CN114862171A

CN114862171A - Risk assessment method and device for emergency event

Info

Publication number: CN114862171A
Application number: CN202210459875.2A
Authority: CN
Inventors: 王东博; 林川; 林宜营; 党佩
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2022-04-24
Filing date: 2022-04-24
Publication date: 2022-08-05

Abstract

The embodiment of the specification provides a risk assessment method and device for an emergency event, wherein the risk assessment method for the emergency event comprises the following steps: acquiring an emergency event to be processed; extracting an event subject of the emergency event from the emergency event; the event main body comprises a user account and target product information, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product; inquiring corresponding risk assessment data in a main body portrait library of a target product according to the event main body; the risk assessment data includes: the data processing method comprises the following steps that first end internal data related to an event main body in a platform where a target product is located and first end external data related to the event main body outside the platform where the target product is located; and determining to carry out risk evaluation on the emergency event according to the risk evaluation data to obtain a risk evaluation result.

Description

Risk assessment method and device for emergency event

Technical Field

The present invention relates to the field of emergency response, and in particular, to a method and an apparatus for risk assessment of an emergency event.

Background

With the development of internet technology, the efficiency of information dissemination on the internet is rapidly increasing. Sharing the experience of an individual using some products over the internet may provide some reference to others using the same products, or to others who are interested in using the same products. Positive or negative evaluations of a small number of individuals on a product may be magnified several times by the internet, with unexpected consequences.

Disclosure of Invention

One or more embodiments of the present disclosure provide a method for risk assessment of an emergency event. The risk assessment method for the emergency event comprises the following steps: and acquiring the emergency event to be processed. And extracting the event subject of the emergency event from the emergency event. The event main body comprises a user account and information of the target product, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product. And inquiring corresponding risk assessment data in a main body portrait library of the target product according to the event main body. The risk assessment data includes: the data comprises first end internal data related to the event main body in a platform where the target product is located, and first end external data related to the event main body outside the platform where the target product is located. And determining to carry out risk assessment on the emergency event according to the risk assessment data to obtain a risk assessment result.

One or more embodiments of the present specification provide an emergency risk assessment device, including: the acquisition module is configured to acquire the emergency event to be processed. An extraction module configured to extract an event subject of the emergency event from the emergency event. The event main body comprises a user account and information of the target product, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product. And the query module is configured to query corresponding risk assessment data in the subject portrait database of the target product according to the event subject. The risk assessment data includes: the data comprises first end internal data related to the event main body in a platform where the target product is located, and first end external data related to the event main body outside the platform where the target product is located. And the evaluation module is configured to determine to carry out risk evaluation on the emergency event according to the risk evaluation data to obtain a risk evaluation result.

One or more embodiments of the present specification provide an emergency event risk assessment device including: a processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to: and acquiring the emergency event to be processed. And extracting the event subject of the emergency event from the emergency event. The event main body comprises a user account and information of the target product, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product. And inquiring corresponding risk assessment data in a main body portrait library of the target product according to the event main body. The risk assessment data includes: the data comprises first end internal data related to the event main body in a platform where the target product is located, and first end external data related to the event main body outside the platform where the target product is located. And determining to carry out risk assessment on the emergency event according to the risk assessment data to obtain a risk assessment result.

One or more embodiments of the present specification provide a storage medium storing computer-executable instructions that, when executed by a processor, implement the following: and acquiring the emergency event to be processed. And extracting the event subject of the emergency event from the emergency event. The event main body comprises a user account and information of the target product, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product. And inquiring corresponding risk assessment data in a main body portrait library of the target product according to the event main body. The risk assessment data includes: the data comprises first end internal data related to the event main body in a platform where the target product is located, and first end external data related to the event main body outside the platform where the target product is located. And determining to carry out risk assessment on the emergency event according to the risk assessment data to obtain a risk assessment result.

Drawings

In order to more clearly illustrate one or more embodiments or technical solutions in the prior art in the present specification, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present specification, and for those skilled in the art, other drawings can be obtained according to the drawings without inventive exercise;

FIG. 1 is a flowchart illustrating a method for risk assessment of an emergency event according to one or more embodiments of the present disclosure;

FIG. 2 is a schematic diagram of an event risk assessment matrix used in a method for risk assessment of an emergency event according to one or more embodiments of the present disclosure;

FIG. 3 is a process flow diagram of a method for performing risk assessment of an emergency event by an emergency response platform according to one or more embodiments of the present disclosure;

FIG. 4 is a schematic diagram of an emergency risk assessment device according to one or more embodiments of the present disclosure;

fig. 5 is a schematic structural diagram of a risk assessment device for an emergency event according to one or more embodiments of the present disclosure.

Detailed Description

In order to make those skilled in the art better understand the technical solutions in one or more embodiments of the present disclosure, the technical solutions in one or more embodiments of the present disclosure will be clearly and completely described below with reference to the drawings in one or more embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, and not all embodiments. All other embodiments that can be derived by a person skilled in the art from one or more of the embodiments described herein without making any inventive step shall fall within the scope of protection of this document.

The embodiment of the risk assessment method for the emergency event provided by the specification comprises the following steps:

referring to fig. 1, the method for risk assessment of an emergency event provided in this embodiment specifically includes steps S102 to S108.

In practical applications, emergency events frequently occur in various industries, and the sources of the emergency events are diversified, and the emergency events may come from users or merchants, and may also come from external market environments, regulatory departments and the like. If the emergency event is not accurately and timely processed, the emergency event can be further fermented and upgraded, and huge loss is caused at the economic level and even the reputation level.

