CN111782917A

CN111782917A - Method and apparatus for visual analysis of financial penalty data

Info

Publication number: CN111782917A
Application number: CN202010842522.1A
Authority: CN
Inventors: 苏豫陇
Original assignee: Alipay Hangzhou Information Technology Co Ltd
Current assignee: Alipay Hangzhou Information Technology Co Ltd
Priority date: 2020-08-20
Filing date: 2020-08-20
Publication date: 2020-10-16

Abstract

The embodiment of the specification provides a method and a device for performing visual analysis on financial penalty data. In the method, a web crawler is used for crawling financial penalty information from a financial supervision website, and structural analysis is carried out on the crawled financial penalty information to obtain penalty field data corresponding to a penalty information field; and performing cluster analysis on the obtained penalty field data to obtain penalty statistics corresponding to each penalty information field, and generating an early warning map for the rule risk according to the penalty statistics obtained by the cluster analysis and the corresponding penalty information fields.

Description

Method and apparatus for visual analysis of financial penalty data

Technical Field

The embodiment of the specification relates to the technical field of data processing, in particular to a method and a device for performing visual analysis on financial penalty data.

Background

The financial supervision authorities supervise and manage each financial institution to ensure that each financial institution operates legally and in compliance. When the financial institution has illegal operation, the financial supervision institution can perform penalty on the illegal financial institution and publicize the penalty case on the official website.

The financial supervision institution publicizes the penalty cases which comprise various penalty information such as penalty reasons, penalty amount and the like, and the penalty information can reflect the current or recent financial penalty strength, the penalty financial service range and the like to a certain extent, and the penalty information is closely related to the compliance risk service of the financial institution. Therefore, how to perform data analysis for compliance risk based on the public financial penalty information is an urgent problem to be solved.

Disclosure of Invention

In view of the foregoing, embodiments of the present specification provide a method and apparatus for visual analysis of financial penalty data. In the method and the device, financial penalty information is crawled from a financial supervision website by using a web crawler, the crawled financial penalty information is structurally analyzed, the obtained penalty field data is subjected to cluster analysis to obtain penalty statistics for each penalty information field, and an early warning graph for rule risks is generated according to the penalty statistics obtained by the cluster analysis and the corresponding penalty information fields. By the method and the device, the visual analysis aiming at the compliance risk based on the financial punishment information is realized.

According to an aspect of embodiments herein, there is provided a method for visual analysis of financial penalty data, comprising: crawling financial penalty information from a financial supervision website by using a web crawler; performing structured analysis on the crawled financial punishment information to obtain punishment field data corresponding to a punishment information field; performing clustering analysis on the obtained penalty field data to obtain penalty statistics corresponding to each penalty information field; and generating an early warning map for the regulatory risk according to the penalty statistic obtained by the clustering analysis and the corresponding penalty information field.

Optionally, in an example of the above aspect, each penalty information field includes a plurality of field data categories, and generating the early warning map for the risk of the rule according to the penalty statistics obtained by the cluster analysis and the corresponding penalty information field includes: when the penalty statistic corresponding to the field data category in the penalty information field is larger than a penalty threshold, determining that compliance risk exists for the penalty information field; and generating an early warning graph aiming at the penalty information field according to the penalty statistic corresponding to the penalty information field with the compliance risk.

Optionally, in an example of the above aspect, the penalty amount thresholds for respective field data categories in the penalty information field are different.

Optionally, in an example of the above aspect, further comprising: and providing the penalty statistics corresponding to the penalty information fields with the compliance risks to the trained compliance risk prediction model so as to predict and obtain a compliance risk trend graph aiming at the penalty information fields.

Optionally, in an example of the above aspect, further comprising: and pushing the generated early warning image to related personnel.

Optionally, in an example of the above aspect, pushing the generated early warning map to the relevant person includes: and pushing the generated early warning image to related personnel according to the punishment information field and the pushing keyword.

Optionally, in one example of the above aspect, the penalty information field includes at least one of a penalty text number, a regulatory agency name, a penalized agency name, a penalty time, a penalty area, a penalty amount, and a penalty event routing.

According to another aspect of embodiments herein, there is also provided an apparatus for visual analysis of financial penalty data, comprising: the information crawling unit is used for crawling financial penalty information from the financial supervision website by using a web crawler; the information structured analysis unit is used for carrying out structured analysis on the crawled financial punishment information so as to obtain punishment field data corresponding to the punishment information field; the data clustering analysis unit is used for carrying out clustering analysis on the obtained penalty field data to obtain penalty statistic corresponding to each penalty information field; and the early warning graph generating unit is used for generating an early warning graph aiming at the compliance risk according to the penalty statistic obtained by the clustering analysis and the corresponding penalty information field.

