
In the present disclosure, an individual user will be described as an example, and those skilled in the art will understand that the technical solution of the present disclosure is also applicable to a shop user, an enterprise user, and other types of users.
For individual users, the transaction payment risks encountered often include risks caused by information leakage, such as theft of an account or trapping of a fraud, counterfeit customer service, or the like. Such risks are often relatively easy to wake up a user after communicating with the user. However, with the development of electronic payment, the transaction payment risk also involves some risk operations caused by non-strangers after the users trust, such as luring the users to carry out huge money transfer to collect money by using the historical information of "profitability" such as false APP and the like. In this case, users are often extremely difficult to wake up based on a sense of trust and a "profitable" enticement on a past-contact basis. Particularly, the non-strangers have different trust construction means aiming at different types of people, such as the old people, the young student groups and the like, and the users are difficult to wake up and stop paying in time only by the existing risk prompting method. The present disclosure will hereinafter describe a general interactive wind control method and system, taking as an example such users that are extremely difficult to wake up.
FIG. 1 is a flow chart illustrating a general interactive wind control method 100 according to an embodiment of the present disclosure. In the embodiment described in connection with fig. 1, the user deeply trusts "experts" in a certain length of stock-fighting group chat, which will start investing in the "expert" recommended stock-fighting APP.
At 102, an operation of a user is received and initially determined to be at risk.
In one embodiment of the present disclosure, a user makes a transfer request on a stock-casting APP. Based on the transfer request, the APP environment is found to be in doubt. At this time, it may be preliminarily determined that the operation is at risk.
At 104, coarse-grained multi-dimensional information related to the operation is obtained based on the scenario of the operation.
In the present embodiment, based on the above user operations, the operation scene is a stock-fighting scene in financing. According to the stock-frying scene, coarse-grained multi-dimensional information related to the operation can be obtained.
The coarse-grained multi-dimensional information includes categories of people to which the user belongs, user intent, and risk. In this embodiment, the population to which the user belongs may be differentiated by age and risk tolerance. For example, retirees with a rich pension may belong to the elderly population, which may have relatively low risk tolerance in terms of investment and relatively conservative investment style. The accumulated middle-aged and young-aged staff can belong to middle-aged people, and have certain risk tolerance in investment. Students who do not have income by themselves may belong to a group of young people who do not have risk tolerance in investment, but who may be relatively aggressive in investment style.
In this embodiment, the current user intent may appear in the coarse-grained, multi-dimensional information as a transfer in financing. In an electronic trading scenario, without exhaustive enumeration, user intent may be roughly divided into: ..
In this embodiment, the risk category is currently an operational risk. In an electronic trading scenario, without exhaustive enumeration, risk categories for a user may be roughly divided into: sensitive information leaks, environmental risks, operational risks, user property losses, and the like. The risk categories are dynamic, interconvertible and both. Still further, the risks involved in the risk operations may be ranked according to different scenarios, e.g., high risk, medium risk, low risk, etc.
At 106, the corresponding interactive wind control component is presented to the user based on the coarse-grained multi-dimensional information.
Based on the coarse-grained multi-dimensional information obtained at 104, i.e., the user's belonged population, user intent, risk category, etc., appropriate interactive wind control components are recommended. For example, a juvenile group recommendation system or an APP terminal internal examination paper product, and a user belonging to an elderly group recommends an intelligent voice outbound product.
Those skilled in the art will appreciate that the interactive wind control component can be further subdivided for groups of people, and there are many more different forms of components, such as intelligent voice-out products, electronic interactive products within the system (e.g., intelligent interactive reporting products, intelligent interactive examination paper products), and so on. The interactive wind control component is further subdivided according to the scene. For example, for a shopping scenario, the crowd may be further subdivided for different personalities or preferences, and more targeted interactive wind-control components may be provided.
At 108, multiple rounds of interaction are performed with the user using the corresponding interactive wind control component to gather updated multidimensional information.
Next, multiple rounds of interaction with the user may be performed using the corresponding interactive wind control components to gather updated multidimensional information. The updated multidimensional information includes user behavior, transaction environment, associations, and the like.