An emergency event is a single risk or systematic risk event that has caused or may have an adverse effect on, or jeopardizes the proper operation of, a particular subject, requiring immediate emergency management action to be taken. The specific object here may be a producer of the product, an organization or organization including a plurality of members, or any other group having a risk assessment requirement. In the method for risk assessment of an emergency event provided in this embodiment, a producer of a product is taken as an example to illustrate how to perform risk assessment on an emergency event of the producer of the product, and other specific objects are similar to the producer of the product and are not described in detail below.

And step S102, acquiring the emergency event to be processed.

The performer of step S102 may be an emergency response platform of the producer of the product. The source of the emergency event can be a common user of the product, a merchant user of the product, an external market environment, a supervision department, and the like, and the source of the emergency event is not particularly limited in the specification. The pending emergency event may be an emergency event that has just been detected and requires a risk assessment.

The emergency event to be processed may be that the user of the target product makes a preset type evaluation on the target product, so as to negatively affect the target product, or may negatively affect the target product, or endanger the normal operation of the target product.

The target product may be a program, for example, payment program 1; the target product may also be an applet in a program, for example, a takeaway applet in payment program 1; the target product may also be a function of the program, for example, the code scanning function of the payment program 1.

The preset type evaluation may be a negative evaluation, for example, criticizing that the target product is not good; or a comprehensive evaluation including both positive evaluation and negative evaluation, for example, evaluating the merits and demerits of the target product from different angles; it may also be a rating containing constructive opinions, e.g., suggesting how the target product improves.

The user of the target product may be a merchant user or a non-merchant user. The target product may be a product used by a non-merchant user, such as a takeaway application used by the non-merchant user when ordering food, or the target product may be a product used by a merchant user, such as a merchant version takeaway application used by the merchant user when serving food for the non-merchant user.

Taking a target product as the function X of the payment application 1 as an example, the emergency event to be processed may be that a user a of the payment application sends a piece of information on the social application, that is, the function X of the payment application 1 is very bad and is forcibly quitted after being used for half of the time, and uploads a screenshot of using the payment application 1 by himself, the information is approved by a plurality of users on the social application, and a large amount of forwarding support is supported, and the emergency event causes adverse effects on the payment application 1.

Step S104, extracting an event main body of the emergency event from the emergency event; the event body comprises a user account and target product information, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product.

The information of the target product may be a name of the target product, a product number of the target product, or other identification information that can be used to uniquely identify the target product, and so on, which are not listed here.

The event body may include a user who has made a preset type evaluation on the target product, a user account number that the user logs in when using the target product, and a name, a product number, or other identification information that may be used to uniquely identify the target product.

Illustratively, the pending emergency event is that a user a of the payment application sends a message "function X of the payment application 1 is very bad, and is forced to quit when half of the function X is used frequently" on the social application, and uploads a screenshot of using the payment application 1 by himself, and the message is approved by many users on the social application and is supported by mass forwarding. Event subjects extracted from the emergency event include, but are not limited to: the user A, the payment account number of the user A in the payment application 1 and the function X of the payment application 1.

Step S106, according to the event body, inquiring corresponding risk evaluation data in a body portrait library of the target product; the risk assessment data includes: the data processing method comprises the steps of first end internal data related to an event main body in a platform where a target product is located and first end external data related to the event main body outside the platform where the target product is located.

A body representation library may be used to store user representations. The user behaviors can be traced, the information overall view of the user is gradually built in a mode of marking the user with a label, the user portrait is generated, and the user requirements are mined out from the portrait, so that the service and the customer satisfaction of offline and online services are improved.

The subject image library of the target product can be a database which is established in advance by the target product and is used for storing user characteristic data, and the user characteristic data can comprise risk assessment data corresponding to a user.

In the case that the target product is an application program, the subject image library of the target product may be a database that is pre-established by the application program and used for storing user characteristic data. In the case that the target product is a function of an application program or an applet, the main body image library of the target product may be a database which is pre-established by the application program corresponding to the target product and is used for storing user feature data.

The first end internal data may be data for risk assessment, which can be directly obtained by querying in the system to which the target product belongs, and the producer of the target product may process or intervene in the first end internal data. The first offsite data may be data for risk assessment, which may be captured by a manufacturer of the target product through a web crawler or acquired in a specific website page screenshot manner, but the manufacturer of the target product cannot intervene in the first offsite data.

In the main body image library of the target product, user accounts of various users can be stored in advance, and for the whole application program used by each user, first end internal data which is related to the whole application program and first end external data which is related to the whole application program can be stored; for each function used by each user in the application, first in-terminal data associated with each function and first out-of-terminal data associated with each function may be stored; first in-terminal data associated with each sub-program and first out-terminal data associated with each sub-program may be stored for each sub-program used by each user in the application program.

According to the user account number in the event main body and the information of the target product, the main body image library of the target product can be inquired to obtain the first end internal data related to the target product and the first end external data related to the target product.

For example, the event body includes a user account used by the user a when using the function X of the payment application 1, that is, the payment account of the user a in the payment application 1, and a number "001" corresponding to the function X in the payment application 1, then according to the payment account of the user a in the payment application 1, each function used by the user a in the application program can be obtained by querying in a body portrait library of the payment application 1, and according to the number "001", first internal data associated with the function X and first external data associated with the function X can be further obtained by querying.

It should be noted that, if, in an emergency event, a user claims that some negative experiences are encountered in the process of using a target product, but actually the user is not a real user of the target product, but compiles false information to dirty a target product, in this case, although the corresponding risk assessment data cannot be obtained by querying in the main body image library of the target product, the producer of the target product very easily obtains evidence for clarifying the fact to cope with the emergency event, and then it can be determined that the risk assessment result of the emergency event to be processed is extremely low in risk degree.

