CN111353728A - Risk analysis method and system - Google Patents
Risk analysis method and system Download PDFInfo
- Publication number
- CN111353728A CN111353728A CN202010373414.4A CN202010373414A CN111353728A CN 111353728 A CN111353728 A CN 111353728A CN 202010373414 A CN202010373414 A CN 202010373414A CN 111353728 A CN111353728 A CN 111353728A
- Authority
- CN
- China
- Prior art keywords
- risk
- entity
- target entity
- feedback
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
An embodiment of the present specification provides a risk analysis method, including: acquiring at least one target entity; obtaining a risk evaluation result of at least one risk direction of the target entity according to the target entity and at least one associated entity of the target entity; generating a risk link for the target entity according to at least one feedback of a risk assessment result for at least one risk direction of the target entity, the risk link comprising at least: the target entity, and the risk assessment result of the at least one feedback concerned risk direction and/or the risk assessment result approved by the at least one feedback; and the risk link of the target entity is used for providing a risk evaluation result of the target entity on line.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a risk analysis method and system.
Background
With the development of modern technology, security and risk prevention in various fields are of great importance. Risk analysis is an important ring of risk prevention, for example, by performing risk analysis on a business, a merchant, a business, a project, and the like, and preparing risk prevention in advance based on the analysis result.
The current risk analysis methods are various, and can adopt a manual data analysis method or an automatic data processing risk analysis method. The accuracy of the risk analysis results directly affects the prevention effect. Therefore, there is a need for an automatic risk analysis method and system, which can achieve more comprehensive, accurate and efficient analysis effect for determining an object to be analyzed.
Disclosure of Invention
One aspect of the present description provides a method of risk analysis. The method comprises the following steps: acquiring at least one target entity; obtaining a risk evaluation result of at least one risk direction of the target entity according to the target entity and at least one associated entity of the target entity; generating a risk link for the target entity according to at least one feedback of a risk assessment result for at least one risk direction of the target entity, the risk link comprising at least: the target entity, and the risk assessment result of the at least one feedback concerned risk direction and/or the risk assessment result approved by the at least one feedback; and the risk link of the target entity is used for providing a risk evaluation result of the target entity on line.
Another aspect of the present description provides a risk analysis system. The system comprises: an acquisition module for acquiring at least one target entity; the risk evaluation module is used for obtaining a risk evaluation result of at least one risk direction of the target entity according to the target entity and at least one associated entity of the target entity; the link generation module is used for generating a risk link of the target entity according to at least one feedback of a risk evaluation result of at least one risk direction of the target entity, wherein the risk link at least comprises the target entity and the risk evaluation result of the risk direction concerned by the at least one feedback and/or the risk evaluation result approved by the at least one feedback; and the risk link of the target entity is used for providing a risk evaluation result of the target entity on line.
Another aspect of the present specification provides a risk analysis device comprising at least one storage medium and at least one processor, the at least one storage medium storing computer instructions; the at least one processor is configured to execute the computer instructions to implement a risk analysis method.
Drawings
The present description will be further explained by way of exemplary embodiments, which will be described in detail by way of the accompanying drawings. These embodiments are not intended to be limiting, and in these embodiments like numerals are used to indicate like structures, wherein:
FIG. 1 is a schematic diagram of an application scenario of a risk analysis system according to some embodiments of the present description;
FIG. 2 is a block diagram of a risk analysis system according to some embodiments of the present description;
FIG. 3 is an exemplary flow diagram of a risk analysis method according to some embodiments of the present description;
FIG. 4 is an exemplary flow diagram illustrating a method of determining at least one associated entity of a target entity according to some embodiments of the present description;
FIG. 5 is a schematic diagram of a risk assessment result of at least one risk direction of a target entity obtained by a risk discrimination model according to some embodiments of the present description;
FIG. 6 is a schematic diagram of a heterogeneous knowledge graph in accordance with some embodiments of the present description.
Detailed Description
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings used in the description of the embodiments will be briefly described below. It is obvious that the drawings in the following description are only examples or embodiments of the present description, and that for a person skilled in the art, the present description can also be applied to other similar scenarios on the basis of these drawings without inventive effort. Unless otherwise apparent from the context, or otherwise indicated, like reference numbers in the figures refer to the same structure or operation.
It should be understood that "system", "device", "unit" and/or "module" as used in this specification is a method for distinguishing different components, elements, parts or assemblies at different levels. However, other words may be substituted by other expressions if they accomplish the same purpose.
As used in this specification and the appended claims, the terms "a," "an," "the," and/or "the" are not intended to be inclusive in the singular, but rather are intended to be inclusive in the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that steps and elements are included which are explicitly identified, that the steps and elements do not form an exclusive list, and that a method or apparatus may include other steps or elements.
Flow charts are used in this description to illustrate operations performed by a system according to embodiments of the present description. It should be understood that the preceding or following operations are not necessarily performed in the exact order in which they are performed. Rather, the various steps may be processed in reverse order or simultaneously. Meanwhile, other operations may be added to the processes, or a certain step or several steps of operations may be removed from the processes.
FIG. 1 is a schematic diagram of an application scenario of an exemplary risk analysis system, shown in accordance with some embodiments of the present description. As shown in fig. 1, a user terminal 110, a processing device 120, a network 130, and a storage device 140 may be included in an application scenario of the risk analysis system.
The network 130 may connect the various components of the system and/or connect the system with external resource components. The network 130 allows communication between the various components and with other components outside the system to facilitate the exchange of data and/or information. In some embodiments, the network 130 may be any one or more of a wired network or a wireless network. For example, network 130 may include a cable network, a fiber optic network, a telecommunications network, the internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a bluetooth network, a ZigBee network (ZigBee), Near Field Communication (NFC), an in-device bus, an in-device line, a cable connection, and the like, or any combination thereof. The network connection between the parts can be in one way or in multiple ways. In some embodiments, the network may be a point-to-point, shared, centralized, etc. variety of topologies or a combination of topologies. In some embodiments, the network 130 may include one or more network access points. For example, the network 130 may include wired or wireless network access points, such as base stations and/or network switching points 130-1, 130-2, …, through which one or more components of the access point system 100 may connect to the network 130 to exchange data and/or information.
