Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the technical solutions of the present application will be clearly and completely described below with reference to specific embodiments and corresponding drawings. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Some embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for supervising a financial enterprise according to an embodiment of the present application. Some of the input parameters or intermediate results in the flow allow for manual intervention adjustments to help improve accuracy.
The implementation of the analysis method according to the embodiment of the present application may be a terminal device or a server, which is not particularly limited in the present application. For ease of understanding and description, the following embodiments are described in detail with reference to a server.
It should be noted that the server may be a single device, or may be a system formed by a plurality of devices, that is, a distributed server, which is not particularly limited in the present application.
The flow in fig. 1 includes the following steps:
s101: acquiring a supervision data source of a supervision enterprise in a preset period; the supervision data source comprises risk perception information and basic information of a supervision enterprise; the risk perception information comprises network investment advertisements, complaint reports and negative public opinion; the basic information includes financial management data, business data, equity data and judicial data.
Where a supervising enterprise refers to a financial institution-like or non-financial institution engaged in a financial activity.
In some embodiments of the present application, a wind-control big data center needs to be pre-constructed, and is used as a big database related to wind control, and data management and quality control are performed from the perspective of data fusion application by collecting government data, enterprise data, internet data and management platform self data, so as to obtain risk perception information and basic information of a supervisory enterprise, thereby forming a multidimensional risk prevention and control data center, that is, the risk prevention and control data center is used for storing a supervision data source of the supervisory enterprise.
Based on the method, the construction process of the risk prevention and control data center mainly comprises Internet data acquisition, organization data acquisition, data development and data management. It should be noted that, the organization data includes government data, enterprise data and management platform own data, which are mainly obtained through interface call, and the internet data is crawled through the internet platform.
It should be noted that, in the process of organizing data collection, the data convergence service provides a high-speed channel for data migration, conversion and filtering among different data source types, and simultaneously provides a one-stop service platform for various complex query calculations such as aggregation and association among heterogeneous data sources. The user can visually configure complex task templates, start instant tasks by one key, monitor the execution condition of the tasks in real time, the health state of the whole cluster and other information through the data aggregation service.
In the process of internet data acquisition, the internet data acquisition needs to automatically grasp information related to enterprises from the internet at regular intervals, and the grasping result process is processed to form structured data. Information, public opinion information, market behavior data and the like about enterprises in the Internet are collected, and portrait analysis, risk early warning and the like of the enterprises are realized.
The system can support the function of providing deep multi-channel network information acquisition and monitoring source configuration, and can monitor a plurality of channel data sources. In addition, the method can provide perfect information pretreatment mechanism, hyperlink analysis, coding identification, URL duplication removal, anchor text processing, junk information filtering, content duplication removal, keyword extraction, text extraction and the like. In addition, the system supports the realization of the collection of public opinion data of news, forum, microblog and other categories through the internet data collection function, and realizes the focus of hot public opinion information. In addition, the data acquisition of the emergency including the cross-time and cross-space comprehensive content is supported, the occurrence overview of the emergency is known, and the data acquisition of the emergency is realized.
In the process of data development, data development operates on data in units of projects. Support model development, script development, ETL development. The data developer can construct a business-based data processing flow through a data model development tool, an SQL online editor and an ETL development tool provided by data development, and meanwhile supports multi-person collaborative development.
The large data acquisition technology is used for crawling mass internet data related to enterprise credit assessment, wherein the mass internet data comprise enterprise multidimensional data such as enterprise operating conditions, enterprise development and development, enterprise operating risks, judicial risks, public opinion data and the like.
By enterprise authorization, various enterprise government data are fused, platform data such as financial system online transaction and enterprise loan application behavior data are gradually accumulated, based on a multi-source data set, data extraction, data conversion and data fusion are carried out on multi-source data by using large data processing technologies such as ETL and large data technology components such as Hadoop, spark, storm, kafka, and finally the multi-source data are summarized in a standard data warehouse established by technologies such as Hive, hbase and relational databases to build a standard data catalog, so that standard data service is provided.
It should be noted that, a supervisory enterprise database needs to be constructed for the monitoring area, where the supervisory enterprise database includes a plurality of designated supervisory enterprises.
Based on this, the process of acquiring the supervisory data source of the supervisory enterprise is as follows:
First, for internet data collection, i.e. for risk awareness information, mainly from internet data, the following is true:
And crawling initial risk perception information of the monitoring area to the Internet platform in a preset period. The initial risk perception information comprises initial network investment advertisements, initial complaint reports and initial negative public opinion.
For example, initial network investment advertising includes advertising a false high-yield investment program. Initial complaint reporting includes investors finding a institution suspected of illegal financial activity and reporting to relevant regulatory authorities. The initial negative public opinion includes that enterprises are uncovered and have the problems of illegal funding, fraudulent investment, illegal sales of financial products and the like.
It should be noted that, the enterprise involved in the initial risk awareness information may not be a supervising enterprise, i.e. it is not found and added to the supervising enterprise database in time, or it is not a financial institution-like enterprise and cannot be identified. That is, the monitoring area is mainly comprised in the supervising enterprise database, and the class financial institution is the main object of the financial risk supervision.
That is, it is possible to timely find out, through internet data, a financial institution-like or a non-financial institution that does not belong to the supervising enterprise, but that is at risk for finance. Therefore, it is necessary to add such enterprises that are not found in time to the supervising enterprise database to supervise the enterprises.
Based on this, first, the name of the business to which each piece of initial risk perception information belongs is determined to generate an initial risk perception information table of the monitoring area. The fields of the initial risk perception information table comprise enterprise names, initial network investment advertisements, initial complaint reports and initial negative public opinion.
Then, the enterprises involved in the initial risk awareness information are determined, and whether the enterprises are in the regulatory database is judged.
If not, determining the enterprise as a supervision enterprise, and adding the enterprise to a supervision enterprise database to update the supervision enterprise database.
The process of adding the enterprise to the supervision enterprise database is specifically as follows:
in the initial risk awareness information table, a first color marking is performed on the name of the business. Wherein the business name of the supervising business is a second color mark.
Based on the operation of the user, enterprise information of the enterprise is obtained.
And receiving a warehouse-in request, determining the enterprise as a supervising enterprise, and adding the enterprise to a supervising enterprise database based on the enterprise information.
That is, enterprises involved in the risk awareness information are distinguished from the supervising enterprise database or from the supervising enterprise database to visually present to the user.
For example, negative public opinion, network advertising, complaint reporting are categorized into three categories of cues.
The first category is public opinion cues of the enterprise (the enterprise in the supervising enterprise database) within the system, and in the initial risk awareness information table, the enterprise name is marked with a red box.
The second type is public opinion clues of enterprises outside the system (enterprises which are not in supervision enterprise databases), in the initial risk perception information table, enterprise names are marked by blue frames, auditors need to click on the enterprise names first, pop up information auditing mechanisms to put in warehouse popup windows, fill in real mechanism information, click to confirm, add the mechanisms into the system, and after operation and put in warehouse, the identification of the clues can be defaulted to be valid.
And thirdly, performing a clue word dividing and warehousing operation, wherein an auditor clicks clue detail information, slides related words through a mouse, pops up clue editing popup windows, and performs a mechanism warehousing operation after supplementing information.
The auditor needs to audit whether the clue is valid or not, and generates valid and invalid identifiers in the operation column for recommending enterprise grid type risk points by the system.
For the updated supervising enterprise database, initial risk awareness information for each supervising enterprise is generated. It should be noted that, the types of the initial risk sensing information of each supervising enterprise may be different, for example, a the initial sensing risk information of the supervising enterprise in the past period includes an initial network investment advertisement and an initial complaint report, b the initial sensing risk information of the supervising enterprise in the past period includes an initial network investment advertisement, and c the initial sensing risk information of the supervising enterprise in the past period includes an initial negative public opinion.
Secondly, for tissue data acquisition, i.e. for basic information, mainly from tissue data, the following are:
and acquiring initial basic information of each supervision enterprise through a preset interface.
And thirdly, carrying out data management on the initial risk perception information and the initial basic information to obtain risk perception information and basic information of each supervision enterprise.
The data management process is as follows:
Firstly, according to naming standards, field standards and content standards of a wind control big data center, standard verification is carried out on initial risk perception information and initial basic information, and verification initial risk perception information and verification initial basic information are obtained.
The naming standards comprise standards of table names and field names, the field standards comprise standards of field types and field lengths, and the content standards comprise content standards in a fixed format.
It should be noted that, the naming standard refers to a naming standard for determining the item, mainly including the table name and the field name, and includes the following classes: all uppercase, all lowercase, hump, prefix, suffix, regular. By setting the corresponding naming standards, whether the naming of the logical model and the naming of the physical model meet the specification can be detected periodically in the project implementation process, so that a detection report is produced.
The field standard refers to the field standard of the project, and refers to whether the setting of the field type and the length limit accords with the standard, and the support of the most common database types can cause more field type redundancy, so the field standard can be set here to be determined by the type of the data source bound by the project and be automatically loaded.
The content standard is mainly used for detecting data content with a fixed format, and is divided into two types, namely built-in type and manual type, wherein the built-in type comprises IP address, URL, domain name, fixed telephone, mobile phone number, time, date, identity card and the like.
The standard check is to provide data standardized physical examination capability for standard check, support the standard to perform standardized check on specific data tables, fields, data types, processes, tasks and the like, and output results.
And then, carrying out data cleaning on the verification initial risk perception information and the verification initial basic information to obtain cleaning initial risk perception information and cleaning initial basic information.
It should be noted that, the cleaning conversion of data is required to filter incomplete data, erroneous data, and duplicate data. The method comprises the steps of cleaning rules, data conversion, parameter management, cleaning logs and the like.
The cleansing rules refer to providing a configuration of data cleansing rules, detecting data items. Incomplete data determines a missing value range, and strategies are respectively formulated according to the missing proportion and the field importance.
The data conversion is to support multiple processing methods for converting the data format.
Parameter management refers to providing data standardization and data conversion mapping rule parameter unified configuration management service, including adding, editing, deleting and the like.
The cleaning log is used for supporting two cleaning log modes of intelligent segmentation and custom segmentation.
And finally, carrying out data quality management on the cleaning initial risk perception information and the cleaning initial basic information so as to remove the invalid cleaning initial risk perception information and the invalid cleaning initial basic information and obtain risk perception information and basic information of each supervision enterprise.
The process of data quality management is as follows:
first, a plurality of risk awareness information management rules and a plurality of base information management rules for data quality management are determined.
Setting a risk awareness information management task for each risk awareness information management rule, and setting a basic information management task for each basic information management rule.
And executing the risk perception information management task according to the starting time of the risk perception information management task, and performing data quality management on the cleaning initial risk perception information.
And executing the basic information management task according to the starting time of the basic information management task, and performing data quality management on the cleaning initial basic information.
Therefore, risk perception information which does not accord with the risk perception information management rule can be removed, or basic information which does not accord with the basic information management rule can be removed.
For example, the nodes for data quality management include quality rule management, quality task initiation, quality task monitoring, result detail viewing, and result history viewing.
The quality rule management is to support the following field level and table level class quality rule configuration for a specific data table by a pointer; the rules display the configured rules in a list form, the display column comprising: rule type, rule name, creator, next execution time. Rules may be added, deleted, modified, and manipulated under the page.
The quality task starting is to configure and execute quality auditing tasks based on quality auditing rules, and task execution supports timing starting, conditional starting and starting failure mail notification.
The quality task monitoring is to monitor the execution condition of the data inspection rule, and the list display items comprise: task name, execution start time, execution end time, task execution status (success, failure).
The result detail viewing means to support the viewing of the auditing result details of the completion of the operation, including the operation time of each audit, auditing result and problem description, etc.
The result history viewing refers to the fact that each time a task runs, one instance is generated, and the result of each instance is supported to be viewed.
According to the data quality evaluation index system and the data quality detection requirement in production, a data quality evaluation model is established, data quality evaluation suitable for the data per se is carried out on different business data, and data is reversely tracked according to an evaluation result to perfect.
S102: and carrying out risk analysis on the supervision enterprises according to the risk perception information and the basic information, and determining the risk level of the supervision enterprises.
In some embodiments of the present application, the risk analysis for a supervising enterprise is as follows:
Firstly, determining whether a supervision enterprise is a risk aware enterprise according to risk aware information so as to conduct behavior supervision on the supervision enterprise.
The process of determining whether the supervising enterprise is a risk aware enterprise is as follows: based on the identification operation of the user, obtaining the identification of the risk perception information; an identification is used to indicate whether the risk awareness information is valid. Judging whether the identification of the risk perception information is a valid identification. If yes, determining that the supervision enterprise is a risk perception enterprise. If not, determining that the supervising enterprise is a non-risk aware enterprise.
And then, analyzing the risk perception information and the basic information through a pre-constructed enterprise portrait model to determine enterprise portrait labels of the supervision enterprises. The business portrait tags include business identification tags, business asset value tags, business stakeholder tags, and business risk tags. The enterprise identification tag comprises an enterprise where an enterprise is located, an enterprise area and enterprise properties; enterprise asset value tags include asset liability changes and business earnings; the enterprise stakeholder labels comprise enterprise equity distribution conditions and enterprise association map conditions of all stakeholders; the enterprise risk tag includes an illegal financial activity risk situation.
The process of constructing the enterprise portrait is as follows: and (5) accurately portraying the enterprise by applying a big data technology and a knowledge graph technology according to business requirements. The once complete enterprise portrait construction process is as follows: data collection, data cleaning, data modeling and portrait construction. The key of enterprise portraits is to output labels, carry out statistical analysis from the original data of a data warehouse to obtain fact labels, then carry out business modeling analysis to obtain model labels, and then carry out model prediction to obtain prediction labels. And confirming that enterprise portrait modeling is carried out by adopting a cluster analysis method according to service requirements, and finally outputting enterprise portrait labels which comprise three categories of enterprise own labels, model labels after enterprise portrait modeling and final forecast labels, wherein all fields obtained by screening conditions enter a subsequent data modeling flow.
FIG. 2 is a schematic diagram of the construction of an enterprise portrait tag according to an embodiment of the present application.
As shown in fig. 2, the enterprise dataset construction: and determining the range of the enterprise information, preprocessing the data after the enterprise information is acquired to improve the data quality, forming enterprise indexes, and extracting enterprise attributes and enterprise staff attributes. And finally, carrying out statistical analysis on the enterprise information.
Knowledge learning: a large amount of knowledge is hidden under the surface layer data, the value of the query predicate is predicted under the condition of the given evidence predicate by means of a discriminant knowledge learning algorithm DSL, and the L-BFGS algorithm is used for weight learning, so that a reasonable network structure is generated.
Knowledge reasoning: based on the model and the weight thereof learned in the knowledge learning stage, the Lazy-MC-SAT algorithm is realized to perform reasoning of the relation between the entities and the entity attribute, and the relationship is compared with other knowledge reasoning algorithms.
Constructing an enterprise portrait tag: on the basis of the enterprise knowledge graph, the enterprise is imaged by means of a graph. And by means of enterprise portraits, enterprise situation analysis is performed from the dimensions of enterprise credit, development stage, scientific research capability and the like. Through the enterprise portrait, the information of each aspect of the enterprise can be visually checked, including enterprise basic information, illegal financial activity risk, public opinion information, network advertisement, judicial risk operation risk, associated information, department data and the like, which has great significance in aspects such as enterprise background investigation, enterprise credit evaluation and high-quality enterprise mining.
The enterprise portrait labels of the determined supervision enterprises are as follows: and analyzing the basic information through a pre-constructed enterprise portrait model to obtain enterprise identification tags, enterprise asset value tags and enterprise stakeholder tags of the supervision enterprises. And performing cluster analysis on the enterprise identification tag, the enterprise asset value tag, the enterprise stakeholder tag and the risk perception information to obtain an enterprise risk tag of the supervision enterprise. And determining whether the supervision enterprise is an portrait risk enterprise according to the enterprise portrait label so as to carry out penetrating supervision on the supervision enterprise.
The purpose of the enterprise basic information analysis is to sort and classify the existing data collected by the data center of the platform and select variables suitable for enterprise portraits from the data.
It should be noted that, the purpose of the feature analysis of the enterprise risk tag is to analyze the data quality and the single variable occurrence ratio of each variable of the data, check whether the data accords with the business logic, and derive a new variable according to the existing variable, so that the clustering model can learn the rules in the data better. For example, the analysis content includes business base information, legal base information, business account base information, transaction records, liability information, legal credit reports, and the like. Comprising: on one hand, the whole quality of the data is checked, and variables with poor quality are processed or discarded from the comprehensive consideration of both data and service. On the other hand, the statistical index of each variable and the distribution situation of each interval are analyzed to obtain the distribution trend of the enterprise in each variable, and the variable with abnormal data expression is eliminated. On the other hand, partial variables are derived, the data features hidden in the original variables are further explored, and the accuracy of enterprise portraits is improved.
The implementation of penetration supervision needs to realize penetration of equity, penetration of fund flow direction, substantial penetration of business and the like. On one hand, the penetration of the equity stakeholder's equity is enhanced, the penetration is developed around the stakeholder's share-in funds, the association relation network is hidden, the equity funds are separated, and the like, and partial illegal stakeholders are urged to complete the equity clearing and transferring. On the other hand, the flow direction penetration of funds is enhanced, the penetration of the fund application of the personal insurance company is developed, more than 10 models such as stockholder mutual throwing, stockholder holding and the like are established, the silver, insurance and trust supervision data sources are penetrated, and the penetration reveals the hidden trouble of the insurance funds being thrown to the high-risk field, stockholder relatives and the like through layer-by-layer nesting. On the other hand, the enhanced business is substantially penetrated, for example, a part of bank internet common Hui Xing small micro-enterprise loan business is selected to carry out online intelligent analysis and monitoring, and on-site verification is carried out aiming at suspicious spots, and the conditions of inaccurate enterprise allocation, virtual loan increase scale and the like of a part of common business are found.
And finally, matching the supervision enterprises in a pre-constructed mapping relation table, and determining the risk level of the supervision enterprises. The mapping relation table comprises mapping relations among risk perception enterprises, portrait risk enterprises and risk levels.
S103: and when the risk level is greater than a preset level threshold, generating risk early warning information of the supervision enterprise, and sending the risk early warning information to a supervision terminal.
And when the risk level is lower than or equal to a preset level threshold, risk early warning information of the supervising enterprise is not generated.
Therefore, a financial risk prevention and control full-chain product system is formed based on the collection and analysis of enterprise big data, the extraction and labeling of financial risk characteristics, the establishment of a quantitative early warning model and the carding research of the full-service flow of active discovery, quantitative monitoring, grading early warning, checking and resolving and sorting disposal, and is used for energizing departments such as local financial regulatory authorities, industry supervision and the like by applying supervision technologies, innovating a supervision thinking method and improving the digital supervision capability.
For example, when a company has a high risk, the operator should check again as soon as possible whether the risk point to which the company belongs is authentic, and write a risk analysis report of the company. The financial staff is informed of the specific situation and then discusses whether the financial staff needs to check and issue the financial staff to counties. If so, clicking the right check down button to perform the next operation. And selecting a main delivery unit and a copy unit which are required to be delivered according to the county of the enterprise, selecting a check expiration date and filling specific requirements for checking the county, and completing delivery operation after uploading related accessories.
In some embodiments of the application, full-scale macro statistical analysis and multi-dimensional deep detail analysis are performed on illegal funding and other illegal financial activity conditions of functional departments, so that the illegal funding and other illegal financial activity risks of financial enterprises are perceived. And comprehensively analyzing the activity condition of all-market early warning inauguration enterprises.
Based on the information, risk early warning information of the monitoring area in each history period is obtained, wherein the risk early warning information comprises enterprise addresses and enterprise types of risk early warning supervision enterprises.
And generating a quantity change trend graph of the monitoring area based on the risk early warning information. And the coordinate axis of the quantity change trend graph is the historical cycle time and the quantity of risk early warning supervision enterprises.
And generating a regional distribution map of the monitoring area based on the risk early warning information. And displaying the coordinates of the risk early warning supervision enterprises on the regional distribution map. The coordinates include registered coordinates and actual business coordinates.
And generating a type distribution map of the monitoring area based on the risk early warning information.
For example, the trend of quantity change can early warn the trend of the quantity change of enterprises over time, and help quickly learn the activity trend of financial risks of the enterprises.
Regional distribution: drawing a map of the illegal financial activity condition of the area, finding out high-risk counties, enhancing supervision of enterprises in the heavy-spot area, and displaying coordinates of the high-risk enterprises on the map, wherein the coordinates comprise registration place coordinates, actual operation place coordinates and the like. Risk ranking within the region is visually presented.
Type distribution: statistics and early warning of the fund types, operation entities and online and offline distribution conditions of enterprises.
Status distribution: and analyzing the financial performance distribution of the high-risk enterprises to find the high-risk performance type.
Data ranking: and analyzing the advertisement quantity, the negative public opinion quantity, the yield and the enterprise ranking of the early warning indexes.
Obviously, under the wide application background of the internet technology, illegal financial activities such as illegal funding have large risk infectivity and strong destructive power, and become an important factor for currently influencing, aggravating and even inducing regional, industrial and systematic risks. Internet financial supervision faces a plurality of difficulties, mainly manifested by difficult discovery, difficult study and judgment, difficult decision making, difficult control and difficult treatment. Traditional supervision modes of personal air defense alone cannot cope with the current severe situation.
The technology such as big data and cloud computing is fully utilized, a big data monitoring and early warning system which is sound aiming at illegal financial activities such as illegal funding is established, the digital monitoring and early warning efficiency is comprehensively improved, the working center is further changed from 'post discovery' to 'pre-early warning', from 'post treatment' to 'pre-striking', and from passive response to active striking.
From the technical capability, the understanding of risks is remodelled, and the risk management method is changed, so that a digital wind control mode of 'heavy main body and strong data' is formed. Strengthening the application of data resource fusion with judicial, social security, industry and commerce, tax, water, electricity and gas and the like, and increasing dynamic monitoring and accurate portraits in key fields: firstly, the financing cost and the potential risk condition of a normal enterprise; secondly, the edge enterprises slide to the risk level of illegal financial activities; and thirdly, risk evolution trend of illegal financial activity subjects possibly suspected.
From the operation mode, unified standards in aspects of sound data identification, collection, use, monitoring and the like are established for the data for risk management, the use standard is defined, and the authorized application and confidentiality management of the management data are enhanced. The intelligent technologies such as data mining and machine learning are fully utilized, the monitoring of fixed-point and high-frequency transaction data is enhanced, high-risk transactions are effectively screened, and the accuracy of risk identification and treatment of related financial business activities is improved.
From the supervision direction, the support force for upgrading the automatic, on-line and intelligent approval mechanism is increased, and the risk monitoring mode of heavy main body and strong data is promoted to fall to the ground. The advantage of basic level touch is fully utilized, the small and scattered risks are dynamically evaluated, and the monitoring, evaluating and early warning capabilities are improved in a multi-level and multi-dimensional manner.
It should be noted that, although the embodiment of the present application is described with reference to fig. 1 to sequentially describe steps S101 to S103, this does not represent that steps S101 to S103 must be performed in strict order. The steps S101 to S103 are sequentially described according to the sequence shown in fig. 1 according to the embodiment of the present application, so as to facilitate the understanding of the technical solution of the embodiment of the present application by those skilled in the art. In other words, in the embodiment of the present application, the sequence between the steps S101 to S103 may be appropriately adjusted according to the actual needs.
The method of fig. 1 can combine risk perception information of internet data and enterprise basic information, based on the collection of data, analysis of data and sharing of data as main lines, and utilizes the collection mode of big data and the analysis means of artificial intelligence to actively identify and discover illegal financial activities and illegal fund collecting activities, continuously monitor and early warning, and perform offsite supervision on local financial industries such as local transaction places, financing and business insurance, so that grippers and means for strengthening financial risk monitoring and control work realize digital global supervision, intelligent dynamic supervision and the like, thereby improving the omnibearing property of financial enterprise supervision and more efficiently and accurately realizing financial enterprise supervision.
Based on the same thought, some embodiments of the present application also provide a device and a non-volatile computer storage medium corresponding to the above method.
Fig. 3 is a schematic structural diagram of a financial enterprise supervision apparatus according to an embodiment of the present application, including:
At least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to:
Acquiring a supervision data source of a supervision enterprise in a preset period; the supervision data source comprises risk perception information and basic information of a supervision enterprise; the risk perception information comprises network investment advertisements, complaint reports and negative public opinion; the basic information comprises financial management data, industrial and commercial data, stock right data and judicial data;
According to the risk perception information and the basic information, carrying out risk analysis on the supervision enterprise, and determining the risk level of the supervision enterprise;
and when the risk level is greater than a preset level threshold, generating risk early warning information of the supervision enterprise, and sending the risk early warning information to a supervision terminal.
Some embodiments of the present application provide a financial enterprise monitoring non-volatile computer storage medium storing computer executable instructions configured to:
Acquiring a supervision data source of a supervision enterprise in a preset period; the supervision data source comprises risk perception information and basic information of a supervision enterprise; the risk perception information comprises network investment advertisements, complaint reports and negative public opinion; the basic information comprises financial management data, industrial and commercial data, stock right data and judicial data;
According to the risk perception information and the basic information, carrying out risk analysis on the supervision enterprise, and determining the risk level of the supervision enterprise;
and when the risk level is greater than a preset level threshold, generating risk early warning information of the supervision enterprise, and sending the risk early warning information to a supervision terminal.
The embodiments of the present application are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the apparatus and medium embodiments, the description is relatively simple, as it is substantially similar to the method embodiments, with reference to the section of the method embodiments being relevant.
The devices and media provided in the embodiments of the present application are in one-to-one correspondence with the methods, so that the devices and media also have similar beneficial technical effects as the corresponding methods, and since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media are not repeated here.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.
Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises the element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the technical principle of the present application should fall within the protection scope of the present application.