Optionally, after the emergency event to be processed is acquired, before querying corresponding risk assessment data in a subject portrait library of the target product according to an event subject, the risk assessment method for the emergency event further includes: determining a corresponding risk event type in a plurality of preset risk event types according to the emergency event; according to the event subject, inquiring corresponding risk assessment data in a subject portrait library of the target product, wherein the risk assessment data comprises: and inquiring the first end internal data and the first end external data in the main body image library of the target product according to the event main body and the risk event type.

The preset risk event type may include a business operation risk, and may also include other preset risk event types. Each preset risk event type has a corresponding preset event type characteristic. And aiming at the same target product, the risk evaluation data corresponding to the emergency events of different preset risk event types are different.

In specific implementation, event type feature data can be extracted from the emergency event, according to the extracted event type feature data, matched preset event type features are determined in the preset event type features corresponding to each preset risk event type, and then the preset risk event type corresponding to the matched preset event type features is determined as the risk event type of the emergency event.

The main body image library of the target product can be stored with user account numbers of all users in advance, and for the whole application program used by each user, first end internal data which are integrally associated with the application program and respectively belong to multiple preset risk event types and first end external data which are integrally associated with the application program and respectively belong to multiple preset risk event types can be stored; for each function used by each user in the application program, first in-terminal data associated with each function and respectively belonging to multiple preset risk event types and first out-terminal data associated with each function and respectively belonging to multiple preset risk event types can be stored; for each sub-program used by each user in the application program, first in-terminal data associated with each sub-program and respectively belonging to a plurality of preset risk event types and first out-terminal data associated with each sub-program and respectively belonging to a plurality of preset risk event types may be stored.

According to the risk event type of the emergency event, the user account number in the event subject and the information of the target product, the first terminal internal data related to the target product and the first terminal external data related to the target product can be obtained by inquiring in the subject image library of the target product.

By combining the event main body and the risk event type, the data in the first end and the data in the second end are inquired in the main body image library, so that the range of the data for risk assessment can be narrowed, and the risk assessment efficiency can be improved.

Optionally, before querying, according to the event subject, the corresponding risk assessment data in the subject representation library of the target product, the risk assessment method for the emergency event further includes: acquiring a risk event; the risk events include public sentiment events and/or complaint events; extracting risk event subjects from the risk events; obtaining complaint risk information, wind control risk information and technical risk information of a risk event main body as second end internal data associated with the risk event main body; acquiring public opinion risk information, stability maintenance risk information, supervision risk information, litigation risk information and resource loss risk information of risk event main bodies, wherein the public opinion risk information, stability maintenance risk information, supervision risk information, litigation risk information and resource loss risk information are used as second external data associated with the risk event main bodies; the risk event body, the second internal data and the second external data are written into the body portrait library.

The risk event may be a public sentiment event, for example, a user A criticizes a target product by sending a message on a social platform, and the message is forwarded and commented by many people. The risk event may also be a complaint event, for example, the user leaves a message about a complaint target product through a complaint channel of the target product.

The risk event body may include a user account registered when a user who has made a preset type of evaluation for a target product in public opinion or complaints uses the target product, and information of the target product.

And obtaining complaint risk information, wind control risk information and technical risk information of the risk event main body as second end internal data associated with the risk event main body. In specific implementation, the risk event subject can be used as a search keyword to query in a system to which the target product belongs to obtain complaint risk information, wind control risk information and technical risk information associated with the risk event subject. It should be noted that the appearances of "first" and "second" in this specification do not have actual meanings, but are merely provided for convenience in distinguishing between similar technical features in different cases.

The data in the second end may be complaint risk information, wind control risk information, and technical risk information associated with a risk event subject, which can be directly obtained by querying in the system to which the target product belongs, and the producer of the target product may process or intervene in the data in the second end. The second external data may be public opinion risk information, stability maintenance risk information, supervision risk information, litigation risk information, and asset risk information associated with the risk event subject, which are captured by a target product producer through a web crawler or captured on a specific website page, but the target product producer cannot intervene in the second external data.

And acquiring public opinion risk information, stability maintaining risk information, supervision risk information, litigation risk information and investment risk information of the risk event main body as second external data associated with the risk event main body. In specific implementation, the second extraterminal data outside the system to which the target product belongs can be obtained through crawling by a web crawler or in a mode of capturing a picture from a specific page of a specific website.

The risk event body, the second internal data and the second external data are written into the body portrait library. In specific implementation, the second intra-terminal data associated with the risk event subject and the second extra-terminal data associated with the risk event subject may be stored in the subject image library according to a pre-designed event risk assessment matrix.

It should be noted that, for the same target product, the data in the first end and the data in the second end may be the same data, but the definitions are different, the data in the first end is defined as data for risk assessment associated with an event subject of an emergency event to be processed in a platform where the target product is located, and the data in the second end is defined as complaint risk information, wind control risk information, and technical risk information associated with a risk event subject of the risk event in the platform where the target product is located. The first end external data and the second end external data are the same, and are not described herein again.

Fig. 2 is a schematic diagram of an event risk assessment matrix used in a risk assessment method for an emergency event according to one or more embodiments of the present disclosure.

In the subject image library of the target product, risk assessment data may be stored in accordance with an event risk assessment matrix as shown in fig. 2. As shown in fig. 2, the event risk assessment matrix may include eight dimensions, which are: public opinion risks, customer complaints risks, stability maintenance risks, regulatory risks, litigation risks, capital loss risks, wind control risks, and technical risks, wherein technical risks include technical risks-products and technical risks-industries.