The data refers to a digital representation of information and may include various types such as binary data, text data, image data, video data, and the like. Instructions refer to programs that may control a device or apparatus to perform a particular function.
In some embodiments, user terminal 110, as well as other possible system components, may include storage device 140.
In some embodiments, the user terminal 110, as well as other possible system components, may include a processing device 120.
In some embodiments, the processing device 120 may perform analysis to determine at least one associated entity of the target entity, may perform processing analysis on the target entity and the associated entity related data to obtain a risk assessment result of at least one risk direction of the target entity, and may generate a risk link of the target entity according to feedback of the risk assessment result of the risk direction of the target entity. The storage device 140 may store data analysis information obtained by the processing device 120, such as risk characteristics of the target entity and at least one associated entity of the target entity, risk assessment results of at least one risk direction of the target entity, and a risk link of the target entity. Processing device 120, storage device 140, and user terminal 110 may communicate and transfer data via network 130. The user terminal 110 may be configured to input an entity to be risk analyzed and feedback of risk assessment results of a target entity in various risk directions, and may transmit the input information to the storage device 140 and/or the processing device 120 through a network and receive feedback information of the storage device 140 and/or the processing device 120. The above information transfer relationship between the devices is merely an example, and the present application is not limited thereto.
The risk analysis system may be used for risk analysis of an enterprise. In some embodiments, each designated enterprise may be analyzed in the processing device 120, the related enterprise and natural person may be found through a natural person, an enterprise heterogeneous knowledge graph, and the like, and the analysis may be performed according to the related data of the enterprise, the related enterprise and natural person, such as risk characteristics, to obtain a risk assessment result of at least one risk direction of each enterprise, further obtain a risk link of each enterprise, and store the analysis data obtained by the processing device 120 in the storage device 140, and use the analysis data for a platform of risk query. The query platform is connected to the user terminal through the network 130, and the user can input an enterprise to be risk analyzed by using the user terminal 110, and the platform can receive a target enterprise to be analyzed, find a risk link of the target enterprise in the storage device, and correspondingly provide a risk evaluation result of at least one risk direction in the risk link to the user. The user can realize more efficient, comprehensive and effective risk analysis through the risk analysis system in the specification.
FIG. 2 is a block diagram of an exemplary risk analysis system shown in accordance with some embodiments of the present description. As shown in fig. 2, the risk analysis system may include an acquisition module 210, a risk assessment module 220, a link generation module 230, and an associated entity determination module 240.
The obtaining module 210 may be configured to obtain at least one target entity.
The risk assessment module 220 may be configured to obtain a risk assessment result of at least one risk direction of the target entity according to the target entity and at least one associated entity of the target entity.
In some embodiments, the risk assessment module 220 may be configured to determine a risk assessment result of at least one risk direction of the target entity based on a risk discrimination model; wherein inputting the risk discrimination model at least comprises: a risk profile of the target entity and a risk profile of the at least one associated entity.
In some embodiments, the risk discrimination model may be a neural network model or at least one logistic regression model. The obtaining, by the risk discrimination model, a risk assessment result of at least one risk direction of the target entity according to the risk characteristics of the target entity and the risk characteristics of the at least one associated entity includes: and inputting the risk characteristics of the target entity and the risk characteristics of the associated entity into the neural network model to obtain a risk evaluation result of at least one risk direction of the target entity. And each of the at least one logistic regression model corresponds to each risk direction, and the risk characteristics of the target entity and the risk characteristics of the associated entity are input into the logistic regression model corresponding to the risk direction to obtain a risk evaluation result of the risk direction.
In some embodiments, the risk assessment results may include risk scoring results and/or risk text results generated from the risk scoring results, the risk characteristics of the target entity, and the risk characteristics of the associated entity.
The link generating module 230 may be configured to generate a risk link for the target entity according to at least one feedback of a risk assessment result for at least one risk direction of the target entity, where the risk link at least includes: the target entity, and the risk assessment result of the at least one feedback concerned risk direction and/or the risk assessment result approved by the at least one feedback; and the risk link of the target entity is used for providing a risk evaluation result of the target entity on line.
In some embodiments, the link generation module 230 may be further configured to obtain text information of the at least one feedback, identify the text of the at least one feedback through an identification model, and determine a risk assessment result of a risk direction concerned by the at least one feedback and/or a risk assessment result of a risk direction approved by the at least one feedback.
In some embodiments, the risk analysis system further includes a correlation entity determination module 240. The associated entity determining module 240 may be configured to obtain at least one other entity, where the other entity is associated with the target entity through one or more layers of relationships; determining an association weight between the target entity and each of the at least one other entity based on the relationship information for the one or more levels of relationships; and taking the other entities with the association weights meeting preset conditions as at least one associated entity of the target entity. In some embodiments, the association weight may be determined based on relationship information of the issuing entity and the receiving entity for each of the one or more levels of relationships and relationship information of the issuing entity and other directly related entities.
It should be understood that the system and its modules shown in FIG. 2 may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may be stored in a memory for execution by a suitable instruction execution system, such as a microprocessor or specially designed hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such code being provided, for example, on a carrier medium such as a diskette, CD-or DVD-ROM, a programmable memory such as read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system and its modules of the present application may be implemented not only by hardware circuits such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also by software executed by various types of processors, for example, or by a combination of the above hardware circuits and software (e.g., firmware).
It should be noted that the above description of the system 200 and its modules is merely for convenience of description and should not limit the present disclosure to the illustrated embodiments. It will be appreciated by those skilled in the art that, given the teachings of the present system, any combination of modules or sub-system configurations may be used to connect to other modules without departing from such teachings. For example, the acquiring module 210, the risk evaluating module 220, the link generating module 230, and the associated entity determining module 240 disclosed in fig. 2 may be different modules in a system, or may be a module that implements the functions of two or more modules described above. For example, the risk assessment module 220 and the link generation module 230 may be two modules, or one module may have both the functions of risk assessment and link generation. For example, each module may share one memory module, and each module may have its own memory module. Such variations are within the scope of the present application.