Optionally, in an example of the above aspect, each penalty information field includes a plurality of field data categories, and the warning map generating unit: when the penalty statistic corresponding to the field data category in the penalty information field is larger than a penalty threshold, determining that compliance risk exists for the penalty information field; and generating an early warning graph aiming at the penalty information field according to the penalty statistic corresponding to the penalty information field with the compliance risk.

Optionally, in an example of the above aspect, further comprising: and the risk trend prediction unit is used for providing the penalty statistics corresponding to the penalty information field with the compliance risk to the trained compliance risk prediction model so as to predict and obtain a compliance risk trend graph aiming at the penalty information field.

Optionally, in an example of the above aspect, further comprising: and the early warning image pushing unit is used for pushing the generated early warning image to related personnel.

Optionally, in an example of the above aspect, the warning map pushing unit: and pushing the generated early warning image to related personnel according to the punishment information field and the pushing keyword.

According to another aspect of embodiments herein, there is also provided an electronic device, including: at least one processor; and a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform a method for visual analysis of financial penalty data as described above.

According to another aspect of embodiments herein, there is also provided a machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the method for visual analysis of financial penalty data as described above.

Drawings

A further understanding of the nature and advantages of the present disclosure may be realized by reference to the following drawings. In the drawings, similar components or features may have the same reference numerals.

Fig. 1 shows a flowchart of one example of a method for visually analyzing financial penalty data in an embodiment of the present specification.

Fig. 2 is a schematic diagram illustrating an example of penalty field data corresponding to a resulting penalty information field provided by an embodiment of the present specification.

Fig. 3A is a schematic diagram illustrating an example of an early warning diagram according to an embodiment of the present specification.

Fig. 3B is a schematic diagram illustrating another example of an early warning diagram according to an embodiment of the present disclosure.

FIG. 4 illustrates a block diagram of one example of an apparatus for visual analysis of financial penalty data in accordance with embodiments of the present description.

Fig. 5 illustrates a block diagram of an electronic device implementing a method for visual analysis of financial penalty data according to an embodiment of the present description.

Detailed Description

The subject matter described herein will be discussed with reference to example embodiments. It should be understood that these embodiments are discussed only to enable those skilled in the art to better understand and thereby implement the subject matter described herein, and are not intended to limit the scope, applicability, or examples set forth in the claims. Changes may be made in the function and arrangement of elements discussed without departing from the scope of the disclosure. Various examples may omit, substitute, or add various procedures or components as needed. In addition, features described with respect to some examples may also be combined in other examples.

As used herein, the term "include" and its variants mean open-ended terms in the sense of "including, but not limited to. The term "based on" means "based at least in part on". The terms "one embodiment" and "an embodiment" mean "at least one embodiment". The term "another embodiment" means "at least one other embodiment". The terms "first," "second," and the like may refer to different or the same object. Other definitions, whether explicit or implicit, may be included below. The definition of a term is consistent throughout the specification unless the context clearly dictates otherwise.

In this specification, the term "compliance" means that the financial institution's business activities are in accordance with laws, rules and guidelines. The term "compliance risk" refers to the risk that a financial institution fails to comply with legal regulations, regulatory requirements, rules, relevant guidelines set by an autonomic organization, behavioral guidelines that have been applied to the bank's own business activities, and may be subject to legal sanctions or regulatory penalties, significant financial loss, or loss of reputation.

Fig. 1 illustrates a flow chart of one example of a method 100 for visual analysis of financial penalty data in an embodiment of the present description.

As shown in FIG. 1, at 110, the financial penalty information is crawled from a financial administration website using a web crawler.

In the embodiment of the present specification, the financial supervision website may be designated, for example, an official website of the chinese people bank, the chinese certificate and the chinese bank insurance. The financial penalty information is the penalty information of the financial supervision institution to the financial institution, and the financial penalty information of the public can include files in the formats of webpage text, word, pdf, excel, picture and the like.

In embodiments of the present specification, the web crawlers may include general web crawlers, focused web crawlers, and the like. In one example, the web crawler may crawl all information in the various financial regulatory websites, including all web pages and attachment resources of the various financial regulatory websites, including financial penalty information and other information. And after the financial punishment information is crawled to the local, the financial punishment information is screened from the crawled information. In the example, the web crawler only needs to execute crawling operation, and does not need to execute operations such as information screening and the like at the same time, so that the crawling efficiency of the web crawler is improved.