Wherein, the data of the customer complaint risk dimension can be the complaint risk information; the data of the "wind-controlled risk dimension" may be the aforementioned wind-controlled risk information; the data for the "technical risk-product" dimension and the data for the "technical risk-industry" dimension may be the aforementioned technical risk information. The data of the "public opinion risk" dimension may be public opinion risk information; the data of the "stability maintenance risk" dimension may be the aforementioned stability maintenance risk information; the data of the "regulatory risk" dimension may be the aforementioned regulatory risk information; the data for the "litigation risk" dimension may be the aforementioned litigation risk information; and the data for the "asset risk" dimension may be the aforementioned asset risk information.

Magnitude, referring to magnitude, it is understood that a plurality of quantity thresholds, e.g., 100, 200, 500, 1000, 2000, 10000 … …, are preset to divide the quantity into a plurality of value intervals, e.g., 0-100, 101-.

Illustratively, the public opinion level may be a value interval in which the total number of forwarding, approval and comment of a message for a negative evaluation of a target product published in the social platform is located, for example, the function X of the application 1 for issuing a message in the social platform by the user a to blame is very unfriendly and experiences very badly, the message is forwarded 3500 pieces, approval 5000 pieces and comment 670 pieces, then the total number of forwarding, approval and comment of the message is 9170 and belongs to the value interval 2000-10000, that is, the public opinion level of the message is a level corresponding to the value interval 2000-10000.

The complaint magnitude may be the number of complaints made to the customer service for the same or similar problems of the target product, for example, 280 complaints about the target product from the user are received in the system to which the target product belongs, and the complaint magnitude may be the magnitude corresponding to the value interval 201 and 500.

In fig. 2, the meaning of the raise work order magnitude, the other maintenance stability magnitude, the supervision work order magnitude, the other supervision magnitude, the case magnitude, the technical risk-total magnitude of the past 90 days in the product, the technical risk-magnitude of each grade in the product, the technical risk-total magnitude of the past 90 days in the industry, and the "magnitude" of each grade in the technical risk-industry is the same as or similar to the "magnitude" in the public opinion magnitude and the customer complaint magnitude, and will not be described in detail below.

In the "hot search ranking" in the "public opinion risk" dimension, the "hot search" may be a function of the social platform to rank the hottest messages in the whole society, and in general, if an emergency event occurs in the "hot search" of the social platform, the attention of the emergency event is high, and the closer the "hot search" ranking is, the higher the attention is.

The "public opinion trend" may be more supporting, neutral or against which party is in question regarding emergency events. For example, if the user makes a criticism for the target product, 70% of the people involved in the discussion support the criticism, 25% of the people involved in the discussion are neutral, and only 5% of the people involved in the discussion question are in doubt and object to the criticism, the public sentiment tendency of the emergency event may be a tendency toward most of the people to support the criticism.

For an emergency event, for example, a user a issues a criticizing message in the social platform, and the function X of the responsibility payment application 1 is not good, the "head public opinion detail" refers to the specific content of the messages with the largest number of times of forwarding the criticizing message, and the specific content of the messages with the largest number of praise in the review of the criticizing message. The forwarding times are large, and the comment praise number is large, so that the viewpoints of forwarding and comment are supported by most people.

In the dimension of the 'stability risk', the 'raise work order' in the 'raise work order level' may be that the user claims that the user wants to do something that may be dangerous, for example, a plurality of users criticize the function X of the payment application 1 on the social platform to cause loss to the user, claim to put forward lawsuits to the producer of the payment application 1, and then a corresponding raise work order may be established according to the speech of each user, and the fact that the user claims to do is recorded.

In "other dimension stability level", the "other dimension stability" may be to establish other dimension stability worksheets for recording some dangerous things found in customer complaint channels or other channels. For example, if the user is in a state of extremely unstable emotion during a telephone complaint and the tone is extremely excited, the call voice can be used for establishing other dimensionally stable worksheets.

The "dimension stability detail" can be the specific content of the Yankee worksheet and other dimension stability worksheets.

In the "supervision risk" dimension, the "supervision work order" in the "supervision work order level" may be that, if many users complain the target product to the supervision department and do not meet the requirements of the supervision department, a corresponding supervision work order may be established according to the complaint of the users to the supervision department, so as to record the complaint content of the users to the supervision department.

The "other supervision" in the "other supervision orders" may be, besides the user complaints, other work orders related to the supervision department, for example, the supervision department issues notification information that needs to strengthen supervision for a certain type of product, and corresponding other supervision work orders may be established according to the notification information.

The "supervision details" may be the specific content of the supervision work order and other supervision work orders.

In the "litigation risk" dimension, "whether or not litigation risk" may be whether or not the user has already made litigation to the producer of the target product, or whether or not the user has expressed an intention to make litigation. The litigation subjects may be the users who initiate litigation.

In the "asset loss risk" dimension, "asset loss" refers to the loss of assets in an emergency event for thinking that it is subject to a target product. "case capital loss" may be that each user claiming to suffer an asset loss on its own because of the target product corresponds to a case.

In the "wind control risk" dimension, "wind control" may be that some suspicious behaviors or violations of the user related to the emergency event are monitored in a system to which the target product belongs, so as to take corresponding wind control measures for the user, for example, to perform penalty on a user account of the user.

The type of penalty, reason for the penalty, number of penalties and time of penalty may reflect whether the user is a good user, a bad, bad user or a bad user. If one user has multiple bad wind control records, the user can be determined to be a bad user, and further, corresponding emergency measures can be taken for the bad user when an emergency event is processed.

The "technical risk-product" may be technical risk information related to the target product, and the "technical risk-industry" may be technical risk information of other products belonging to the same industry as the target product in a system to which the target product belongs.

For example, the target product may be the equity function of city a of payment application 1, and "technical risk-product" may be technical risk information associated with the equity function of city a, and "technical risk-industry" may be technical risk information associated with the equity function of city B, the equity function of city C, the equity function … … of city D, and so on.

In the dimension of "technical risk-product", the "total magnitude of the past 90 days" may be a magnitude to which the number of times of occurrence of the problem of the target product related to the emergency event in the past 90 days belongs, for example, in the emergency event, the user first means that the public deposit function of the city a of the application 1 is responsible for payment, and forcibly quits in the using process, in the past 90 days of the emergency event, 5700 times of different users are forcibly quitted when using the public deposit function of the city a, and the "total magnitude of the past 90 days" is a magnitude corresponding to the value interval 2000 + 10000.

The "highest level in the past 90 days" may be that the problem that the target product relates to the emergency event in the past 90 days is divided into a plurality of technical risk levels, for example, in the emergency event, the user first blamed for paying the application 1, the public fund function of the city a fails, in the past 90 days, the public fund function of the city a fails for a plurality of times, and 3 technical risk levels are involved, which are respectively a technical risk level 1, a technical risk level 2, and a technical risk level 3, and are sorted according to the severity of the technical risk, and the technical risk level 3> the technical risk level 2> the technical risk level 1, and the highest technical risk level in the past 90 days is a technical risk level 3.

The "highest-level average time length" may be an average time length of a fault corresponding to the highest-severity technical risk level, for example, if 3 technical risk level 3 faults occur in the past 90 days, the fault time lengths are 5 minutes, 4 minutes and 6 minutes, respectively, and the highest-level average time length is an average value of the fault time of the 3 faults, that is, 5 minutes.

The "each level magnitude" may be a magnitude to which the occurrence number of the faults corresponding to each technical risk level in the past 90 days belongs, for example, 5000 times of the faults of the technical risk level 1, 450 times of the faults of the technical risk level 2, and 3 times of the faults of the technical risk level 3 occur in the past 90 days, where the magnitude of the technical risk level 1 is a magnitude corresponding to the value interval 2000-10000, the magnitude of the technical risk level 2 is a magnitude corresponding to the value interval 200-500, and the magnitude of the technical risk level 3 is a magnitude corresponding to the value interval 0-100.

In the "technical risk-industry" dimension, the definitions of the "total past 90-day magnitude", the "maximum past 90-day level", the "average time length at the maximum level", and the "magnitude of each level" are similar to the "technical risk-product" dimension, and are not described in detail below.

Optionally, before querying, according to the event subject, the corresponding risk assessment data in the subject representation library of the target product according to the event subject, the risk assessment method for the emergency event further includes: writing basic information of the commercial tenant into the main body image library; and under the condition that the risk event subject is a merchant user, establishing an incidence relation between the risk event subject and the merchant basic information.

Fig. 3 is a process flow diagram of a method for performing risk assessment of an emergency event by an emergency response platform according to one or more embodiments of the present disclosure. As shown in figure 3 of the drawings,

and extracting events from the public sentiment events and the guest right events to obtain risk event bodies, and writing the risk event bodies into a main body portrait library. Wherein the customer event comprises a complaint event. The complaint event can be an event that a written complaint is made through a complaint channel provided by a target product, or an event that a telephone complaint is made through another complaint channel provided by a target product. And writing screen capture sound, user complaints, small program basic information, merchant basic information, stability maintenance work orders and supervision work orders which are related to the target product into a main body portrait library. The screen capture sound and the user complaint can be two feedback channels in parallel, namely a mode of reaching customer service. The target product may be an applet of the application program, may also be a function of the application program, and may also be the application program itself, and the applet basic information may be configured in advance for each risk event main body, and if the target product is an applet of the application program, the applet basic information may be called to provide data support for risk assessment of the target product. The user may be a non-merchant user or a merchant. The basic information of the merchant can be configured for each risk event subject in advance, and if the user is the merchant, the basic information of the merchant can be called to provide data support for risk evaluation of the target product.

The definition of the maintenance work order and the supervision work order can refer to fig. 2, and will not be described herein. Under the condition that a plurality of risk event main bodies, associated second internal data and associated second external data are written in the main body portrait library, the emergency response platform can acquire emergency events to be processed, and extract the events corresponding to the emergency events to obtain event main bodies of the emergency events. And inquiring whether corresponding risk assessment data exist in the main body image library according to the event main body. And if so, performing risk assessment according to the risk assessment data obtained by inquiry.

Optionally, after writing the risk event body, the second internal data and the second external data into the body portrait library, before querying corresponding risk assessment data in the body portrait library of the target product according to the event body, the risk assessment method for the emergency event further includes: training the first evaluation submodel according to the second intra-terminal data to obtain a trained first evaluation submodel for performing intra-terminal risk evaluation on the emergency event; and training the second evaluation submodel according to the second off-terminal data to obtain the trained second evaluation submodel for performing off-terminal risk evaluation on the emergency event.

The data in the second end are complaint risk information, wind control risk information and technical risk information which are related to a risk event main body and can be directly inquired in a system to which the target product belongs, and the data in the second end can be inquired or modified for a producer of the target product. The data in the second end may be checked and changed during the model training process.

And training the first evaluation submodel according to the second intra-terminal data to obtain the trained first evaluation submodel for performing intra-terminal risk evaluation on the emergency event.