Fig. 3 is an exemplary flowchart illustrating a method of risk analysis according to some embodiments of the present description, the method 300 may be performed by the risk analysis system 200. As shown in fig. 3, the risk analysis method 300 may include:
at step 310, at least one target entity is obtained. In particular, this step 310 may be performed by the obtaining module 210.
An entity may refer to an abstraction of a concrete business entity in the real world, such as a business, a natural person, a business, etc. Target entity refers to a specified entity or entities. For example, in risk analysis of a business, the target entity refers to one or more businesses to be risk analyzed.
The method for acquiring the target entity may be a plurality of methods, such as inputting by a user, or selecting from existing entity data, and the description is not limited.
The associated entity may refer to other entities having a preset requirement on the degree of relationship with the target entity, and the associated entity of each target entity may be one or more. The relationship may be any describable relationship, such as a profit relationship, an attribution relationship, a transfer relationship, a business relationship, and the like. For example, the target entity is a business, and the association relationship may refer to a relationship between a business's shareholder, physical controller, board of directors, supervisor, advanced management and the business, and other relationships that may have a transfer of interest with the business.
The associated entity may or may not be of the same type as the target entity. For example, the target entity is a business, and the associated entity or other entities are natural persons or/and businesses.
The relationship degree can be a relationship importance degree, a relationship complexity degree or a relationship intimacy degree, etc. The preset requirement may be that the score of one or more degrees of relationship is greater than a preset threshold, etc.
In some embodiments, the association entity of the target entity may be further determined from other entities based on the degree of relationship between the other entities and the target entity in the relationship representation (e.g., heterogeneous knowledge graph, etc.) of the entity and the entity. For the relationship representation between the entities and the specific method for determining the associated entities, refer to fig. 4 and the related description thereof, which are not repeated herein.
The risk direction may refer to a relevant area where the target entity may be at risk. For example, the target entity is an enterprise, and the risk direction thereof may include natural risks (such as flood, storm, etc.), economic risks (such as financing risk, debt risk, etc.), technical risks (such as technical change, technical use, etc. constituting risks to the enterprise), or legal risks (such as intellectual property legal risk, contract legal risk, human resource management legal risk, etc.).
The risk assessment result of the risk direction refers to the risk condition of the target entity in a certain risk direction. Specifically, the evaluation result of the risk direction may be whether a risk exists in the risk direction, or details of the risk existing in the risk direction, such as the degree of the risk, the specific content of the risk, and the like.
In some embodiments, the relevant data of the target entity and its associated entities may be analyzed to determine the risk assessment results of the target entity in different risk directions. The relevant data of the target entity and its associated entities may include: a risk profile of the target entity and a risk profile of the associated entity.
The risk characteristics refer to risk situations of the entity in various risk directions, for example, the entity is a business, and the risk characteristics of the business on the financing risk include: risk condition of financing amount of the enterprise, risk condition of investment company, risk condition of financing time, etc. The risk features of the entity may be obtained by extracting features of data of the entity-related information, for example, the risk features of the enterprise may be obtained by extracting features based on text data of related litigation conditions, loan conditions, and the like of the enterprise. The feature extraction method may include: principal component analysis, machine learning, and the like. For example, a principal component analysis method may be adopted to extract text features of various relevant information data of an entity to obtain risk features, where the risk features include risk situations in various risk directions.
In some embodiments, modeling or analyzing the relevant data (e.g., risk characteristics) of the target entity and the at least one associated entity of the target entity using various data analysis algorithms, such as regression analysis, discriminant analysis, and the like, may be performed to obtain a risk assessment result of the target entity in at least one risk direction.
In some embodiments, the risk assessment result of at least one risk direction of the target entity may be determined by analyzing and processing the relevant data of the target entity and the associated entity based on a risk discrimination model. Specifically, the risk characteristics of the target entity and the risk characteristics of at least one associated entity are input into a risk discrimination model, and the risk discrimination model outputs a risk evaluation result of the target entity in at least one risk direction. The risk discrimination model may employ a neural network model or at least one logistic regression model. For details of the risk discrimination model, reference may be made to fig. 5 and its related description, which are not repeated herein.
In some embodiments, the risk assessment results may include risk scoring results and/or risk text results. The risk scoring result may be a score of a risk level condition, for example, the target entity is enterprise a, and the risk scoring result of enterprise a on the financing risk is 80 points, which indicates that the risk level of the financing risk is high. The risk text result refers to a result expressed by a text (such as a natural language, a message, or other machine language) for the risk condition, for example, the target entity is enterprise a, and the risk text result of enterprise a at the financing risk is: the message that the enterprise a risk score result is 80 points represents, or the natural language representation of the content of the specific risk condition of the enterprise a on the financing risk may be "enterprise a has a high risk on the financing risk, which may cause a risk that the project-related participating party cannot fulfill the obligation and obligation".
In some embodiments, the risk text result may be generated from the risk scoring result, the risk characteristics of the target entity, and the risk characteristics of the associated entity. In particular, the risk text results may be generated by a neural network model or various machine language generators.
In some embodiments, the neural network model may employ a neural network model commonly used in natural language processing such as RNN, CNN, transform, and the like. And inputting the risk scoring result, the risk characteristics of the target entity and the risk characteristics of the associated entity into the neural network model, and outputting to obtain a risk text result expressed by the natural language. Taking a Transformer as an example, the model is obtained by training based on a plurality of groups of training samples, and each group of training samples comprises: the risk scoring result of the sample entity, the risk characteristics of the sample entity and the risk characteristics of the associated entity of the sample entity, wherein the label of each group of samples is the risk text result of the sample entity.
In some embodiments, the machine language generator may employ a language conversion tool such as a message generation module, a binary language converter, and the like, and input the risk scoring result, the risk feature of the target entity, and the risk feature of the associated entity into the machine language generator, and output a risk text result represented by the machine language.
As can be seen from the foregoing, the risk text result may represent the risk score, the specific risk condition content of the target entity in each risk direction, and the specific risk condition content of the associated entity of the target entity in each risk direction.
In some embodiments, corresponding risk text results may also be set for different risk assessment results in advance, and after determining the risk assessment results, the corresponding risk text results may be directly obtained.