In another example, the web crawler may crawl only financial penalty information in various financial regulatory websites, which may be sourced from web pages, attachments, etc. For example, a web crawler may filter and crawl financial penalty information in a web page through a regularized expression. Like this, reduced the amount of crawling of web crawler from each financial supervision website, the information that web crawler crawled is financial punishment information basically moreover to the information quality that web crawler crawled is higher.

The web crawler may crawl financial penalty information at specified times, which may be specified time points or specified time intervals.

When the financial supervision website comprises a plurality of financial penalty information issued at different time points, the network crawler can determine the time point of the last crawling each time, and then crawl the financial penalty information from the time point of the last crawling to the current time point. Repeated crawling can be avoided, and crawling efficiency of the web crawler is improved.

In the embodiment of the specification, the financial penalty is only made by a specific financial supervision institution, the financial penalty information is also disclosed by the financial supervision institution making the penalty, the financial penalty information disclosed on the financial supervision website is generally issued for the first time, and the financial penalty information on other websites can be the same financial penalty information transferred from the financial supervision website. Therefore, in the embodiment of the specification, the financial penalty information is crawled from the designated financial supervision website in a targeted manner, the whole-network crawling is not needed, the crawling information amount is reduced, the crawling efficiency of the web crawler is higher, the financial penalty information crawled from the financial supervision website is released for the first time, repeated financial penalty information crawled from other websites is avoided, and the crawling information quality is improved.

After the financial penalty information is crawled, at 120, the crawled financial penalty information is structurally analyzed to obtain penalty field data corresponding to the penalty information field.

In the embodiment of the present specification, the penalty information field is used to indicate a structured field, and may include at least one of fields of a penalty text number, a regulatory agency name, a name of a mechanism to be penalized, a penalty time, a penalty area, a penalty amount, and a penalty routing. The penalty field data corresponding to the penalty information field is structured data stored in the field indicated by the penalty information field.

The financial punishment information is used for uniquely identifying the financial punishment information. The penalty reasons can include credit management violation, case prevention and control management insufficiency, business violation outside the meter, internal control management insufficiency, credit management violation, employee behavior violation, regulation violation supervision index or supervision index non-compliance, and investment business violation development.

The financial penalty information may be pre-processed before being structurally analyzed. Specifically, financial penalty information in various formats can be converted into text information in a uniform format, so that detailed data can be extracted from each piece of financial penalty information conveniently in the following process. Then, semantic recognition processing is performed on each text message, and each text message is arranged into corresponding detail data, wherein the detail data are specific and detailed data from the corresponding text message.

For example, a content of financial penalty information is that "branch office in bank B area a violates" business bank financing product sales management method "thirteenth article because non-standard financing investment information is not sufficiently disclosed," notification about issues related to the operation of financing business of regulation business of business bank "third article," third article "supervision and management law of the banking industry of the republic of china" forty-six article, and 20 ten thousand yuan of penalized renminbi ", and detail data corresponding to the financial penalty information obtained through the above preprocessing includes: bank A, branch bank B, non-standard financing investment information disclosure is insufficient, and the fine RMB is 20 ten thousand yuan.

And carrying out structured analysis on the detail data obtained by preprocessing, and sorting the detail data into structured data. For the detail data obtained by converting financial penalty information, the structured data after being sorted can include: title, time of release, name of unit of release, number of penalty text, name of regulatory agency, name of agency to be penalized, time of penalty, region of penalty, amount of penalty, and cause of penalty, etc. In the above example, the obtained detail data is subjected to structured analysis, and the obtained structured data includes: name of the punished agency: bank a, branch in area B, punish area: region B, penalty issues by: the non-standard financing investment information is not fully disclosed, and the penalty amount is: 20 ten thousand yuan RMB.

Each financial penalty information may correspond to a plurality of structured data, each structured data corresponding to a structured field. After structured parsing, structured data corresponding to the penalty information field (i.e., penalty field data) is screened out from the structured data after structured parsing.

Taking fig. 2 as an example, fig. 2 shows a schematic diagram of an example 200 of penalty field data corresponding to a resulting penalty information field provided by an embodiment of the present specification.

As shown in fig. 2, the penalty information field includes a penalty text number, a supervision agency name, a penalized agency name, a penalty time, a penalty area, a penalty amount and a penalty event manager, and each financial penalty information corresponds to a set of penalty field data, and each set of penalty field data includes penalty field data corresponding to the above 7 types of penalty information fields.