The second external data may be public opinion risk information, stability maintenance risk information, supervision risk information, litigation risk information and resource loss risk information associated with the risk event main body, which are captured by a producer of the target product through a web crawler or obtained in a screenshot mode of a specific website page, and the second internal data may be queried but cannot be modified for the producer of the target product. Then the second outlier data may be checked for non-change during the model training process.

Thus, the second-end in-data and the second-end out-data may be trained using different types of evaluation submodels, respectively.

A first evaluation submodel, including and not limited to: the method comprises the steps of a first evaluation submodel of complaint risk dimensionality, a first evaluation submodel of wind control risk dimensionality and a first evaluation submodel of technology risk dimensionality.

The training process is illustrated by taking the first evaluation submodel of the complaint risk dimension as an example as follows: in specific implementation, the complaint risk information carrying the score label can be input into a first evaluation submodel of the complaint risk dimension, a corresponding submodel score is output, the submodel score is used as a score prediction result, and a loss function value is calculated according to the score label and the submodel score, so that one-time model training is completed. And training the first evaluation submodel for multiple times until the loss function value meets the preset numerical value condition, and stopping training. And determining the first evaluation submodel obtained by the last training as the first evaluation submodel of the complaint risk dimensionality after the training for performing the intra-terminal risk evaluation on the emergency.

Because the data input into the second end of the first evaluation submodel come from the system to which the target product belongs, the data can be inquired or modified, and therefore, the first evaluation submodel can be subjected to feedback regulation in the model training process to form closed-loop control.

A second evaluation submodel, including and not limited to: a second evaluation submodel for public opinion risk dimensions, a second evaluation submodel for stability maintenance risk dimensions, a second evaluation submodel for supervision risk dimensions, a second evaluation submodel for lities risk dimensions, and a second evaluation submodel for capital loss risk dimensions.

Taking the second evaluation submodel of the public opinion risk dimension as an example, the training process is as follows: in specific implementation, public opinion risk information carrying a score label can be input into a second evaluation submodel of public opinion risk dimensionality, corresponding submodel scores are output, the submodel scores are used as score prediction results, and loss function values are calculated according to the score label and the submodel scores, so that one-time model training is completed. And training the second evaluation submodel for multiple times until the loss function value meets the preset numerical value condition, and stopping training. And determining the second evaluation submodel obtained by the last training as the second evaluation submodel of the public opinion risk dimension after training for performing the off-end risk evaluation on the emergency.

In the model training process, since the second outlier data is from outside the system to which the target product belongs, for example, the producer of the target product obtains the second outlier data by means of web crawler capture or screenshot on a specific website page, and the second outlier data can be queried but cannot be modified, the second estimator sub-model cannot be feedback-adjusted by adjusting the second outlier data in the model training process, and open-loop control is formed.

And S108, determining to carry out risk evaluation on the emergency event according to the risk evaluation data to obtain a risk evaluation result.

The risk assessment result may be ranked according to the pre-ranked risk levels, for example, level 1, level 2, and level 3 … …, wherein the ranking is according to the importance: level 1 is greater than level 2 is greater than level 3.

Optionally, determining to perform risk assessment on the emergency event according to the risk assessment data to obtain a risk assessment result, where the risk assessment result includes: inputting the data in the first terminal into the trained first evaluation sub-model, and outputting a first evaluation result; inputting the first external data into the trained second evaluation submodel, and inputting a second evaluation result; and determining a risk evaluation result of the emergency event according to the first evaluation result and the second evaluation result.

The first intra-end data may include complaint risk information, wind control risk information, and technical risk information. For example, the complaint risk information of the emergency event may be input into a first evaluation submodel of the complaint risk dimension to obtain a corresponding submodel score, and the submodel score is determined as a first evaluation result of the emergency event in the complaint risk dimension.

The second intra-terminal data may include public opinion risk information, stability risk information, regulatory risk information, litigation risk information, and investment risk information. Illustratively, the public opinion risk information of the emergency event can be input into a second evaluation submodel of the public opinion risk dimension to obtain a corresponding submodel score, and the submodel score is determined as a second evaluation result of the emergency event in the public opinion risk dimension.

After the submodel score of each dimension is obtained, the total evaluation score of the emergency event can be calculated according to the submodel score of each dimension and a preset score calculation formula. In the process of calculating the evaluation total score, different dimensionality score weights can be preset in different dimensionalities, so that the evaluation total score can embody the comprehensive result of each dimensionality with different importance.

In specific implementation, a plurality of numerical intervals can be divided in advance, the numerical interval in which the total evaluation score is located can be determined according to the total evaluation score of the emergency event obtained through calculation, and the risk grade corresponding to the numerical interval is used as the risk evaluation result of the emergency event.

The risk assessment results for the emergency event may include: low risk, medium risk, high risk.

Optionally, after inputting the risk assessment data into the risk assessment model and outputting the risk assessment result of the emergency event, the method for assessing the risk of the emergency event further includes: if the first risk evaluation result of the emergency event is low risk, determining the emergency event as an event to be patrolled and examined; and carrying out polling treatment on the event to be polled.

And if the first risk evaluation result of the emergency event is low risk, determining that the emergency event needs to be subjected to patrol inspection within a preset time range, and monitoring the low risk event regularly to avoid sudden fermentation of the low risk event.

Optionally, the polling processing is performed on the event to be polled, including: acquiring the latest risk evaluation data of an event to be patrolled; inputting the latest risk evaluation data into a risk evaluation model, and outputting a polling result of an event to be polled; judging whether the number of times that the inspection result of the event to be inspected is low risk is greater than or equal to a preset threshold value or not under the condition that the inspection result is low risk; if yes, stopping the risk evaluation process of the event to be patrolled and examined; and if not, returning to execute the latest risk assessment data of the event to be patrolled and examined after the preset time period.

In the case that it is determined through step S108 that the risk evaluation result of an emergency event to be processed is a low risk, the emergency event may be determined as an event to be patrolled without directly closing the processing flow of the event to be patrolled, that is, the risk evaluation flow of the event to be patrolled. In this case, whether the event to be inspected has a trend of increasing risks or not may be evaluated once again at intervals, and if the risk evaluation results of the preset number of times continuously keep low risks, it may be determined that there is no possibility of sudden low-risk fermentation, and the processing flow of the event to be inspected may be closed. The risk assessment result of the event to be patrolled and examined is detected regularly, so that the possibility of fermentation of the low-risk emergency event can be pre-warned.

The embodiment of the risk assessment device for the emergency event provided by the specification is as follows:

in the above embodiment, a method for risk assessment of an emergency event is provided, and correspondingly, a device for risk assessment of an emergency event is also provided, which is described below with reference to the accompanying drawings.

Referring to fig. 4, a schematic diagram of a risk assessment device for emergency events provided in the present embodiment is shown.

Since the device embodiments correspond to the method embodiments, the description is relatively simple, and the relevant portions may refer to the corresponding description of the method embodiments provided above. The device embodiments described below are merely illustrative.

The embodiment provides a risk assessment device for emergency events, which includes:

an obtaining module 402 configured to obtain an emergency event to be processed;

an extraction module 404 configured to extract an event subject of an emergency event from the emergency event; the event main body comprises a user account and target product information, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product;

a query module 406 configured to query a subject representation library of the target product for corresponding risk assessment data based on the event subject; the risk assessment data includes: the data processing method comprises the following steps that first end internal data related to an event main body in a platform where a target product is located and first end external data related to the event main body outside the platform where the target product is located;

and the evaluation module 408 is configured to determine to perform risk evaluation on the emergency event according to the risk evaluation data to obtain a risk evaluation result.

corresponding to the above-described emergency risk assessment method, based on the same technical concept, one or more embodiments of the present disclosure further provide an emergency risk assessment device, which is configured to execute the above-described emergency risk assessment method, and fig. 5 is a schematic structural diagram of the emergency risk assessment device provided in one or more embodiments of the present disclosure.

The risk assessment device for emergency events provided by the embodiment comprises:

as shown in FIG. 5, the risk assessment device for emergency events may vary significantly depending on configuration or performance, and may include one or more processors 501 and memory 502, where the memory 502 may store one or more stored applications or data. Memory 502 may be, among other things, transient or persistent storage. The application stored in memory 502 may include one or more modules (not shown), each of which may include a series of computer-executable instructions in a risk assessment device for emergency events. Still further, the processor 501 may be configured to communicate with the memory 502 to execute a series of computer-executable instructions in the memory 502 on a risk assessment device for an emergency event. The risk assessment device for emergency events may also include one or more power sources 503, one or more wired or wireless network interfaces 504, one or more input/output interfaces 505, one or more keyboards 506, and the like.

In one particular embodiment, an emergency event risk assessment device includes a memory, and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the emergency event risk assessment device, and the one or more programs configured for execution by the one or more processors include computer-executable instructions for:

acquiring an emergency event to be processed;

extracting an event subject of the emergency event from the emergency event; the event main body comprises a user account and target product information, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product;

inquiring corresponding risk assessment data in a main body portrait library of a target product according to the event main body; the risk assessment data includes: the data processing method comprises the following steps that first end internal data related to an event main body in a platform where a target product is located and first end external data related to the event main body outside the platform where the target product is located;

and determining to carry out risk evaluation on the emergency event according to the risk evaluation data to obtain a risk evaluation result.

An embodiment of a storage medium provided in this specification is as follows:

on the basis of the same technical concept, one or more embodiments of the present specification further provide a storage medium corresponding to the above-described emergency risk assessment method.

The storage medium provided in this embodiment is used to store computer-executable instructions, and when executed by a processor, the computer-executable instructions implement the following processes:

acquiring an emergency event to be processed;

It should be noted that the embodiment of the storage medium in this specification and the embodiment of the risk assessment method for an emergency event in this specification are based on the same inventive concept, and therefore, specific implementation of this embodiment may refer to implementation of the corresponding method described above, and repeated details are not described again.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

In the 30 s of the 20 th century, improvements in a technology could clearly be distinguished between improvements in hardware (e.g., improvements in circuit structures such as diodes, transistors, switches, etc.) and improvements in software (improvements in process flow). However, as technology advances, many of today's process flow improvements have been seen as direct improvements in hardware circuit architecture. Designers almost always obtain the corresponding hardware circuit structure by programming an improved method flow into the hardware circuit. Thus, it cannot be said that an improvement in the process flow cannot be realized by hardware physical modules. For example, a Programmable Logic Device (PLD), such as a Field Programmable Gate Array (FPGA), is an integrated circuit whose Logic functions are determined by programming the Device by a user. A digital system is "integrated" on a PLD by the designer's own programming without requiring the chip manufacturer to design and fabricate application-specific integrated circuit chips. Furthermore, nowadays, instead of manually making an Integrated Circuit chip, such Programming is often implemented by "logic compiler" software, which is similar to a software compiler used in program development and writing, but the original code before compiling is also written by a specific Programming Language, which is called Hardware Description Language (HDL), and HDL is not only one but many, such as abel (advanced Boolean Expression Language), ahdl (alternate Hardware Description Language), traffic, pl (core universal Programming Language), HDCal (jhdware Description Language), lang, Lola, HDL, laspam, hardward Description Language (vhr Description Language), vhal (Hardware Description Language), and vhigh-Language, which are currently used in most common. It will also be apparent to those skilled in the art that hardware circuitry that implements the logical method flows can be readily obtained by merely slightly programming the method flows into an integrated circuit using the hardware description languages described above.

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

The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functions of the units may be implemented in the same software and/or hardware or in multiple software and/or hardware when implementing the embodiments of the present description.

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

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

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

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

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

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

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

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

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

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The above description is only an example of this document and is not intended to limit this document. Various modifications and changes may occur to those skilled in the art from this document. Any modifications, equivalents, improvements, etc. which come within the spirit and principle of the disclosure are intended to be included within the scope of the claims of this document.

Claims

1. A method for risk assessment of an emergency event, comprising:

acquiring an emergency event to be processed;

extracting an event subject of the emergency event from the emergency event; the event main body comprises a user account and information of a target product, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product;

inquiring corresponding risk assessment data in a main body portrait library of the target product according to the event main body; the risk assessment data includes: the data in the first end, which is associated with the event main body, in the platform where the target product is located, and the data out of the first end, which is associated with the event main body, outside the platform where the target product is located;

and determining to carry out risk assessment on the emergency event according to the risk assessment data to obtain a risk assessment result.

2. The method of claim 1, after the obtaining of the emergency event to be processed and before the querying of the corresponding risk assessment data in the subject representation library of the target product according to the event subject, further comprising:

determining a corresponding risk event type in a plurality of preset risk event types according to the emergency event;

the inquiring of the corresponding risk assessment data in the subject portrait database of the target product according to the event subject comprises the following steps:

and querying the first internal data and the first external data in a main body portrait library of the target product according to the event main body and the risk event type.

3. The method of claim 1, said querying a subject representation library of said target product for corresponding risk assessment data according to said event subject, further comprising:

acquiring a risk event; the risk event comprises a public sentiment event and/or a complaint event;

extracting risk event subjects from the risk events;

obtaining complaint risk information, wind control risk information and technical risk information of the risk event subject as second end internal data associated with the risk event subject; acquiring public opinion risk information, stability maintenance risk information, supervision risk information, litigation risk information and resource loss risk information of the risk event subject, and taking the public opinion risk information, stability maintenance risk information, supervision risk information, litigation risk information and resource loss risk information as second external data associated with the risk event subject;

and writing the risk event main body, the second end internal data and the second end external data into the main body image library.

4. The method of claim 3, after writing the risk event body, the second in-terminal data, and the second out-terminal data to the body representation library, and before querying the body representation library of the target product for corresponding risk assessment data based on the event body, further comprising:

training a first evaluation submodel according to the second intra-terminal data to obtain the trained first evaluation submodel for performing intra-terminal risk evaluation on the emergency event; and training a second evaluation submodel according to the second external data to obtain the trained second evaluation submodel for performing external risk evaluation on the emergency event.

5. The method of claim 4, wherein determining a risk assessment for the emergency event based on the risk assessment data to obtain a risk assessment result comprises:

inputting the data in the first terminal into the trained first evaluation submodel, and outputting a first evaluation result; inputting the first external data into the trained second evaluation submodel, and inputting a second evaluation result;

and determining a risk evaluation result of the emergency event according to the first evaluation result and the second evaluation result.

6. The method of claim 1, after inputting the risk assessment data into a risk assessment model and outputting a risk assessment result for the emergency event, further comprising:

if the first risk evaluation result of the emergency event is low risk, determining the emergency event as an event to be patrolled and examined;

and carrying out routing inspection treatment on the event to be routed.

7. The method of claim 6, wherein routing inspection of the event to be routed comprises:

acquiring the latest risk evaluation data of the event to be patrolled;

inputting the latest risk evaluation data into the risk evaluation model, and outputting the inspection result of the event to be inspected;

judging whether the number of times that the inspection result of the event to be inspected is low risk is greater than or equal to a preset threshold value or not under the condition that the inspection result is low risk;

if yes, stopping the risk evaluation process of the event to be patrolled and examined;

and if not, returning to execute the acquisition of the latest risk assessment data of the event to be patrolled after a preset time period.

8. The method of claim 3, further comprising, prior to said querying, according to said event subject, corresponding risk assessment data in a subject representation library of said target product according to said event subject, said method further comprising:

writing basic information of a merchant into the main body image library;

and under the condition that the risk event subject is a merchant user, establishing an incidence relation between the risk event subject and the merchant basic information.

9. A risk assessment device for emergency events, comprising:

the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is configured to acquire an emergency event to be processed;

an extraction module configured to extract an event subject of the emergency event from the emergency event; the event main body comprises a user account and information of a target product, wherein the user account is logged in when a user who evaluates the target product in a preset type uses the target product;

the query module is configured to query corresponding risk assessment data in a subject portrait library of the target product according to the event subject; the risk assessment data includes: the data in the first end, which is associated with the event main body, in the platform where the target product is located, and the data out of the first end, which is associated with the event main body, outside the platform where the target product is located;

and the evaluation module is configured to determine to carry out risk evaluation on the emergency event according to the risk evaluation data to obtain a risk evaluation result.

10. A risk assessment device for emergency events, comprising:

a processor; and the number of the first and second groups,

a memory configured to store computer-executable instructions that, when executed, cause the processor to:

acquiring an emergency event to be processed;

11. A storage medium storing computer-executable instructions that when executed by a processor implement the following:

acquiring an emergency event to be processed;