Feedback may refer to actions taken by a user who received or viewed the risk assessment result on the risk assessment result. The content of the feedback may include whether the risk assessment result is accurate or inaccurate, whether the risk assessment result is good or bad, or whether the risk direction is a direction of concern. The feedback mode can be any mode capable of realizing evaluation, such as voice communication, text description or clicking preset options.
According to the feedback content, whether the user approves a certain risk evaluation result or whether the user pays attention to a certain risk direction can be determined. For more details on the risk assessment result or the approved risk assessment result for determining the concerned risk assessment direction based on the feedback, refer to step 332, step 334 and the related description thereof, which are not repeated herein.
In some embodiments, the feedback of the risk assessment result of at least one risk direction of the target entity may be obtained by reading the feedback of the risk assessment result on line from the user, or by reading the feedback of the risk assessment result from the user in a historical database.
The risk link may be used in a platform, such as an enterprise risk query platform, that provides the target entity's risk assessment results in at least one risk direction online. The link comprises a target entity and a risk assessment result of at least one risk direction of the target entity, wherein the risk assessment result in the link is determined based on the feedback. Specifically, based on the feedback, the risk assessment results of the multiple risk directions of the target entity determined in step 320 are screened to screen out the risk assessment results that do not meet the user requirements. In some embodiments, in order to meet the user requirements, the risk assessment results of the risk directions concerned and/or the risk assessment results of the approved risk directions are fed back and retained in the risk link, so that more effective and accurate assessment results are provided for the query user of the platform.
The number of users who feedback can be multiple, and it can be understood that the number of feedback results can also be multiple. Furthermore, a plurality of feedbacks may be statistically processed, and the risk assessment result of the risk direction in which the concerned or/and approved feedback quantity satisfies the preset condition is retained in the risk link. The preset condition may be the feedback number Top N (N ═ 1, 2, 3 …), or may be greater than the preset number.
For example, for enterprise a, based on step 320, the risk assessment result of risk direction 1, the risk assessment result of risk direction 2, the risk assessment result of risk direction 3, and the risk assessment result of risk direction 4 are determined, and these results are sent to 100 users, where the number of feedback approved by risk direction 1 is 20, the number of feedback of interest is 40, the number of feedback approved by risk direction 2 is 30, the number of feedback of interest is 20, the number of feedback approved by risk direction 3 is 40, the number of feedback of interest is 15, the number of feedback approved by risk direction 4 is 10, the number of feedback of interest is 25, and the preset condition is Top1, then risk direction 1 is the risk direction of interest, and the risk assessment result of risk direction 3 is an approved result, and then the risk link of enterprise a is: enterprise a, risk assessment results for risk direction 1, and risk assessment results for risk direction 3. By the method, risk results can be provided for the query users on the premise that most of the query users are satisfied.
Corresponding risk links exist in different target entities, for example, enterprise a corresponds to risk link 1, enterprise B corresponds to risk link 2, and when the risk of enterprise a is queried on an enterprise risk query platform, the risk direction in risk link 1 and the corresponding risk assessment result are provided to a querying user.
In some embodiments, generating a risk link for the target entity based on at least one feedback of the risk assessment result for at least one risk direction of the target entity may comprise:
The text information of the feedback refers to a text representation of the feedback content. It is understood that the text information may be text content directly input by the user for feedback; or text content recognized based on user voice information; the text content can be generated after the preset option is selected; the text related to the user feedback content may also be determined in other manners, and this embodiment is not limited.
And 334, identifying the text information of the at least one feedback through an identification model, and determining a risk evaluation result of the risk direction concerned by the at least one feedback and/or a risk evaluation result approved by the at least one feedback. In particular, this step 334 may be performed by the link generation module 230.
The recognition model is a model for performing semantic recognition on the text information and obtaining the text category. Specifically, the input to the recognition model may be: the output of the text information fed back by the risk assessment result of a certain risk direction may be: feedback categories, such as "feedback concern" representing a risk assessment result concerning the risk wind direction and/or "feedback approval" representing approval of the risk assessment result.
In some embodiments, the recognition model may be a neural network model, such as Bi-LSTM, BERT, textCNN, or other functionally similar text classification neural network, or a model composed of a text coding model and a classification model that can semantically recognize and classify text information. The classification model can adopt a logistic regression model, a classification and regression tree, a support vector machine or other classification models, and the text coding model can adopt BilSTM, Transformer or other text coding models. Taking an example that the text coding model and the classification model form the recognition model, the text coding model is used for coding input text information to generate a vector of the text, and the classification model is used for classifying the input text vector to obtain a feedback type of the input text vector.
After the feedback type of the fed back text information is obtained in the above manner, the type of the risk assessment result of the fed back risk direction can be determined. Specifically, if the feedback category belongs to "feedback attention", determining the risk evaluation result of the corresponding risk direction as the risk evaluation result of the feedback attention risk direction; if "feedback approval," the corresponding risk assessment result is determined as the feedback approved risk assessment result.
The foregoing steps 332 and 334 are only method steps for generating a risk link for a target entity in one embodiment, so steps 332 and 334 are optional steps to perform.
The above embodiment realizes: (1) risk identification is not limited to the target entity, other entities (enterprises, natural people and the like) closely related to the target entity are covered, and identified risks are more comprehensive and accurate; (2) by feeding back the precipitation risk link and applying the precipitation risk link to online query, a risk evaluation result of a risk direction approved or concerned by a user can be provided for the user by combining with the user demand, and the user experience is improved.
Fig. 4 is an exemplary flow diagram of a method of determining at least one associated entity of a target entity according to some embodiments of the present description as shown in fig. 4, the method 400 may include:
step 410, at least one other entity is obtained, and the other entity is associated with the target entity through one or more layers of relationships. In particular, this step 410 may be performed by the associated entity determining module 240.
In some embodiments, other entities may be associated with the target entity through one or more layers of relationships. See step 320 for an introduction of the relationship.
A level of relationship means that the target entity is directly related to the other entities. A multi-level relationship means that the target entity is not directly related to the other entities, but rather an indirect relationship is created through one or more other entities. For example, the target entity is enterprise a, enterprise B has a business relationship with enterprise a, enterprise C has a business relationship with enterprise B, enterprise B is directly associated with enterprise a through a one-tier relationship, and enterprise C is associated with enterprise a through a 2-tier (i.e., multi-tier) relationship.
There may be a variety of entity-to-entity relational representations. In some embodiments, the relationships between entities may be represented by heterogeneous knowledge graphs, which may refer to representations of relationships between different types of entities and entities, where relationships are represented by edges. As shown in FIG. 6, two different types of entities (e.g., businesses and natural persons) may be represented by U and I, respectively, where there is an investment relationship between U1 and I3, e.g., U1 is an investor in U3; there is a board of directors relationship between U2 and I2, e.g., I2 is the board of U2; there is a corporate relationship between U3 and I1, e.g., I1 is the corporate of U3; there is a couple relationship between I3 and I2. In the heterogeneous knowledge graph, a layer of relationship refers to connection between entities through edges, such as U1 and U3, I2 and U2, I1 and U3, I2 and I3, and the like. In the heterogeneous knowledge graph, the multi-layer relationship means that entities are indirectly connected with each other through multiple edges, for example, no edge exists between I1 and U1, but the intermediate entities U3 are related, and I1 and U1 are indirectly connected through 2 edges, in other words, a 2-layer relationship exists between I1 and U1; u2 is similar to the case of I3 and will not be described in detail.
In some embodiments, the relationship between the entities may also be represented by other manners, such as a mapping table, and the like, which is not limited in this embodiment.
In some embodiments, other entities of the target entity and relationship information between the target entity and other entities, and specific contents of the relationship information, may be obtained from a heterogeneous knowledge map, a mapping table, or other form of relationship representation in step 420.
The processing device may obtain the relationships between the entities in various common ways, such as reading the heterogeneous knowledge graph directly from the storage identification, and further obtaining other entities having one or more layers of relationships with the target entity based on the information. The processing device may define the number of layers of the multi-layer relationship or otherwise define the scope of the other entity being acquired.
Step 420, determining an association weight between the target entity and each of the at least one other entity based on the relationship information of the one or more layers of relationships. In particular, this step 420 may be performed by the associated entity determining module 240.
The relationship information may be any information of the relationship between the entities, including the relationship type, etc. The relationship information may also include other information, such as the accuracy of the relationship, the relationship value, etc., and the embodiment is not limited. The relationship value may be a measure of the importance of the relationship or the intimacy of the relationship, and may be customized according to the needs of the service. For example, the association value of the shareholder relationship is 2, and the association value of the corporate relationship is 5. For another example, if the shareholder relationship is 20%, the correlation value is 0.4(0.2 × 2).
The processing device may determine the associated entity of the target entity from the other entities based on the degree of association of the target entity with the other entities, as depicted in step 320. In some embodiments, the magnitude of the degree of relationship may be measured by the association weight.
In some embodiments, the processing device may determine the association weights between the target entities and other entities based on the relationship information of the issuing entity and the receiving entity for each layer of relationship between the target entities and other entities, and the relationship information of the issuing entity and other directly related entities. Specifically, first, the association weight of each layer of relationship may be determined based on the relationship information between the sending entity and the receiving entity of each layer of relationship and the relationship information between the sending entity and other directly related entities, and then the association weight between the target entity and other entities may be obtained based on the association weight of each layer of relationship.
In some embodiments, the target entity may be an issuing party of the relationship, the other entities may be receiving parties of the relationship, and the issuing entity and the receiving entity correspond to two ends of a certain layer of relationship between the target entity and the other entities, where the entity close to the target entity is the issuing entity and the entity close to the other entities is the receiving entity. In the heterogeneous knowledge graph, edges represent relationships between entities, and the issuing entity and the receiving entity are 2 entities connected by the edges. Taking fig. 6 as an example, if U1 is the target entity and I1 is the other entity, there are two layers of relationships between I1 and U1, including: u1 and U3, U3 and I1. Each layer relationship comprises a corresponding issuing entity and receiving entity: u1 and U3 connected by edges, U1 being the issuing entity and U3 being the accepting entity; u3 and I1 connected by edges, U3 being the issuing entity and I1 being the accepting entity.
The other directly related entities refer to entities directly related to the issuing entity except the receiving entity, and in the heterogeneous knowledge graph, the other directly related entities are other entities connected with the issuing entity through edges. As shown in fig. 6, the entities directly connected to U3 include U1, U2 and I1, and when U3 is the issuing entity, U1 is the accepting entity, and U2 and I1 are the other related entities.
Similar to the aforementioned relationship information, the relationship information of the issuing entity and the receiving entity, or the relationship information of the issuing entity and other directly related entities may contain the type of relationship or/and relationship value, etc. If the relationship information does not include a relationship value, the relationship value may be determined based on the type of the relationship through a preset rule, for example, the preset rule may be that the association value of the shareholder relationship is 2, the association value of the corporate relationship is 5, and the like.
In some embodiments, the ratio of the relationship value of the issuing entity to the accepting entity in a certain layer of relationship between the target entity and other entities to the relationship value of the issuing entity to all directly related entities can be used as the association weight of the layer of relationship.
Continuing with the example of fig. 6, there are two layers of relationships between the target entity U1 and other entities I1, for the layer of relationships between U1 and U3, U1 is the issuing entity, U3 is the accepting entity, U1 and U3 are the investment relationship, the relationship value is 2, but no other directly related entities exist in U1, therefore, the association weight w of the layer of relationships is12/2 ═ 1; for the layer relationship of U3 and I1, the issuing entity U3 and the accepting entity I1 are legal relationships, and the relationship value is 5; meanwhile, U3 has another directly related entity U2, and U2 and U3 are investment relations, and the relation value is 2, so the association weight w of the layer is 5/(2+5) 0.71.
The above examples only illustrate some of the available methods, and the processing device may also use other rules and algorithms to calculate the association weight of each layer of relationship between the target entity and other entities, which is not limited in this application.
In some embodiments, based on the obtained association weight for each layer, the association weight of the target entity with other entities may be determined. For example, the association weight of each layer of relationship may be calculated or weighted (e.g., averaged, integrated, or squared, etc.), and the calculation result may be used as the association weight between the target entity and the other entity.