Specifically, for the financial penalty information 1, the penalty field data corresponding to the obtained penalty information field includes: the penalty field data corresponding to the penalty text book number is No. 3 [2001], the penalty field data corresponding to the supervision institution name is China Miner Bank, the penalty field data corresponding to the punished institution name is Bank B, the penalty field data corresponding to the penalty time is 1/2/2001, the penalty field data corresponding to the penalty area is B, the penalty field data corresponding to the penalty amount is 20 ten thousand RMB, and the penalty event is not fully revealed by the non-standard financial investment information corresponding to the penalty field data.

For the financial penalty information 2, the penalty field data corresponding to the obtained penalty information field includes: the penalty field data corresponding to the penalty text book number is [2006] No. 4, the penalty field data corresponding to the supervision institution name is China banking prison, the penalty field data corresponding to the penalized institution name is C Bank D, the penalty field data corresponding to the penalty time is 2006, 7, 6, 7, 2006, D, the penalty field data corresponding to the penalty area, 50 million RMB, and the penalty event is the management lost after loan according to the corresponding penalty field data.

In an example, the obtained penalty field data corresponding to each penalty information field may be returned to the relational database for storage, so that the online front-end device can obtain the penalty field data of each penalty information field in real time, perform visual analysis based on the obtained penalty field data, and obtain a visual analysis graph in real time.

Next, at 130, the obtained penalty field data is subjected to cluster analysis to obtain penalty statistics corresponding to each penalty information field.

In one example, a cluster analysis is performed for all penalty information fields corresponding to the resulting penalty field data. And classifying all the penalty field data corresponding to the penalty information field aiming at each penalty information field, aggregating the penalty field data belonging to the same field data type, and then counting the number of the penalty field data included in each field data type in the penalty information field.

For example, the penalty information fields included in the obtained penalty field data include a penalty text number, a regulatory agency name, a name of a mechanism to be penalized, a penalty time, a penalty area, a penalty amount, and a penalty cause, and then cluster analysis is performed for each of the penalty information fields. Taking cluster analysis for the penalty area as an example, the penalty area comprises all provinces, and the penalty statistic of each province is counted according to the penalty field data corresponding to the penalty area, wherein the penalty statistic of all provinces is the penalty statistic for the penalty area.

In the example, all the penalty information fields corresponding to the penalty field data are subjected to cluster analysis, so that the penalty statistic corresponding to each penalty information field can be obtained in real time when visual analysis is subsequently performed, cluster analysis is not required to be performed again, and timeliness of the visual analysis is improved.

In another example, the cluster analysis may be performed only for the designated penalty information field, resulting in the penalty statistics corresponding to the designated penalty information field. The designated penalty information field may be determined according to the point of interest for which the compliance risk is directed. For example, the point of interest for which a compliance risk is targeted may be a compliance risk for a penalty area, a compliance risk for various penalty issues, and the like. For example, the compliance risk for which the visual analysis is directed is that of a penalty area, and the purpose of the visual analysis is to alert the area where there is a compliance risk, based on which the specified penalty information field includes the penalty area.

Further, for one penalty information field, if the penalty information field corresponds to penalty field data of multiple field data types, cluster analysis may be performed only on the penalty field data of the specified field data type, so as to obtain a penalty statistic corresponding to the specified field data type.

For example, in the obtained penalty field data, the field data categories corresponding to the penalty regions include regions such as the Zhejiang, Henan, Shandong, and Shaanxi regions, and three regions such as the Zhejiang, Henan, and Shandong regions may be used as the designated field data categories, and then the cluster analysis is performed on the penalty field data corresponding to the three regions to obtain the penalty statistic corresponding to the three regions.

In the above example, only the data of the designated penalty field is subjected to cluster analysis, so that the data amount of the cluster analysis is reduced, the efficiency of the cluster analysis is improved, the efficiency of generating the early warning diagram is higher, and the timeliness of the visual analysis is improved.

At 140, an early warning map for regulatory risk is generated according to the penalty statistics obtained by the cluster analysis and the corresponding penalty information fields.

The early warning map can be any one of display maps such as a pie chart, a histogram, a line chart and a map. In one example, the display graph type adopted by the early warning graph can be determined according to the penalty information field aimed at by the early warning graph. For example, when the early warning map is directed to a plurality of penalty information fields, each penalty information field corresponds to one dimension and one dimension corresponding to the penalty statistics, the early warning map needs to display the penalty statistics corresponding to the plurality of penalty information fields from at least three dimensions, and based on this, the early warning map may adopt a histogram or a line graph, etc. capable of displaying at least three dimensions.