In an embodiment of the present disclosure, a user makes a transfer request on a stock cast APP. Under the condition that the user belongs to the old people, the intelligent voice outbound product is used for carrying out multi-round interaction with the old user. During the interaction, for example, the problem of the first round of interaction may involve: how does stock APP know? To which company will the invested funds be transferred? Based on the user's first turn of responses, for example, by pointing at a "specialist" in a group chat, investing money, i.e., forwarding to the company to which the stock APP belongs, and so on, a portion of the updated multidimensional information may be obtained. For example, a chain of sequence behaviors of the user can be constructed, and whether the environment of the stock market APP is normal or not can be inquired, the operation range of a company to which the stock market APP belongs can be inquired, and the like.
The problem of the second round of interaction may involve: is the "expert" aware of the identity? Suspected risk of stock investment APP? Is it a company that is not a financial business? Based on the user's second turn of responses, e.g., "expert" recruits alligator for well-known private, which calls the company to be a well-known investment company, there are many more users in the group that are well-paid, etc., another portion of the updated multidimensional information may be obtained.
The number of turns required by the multi-turn interaction can be preset according to a specific scene or risk category and rules, or can be adjusted in real time by the system according to a strategy, or even can be manually set by customer service personnel. By way of example, the system policy may be: for high-risk operation, the user is required to confirm that the operation is high-risk operation and the risk is to be released as a stop condition for multiple rounds of interaction.
At 110, the updated multidimensional information is analyzed to obtain fine-grained multidimensional information.
Based on the updated multidimensional information collected at 108, it can be analyzed to obtain fine-grained multidimensional information. The fine-grained multi-dimensional information includes actual intent of the user, scene risk probability, risk probability of the operation, abnormal data of participants of the operation, and the like.
In embodiments of the present disclosure, based on the user's answers, it may be learned that the user's actual intent is to make a high-risk investment to achieve a high-return benefit. Based on the suspected false APP of the stock-casting APP, the scene risk probability is high. Based on the transfer amount of the user, the risk probability of the operation can be judged to be high in advance. Based on the 'expert' information provided by the user, whether the recent performance of the 'expert' accords with the profit claimed by a plurality of users can be inquired; if not, a participant exception to the operation is identified.
At 112, the user is exposed to the presence of a risk based on the fine-grained multi-dimensional information.
And according to the fine-grained multi-dimensional information acquired at 110, revealing whether the risk exists or not to the user.
In the embodiment of the disclosure, the user is revealed that the risk is high and exists based on the multi-dimensional information with fine granularity.
Those skilled in the art will appreciate that the above information acquisition and analysis may be performed using speech recognition and natural language processing techniques, and multiple rounds of interactive sessions with a user may be performed using targeted dialog techniques; and, as the user intention recognition technology advances, vertical information acquisition can be accomplished efficiently and accurately. The technical solution of the present disclosure may incorporate new information processing technology, which is not described herein.
FIG. 2 is a timing diagram illustrating an interactive wind control assembly according to an embodiment of the present disclosure. The timing diagram of the interactive component is mainly divided into two parts, product recommendation and interactive promotion.
In the product recommendation stage, the user initiates transaction operation (1) and recognizes risks through a wind control engine, a product recommendation component relies on a strategy engine, and recommends a proper product (2) by analyzing the user belonging crowd, the user intention, the risk category and the like, for example, young people recommend the payment treasure end internal examination paper product, and old people recommend the intelligent voice outbound product.
The product recommendation component can synthesize the risk category, the user intention and the service preference to perform multidimensional decision 3 and output personalized service products to the user (4).
And (3) an interactive propulsion phase: and (5) the user interacts with the recommended interactive component (6) through a medium, such as a telephone, an app and the like, and the intelligent interactive component continuously performs information confirmation, intention identification, risk judgment (7) and the like in the interaction process, so that the purpose of releasing the risk (8) is finally achieved. Note that the process of the interaction may be a multi-round interaction (loop).
The two parts of the product recommendation and the interactive promotion aim at accurately acquiring user information, and performing targeted risk prompt after accurate risk judgment, so that risks are effectively released due to strong persuasion.