Continuing with the example of fig. 6, the association weight R of the target entity U1 with the other entity I1 may be determined by 0.6 × 0.5.5-0.3.
In some embodiments, the processing device may determine the association weights between the target entity and other entities based on preset rules. For example, when the number of relation layers between the target entity and other entities is 1, the association weight between the target entity and other entities is 1; when the number of layers is 2, the association weight is 0.5; when the number of layers is 3, the association weight is 0.25; and so on. The association weight may also be determined by other similar rules, which are not described in detail.
And step 430, taking other entities with the association weights meeting preset conditions as at least one associated entity of the target entity. In particular, this step 430 may be performed by the associated entity determining module 240.
In some embodiments, the processing device may be purpose-dependentAnd determining whether the other entities are the associated entities of the target entity or not according to whether the associated weight between the target entity and the other entities meets the preset condition or not. For example, a threshold τ may be set when the correlation weight R between the target entity and the other entity QQWhen the value is more than tau, the other entity Q can be determined as the related entity of the target entity. For another example, a rank N may be set, and when the rank N of the association weight between the target entity and the other entity M in the association weights of the target entity and all other entities belongs to the top N, it may be determined that the other entity M is the associated entity of the target entity. The above is only an example of the preset condition, and in some embodiments, the preset condition may be set in any other manner known to those skilled in the art, which is not limited in this application.
In this embodiment, when determining the associated entity of the target entity by the association weight, the relationship degree (e.g., the degree of closeness, the degree of importance, etc.) may be determined, so that the determined associated entity has more practical significance.
Fig. 5 is a schematic diagram of a risk assessment result of at least one risk direction of a target entity obtained by a risk discrimination model according to some embodiments of the present description.
In some embodiments, the risk discrimination model may be a neural network model or at least one logistic regression model, and the neural network model or the at least one logistic regression model obtains the risk assessment result of the at least one risk direction of the target entity according to the risk characteristics of the target entity and the risk characteristics of the at least one associated entity.
In some embodiments, the risk discrimination model may employ a neural network model, and the risk characteristics of the target entity and the risk characteristics of the associated entity are input into the neural network model, and a risk assessment result, such as a risk scoring result, of at least one risk direction of the target entity is output. In particular, the neural network model may employ, for example, SVM, random forest models, or other functionally similar multi-classification models.
Taking an SVM as an example, inputting the risk characteristics of the target entity and the risk characteristics of the associated entity into the SVM, wherein the SVM output may be categories of the target entity in each risk direction, the categories may be risk levels or whether risks occur, the output may also be probabilities of the occurrence of the risks, and further, the risk levels are determined according to the probability values.
In some embodiments, the risk discrimination model may employ at least one logistic regression model, each of the at least one logistic regression model corresponding to each risk direction, respectively. And inputting the risk characteristics of the target entity and the risk characteristics of the associated entity into a logistic regression model corresponding to a certain risk direction to obtain a risk evaluation result of the risk direction. Specifically, for each logistic regression model, the risk characteristics of the target entity and the risk characteristics of the associated entity are input, and the output is the category of the target entity in the risk direction corresponding to the model or the probability of risk occurrence.
The embodiment of the present specification further provides an apparatus, which at least includes a processor and a memory. The memory is to store instructions. The instructions, when executed by the processor, cause the apparatus to implement the method of risk analysis described previously. The method may include: acquiring at least one target entity; obtaining a risk evaluation result of at least one risk direction of the target entity according to the target entity and at least one associated entity of the target entity; generating a risk link for the target entity according to at least one feedback of a risk assessment result for at least one risk direction of the target entity, the risk link comprising at least: the target entity, and the risk assessment result of the at least one feedback concerned risk direction and/or the risk assessment result approved by the at least one feedback; and the risk link of the target entity is used for providing a risk evaluation result of the target entity on line.
The beneficial effects that may be brought by the embodiments of the present description include, but are not limited to: (1) the identified risks are not limited to entities such as enterprises, but cover associated entities closely related to the entities, so that the risks of target entities such as enterprises, natural people and the like can be rapidly and comprehensively identified; (2) and the risk link is stored based on the feedback of the risk evaluation result, so that a target entity risk identification link which is really useful for the client can be precipitated, and the risk analysis is more effective. It is to be noted that different embodiments may produce different advantages, and in different embodiments, any one or combination of the above advantages may be produced, or any other advantages may be obtained.
Having thus described the basic concept, it will be apparent to those skilled in the art that the foregoing detailed disclosure is to be regarded as illustrative only and not as limiting the present specification. Various modifications, improvements and adaptations to the present description may occur to those skilled in the art, although not explicitly described herein. Such modifications, improvements and adaptations are proposed in the present specification and thus fall within the spirit and scope of the exemplary embodiments of the present specification.
Also, the description uses specific words to describe embodiments of the description. Reference throughout this specification to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic described in connection with at least one embodiment of the specification is included. Therefore, it is emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, some features, structures, or characteristics of one or more embodiments of the specification may be combined as appropriate.
Moreover, those skilled in the art will appreciate that aspects of the present description may be illustrated and described in terms of several patentable species or situations, including any new and useful combination of processes, machines, manufacture, or materials, or any new and useful improvement thereof. Accordingly, aspects of this description may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the present description may be represented as a computer product, including computer readable program code, embodied in one or more computer readable media.
The computer storage medium may comprise a propagated data signal with the computer program code embodied therewith, for example, on baseband or as part of a carrier wave. The propagated signal may take any of a variety of forms, including electromagnetic, optical, etc., or any suitable combination. A computer storage medium may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated over any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or any combination of the preceding.
Computer program code required for the operation of various portions of this specification may be written in any one or more programming languages, including an object oriented programming language such as Java, Scala, Smalltalk, Eiffel, JADE, Emerald, C + +, C #, VB.NET, Python, and the like, a conventional programming language such as C, Visual Basic, Fortran2003, Perl, COBOL2002, PHP, ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or processing device. In the latter scenario, the remote computer may be connected to the user's computer through any network format, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as a software as a service (SaaS).