In another example, the display graph type adopted by the warning graph can be further determined according to a data comparison form required to be displayed by the warning graph, wherein the data comparison form comprises a proportion comparison form, a gradient form, a continuous variation form, a region comparison form and the like. When the proportion of the data is required to be displayed in the early warning graph, a pie graph can be adopted; when the early warning graph needs to display the difference of data in a gradient form, a histogram can be adopted; when the early warning graph needs to show the change trend of the data in a continuous change form, a line graph can be adopted, and when the early warning graph needs to show the data related to the region in a region comparison form, a map can be adopted.

Each generated early warning map may be directed to one or more penalty information fields. Taking fig. 3A and 3B as an example, fig. 3A and 3B show schematic diagrams of an example of an early warning diagram of an embodiment of the present specification. The warning map shown in fig. 3A is the penalty statistics for the penalty area and the warning map shown in fig. 3B is for the financial statistics or delivery violations, penalty amount, and penalty time in the penalty event.

The early warning graph can reflect the penalty statistic and the change situation corresponding to each field data type in the corresponding penalty information field, and for the field data type with larger penalty statistic reflected by the early warning graph or the field data type with continuously rising corresponding penalty statistic, the possibility that the business related to the field data type has the risk of compliance is shown, and the business related to the field data type needs to be paid attention in the compliance.

In one example of an embodiment of the present specification, each penalty information field may include a plurality of field data categories. For example, the penalty information field "penalty region" may include field data categories of Zhejiang, Henan, Shandong, etc., and the penalty information field "penalty event routing" may include field data categories of credit management violations, off-table traffic violations, credit management violations, etc.

The obtained penalty statistics corresponding to the penalty information field may include penalty statistics corresponding to each field data category in the penalty information field, and the penalty statistics corresponding to each field data category is compared with a corresponding penalty amount threshold.

In this example, the penalty amount threshold may be specified. In one example, one penalty information field corresponds to one penalty amount threshold, and different penalty information fields may correspond to different penalty amount thresholds. Each field data category belonging to the same penalty information field is compared to the same penalty amount threshold. In another example, one penalty information field may correspond to multiple penalty amount thresholds, and the penalty amount thresholds may differ for different field data categories. In this example, different penalty amount thresholds may be set in a targeted manner according to different field data categories, and the penalty amount thresholds may be set according to characteristics of the field data categories, so that subsequent determination of compliance risks is more accurate.

For example, for a penalty area (penalty information field), the provinces in the eastern region (corresponding field data categories) may have more financial institutions than the provinces in the western region (corresponding field data categories), and thus, the penalty amount threshold value for each province in the eastern region may be larger and the penalty amount threshold value for each province in the western region may be smaller.

Determining whether there is a compliance risk for the penalty information field based on a comparison of the penalty statistic corresponding to each field data category to a penalty amount threshold.

In one example, when there is at least one penalty statistic in the penalty information field corresponding to a field data category that is greater than a penalty amount threshold, it may be determined that a compliance risk exists for the penalty information field.

In another example, the number of field data categories in the statistical penalty information field for which the corresponding penalty statistic is greater than the penalty amount threshold may be determined to be at risk of compliance when the counted number is greater than a specified number threshold. When the counted number is not greater than the specified number threshold, it may be determined that there is no compliance risk for the penalty information field. In the absence of compliance risk, the early warning map for the penalty information field may not be generated.

In this example, the specified quantity threshold may be specified, and the specified quantity threshold may be determined according to the number of field data categories in the penalty information field. The specified number thresholds may be different for different penalty information fields. For example, if the specified number threshold is one third of the number of field data categories in the penalty information field, it may be determined that there is a compliance risk for the penalty information field when the penalty statistic corresponding to more than one third of the field data categories in the penalty information field is greater than the penalty number threshold.

When it is determined that the compliance risk exists for the penalty information field, an early warning map for the penalty information field can be generated according to the penalty statistic corresponding to the penalty information field with the compliance risk. For example, the penalty information field that determines that there is a compliance risk is a penalty area, and the penalty information field includes field data of the following types: zhejiang, Henan, Shandong, Shaanxi, Jiangsu, Hunan, Guangdong, Anhui, Fujian and Hubei, each province corresponds to one penalty statistic, and then an early warning graph generated according to the penalty statistics of the 10 provinces is shown in FIG. 3B.

In an example of the embodiment of the present specification, for the penalty information field with compliance risk, a penalty statistic corresponding to the penalty information field with compliance risk may also be provided to the trained compliance risk prediction model, so as to predict a compliance risk trend graph for the penalty information field.

The compliance risk prediction model may be a machine learning model, and the compliance risk prediction model may be trained using historical financial penalty information data for each penalty information field. The trained compliance risk prediction model can output a compliance risk trend graph aiming at the penalty information field according to the penalty statistic corresponding to the input penalty information field, the compliance risk trend graph can show penalty number trends corresponding to all field data types in the penalty information field, and whether compliance risks exist in the penalty information field can be predicted according to the penalty number trends of all field data types.

After the early warning map for the regulatory risk is generated, the generated early warning map can be pushed to related personnel. In one example, the generated early warning map may be pushed directly to the relevant personnel in response to the early warning map generation. In this example, the device that generates the early warning map may be actively pushed to the relevant personnel at the time of early warning map generation. For related personnel, the early warning graph of the compliance risk can be acquired in real time without request operation, convenience is provided for the related personnel, the related personnel can know the compliance risk condition in time, corresponding measures can be taken in time, and violation punishment is avoided.

In another example, the generated early warning map may be pushed to the relevant person in response to a request by the relevant person. In the example, pushing is carried out according to the request of related personnel, more pertinence is achieved, the pushing efficiency is higher, personnel with demands can receive the early warning image in time, and personnel without demands cannot be disturbed by the pushing information.

In another example, the warning map may be pushed to all relevant persons, for example, all staff in the financial institution, so that all relevant persons can acquire the warning map, and any one of the relevant persons is prevented from being missed.

In another example, the warning map can be pushed to designated related personnel, so that the warning map is pushed in a targeted manner, and the situation that the warning map is pushed to unspecified personnel is avoided, and the unspecified personnel cannot be disturbed by the push message.

In another example, the relevant people to be pushed may be determined from the penalty information field and the push keyword. The push keywords correspond to related persons to be pushed, the push keywords may be determined according to the corresponding related persons to be pushed, and the push keywords may be feature words of the corresponding related persons, such as region features, work field features, work content features, and the like. For example, if the relevant person to be pushed is located in zhejiang, the pushing keyword corresponding to the person includes zhejiang. For another example, if the relevant person to be pushed is a person in a compliance department of a financial institution, the pushing keyword corresponding to the person may include: the name of the financial institution, the name of the compliance department and other work field characteristic words. For another example, if the work content of the relevant person to be pushed relates to credit management work, the push keyword corresponding to the person may include work content feature words such as credit, credit management, and the like.

The corresponding relation between the pushing keywords and the related personnel can be preset, the penalty information field aimed at by the early warning image is matched with the pushing keywords, if the penalty information field is matched with the pushing keywords, the related personnel corresponding to the matched pushing keywords are determined according to the preset corresponding relation, and then the early warning image is pushed to the related personnel.

For example, the penalty information field is a penalty region, the field data types in the penalty information field include zhejiang, south of the river and east of the mountain, the determined push keywords of the relevant persons are zhejiang, south of the river and east of the mountain, respectively, and the generated early warning maps are pushed to the relevant persons corresponding to the push keywords of zhejiang, south of the river and east of the mountain, respectively.

Further, the field data type with the compliance risk in the penalty information field can be matched with the pushing keyword, and only the early warning graph is pushed to the related personnel related to the field data type with the compliance risk.

By setting the push keywords in the above example, the relevant persons to be pushed are determined according to the push keywords in the process of generating the early warning diagram each time, and thus, the process of each time is only pushed to specific relevant persons. In addition, different early warning image pushes related personnel determined according to the penalty information fields and the push keywords of the early warning image pushed at this time can be different, and the related personnel determined by each time of pushing is only related to the process, so that personalized service pushed at each time is realized.

Fig. 4 shows a block diagram of an example of an apparatus for performing visual analysis of financial penalty data (hereinafter referred to as a visual analysis apparatus 400) according to an embodiment of the present specification.

As shown in fig. 4, the visualization analyzing apparatus 400 may include an information crawling unit 410, an information structure parsing unit 420, a data cluster analyzing unit 430, and an advance warning map generating unit 440.

The information crawling unit 410 is configured to crawl financial penalty information from a financial administration website using a web crawler. The operation of the information crawling unit 410 may refer to the operation of block 110 described above with reference to fig. 1.