After the user information is acquired and before the related risks are judged, real-time identification of the user intention is needed, so that the system or APP can identify the information most relevant to the current operation of the user, and the purpose of updating the user intention in real time is achieved. In different scenarios, the requirements of user operations fall into three broad categories: navigational, informational, and transactional. In practice, user intent recognition may translate into a classification problem, i.e., using a string of instructions (e.g., query, etc.) and related information to derive an operational intent category, and then performing further operations under the specific intent category.
Specifically, the data used for the intention recognition is generally an operation log of the user. After log data is acquired, the clean-up removes noise data or unwanted information. It is then considered to extend the intention-related information using the previous log information. These previous log information may be weighted in time or importance. And will not be described in detail herein.
FIG. 3 is a block diagram illustrating a generic interactive wind control system 300 according to an embodiment of the present disclosure.
According to an embodiment of the present disclosure, the universal interactive wind control system 300 includes a policy engine module 302, a product recommendation module 304, and an interaction module 306.
The policy engine module 302 is configured to receive an operation of a user and preliminarily determine that the operation is risky, and obtain coarse-grained multi-dimensional information related to the operation based on a scenario of the operation.
The coarse-grained multi-dimensional information includes categories of people to which the user belongs, user intent, and risk. The population to which the user belongs can be differentiated according to different ages and risk tolerance. User intent can be broadly categorized as shopping, financing, media content consumption, and the like. The risk categories for the user can be roughly divided into: sensitive information leaks, environmental risks, operational risks, user property losses, and the like. The risk categories are dynamic, interconvertible and both.
The product recommendation module 304 is configured to present the corresponding interactive wind control component to the user based on the coarse-grained multi-dimensional information, that is, the user belongs to the crowd, the user intention, the risk category, and the like.
The interaction module 306 is configured to perform multiple rounds of interactions with the user using the corresponding interactive wind control component to collect updated multidimensional information. The updated multidimensional information includes user behavior, transaction environment, associations, and the like.
The policy engine module 302 then further analyzes the updated multidimensional information to obtain fine-grained multidimensional information. The fine-grained multi-dimensional information includes actual intent of the user, scene risk probability, risk probability of the operation, abnormal data of participants of the operation, and the like.
Further, the interaction module 306 reveals to the user whether the risk exists according to the fine-grained multi-dimensional information. In the embodiment of the disclosure, the user is revealed that the risk is high and exists based on the multi-dimensional information with fine granularity.
FIG. 4 is a diagram illustrating a layered architecture of a universal interactive wind control system according to an embodiment of the present disclosure.
In an embodiment of the present disclosure, the layered architecture of the universal interactive wind control system is divided into an application layer 402, an access layer 404, a service layer 406, an engine layer 408, and an optional channel layer 410 from top to bottom.
The application layer 402 is used for accessing various terminals to use interactive capacity, and self-test is rapidly carried out; the service layer 402 provides corresponding different services based on different types of product forms and interaction forms; the engine layer 408 performs intention identification and problem recommendation by using the model, arranges a flow or intervenes in the recommended problem, acquires external dependence data by using a data processor in the engine layer 408, and performs data processing based on the rule and the model; the channel layer 410 selects different channels to reach the user based on different products, such as in the form of a call back through a phone or in the form of a test book in the app end; the access layer 404 extends the custom interface controller to agree on a data interaction format or protocol with different upstream services.
The entire data stream is routed through the configuration/router module 412 to the corresponding module, and context and interactive session information is saved through the context/session module 416 to concatenate the entire interactive data stream.
The layered architecture of the universal interactive wind control system in the embodiment has flexible and rich functions and strong component expansibility. In one embodiment, the policy engine module 302 of fig. 3 may be comprised of an access layer 404, an engine layer 408, and a configuration/router module 412. The engine layer 408 can flexibly apply the combination model and the rule, so that the policy engine module 302 can perform risk identification and interactive problem recommendation by using the interaction model and the risk identification model, perform problem intervention or global bottoming in a specific scene, and combine the accuracy of the model algorithm and the flexibility of rule configuration. In another embodiment, the engine layer 408 may perform flow orchestration for flow comparison to fixed scenarios.