Additionally, the order in which the elements and sequences of the process are recited in the specification, the use of alphanumeric characters, or other designations, is not intended to limit the order in which the processes and methods of the specification occur, unless otherwise specified in the claims. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing processing device or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the present specification, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to imply that more features than are expressly recited in a claim. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
Numerals describing the number of components, attributes, etc. are used in some embodiments, it being understood that such numerals used in the description of the embodiments are modified in some instances by the use of the modifier "about", "approximately" or "substantially". Unless otherwise indicated, "about", "approximately" or "substantially" indicates that the number allows a variation of ± 20%. Accordingly, in some embodiments, the numerical parameters used in the specification and claims are approximations that may vary depending upon the desired properties of the individual embodiments. In some embodiments, the numerical parameter should take into account the specified significant digits and employ a general digit preserving approach. Notwithstanding that the numerical ranges and parameters setting forth the broad scope of the range are approximations, in the specific examples, such numerical values are set forth as precisely as possible within the scope of the application.
For each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., cited in this specification, the entire contents of each are hereby incorporated by reference into this specification. Except where the application history document does not conform to or conflict with the contents of the present specification, it is to be understood that the application history document, as used herein in the present specification or appended claims, is intended to define the broadest scope of the present specification (whether presently or later in the specification) rather than the broadest scope of the present specification. It is to be understood that the descriptions, definitions and/or uses of terms in the accompanying materials of this specification shall control if they are inconsistent or contrary to the descriptions and/or uses of terms in this specification.
Finally, it should be understood that the embodiments described herein are merely illustrative of the principles of the embodiments of the present disclosure. Other variations are also possible within the scope of the present description. Thus, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be considered consistent with the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.
Claims (15)
1. A method of risk analysis, comprising:
acquiring at least one target entity;
obtaining a risk evaluation result of at least one risk direction of the target entity according to the target entity and at least one associated entity of the target entity;
generating a risk link for the target entity according to at least one feedback of a risk assessment result for at least one risk direction of the target entity, the risk link comprising at least: the target entity, and the risk assessment result of the at least one feedback concerned risk direction and/or the risk assessment result approved by the at least one feedback;
and the risk link of the target entity is used for providing a risk evaluation result of the target entity on line.
2. The method of claim 1, wherein obtaining a risk assessment result of at least one risk direction of the target entity according to the target entity and at least one associated entity of the target entity comprises:
determining a risk assessment result of at least one risk direction of the target entity based on a risk discrimination model;
wherein inputting the risk discrimination model at least comprises: a risk profile of the target entity and a risk profile of the at least one associated entity.
3. The method of claim 1, the generating a risk link for the target entity based on at least one feedback of risk assessment results for at least one risk direction of the target entity, comprising:
acquiring the text information of the at least one feedback;
and identifying the text information of the at least one feedback through an identification model, and determining a risk evaluation result of the risk direction concerned by the at least one feedback and/or a risk evaluation result approved by the at least one feedback.
4. The method of claim 1, determining at least one associated entity of the target entity comprising:
obtaining at least one other entity, wherein the other entity is associated with the target entity through one or more layers of relations;
determining an association weight between the target entity and each of the at least one other entity based on the relationship information for the one or more levels of relationships;
and taking the other entities with the association weights meeting preset conditions as at least one associated entity of the target entity.
5. The method of claim 4, the determining an association weight between the target entity and each of the at least one other entity based on the relationship information for the one or more levels of relationships comprising:
the association weight is determined based on relationship information of the originating entity and the receiving entity for each of the one or more levels of relationships and relationship information of the originating entity and other directly related entities.
6. The method of claim 1, the risk assessment results comprising:
and generating a risk scoring result and/or a risk text result according to the risk scoring result, the risk characteristics of the target entity and the risk characteristics of the associated entity.
7. The method of claim 2, wherein the risk discrimination model is a neural network model or at least one logistic regression model, and the risk discrimination model obtains a risk assessment result of at least one risk direction of the target entity according to the risk features of the target entity and the at least one associated entity, and comprises:
inputting the risk characteristics of the target entity and the risk characteristics of the associated entity into the neural network model to obtain a risk evaluation result of at least one risk direction of the target entity;
and each of the at least one logistic regression model corresponds to each risk direction, and the risk characteristics of the target entity and the risk characteristics of the associated entity are input into the logistic regression model corresponding to the risk direction to obtain a risk evaluation result of the risk direction.
8. A risk analysis system, comprising:
an acquisition module for acquiring at least one target entity;
the risk assessment module is used for obtaining a risk assessment result of at least one risk direction of the target entity according to the target entity and at least one associated entity of the target entity;
a link generation module, configured to generate a risk link of the target entity according to at least one feedback of a risk assessment result for at least one risk direction of the target entity, where the risk link at least includes: the target entity, and the risk assessment result of the at least one feedback concerned risk direction and/or the risk assessment result approved by the at least one feedback; and the risk link of the target entity is used for providing a risk evaluation result of the target entity on line.
9. The system of claim 8, the risk assessment module further to:
determining a risk assessment result of at least one risk direction of the target entity based on a risk discrimination model;
wherein inputting the risk discrimination model at least comprises: a risk profile of the target entity and a risk profile of the at least one associated entity.
10. The system of claim 8, the link generation module further to:
acquiring the text information of the at least one feedback;
and identifying the text information of the at least one feedback through an identification model, and determining a risk evaluation result of the risk direction concerned by the at least one feedback and/or a risk evaluation result approved by the at least one feedback.
11. The system of claim 8, further comprising an associated entity determination module to:
obtaining at least one other entity, wherein the other entity is associated with the target entity through one or more layers of relations;
determining an association weight between the target entity and each of the at least one other entity based on the relationship information for the one or more levels of relationships;
and taking the other entities with the association weights meeting preset conditions as at least one associated entity of the target entity.
12. The system of claim 11, the associated entity determination module further to:
the association weight is determined based on relationship information of the originating entity and the receiving entity for each of the one or more levels of relationships and relationship information of the originating entity and other directly related entities.
13. The system of claim 8, the risk assessment results comprising:
and generating a risk scoring result and/or a risk text result according to the risk scoring result, the risk characteristics of the target entity and the risk characteristics of the associated entity.