The information structural analysis unit 420 is configured to perform structural analysis on the crawled financial penalty information to obtain penalty field data corresponding to the penalty information field. The operation of the information structure analysis unit 420 may refer to the operation of block 120 described above with reference to fig. 1.

The data cluster analysis unit 430 is configured to perform cluster analysis on the obtained penalty field data to obtain penalty statistics corresponding to each penalty information field. The operation of the data cluster analysis unit 430 may refer to the operation of block 130 described above with reference to fig. 1.

The early warning map generating unit 440 is configured to generate an early warning map for the compliance risk according to the penalty statistics obtained by the cluster analysis and the corresponding penalty information fields. The operation of the warning map generation unit 440 may refer to the operation of block 140 described above with reference to fig. 1.

In one example, each penalty information field includes a plurality of field data categories, and the warning map generation unit 440 is configured to: when the penalty statistic corresponding to the field data category in the penalty information field is larger than a penalty threshold, determining that compliance risk exists for the penalty information field; and generating an early warning graph aiming at the penalty information field according to the penalty statistic corresponding to the penalty information field with the compliance risk.

In one example, the visualization analyzing apparatus 400 may further include a risk trend prediction unit, and the risk trend prediction unit may be configured to provide the penalty statistics corresponding to the penalty information field for which the compliance risk exists to the trained compliance risk prediction model to predict the compliance risk trend map for the penalty information field.

In one example, the visualization analysis apparatus 400 may further include an early warning graph pushing unit, and the early warning graph pushing unit may be configured to push the generated early warning graph to the related person, and may be further configured to push the generated early warning graph to the related person according to the penalty information field and the pushing keyword.

Embodiments of methods and apparatus for visual analysis of financial penalty data according to embodiments herein are described above with reference to fig. 1-4.

The device for visually analyzing the financial penalty data according to the embodiments of the present disclosure may be implemented by hardware, software, or a combination of hardware and software. The software implementation is taken as an example, and is formed by reading corresponding computer program instructions in the storage into the memory for operation through the processor of the device where the software implementation is located as a logical means. In the embodiments of the present specification, the means for visually analyzing the financial penalty data may be implemented, for example, using electronic equipment.

Fig. 5 illustrates a block diagram of an electronic device 500 implementing a method for visual analysis of financial penalty data according to embodiments of the present description.

As shown in fig. 5, the electronic device 500 may include at least one processor 510, a storage (e.g., non-volatile storage) 520, a memory 530, and a communication interface 540, and the at least one processor 510, the storage 520, the memory 530, and the communication interface 540 are connected together via a bus 550. The at least one processor 510 executes at least one computer-readable instruction (i.e., the elements described above as being implemented in software) stored or encoded in memory.

In one embodiment, computer-executable instructions are stored in the memory that, when executed, cause the at least one processor 510 to: crawling financial penalty information from a financial supervision website by using a web crawler; performing structured analysis on the crawled financial punishment information to obtain punishment field data corresponding to a punishment information field; performing clustering analysis on the obtained penalty field data to obtain penalty statistics corresponding to each penalty information field; and generating an early warning map for the regulatory risk according to the penalty statistic obtained by the clustering analysis and the corresponding penalty information field.

It should be appreciated that the computer-executable instructions stored in the memory, when executed, cause the at least one processor 510 to perform the various operations and functions described above in connection with fig. 1-4 in the various embodiments of the present description.

According to one embodiment, a program product, such as a machine-readable medium, is provided. A machine-readable medium may have instructions (i.e., elements described above as being implemented in software) that, when executed by a machine, cause the machine to perform various operations and functions described above in connection with fig. 1-4 in the various embodiments of the present specification.

Specifically, a system or apparatus may be provided which is provided with a readable storage medium on which software program code implementing the functions of any of the above embodiments is stored, and causes a computer or processor of the system or apparatus to read out and execute instructions stored in the readable storage medium.

In this case, the program code itself read from the readable medium can realize the functions of any of the above-described embodiments, and thus the machine-readable code and the readable storage medium storing the machine-readable code constitute a part of the embodiments of the present specification.

Computer program code required for the operation of various portions of the present 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 2003, Perl, COBOL 2002, PHP, and ABAP, a dynamic programming language such as Python, Ruby, and Groovy, or other programming languages. The program code may execute on the user's computer, or on the user's computer as a stand-alone software package, or partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. 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).

Examples of the readable storage medium include floppy disks, hard disks, magneto-optical disks, optical disks (e.g., CD-ROMs, CD-R, CD-RWs, DVD-ROMs, DVD-RAMs, DVD-RWs), magnetic tapes, nonvolatile memory cards, and ROMs. Alternatively, the program code may be downloaded from a server computer or from the cloud via a communications network.

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

Not all steps and elements in the above flows and system structure diagrams are necessary, and some steps or elements may be omitted according to actual needs. The execution order of the steps is not fixed, and can be determined as required. The apparatus structures described in the above embodiments may be physical structures or logical structures, that is, some units may be implemented by the same physical entity, or some units may be implemented by a plurality of physical entities, or some units may be implemented by some components in a plurality of independent devices.

The term "exemplary" used throughout this specification means "serving as an example, instance, or illustration," and does not mean "preferred" or "advantageous" over other embodiments. The detailed description includes specific details for the purpose of providing an understanding of the described technology. However, the techniques may be practiced without these specific details. In some instances, well-known structures and devices are shown in block diagram form in order to avoid obscuring the concepts of the described embodiments.

Although the embodiments of the present disclosure have been described in detail with reference to the accompanying drawings, the embodiments of the present disclosure are not limited to the specific details of the embodiments, and various simple modifications may be made to the technical solutions of the embodiments of the present disclosure within the technical spirit of the embodiments of the present disclosure, and all of them fall within the scope of the embodiments of the present disclosure.

The previous description of the disclosure is provided to enable any person skilled in the art to make or use the disclosure. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the scope of the disclosure. Thus, the description is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for visual analysis of financial penalty data, comprising:

crawling financial penalty information from a financial supervision website by using a web crawler;

performing structured analysis on the crawled financial punishment information to obtain punishment field data corresponding to a punishment information field;

performing clustering analysis on the obtained penalty field data to obtain penalty statistics corresponding to each penalty information field; and

and generating an early warning map for the regulatory risk according to the penalty statistic obtained by the clustering analysis and the corresponding penalty information field.

2. The method of claim 1, wherein each penalty information field comprises a plurality of field data categories,

generating an early warning map for the regulatory risk according to the penalty statistic obtained by the clustering analysis and the corresponding penalty information field comprises the following steps:

when the penalty statistic corresponding to the field data category in the penalty information field is larger than a penalty threshold, determining that compliance risk exists for the penalty information field; and

and generating an early warning graph aiming at the penalty information field according to the penalty statistic corresponding to the penalty information field with the compliance risk.

3. The method of claim 2, wherein the penalty amount threshold is different for each field data category in the penalty information field.

4. The method of claim 2, further comprising:

and providing the penalty statistics corresponding to the penalty information fields with the compliance risks to the trained compliance risk prediction model so as to predict and obtain a compliance risk trend graph aiming at the penalty information fields.

5. The method of claim 1, further comprising:

and pushing the generated early warning image to related personnel.

6. The method of claim 5, wherein pushing the generated early warning map to the relevant personnel comprises:

and pushing the generated early warning image to related personnel according to the punishment information field and the pushing keyword.

7. The method of claim 1, wherein the penalty information field comprises at least one of a penalty text number, a regulatory agency name, a penalized agency name, a penalty time, a penalty area, a penalty amount, and a penalty event routing.

8. An apparatus for visual analysis of financial penalty data, comprising:

the information crawling unit is used for crawling financial penalty information from the financial supervision website by using a web crawler;

the information structured analysis unit is used for carrying out structured analysis on the crawled financial punishment information so as to obtain punishment field data corresponding to the punishment information field;

the data clustering analysis unit is used for carrying out clustering analysis on the obtained penalty field data to obtain penalty statistic corresponding to each penalty information field; and

and the early warning map generating unit is used for generating an early warning map for the compliance risk according to the penalty statistic obtained by the clustering analysis and the corresponding penalty information field.

9. The apparatus of claim 8, wherein each penalty information field comprises a plurality of field data categories,

the early warning map generation unit:

10. The apparatus of claim 9, further comprising:

and the risk trend prediction unit is used for providing the penalty statistics corresponding to the penalty information field with the compliance risk to the trained compliance risk prediction model so as to predict and obtain a compliance risk trend graph aiming at the penalty information field.

11. The apparatus of claim 8, further comprising:

and the early warning image pushing unit is used for pushing the generated early warning image to related personnel.

12. The apparatus of claim 11, wherein the warning map pushing unit:

13. An electronic device, comprising:

at least one processor, and

a memory coupled with the at least one processor, the memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the method of any of claims 1-7.

14. A machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the method of any one of claims 1 to 7.