The extensibility is strong and is realized by the policy engine module 302, that is, the custom interface controller is expanded in the access layer 404, the data interaction format is agreed with different upstream business parties, different models are expanded in the engine layer 408, the custom rule is configured, and corresponding data processing preparation is performed through processing. Thus, the policy engine module is scalable according to the scenario.
In the present embodiment, the product recommendation module 304 and the interaction module 306 of FIG. 3 are comprised of an application layer 402, a service layer 406, a channel layer 410, and a context/session module 416. It is understood that in different scenarios, the layered architecture may be adjusted based on different requirements to form a corresponding interactive wind control system.
The product recommendation module 304 and the interaction module 306 can perform capability enhancement through the policy engine module 302, and the product recommendation module 304 can recommend a suitable product according to the crowd to which the user belongs, the user intention, the risk category and the like by depending on the policy engine module 302; the interactive module 306 may use the policy engine module 302 as a flow orchestration tool or post-intervener to the model.
FIG. 5 is a diagram illustrating a policy engine data structure in a generic interactive wind control system according to an embodiment of the present disclosure. FIG. 5 shows a content policy tree of one test in the embodiment to show the data structure of the lower policy engine.
In one embodiment, the policy engine is a tree structure that mainly includes a root node (e.g., policy aware questionnaire questions), leaf nodes (e.g., part-time brush order maneuver conditions), and other nodes (rule nodes). The root node mainly stores basic information of the strategy, including applicable products, scenes, interactive forms and the like of the strategy; the leaf nodes are mainly related to specific type output contents of the interactive products, if the interactive examination papers are related to examination questions, the interactive outbound calls are related to conversation information. The ability of recommending distribution or arrangement mainly depends on the rule nodes, the rule nodes can carry out configuration of a series of conditions and logical calculation of the conditions, and the calculation and comparison of the feature scripts are behind the conditions.
Those skilled in the art can understand that the data structure of the policy engine may adopt various data structures according to different scenarios, and details are not described herein.
By utilizing the universal interactive wind control system, the user behavior characteristics can be automatically attached to carry out real-time risk confrontation, the safety of a user account and the safety of payment transaction are ensured, the interference on the user is reduced to the minimum, and the safety and experience are efficiently integrated and mutually promoted by combining seemingly 'irreconcilable contradictions'.
According to the technical scheme, the users are contacted through various interactive products in an interactive service mode, transaction risk information is deeply communicated with the users, the users are helped to discriminate and reveal fraud risks, and the purpose of helping the users stop payment is finally achieved. Aiming at the problem of inaccurate risk analysis and identification, effective information is continuously acquired in the interaction process with users in various forms, risk identification is carried out in real time based on historical information and latest interaction information, intention identification is carried out by using a model, and a policy engine is used for rule intervention, so that the risk identification preparation rate is improved; aiming at the problems that the original risk disclosure documents or products are not flexible enough and the disclosure effect is insufficient, different interactive products are recommended for different users, information is continuously confirmed with the users in a targeted manner in the multi-round interaction process, risk information is disclosed, and the capability of touching the users to disclose the risks by really combining the mind of the users is achieved.
The various steps and modules of the general interactive wind control method and system described above may be implemented in hardware, software, or a combination thereof. If implemented in hardware, the various illustrative steps, modules, and circuits described in connection with the present invention may be implemented or performed with a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA), or other programmable logic component, hardware component, or any combination thereof. A general purpose processor may be a processor, microprocessor, controller, microcontroller, or state machine, among others. If implemented in software, the various illustrative steps, modules, etc. described in connection with the present invention may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Software modules implementing the various operations of the present invention may reside in storage media such as RAM, flash memory, ROM, EPROM, EEPROM, registers, hard disk, a removable disk, a CD-ROM, cloud storage, etc. A storage medium may be coupled to the processor such that the processor can read information from, and write information to, the storage medium, and execute the corresponding program modules to perform the steps of the present invention. Furthermore, software-based embodiments may be uploaded, downloaded, or accessed remotely through suitable communication means. Such suitable communication means include, for example, the internet, the world wide web, an intranet, software applications, cable (including fiber optic cable), magnetic communication, electromagnetic communication (including RF, microwave, and infrared communication), electronic communication, or other such communication means.
It is also noted that the embodiments may be described as a process which is depicted as a flowchart, a flow diagram, a structure diagram, or a block diagram. Although a flowchart may describe the operations as a sequential process, many of the operations can be performed in parallel or concurrently. In addition, the order of the operations may be rearranged.
The disclosed methods, apparatus, and systems should not be limited in any way. Rather, the invention encompasses all novel and non-obvious features and aspects of the various disclosed embodiments, both individually and in various combinations and sub-combinations with each other. The disclosed methods, apparatus, and systems are not limited to any specific aspect or feature or combination thereof, nor do any of the disclosed embodiments require that any one or more specific advantages be present or that a particular or all technical problem be solved.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes may be made in the embodiments without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (17)
1. A universal interactive wind control method, comprising:
receiving an operation of a user and preliminarily judging that the operation is risky;
acquiring coarse-grained multi-dimensional information related to the operation based on the scene of the operation;
presenting a corresponding interactive wind control component to the user based on the coarse-grained multi-dimensional information;
performing a plurality of rounds of interaction with the user using the corresponding interactive wind control assembly to collect updated multi-dimensional information;
analyzing the updated multidimensional information to obtain fine-grained multidimensional information; and
and disclosing whether the risk exists or not to the user according to the fine-grained multi-dimensional information.
2. The method of claim 1, the coarse-grained multi-dimensional information comprising a crowd to which the user belongs, a user intent, and a category of the risk.
3. The method of claim 1, the fine-grained multi-dimensional information comprising user actual intent, scenario risk probability, risk probability of the operation, anomaly data of participants of the operation.
4. The method of claim 1, the analyzing the updated multidimensional information to obtain fine-grained multidimensional information is based on a rule or a model.
5. The method of claim 1, the corresponding interactive wind-controlled component being one of an intelligent voice-out product, an in-system electronic interactive product, and the like.
6. The method of claim 5, wherein the in-system electronic interactive products comprise intelligent interactive reporting products, intelligent interactive test paper products, and the like.
7. The method of claim 5, the corresponding interactive wind control component being subdivided according to a scene.
8. A universal interactive wind control system comprising:
a policy engine module to:
receiving an operation of a user and preliminarily judging that the operation is risky;
acquiring coarse-grained multi-dimensional information related to the operation based on the scene of the operation;
a product recommendation module to:
presenting a corresponding interactive wind control component to the user based on the coarse-grained multi-dimensional information;
an interaction module to:
performing a plurality of rounds of interaction with the user using the corresponding interactive wind control assembly to collect updated multi-dimensional information;
wherein the policy engine module further analyzes the updated multidimensional information to obtain fine-grained multidimensional information; and
the interaction module further reveals whether the risk exists or not to the user according to the fine-grained multi-dimensional information.
9. The system of claim 8, the coarse-grained multi-dimensional information comprising a crowd to which the user belongs, a user intent, and a category of the risk.
10. The system of claim 8, the fine-grained multi-dimensional information comprising user actual intent, scenario risk probability, risk probability of the operation, anomaly data of participants of the operation.
11. The system of claim 8, the policy engine module further analyzing the updated multidimensional information to obtain fine-grained multidimensional information is based on a rule or a model.
12. The system of claim 8, the corresponding interactive wind-controlled component being one of an intelligent voice-out product, an in-system electronic interactive product, and the like.
13. The system of claim 12, wherein the in-system electronic interactive products comprise intelligent interactive reporting products, intelligent interactive test paper products, and the like.
14. The system of claim 8, the corresponding interactive wind control component being subdivided according to a scene.
15. The system of claim 8, the policy engine module is extensible according to a scenario.
16. The system of claim 8, wherein the data structure of the policy engine module is a tree structure.
17. A computer-readable storage medium having stored thereon instructions that, when executed, cause a machine to perform the method of any of claims 1-7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110184105.7A CN112862322A (en) | 2021-02-10 | 2021-02-10 | Universal interactive wind control method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110184105.7A CN112862322A (en) | 2021-02-10 | 2021-02-10 | Universal interactive wind control method and device |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112862322A true CN112862322A (en) | 2021-05-28 |
Family
ID=75989597
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110184105.7A Pending CN112862322A (en) | 2021-02-10 | 2021-02-10 | Universal interactive wind control method and device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112862322A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103150981A (en) * | 2013-01-02 | 2013-06-12 | 曲东阳 | Self-service voice tour-guiding system and triggering method thereof |
CN107180070A (en) * | 2017-03-29 | 2017-09-19 | 暨南大学 | A kind of risk information is classified, recognized and method for early warning and system automatically |
CN110109596A (en) * | 2019-05-08 | 2019-08-09 | 芋头科技(杭州)有限公司 | Recommended method, device and the controller and medium of interactive mode |
CN110598982A (en) * | 2019-08-07 | 2019-12-20 | 阿里巴巴集团控股有限公司 | Active wind control method and system based on intelligent interaction |
CN110705988A (en) * | 2019-09-12 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Interactive blocking method and system for invasive behaviors |
-
2021
- 2021-02-10 CN CN202110184105.7A patent/CN112862322A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103150981A (en) * | 2013-01-02 | 2013-06-12 | 曲东阳 | Self-service voice tour-guiding system and triggering method thereof |
CN107180070A (en) * | 2017-03-29 | 2017-09-19 | 暨南大学 | A kind of risk information is classified, recognized and method for early warning and system automatically |
CN110109596A (en) * | 2019-05-08 | 2019-08-09 | 芋头科技(杭州)有限公司 | Recommended method, device and the controller and medium of interactive mode |
CN110598982A (en) * | 2019-08-07 | 2019-12-20 | 阿里巴巴集团控股有限公司 | Active wind control method and system based on intelligent interaction |
CN110705988A (en) * | 2019-09-12 | 2020-01-17 | 阿里巴巴集团控股有限公司 | Interactive blocking method and system for invasive behaviors |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020037918A1 (en) | Risk control strategy determining method based on predictive model, and related device | |
Yang et al. | Unleashing the power of networks: Shareholder activism, sustainable development and corporate environmental policy | |
CN106097043B (en) | The processing method and server of a kind of credit data | |
CN106780012A (en) | A kind of internet credit methods and system | |
CN107197463A (en) | A kind of detection method of telephone fraud, storage medium and electronic equipment | |
CN111861732A (en) | Risk assessment system and method | |
US11087334B1 (en) | Method and system for identifying potential fraud activity in a tax return preparation system, at least partially based on data entry characteristics of tax return content | |
CN111932268B (en) | Enterprise risk identification method and device | |
CN112840628A (en) | Evidence recording of human-computer interaction communication | |
CN106789844B (en) | Malicious user identification method and device | |
CN110598982B (en) | Active wind control method and system based on intelligent interaction | |
CN112330355B (en) | Method, device, equipment and storage medium for processing consumption coupon transaction data | |
CN111428217A (en) | Method and device for identifying cheat group, electronic equipment and computer readable storage medium | |
CN110166639A (en) | Voice collection method, apparatus, computer equipment and storage medium | |
CN109600724A (en) | A kind of method and apparatus that short message is sent | |
CN113129012A (en) | Payment data processing method, device, equipment and system | |
CN110457601B (en) | Social account identification method and device, storage medium and electronic device | |
CN112910953B (en) | Business data pushing method and device and server | |
CN113485993A (en) | Data identification method and device | |
CN110288488A (en) | Medical insurance Fraud Prediction method, apparatus, equipment and readable storage medium storing program for executing | |
CN112702410B (en) | Evaluation system, method and related equipment based on blockchain network | |
CN109726315A (en) | Data query method, apparatus calculates equipment and storage medium | |
CN108769208A (en) | Specific user's identification and information-pushing method and device | |
CN116485527A (en) | Financial credit risk analysis method and device | |
CN109711984B (en) | Pre-loan risk monitoring method and device based on collection urging |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |