CN111177517B - Method and device for determining severity of risk event - Google Patents
Method and device for determining severity of risk event Download PDFInfo
- Publication number
- CN111177517B CN111177517B CN201911291923.6A CN201911291923A CN111177517B CN 111177517 B CN111177517 B CN 111177517B CN 201911291923 A CN201911291923 A CN 201911291923A CN 111177517 B CN111177517 B CN 111177517B
- Authority
- CN
- China
- Prior art keywords
- score
- normalized
- documents
- document
- determining
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9532—Query formulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
Abstract
The embodiment of the invention discloses a method and a device for determining the severity of a risk event, wherein the method comprises the following steps: determining a first document containing the same risk event; acquiring any combination of one or more of the number of the determined first document, the publishing time interval length of the first document, the importance of a medium for publishing the first document, the number of comments of the first document and capital market change conditions; the severity of the risk event is determined based on any combination of one or more of the number of documents obtained, the length of the time interval during which the first document was published, the importance of the medium in which the first document was published, the number of reviews of the first document, and the capital market change. The embodiment of the invention improves the accuracy of the severity of the risk event.
Description
Technical Field
Embodiments of the present invention relate to, but not limited to, the field of data processing, and more particularly, to a method and apparatus for determining the severity of a risk event.
Background
Documents such as news reports and public articles include reports of events such as "security incidents", "loss", "penalty", and the like. The task of 'risk event discovery' can discover the events from documents such as news reports, the 'risk event discovery' has an important role in the application, and the 'severity' of the 'risk event' has an important significance for the application, such as 'slight loss' and 'severe loss', and '500 yuan of fine' and '1000 ten thousand yuan of fine' have a large difference in the processing and handling of the application. Therefore, determining the severity of a "risk event" is of great importance in the areas of finance and the like.
The current method for determining the severity of a risk event requires the prior collection of a keyword list, which includes: the adjective degree (such as "severe", "mild", etc.); assigning a severity, such as "Severe 2", "Mild 1", "major 3", "Extra-Large 4", etc. to each keyword in the keyword list; and extracting keywords in the keyword table from the document, and taking the severity degree corresponding to the extracted keywords as the severity degree of the 'risk event' corresponding to the document. The method for judging the severity of the risk event depends on a keyword table, and because the keyword table is difficult to cover all the keywords with different formal degrees, the same keyword is in different documents, the representing degrees of the same keyword in different contexts are different, and the severity of the document without the keyword cannot be judged, the method has low accuracy in judging the severity of the risk event.
Disclosure of Invention
The embodiment of the invention provides a method and a device for determining the severity of a risk event, which can improve the accuracy of the severity of the risk event.
The embodiment of the invention provides a method for determining the severity of a risk event, which comprises the following steps:
determining a first document containing the same risk event;
acquiring any combination of one or more of the determined number of the first document, the publishing time interval length of the first document, the importance of the media for publishing the first document, the number of comments of the first document and the capital market change condition;
the severity of the risk event is determined based on any combination of one or more of the number of documents obtained, the length of the time interval during which the first document was published, the importance of the medium in which the first document was published, the number of reviews of the first document, and the capital market change.
In this embodiment of the present invention, the acquiring the first document containing the same risk events includes:
acquiring at least one second document;
respectively determining a risk category and a risk subject in each second document;
and determining that the second document with the same risk category and the same risk subject is the first document with the same contained risk event.
In an embodiment of the present invention, said determining the severity of the risk event based on any combination of one or more of the obtained number of documents, length of time interval during which the first document was published, importance of the medium in which the first document was published, number of reviews of the first document, capital market changes comprises:
determining a score for the risk event based on any combination of one or more of the number of documents, the length of time interval, the importance of the media, the number of reviews, the capital market shift;
determining a severity of the risk event based on the score of the risk event.
In an embodiment of the present invention, said determining a score for said risk event from any combination of one or more of a number of documents, a length of said time interval, an importance of said media, a number of said comments, and a status of said capital market shift comprises:
determining any combination of one or more of a score for the number of documents, a score for the length of the time interval, a score for the importance of the media, a score for the number of reviews, a score for the capital market movement;
normalizing any combination of one or more of the number of documents score, the time interval length score, the media importance score, the number of reviews score, the capital market shift score;
determining the score for the risk event based on any combination of one or more of a score for a normalized number of documents, a score for a normalized length of time interval, a score for an importance of a normalized media, a score for a normalized number of reviews, a score for a normalized capital market shift condition.
In an embodiment of the present invention, the normalizing any combination of one or more of the score of the number of documents, the score of the length of the time interval, the score of the importance of the media, the score of the number of comments, and the score of the capital market volatility comprises:
according to the formula
Normalizing any combination of one or more of the number of documents, the length of time interval, the importance of the media, the number of reviews, and the capital market shift score;
wherein y is the score of the normalized number of documents, x is the score of the number of documents, x is min Is the minimum value of the scores of the number of documents, x max A maximum value of the score for the number of documents;
or y is the fraction of the normalized time interval length, x is the fraction of the time interval length, x min Is the minimum value of a fraction of the time interval length, x max Is the maximum value of the fraction of the time interval length;
or y is the score of the normalized importance of the media, x is the score of the importance of the media min Is the minimum value of the score of the importance of the media, x max A maximum value of a score that is an importance of the media;
or y is the score of the normalized number of comments, x is the score of the number of comments, x min Is the minimum value of the scores of the number of comments, x max A maximum value of the scores of the number of reviews;
alternatively, y is the normalized capital market shift score, x is the capital market shift score min Is the minimum value, x, of the score of the capital market movement max Is the maximum value of the score of the capital market movement.
In an embodiment of the present invention, said determining a score for said risk event from any combination of one or more of a score for normalized number of documents, a score for normalized length of time interval, a score for normalized importance of media, a score for normalized number of reviews, a score for normalized capital market shift, comprises:
determining the score for the risk event as a weighted average of any combination of one or more of the score for the normalized number of documents, the score for the normalized length of time interval, the score for the normalized importance of media, the score for the normalized number of reviews, the score for the normalized capital market shift condition.
In an embodiment of the present invention, said determining the severity of the risk event based on the score of the risk event comprises:
determining the grade corresponding to the risk event according to the score of the risk event; wherein the grade corresponding to the risk event is used for indicating the severity of the risk event.
An embodiment of the present invention provides an apparatus for determining severity of a risk event, including a processor and a computer-readable storage medium, where instructions are stored in the computer-readable storage medium, and when the instructions are executed by the processor, the steps of any one of the above methods for determining severity of a risk event are implemented.
Embodiments of the present invention provide a computer-readable storage medium having stored thereon a computer program, which when executed by a processor, performs the steps of any of the above-described methods for determining the severity of a risk event.
The embodiment of the invention comprises the following steps: determining a first document containing the same risk event; acquiring any combination of one or more of the determined number of the first document, the publishing time interval length of the first document, the importance of the media for publishing the first document, the number of comments of the first document and the capital market change condition; the severity of the risk event is determined based on any combination of one or more of the number of documents obtained, the length of the time interval during which the first document was published, the importance of the medium in which the first document was published, the number of reviews of the first document, and capital market changes. The severity of the risk event is determined according to any combination of one or more of the number of the documents, the time interval length of the first document publishing, the importance of the media publishing the first document, the number of comments of the first document and the capital market change condition, and because the factors are not influenced by subjective factors and do not depend on a keyword table, the accuracy of the severity of the risk event is improved.
Additional features and advantages of embodiments of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of embodiments of the invention. The objectives and other advantages of the embodiments of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
The accompanying drawings are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the examples of the invention serve to explain the principles of the embodiments of the invention and not to limit the embodiments of the invention.
FIG. 1 is a flow chart of a method for determining the severity of a risk event according to one embodiment of the present invention;
fig. 2 is a schematic structural component diagram of an apparatus for determining the severity of a risk event according to another embodiment of the present invention.
Detailed Description
Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that the embodiments and features of the embodiments of the present invention may be arbitrarily combined with each other without conflict.
The steps illustrated in the flow charts of the figures may be performed in a computer system such as a set of computer-executable instructions. Also, while a logical order is shown in the flow diagrams, in some cases, the steps shown or described may be performed in an order different than here.
Referring to fig. 1, one embodiment of the present invention provides a method for determining the severity of a risk event, comprising:
In one illustrative example, obtaining a first document containing the same risk events includes:
acquiring at least one second document;
respectively determining a risk category and a risk subject in each second document; and determining that the second document with the same risk category and the same risk subject is the first document with the same contained risk event.
In another exemplary instance, a separate determination of whether each second document contains a risk event may also be obtained.
In one illustrative example, a text classification technique may be used to determine whether the second document contains risk events and risk categories, and a named entity recognition technique may be used to extract risk subjects.
In one illustrative example, the number of documents refers to the number of all first documents.
In one illustrative example, the first document is published during a time interval of a length between a latest publication time and an earliest publication time among all of the first documents.
In one illustrative example, the importance of the media may be manually annotated.
In one illustrative example, the number of reviews refers to the sum of the number of reviews for all of the first documents.
In an exemplary instance, the capital market change may be a change in stock price, or the like.
In one illustrative example, determining the severity of the risk event based on any combination of one or more of the number of documents obtained, the length of the time interval during which the first document was published, the importance of the media in which the first document was published, the number of reviews of the first document, and capital market movement comprises:
determining a score for the risk event from any combination of one or more of the number of documents, the length of time interval, the importance of the media, the number of reviews, the capital market shift condition; determining a severity of the risk event based on the score of the risk event.
In one illustrative example, determining the score for the risk event from any combination of one or more of the number of documents, the length of the time interval, the importance of the media, the number of reviews, the capital market change condition comprises:
determining any combination of one or more of a score of the number of documents, a score of the length of the time interval, a score of the importance of the media, a score of the number of reviews, and a score of the capital market volatility;
normalizing any combination of one or more of the number of documents score, the time interval length score, the media importance score, the number of reviews score, the capital market shift score;
determining the score for the risk event based on any combination of one or more of a normalized score for number of documents, a normalized score for length of time interval, a normalized score for importance of media, a normalized score for number of reviews, a normalized score for capital market shift.
In one illustrative example, the score for the number of documents is the number of documents.
In an exemplary example, the fraction of the time interval length is the time interval length, and may be in units of days, time, or seconds, as long as the units are uniform.
In one illustrative example, the score of the importance of the media is the importance of the media.
In one illustrative example, the score for a capital market shift is a capital market shift, such as a change in stock price value.
In one illustrative example, normalizing any combination of one or more of the score for the number of documents, the score for the length of the time interval, the score for the importance of the media, the score for the number of reviews, the score for the capital market shift comprises:
according to the formula
Normalizing the score of the number of documents, the score of the length of the time interval, the score of the importance of the media, the score of the number of reviews, the score of the capital market volatility;
wherein y is the score of the normalized number of documents, x is the score of the number of documents, x min Is the minimum value of the scores of the number of documents, x max A maximum value of the score for the number of documents; for example, M first documents are collected, the M first documents are divided into N groups, the risk events included in the first documents of the same group are the same, each group corresponds to a score of the number of documents, the N groups correspond to scores of the number of N documents, and the minimum value of the scores of the number of N documents is the score of the number x min The maximum value is x max ；
Or y is the fraction of the normalized time interval length, x is the fraction of the time interval length, x min Is the minimum of a fraction of the length of the time interval, x max Is the maximum value of the fraction of the time interval length; wherein the maximum and minimum values of the time interval length may be based on the first of the plurality of risk eventsObtaining documents, for example, collecting M first documents, dividing the M first documents into N groups, wherein the risk events contained in the first documents of the same group are the same, each group corresponds to a score of a time interval length, the N groups correspond to scores of N time interval lengths, and the minimum value of the scores of the N time interval lengths is the x-mentioned above min The maximum value is x max ；
Or y is the score of the normalized importance of the media, x is the score of the importance of the media min Is the minimum value of the score of the importance of the media, x max A maximum value of a score that is an importance of the media; the maximum value and the minimum value of the importance of the media may be obtained based on the first documents of the multiple risk events, for example, M first documents are collected, the M first documents are divided into N groups, the risk events included in the first documents of the same group are the same, each group corresponds to a score of the importance of one media, the N groups correspond to scores of the importance of N media, and the minimum value of the scores of the importance of N media is the above x scores of the importance of the media min The maximum value is the above x max ；
Or y is the score of the normalized number of comments, x is the score of the number of comments, and x is min Is the minimum value of the scores of the number of comments, x max A maximum value of the scores of the number of reviews; the maximum value and the minimum value of the number of comments may be obtained based on the first documents of multiple risk events, for example, M first documents are collected, the M first documents are divided into N groups, the risk events contained in the first documents of the same group are the same, each group corresponds to a score of one number of comments, the N groups correspond to scores of N numbers of comments, and the minimum value of the scores of the N numbers of comments is the score of the x number min The maximum value is the above x max ；
Alternatively, y is the normalized capital market shift score, x is the normalized capital market shift score min Is the minimum value, x, of the score of the capital market movement max A maximum value that is a score of the capital market movement; wherein, the materialsThe maximum and minimum of the market movement can be obtained based on the first documents of multiple risk events, for example, collecting M first documents, dividing the M first documents into N groups, the risk events contained in the first documents of the same group are the same, each group corresponds to a score of a capital market movement, the N groups correspond to scores of N capital market movements, and the minimum of the scores of the N capital market movements is the above-mentioned x min The maximum value is x max 。
In one illustrative example, determining the score for the risk event from any combination of one or more of a score for a normalized number of documents, a score for a normalized length of time interval, a score for a normalized importance of media, a score for a normalized number of reviews, and a score for a normalized capital market shift condition comprises:
determining the score for the risk event as a weighted average of any combination of one or more of the score for the normalized number of documents, the score for the normalized length of time interval, the score for the normalized importance of media, the score for the normalized number of reviews, the score for the normalized capital market shift condition.
In one illustrative example, determining the severity of a risk event based on the score of the risk event comprises:
determining the grade corresponding to the risk event according to the score of the risk event; wherein the grade corresponding to the risk event is used for indicating the severity of the risk event.
The severity of the risk event is determined according to any combination of one or more of the number of the documents, the time interval length of the first document publishing, the importance of the media publishing the first document, the number of comments of the first document and the capital market change condition, and because the factors are not influenced by subjective factors and do not depend on a keyword table, the accuracy of the severity of the risk event is improved.
Another embodiment of the present invention is directed to an apparatus for determining the severity of a risk event, comprising a processor and a computer readable storage medium having instructions stored thereon which, when executed by the processor, perform the steps of any of the above methods for determining the severity of a risk event.
Another embodiment of the present invention proposes a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of any of the above-mentioned methods of determining the severity of a risk event.
Referring to fig. 2, another embodiment of the present invention provides an apparatus for determining the severity of a risk event, comprising:
a first determining module 201, configured to determine a first document containing the same risk event;
the obtaining module 202 is configured to obtain any combination of one or more of the determined number of the first document, a time interval length of publishing the first document, an importance of a medium publishing the first document, a number of comments of the first document, and a capital market change condition;
a second determining module 203 for determining the severity of the risk event based on any combination of one or more of the number of documents obtained, the length of the time interval during which the first document was published, the importance of the medium in which the first document was published, the number of reviews of the first document, and capital market changes.
In an exemplary embodiment, the first determining module 201 is specifically configured to:
acquiring at least one second document;
respectively determining a risk category and a risk subject in each second document; and determining that the second document with the same risk category and the same risk subject is the first document with the same contained risk event.
In another exemplary instance, the first determination module 201 may further obtain a separate determination of whether each of the second documents contains a risk event.
In an exemplary instance, the first determination module 201 may employ a text classification technique to determine whether the second document contains risk events and risk categories, and use a named entity recognition technique to extract risk subjects.
In one illustrative example, the number of documents refers to the number of all first documents.
In one illustrative example, the time interval during which the first documents are published is the time interval between the latest publication time and the earliest publication time of all the first documents.
In one illustrative example, the importance of the media may be manually annotated.
In one illustrative example, the number of reviews refers to the sum of the number of reviews for all of the first documents.
In an exemplary instance, the capital market change may be a change in stock price, or the like.
In an exemplary example, the second determining module 203 is specifically configured to:
determining a score for the risk event based on the number of documents, the length of the time interval, the importance of the media, the number of reviews, the capital market movement; determining the severity of the risk event from any combination of one or more of the scores for the risk event.