14. The system of claim 9, wherein the risk discrimination model is a neural network model or at least one logistic regression model, and the risk assessment module is further configured to:
inputting the risk characteristics of the target entity and the risk characteristics of the associated entity into the neural network model to obtain a risk evaluation result of at least one risk direction of the target entity;
and each of the at least one logistic regression model corresponds to each risk direction, and the risk characteristics of the target entity and the risk characteristics of the associated entity are input into the logistic regression model corresponding to the risk direction to obtain a risk evaluation result of the risk direction.
15. A risk analysis device comprising at least one storage medium and at least one processor, the at least one storage medium for storing computer instructions; the at least one processor is configured to execute the computer instructions to implement the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010373414.4A CN111353728A (en) | 2020-05-06 | 2020-05-06 | Risk analysis method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010373414.4A CN111353728A (en) | 2020-05-06 | 2020-05-06 | Risk analysis method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111353728A true CN111353728A (en) | 2020-06-30 |
Family
ID=71197648
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010373414.4A Pending CN111353728A (en) | 2020-05-06 | 2020-05-06 | Risk analysis method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111353728A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113469483A (en) * | 2021-02-23 | 2021-10-01 | 杭州有数金融信息服务有限公司 | Natural person operation risk scoring method, system and equipment |
| US20220147817A1 (en) * | 2020-11-10 | 2022-05-12 | Equifax Inc. | Machine-learning techniques involving monotonic recurrent neural networks |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909274A (en) * | 2017-11-17 | 2018-04-13 | 平安科技（深圳）有限公司 | Enterprise investment methods of risk assessment, device and storage medium |
| CN109272396A (en) * | 2018-08-20 | 2019-01-25 | 平安科技（深圳）有限公司 | Customer risk method for early warning, device, computer equipment and medium |
| CN109492945A (en) * | 2018-12-14 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Business risk identifies monitoring method, device, equipment and storage medium |
| CN109657837A (en) * | 2018-11-19 | 2019-04-19 | 平安科技（深圳）有限公司 | Default Probability prediction technique, device, computer equipment and storage medium |
| CN109740865A (en) * | 2018-12-13 | 2019-05-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, system, equipment and storage medium |
| CN110992169A (en) * | 2019-11-29 | 2020-04-10 | 深圳乐信软件技术有限公司 | Risk assessment method, device, server and storage medium |
| CN111080178A (en) * | 2020-01-22 | 2020-04-28 | 中国建设银行股份有限公司 | Risk monitoring method and device |
-
2020
- 2020-05-06 CN CN202010373414.4A patent/CN111353728A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909274A (en) * | 2017-11-17 | 2018-04-13 | 平安科技（深圳）有限公司 | Enterprise investment methods of risk assessment, device and storage medium |
| CN109272396A (en) * | 2018-08-20 | 2019-01-25 | 平安科技（深圳）有限公司 | Customer risk method for early warning, device, computer equipment and medium |
| CN109657837A (en) * | 2018-11-19 | 2019-04-19 | 平安科技（深圳）有限公司 | Default Probability prediction technique, device, computer equipment and storage medium |
| CN109740865A (en) * | 2018-12-13 | 2019-05-10 | 平安科技（深圳）有限公司 | Methods of risk assessment, system, equipment and storage medium |
| CN109492945A (en) * | 2018-12-14 | 2019-03-19 | 深圳壹账通智能科技有限公司 | Business risk identifies monitoring method, device, equipment and storage medium |
| CN110992169A (en) * | 2019-11-29 | 2020-04-10 | 深圳乐信软件技术有限公司 | Risk assessment method, device, server and storage medium |
| CN111080178A (en) * | 2020-01-22 | 2020-04-28 | 中国建设银行股份有限公司 | Risk monitoring method and device |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220147817A1 (en) * | 2020-11-10 | 2022-05-12 | Equifax Inc. | Machine-learning techniques involving monotonic recurrent neural networks |
| US11960993B2 (en) * | 2020-11-10 | 2024-04-16 | Equifax Inc. | Machine-learning techniques involving monotonic recurrent neural networks |
| CN113469483A (en) * | 2021-02-23 | 2021-10-01 | 杭州有数金融信息服务有限公司 | Natural person operation risk scoring method, system and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110070391B (en) | Data processing method and device, computer readable medium and electronic equipment | |
| CN109670023A (en) | Man-machine automatic top method for testing, device, equipment and storage medium | |
| CN111506723B (en) | Question-answer response method, device, equipment and storage medium | |
| CN112732911A (en) | Semantic recognition-based conversational recommendation method, device, equipment and storage medium | |
| CN112860841A (en) | Text emotion analysis method, device and equipment and storage medium | |
| CN112989761B (en) | Text classification method and device | |
| CN113283795B (en) | Data processing method and device based on two-classification model, medium and equipment | |
| CN110717009A (en) | Method and equipment for generating legal consultation report | |
| CN110955770A (en) | Intelligent dialogue system | |
| CN111353728A (en) | Risk analysis method and system | |
| CN113868391B (en) | Legal document generation method, device, equipment and medium based on knowledge graph | |
| CN116821372A (en) | Knowledge graph-based data processing method and device, electronic equipment and medium | |
| US20220156862A1 (en) | System and method for analyzing grantability of a legal filing | |
| CN110704803A (en) | Target object evaluation value calculation method and device, storage medium and electronic device | |
| CN113011961B (en) | Method, device, equipment and storage medium for monitoring risk of company-related information | |
| CN113807728A (en) | Performance assessment method, device, equipment and storage medium based on neural network | |
| CN111324738B (en) | Method and system for determining text label | |
| CN116402625B (en) | Customer evaluation method, apparatus, computer device and storage medium | |
| CN116757835A (en) | Method and device for monitoring transaction risk in credit card customer credit | |
| CN111507849A (en) | Authority guaranteeing method and related device and equipment | |
| CN116777646A (en) | Artificial intelligence-based risk identification method, apparatus, device and storage medium | |
| CN115545088B (en) | Model construction method, classification method, device and electronic equipment | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| CN114067308A (en) | Intelligent matching method and device, electronic equipment and storage medium | |
| CN113592315A (en) | Method and device for processing dispute order |
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 |