In an illustrative example, the second determining module 203 is specifically configured to determine the score of the risk event based on any combination of one or more of the number of documents, the length of the time interval, the importance of the media, the number of reviews, the capital market change condition in the following manner:
determining any combination of one or more of a score for the number of documents, a score for the length of the time interval, a score for the importance of the media, a score for the number of reviews, a score for the capital market movement;
normalizing any combination of one or more of the number of documents score, the time interval length score, the media importance score, the number of reviews score, the capital market shift score;
determining the score for the risk event based on any combination of one or more of a score for a normalized number of documents, a score for a normalized length of time interval, a score for an importance of a normalized media, a score for a normalized number of reviews, a score for a normalized capital market shift condition.
In one illustrative example, the score for the number of documents is the number of documents.
In an exemplary example, the fraction of the time interval length is the time interval length, and may be in units of days, time, or seconds, and the units are uniform.
In one illustrative example, the score of the importance of the media is the importance of the media.
In one illustrative example, the score for a capital market shift is a capital market shift, such as a change in stock price value.
In an illustrative example, the second determining module 203 is specifically configured to normalize any combination of one or more of the number of documents score, the time interval length score, the importance of the media score, the number of reviews score, the capital market shift score by:
according to the formula
Normalizing any combination of one or more of the number of documents score, the time interval length score, the media importance score, the number of reviews score, the capital market shift score;
wherein y is the score of the normalized number of documents, x is the score of the number of documents, x is min Is the minimum value of the scores of the number of documents, x max A maximum value of the score for the number of documents; wherein the maximum and minimum number of documents may be obtained based on a first document of the plurality of risk events, e.g., collecting M first documents, grouping the M first documents into N groups, as well asThe risk events contained in the first documents of one group are the same, each group corresponds to a score of the number of documents, N groups correspond to scores of the number of N documents, and the minimum value of the scores of the number of N documents is the x min The maximum value is x max ；
Or y is the fraction of the normalized time interval length, x is the fraction of the time interval length, x is min Is the minimum of a fraction of the length of the time interval, x max Is the maximum value of the fraction of the time interval length; for example, M first documents are collected, the M first documents are divided into N groups, the risk events included in the first documents of the same group are the same, each group corresponds to a score of one time interval length, the N groups correspond to scores of N time interval lengths, and the minimum value of the scores of the N time interval lengths is the x min The maximum value is x max ；
Or y is the score of the normalized importance of the media, x is the score of the importance of the media min Is the minimum value of the score of the importance of the media, x max A maximum value of a score that is an importance of the media; the maximum value and the minimum value of the importance of the media may be obtained based on the first documents of the multiple risk events, for example, M first documents are collected, the M first documents are divided into N groups, the risk events included in the first documents of the same group are the same, each group corresponds to a score of the importance of one media, the N groups correspond to scores of the importance of N media, and the minimum value of the scores of the importance of N media is the above x scores of the importance of the media min The maximum value is x max ；
Or y is the score of the normalized number of comments, x is the score of the number of comments, x min Is the minimum value of the scores of the number of comments, x max A maximum value of the scores of the number of reviews; wherein the maximum and minimum number of reviews may be obtained based on the first document of the plurality of risk events, e.g.,collecting M first documents, dividing the M first documents into N groups, wherein the risk events contained in the first documents of the same group are the same, each group corresponds to a score with one comment number, the N groups correspond to the scores with the N comment numbers, and the minimum value of the scores with the N comment numbers is the x-number-of-scores min The maximum value is x max ；
Alternatively, y is the normalized capital market shift score, x is the normalized capital market shift score min Is the minimum value, x, of the score of the capital market movement max A maximum value that is a score of the capital market movement; wherein the maximum and minimum of the capital market movement can be obtained based on the first documents of the plurality of risk events, for example, collecting M first documents, dividing the M first documents into N groups, the first documents of the same group containing the same risk event, each group corresponding to a score of the capital market movement, the N groups corresponding to scores of the N capital market movements, the minimum of the scores of the N capital market movements being the above x scores min The maximum value is x max 。
In an illustrative example, the second determination module 203 is specifically configured to determine the score of the risk event from any combination of one or more of a normalized score of number of documents, a normalized score of length of time interval, a normalized score of importance of media, a normalized score of number of reviews, a normalized score of capital market volatility, in the following manner:
determining the score for the risk event as a weighted average of the score for the normalized number of documents, the score for the normalized length of time interval, the score for the normalized importance of media, the score for the normalized number of reviews, the score for the normalized capital market shift.
In one illustrative example, the second determining module 203 is specifically configured to determine the severity of a risk event based on the score of the risk event in the following manner:
determining the grade corresponding to the risk event according to the score of the risk event; wherein the grade corresponding to the risk event is used for representing the severity of the risk event.
The severity of the risk event is determined according to any combination of one or more of the number of documents, the time interval length of the first document publishing, the importance of the media publishing the first document, the number of comments of the first document and the capital market change condition, and because the factors are not influenced by subjective factors and do not depend on a keyword table, the accuracy of the severity of the risk event is improved.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Although the embodiments of the present invention have been described above, the descriptions are only used for understanding the embodiments of the present invention, and are not intended to limit the embodiments of the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the embodiments of the invention as defined by the appended claims.
Claims (6)
1. A method of determining the severity of a risk event, comprising:
determining a first document containing the same risk events;
acquiring any combination of one or more of the determined number of the first document, the publishing time interval length of the first document, the importance of the media for publishing the first document, the number of comments of the first document and the capital market change condition;
determining the severity of the risk event based on any combination of one or more of the number of documents obtained, the length of the time interval during which the first document was published, the importance of the medium in which the first document was published, the number of reviews of the first document, and capital market changes, including:
determining a score for the risk event from any combination of one or more of the number of documents, the length of time interval, the importance of the media, the number of reviews, the capital market shift condition;
determining a severity of the risk event based on the score of the risk event;
wherein said determining a score for the risk event from any combination of one or more of the number of documents, the length of the time interval, the importance of the media, the number of reviews, the capital market shift condition comprises:
determining any combination of one or more of a score for the number of documents, a score for the length of the time interval, a score for the importance of the media, a score for the number of reviews, a score for the capital market movement;
normalizing any combination of one or more of the number of documents score, the time interval length score, the media importance score, the number of reviews score, the capital market shift score, including: according to the formula
Normalizing any combination of one or more of the number of documents score, the time interval length score, the media importance score, the number of reviews score, the capital market shift score; wherein y is the score of the normalized number of documents, x is the score of the number of documents, x min Is the minimum value of the scores of the number of documents, x max A maximum value of the score for the number of documents; or y is the fraction of the normalized time interval length, x is the fraction of the time interval length, x is min Is the minimum of a fraction of the length of the time interval, x max Is the maximum value of the fraction of the time interval length; or y is the score of the normalized importance of the media, x is the score of the importance of the media min Is the minimum value of the score of the importance of the media, x max A maximum value of a score that is an importance of the media; or y is the score of the normalized number of comments, x is the score of the number of comments, and x is min Is the minimum value of the scores of the number of comments, x max A maximum value of the scores of the number of reviews; alternatively, y is the normalized capital market shift score, x is the normalized capital market shift score min Is the minimum value, x, of the score of the capital market movement max Is the division of the capital market movementThe maximum value of the number;
determining the score for the risk event based on any combination of one or more of a score for a normalized number of documents, a score for a normalized length of time interval, a score for an importance of a normalized media, a score for a normalized number of reviews, a score for a normalized capital market shift condition.
2. The method of claim 1, wherein obtaining a first document containing the same risk events comprises:
acquiring at least one second document;
respectively determining a risk category and a risk subject in each second document;
and determining that the second document with the same risk category and the same risk subject is the first document with the same contained risk event.
3. The method of claim 1, wherein determining the score for the risk event from any combination of one or more of a normalized score for number of documents, a normalized score for length of time interval, a normalized score for importance of media, a normalized score for number of reviews, a normalized score for capital market volatility, comprises:
determining the score for the risk event as a weighted average of any combination of one or more of the score for the normalized number of documents, the score for the normalized length of time interval, the score for the normalized importance of media, the score for the normalized number of reviews, the score for the normalized capital market shift condition.
4. The method of claim 1, wherein determining the severity of a risk event based on the score of the risk event comprises:
determining a grade corresponding to the risk event according to the score of the risk event; wherein the grade corresponding to the risk event is used for representing the severity of the risk event.
5. An apparatus for determining the severity of a risk event comprising a processor and a computer readable storage medium having instructions stored thereon, wherein the instructions, when executed by the processor, carry out the steps of the method for determining the severity of a risk event according to any one of claims 1 to 4.
6. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of determining the severity of a risk event according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911291923.6A CN111177517B (en) | 2019-12-16 | 2019-12-16 | Method and device for determining severity of risk event |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911291923.6A CN111177517B (en) | 2019-12-16 | 2019-12-16 | Method and device for determining severity of risk event |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111177517A CN111177517A (en) | 2020-05-19 |
| CN111177517B true CN111177517B (en) | 2023-04-07 |
Family
ID=70654001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911291923.6A Active CN111177517B (en) | 2019-12-16 | 2019-12-16 | Method and device for determining severity of risk event |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111177517B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751458A (en) * | 2009-12-31 | 2010-06-23 | 暨南大学 | Network public sentiment monitoring system and method |
| CN107679985A (en) * | 2017-09-12 | 2018-02-09 | 阿里巴巴集团控股有限公司 | Feature of risk screening, description message forming method, device and electronic equipment |
| CN108733782A (en) * | 2018-05-08 | 2018-11-02 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of assets trend analysis |
| CN110163407A (en) * | 2019-04-02 | 2019-08-23 | 阿里巴巴集团控股有限公司 | The optimization method and device of quantization strategy |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9336503B2 (en) * | 2013-07-22 | 2016-05-10 | Wal-Mart Stores, Inc. | Value at risk insights engine |
-
2019
- 2019-12-16 CN CN201911291923.6A patent/CN111177517B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751458A (en) * | 2009-12-31 | 2010-06-23 | 暨南大学 | Network public sentiment monitoring system and method |
| CN107679985A (en) * | 2017-09-12 | 2018-02-09 | 阿里巴巴集团控股有限公司 | Feature of risk screening, description message forming method, device and electronic equipment |
| CN108733782A (en) * | 2018-05-08 | 2018-11-02 | 平安科技（深圳）有限公司 | Method, apparatus, computer equipment and the storage medium of assets trend analysis |
| CN110163407A (en) * | 2019-04-02 | 2019-08-23 | 阿里巴巴集团控股有限公司 | The optimization method and device of quantization strategy |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111177517A (en) | 2020-05-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271512B (en) | Emotion analysis method, device and storage medium for public opinion comment information | |
| EP2028806B1 (en) | Bayesian surety check to reduce false positives in filtering of content in non-trained languages | |
| US20090276378A1 (en) | System and Method for Identifying Document Structure and Associated Metainformation and Facilitating Appropriate Processing | |
| CN107291949B (en) | Information searching method and device | |
| CN110084289B (en) | Image annotation method and device, electronic equipment and storage medium | |
| CN110110325B (en) | Repeated case searching method and device and computer readable storage medium | |
| EP3608799A1 (en) | Search method and apparatus, and non-temporary computer-readable storage medium | |
| CN105787133A (en) | Method and device for filtering advertisement information | |
| CN111177373A (en) | Method and device for obtaining training data and method and device for training model | |
| CN111209827A (en) | OCR (optical character recognition) bill problem recognition method and system based on feature detection | |
| CN106878242B (en) | Method and device for determining user identity category | |
| CN115171125A (en) | Data anomaly detection method | |
| US9020212B2 (en) | Automatically determining a name of a person appearing in an image | |
| CN108462624A (en) | A kind of recognition methods of spam, device and electronic equipment | |
| CN111177517B (en) | Method and device for determining severity of risk event | |
| CN113568934A (en) | Data query method and device, electronic equipment and storage medium | |
| CN113064930B (en) | Cold and hot data identification method and device of data warehouse and electronic equipment | |
| CN114581934A (en) | Test paper image processing method, device and equipment | |
| CN108268659B (en) | Method and system for classifying same news information | |
| CN112699873A (en) | Invoice data acquisition system and method based on OCR recognition | |
| CN111539576A (en) | Risk identification model optimization method and device | |
| CN110728240A (en) | Method and device for automatically identifying title of electronic file | |
| CN111177409A (en) | Method and device for realizing data processing, computer storage medium and terminal | |
| EP2857989A1 (en) | Image search system and image search method | |
| CN111428497A (en) | Method, device and equipment for automatically extracting financing information |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |