WO2024040817A1

WO2024040817A1 - Bond risk information processing method based on big data and related device

Info

Publication number: WO2024040817A1
Application number: PCT/CN2022/140776
Authority: WO
Inventors: 刘蕾
Original assignee: 深圳市富途网络科技有限公司
Priority date: 2022-08-25
Filing date: 2022-12-21
Publication date: 2024-02-29
Also published as: CN115470785A

Abstract

The present application discloses a bond risk information processing method based on big data and a related device. The method comprises: performing word segmentation processing on risk information of an issuing object corresponding to a target bond to obtain a plurality of corresponding content words, the risk information comprising financial information, credit information, and historical default information that correspond to the issuing object; determining a feature vector of the risk information on the basis of an importance parameter of a content word matched with a preset keyword table, the keyword table comprising a plurality of keywords related to a preset risk event; matching the feature vector with risk events in a preset risk event library to obtain a target risk event matched with the feature vector, the risk event library comprising a plurality of risk events; and performing risk warning on the basis of the target risk event.

Description

Bond risk information processing methods and related equipment based on big data

Cross-references to related applications

This application requests the priority of the Chinese patent application number "202211032661.3", which was submitted on August 25, 2022 and is titled "Bond risk information processing method and related equipment based on big data". All the Chinese patent applications The contents are incorporated into this application by reference.

Technical field

This application relates to the field of big data technology, specifically, to a bond risk information processing method and related equipment based on big data.

Background technique

Bonds are an important investment tool. When customers invest in bonds, they may gain income or bear certain transaction risks. Among them, the risks of trading bonds include but are not limited to: credit risk, liquidity risk, currency risk, interest rate risk, market risk, etc. If customers choose to invest in high-interest bonds or certain bonds with unique characteristics and risks, they will bear higher risks. For example, if a bond defaults, customers may even lose their principal. Therefore, it is necessary for customers to understand the characteristics of bond products and the degree of risk they need to bear before they make transactions. The data used by related technologies to conduct risk assessment on bonds is too simple, and the risk value obtained through analysis has a large error, which in turn leads to errors in risk warnings, and in turn causes the problem of incomplete data display in the bond trading process.

Technical solutions

In order to solve the above technical problems, embodiments of the present application provide a bond risk information processing method and related equipment based on big data.

According to one aspect of the embodiment of the present application, a bond risk information processing method based on big data is provided, which includes: performing word segmentation processing on the risk information of the issuance object corresponding to the target bond to obtain multiple corresponding content words. The risk information includes issuance Financial information, credit information and historical default information corresponding to the object; determine the feature vector of the risk information based on the importance parameters of the content words matching the preset keyword table. The keyword table includes multiple keys related to the preset risk events. word, where the importance parameter is used to represent the importance of the corresponding target content word to the risk information; the feature vector is matched with the risk events in the preset risk event library to obtain the target risk event that matches the feature vector, and the risk event The library includes multiple risk events; risk reminders are provided based on target risk events.

According to one aspect of the embodiment of the present application, a bond risk information processing device based on big data is provided, including: a word segmentation processing module, used to perform word segmentation processing on the risk information of the issuance object corresponding to the target bond, and obtain multiple corresponding content words, The risk information includes financial information, credit information and historical default information corresponding to the issuance object; the determination module is used to determine the feature vector of the risk information based on the importance parameters of the content words that match the preset keyword table. The keyword table includes multiple Keywords related to preset risk events, in which the importance parameter is used to represent the importance of the corresponding target content word to the risk information; the matching module is used to match the feature vector with the risk events in the preset risk event library , obtain the target risk event that matches the feature vector, and the risk event library includes multiple risk events; the risk prompt module is used to provide risk prompts based on the target risk event.

In an exemplary embodiment, the determination module includes a matching unit, a determination unit and a feature vector acquisition unit, wherein the matching unit is used to match each content word with the keyword table respectively to obtain the target content word; the determination unit is used to determine each target Importance parameters of content words; the feature vector acquisition unit is used to use a vector composed of importance parameters of each target content word as a feature vector.

In an exemplary embodiment, the big data-based bond risk information processing device provided in this embodiment also includes a calculation module, wherein the calculation module is used to use the target matching degree as the weight of the risk event score value corresponding to the target risk event, Calculate the weighted sum of the risk event score values of the target risk event, and use the weighted sum as the risk score value of the target bond. The target matching degree is the matching degree between the target risk event and the feature vector. The risk event library includes risk event score values corresponding to each risk event.

In an exemplary embodiment, the risk prompt module includes a response unit and a loading unit, wherein the response unit is configured to obtain the target risk event and the risk score value in response to the first operation instruction for the target bond triggered in the bond trading page; The loading unit is used to load target risk events and risk score values into the bond trading page.

In an exemplary embodiment, the loading unit is also used to associate the risk level, target risk event, and risk score value of the target bond with the target bond, and load the associated risk level, target risk event, and risk score value into the bond. On the transaction page, the risk level is determined based on the risk score value.

In an exemplary embodiment, the loading unit is also used to bring the risk level, target risk event, risk score value and target bond into the pre-generated risk prompt field template to obtain the corresponding risk prompt field.

In an exemplary embodiment, the big data-based bond risk information processing device provided in this embodiment also includes a response module, configured to load bond information in response to the second operation instruction for the bond information link triggered in the bond transaction page. The information page corresponding to the link is used to display risk information. The target bond is associated with the bond information link for the target bond.

According to one aspect of the embodiment of the present application, an electronic device is provided, including a processor and a memory. Computer-readable instructions are stored on the memory. When the computer-readable instructions are executed by the processor, the above big data-based bond risk information is implemented. Approach.

According to an aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor of a computer, the computer is caused to execute the large-scale method as provided above. Data processing methods for bond risk information.

According to an aspect of an embodiment of the present application, a computer program product or a computer program is provided, the computer program product or the computer program including computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the big data-based bond risk information processing method provided in the above various optional embodiments.

In the technical solution provided by the embodiment of this application, the risk information of the issuance object corresponding to the target bond is segmented to obtain multiple corresponding content words. The risk information includes the financial information, credit information and historical default information corresponding to the issuance object; The feature vector of the risk information is determined based on the importance parameters of the content words that match the preset keyword table. The keyword table includes multiple keywords related to the preset risk events, where the importance parameters are used to represent the corresponding target content words. Regarding the importance of risk information; match the feature vector with the risk events in the preset risk event library to obtain the target risk event that matches the feature vector. The risk event library includes multiple risk events; based on the target risk event risk warning. This embodiment determines the feature vector of the risk information based on the importance parameters of the content words that match the preset keyword table. The above method can fully extract the semantic information in the risk information, and thereby more accurately extract the features in the risk information, so that The feature vector corresponding to the obtained risk information is more accurate, and information related to risk events is extracted to avoid unnecessary waste of computing resources and improve the efficiency of big data risk assessment based on bond information; in addition, this embodiment starts from a smaller granularity Start by analyzing possible risk events in risk information, and provide risk reminders based on risk events, so that users can be more clear about the risks brought by bond products.

It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present application.

Description of drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without exerting creative efforts. In the attached picture:

Figure 1 is a flow chart of a bond risk information processing method based on big data according to an exemplary embodiment of the present application;

Figure 2 is a schematic diagram of jumping from the bond trading page to the information page according to an exemplary embodiment;

Figure 3 is a flow chart of a bond risk warning method according to an exemplary embodiment;

Figure 4 is a block diagram of a big data-based bond risk information processing device according to an exemplary embodiment of the present application;

FIG. 5 shows a schematic structural diagram of a computer system suitable for implementing an electronic device according to an embodiment of the present application.

Detailed ways

Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the appended claims.

The block diagrams shown in the figures are functional entities only and do not necessarily correspond to physically separate entities. That is, these functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and/or processor devices and/or microcontroller devices. entity.

The flowcharts shown in the drawings are only illustrative, and do not necessarily include all contents and operations/steps, nor must they be performed in the order described. For example, some operations/steps can be decomposed, and some operations/steps can be merged or partially merged, so the actual order of execution may change according to the actual situation.

It should also be noted that the “multiple” mentioned in this application refers to two or more. "And/or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and/or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the related objects are in an "or" relationship.

It should be noted that the network elements involved in the embodiments of this application can also be called functions or functional entities, which are not limited by this application. For example, the access and mobility management function network element may also be called the access and mobility management function or the access and mobility management function entity, and the session management function network element may be called the session management function or session management function entity, etc. The names of each network element are not limited in this application. Those skilled in the art can replace the names of the above network elements with other names to perform the same functions, which all fall within the scope of protection of this application.

In order to better understand and explain the solutions of the embodiments of the present application, the technical terms involved in the embodiments of the present application are briefly described below.

First of all, big data refers to a collection of data that cannot be captured, managed and processed with conventional software tools within a certain time range. It requires new processing models to have stronger decision-making power, insight discovery and process optimization capabilities. Massive, high-growth and diversified information assets. With the advent of the cloud era, big data has also attracted more and more attention. Big data requires special technologies to effectively handle large amounts of data within a tolerable time. Technologies applicable to big data include massively parallel processing databases, data mining, distributed file systems, distributed databases, cloud computing platforms, the Internet, and scalable storage systems. Specifically, as people's economic level continues to improve, investment and financial management have become people's mainstream financial management methods. As one of the investment and financial management methods, bonds have also received considerable attention, especially those based on big data. However, investing in bonds based on big data may yield returns and may also bear certain transaction risks. Therefore, in order to enable customers to understand the characteristics of bond products and the risks they need to bear, it is particularly important to assess and prompt bond transaction risks based on big data.

Bond default refers to the failure of the bond issuer to perform its obligations in accordance with the bond agreement reached in advance. The high incidence of bond defaults in recent years has sounded the alarm to individual and institutional investors. Therefore, it is extremely important to identify the risks that may cause bond defaults. important. Traditional smart bond analysis tools often only provide financial data browsing and simple credit rating functions for bonds. The information content is single. Investors cannot obtain an intuitive evaluation of bonds from the provided financial data and credit ratings, and it is difficult to achieve accurate evaluation of bonds. Comprehensive tracking and control of bond default risk points.

Please refer to Figure 1, which is a flow chart of a bond risk information processing method based on big data according to an exemplary embodiment of the present application. The bond risk information processing method based on big data in this embodiment can be applied to the bond risk reminder device. The bond risk reminder device of this application can be a server, a mobile device, or a system in which a server and a mobile device cooperate with each other. . Correspondingly, various parts included in the mobile device, such as each unit, sub-unit, module, and sub-module, may all be provided in the server, may all be provided in the mobile device, or may be provided in the server and the mobile device respectively.

Further, the above-mentioned server may be hardware or software. When the server is hardware, it can be implemented as a distributed server cluster composed of multiple servers or as a single server. When the server is software, it can be implemented as multiple software or software modules, such as software or software modules used to provide distributed servers, or it can be implemented as a single software or software module, which is not specifically limited here.

It can be understood that in the specific implementation of this application, related data such as bond transactions and user data are involved. When the above embodiments of this application are applied to specific products or technologies, user consent or authorization is required, and The collection, use and processing of relevant data need to comply with relevant laws, regulations and standards of relevant countries and regions.

As shown in Figure 1, in an exemplary embodiment, the bond trading risk warning method based on big data at least includes steps S101 to S104, which are described in detail as follows:

Step S101: Perform word segmentation processing on the risk information of the issuance object corresponding to the target bond to obtain multiple corresponding content words.

In this embodiment, the risk information is information that may cause bond default. The risk information includes financial information, credit information and historical default information corresponding to the issuing object. Since the risk source of a bond is usually closely related to the object to which it is issued, this embodiment performs a risk assessment on the target bond by analyzing the risk information of the object to be issued.

For example, the number of default events that occur in the issuance object within a preset time period. In this embodiment, the default event can be for the target bond or other bonds of the issuance object. There is no specific limit here. . Risk information also includes the financial status of the issuer, credit information, third-party credit rating reports or research reports, etc.

Illustratively, this embodiment can obtain an enterprise's financial data and rating agency rating data from public channels and store them. If there is a null value, it will also be stored as a null value; where the financial information includes the enterprise's operating conditions, the enterprise's Solvency, corporate liabilities, corporate operating conditions further include gross sales profit margin, operating net profit margin, corporate solvency further includes short-term liabilities, quick ratio, operating cash flow/interest-bearing liabilities, corporate liabilities further include assets and liabilities ratio, the adjusted asset-liability ratio of the consolidated statement, and the adjusted asset-liability ratio of the parent company; the rating agency data includes the current rating of the rating agency and the rating outlook of the rating agency; the adjusted asset-liability ratio of the consolidated statement = the adjusted asset-liability ratio of the consolidated statement Total liabilities/total adjusted assets; the parent company’s adjusted asset-liability ratio = total adjusted liabilities/total adjusted assets in the parent company’s statement.

Word segmentation is the process of recombining continuous word sequences into semantically independent word sequences according to certain specifications. Word segmentation is the basis of natural language processing. The accuracy of word segmentation directly determines the quality of subsequent part-of-speech tagging, syntactic analysis, word vectors and text analysis. This embodiment can segment the text through the Chinese word segmentation algorithm. The specific word segmentation process is here Don’t go into too much detail.

Illustratively, the risk information is segmented into words through steps S601 to S602. The details are as follows:

Step S601: Split the document string corresponding to the risk information to obtain multiple strings of different lengths.

This embodiment divides the document string corresponding to the risk information according to the number of characters included in the string. For example, the risk information "The market sentiment faced by Evergrande, which is currently under pressure, has further deteriorated", the risk information corresponding to The document string is divided, and the obtained string including one character includes "objective", "pressure", "de", "field", "emotion", "mood", "hua", "jin", "hua", etc., and the obtained string includes two characters. The string includes "current", "former", "under pressure", "pressured", "ever", "everda", "big firm", "face", "market", etc. The string including three characters includes "currently" "Previously under pressure", "under pressure", "emotional", "further", "market situation", etc., including four-character strings including "previously under pressure", "faced", etc., including five-character strings The string includes "market sentiment", "further deterioration", etc. Since the number of content words does not exceed five characters at most, this embodiment sets the characters included in the string when segmenting the document string corresponding to the risk information. No more than 5, which can save computing resources and speed up word segmentation efficiency.

Step S602: Match each character string with a preset dictionary respectively. If there is a match, determine that the corresponding character string is a content word.

Illustratively, this embodiment matches each character string with a general Chinese dictionary. If a match is found, the corresponding character string is determined to be a content word.

The General Chinese Dictionary contains the main vocabulary commonly used in the language and is suitable for readers from different walks of life to use in the language learning process, such as scholars, students at various stages of learning, language teachers or housewives, etc. The General Chinese Dictionary collects representative commonly used vocabulary from all walks of life for the entire public readership. The vocabulary included in the General Chinese Dictionary is more comprehensive than other special dictionaries.

For example, the content words obtained after word segmentation processing are processed to remove stop words, and meaningless modal particles, adverbs, special symbols and punctuation marks are removed. For example, the content word "的" is deleted to save money in subsequent processing. human resources.

Step S102: Determine the feature vector of the risk information based on the importance parameters of the target content words that match the preset keyword table.

In this embodiment, multiple risk events are pre-configured, and risk events refer to possible default events of bond products. This embodiment can determine multiple risk events based on historical default information of bond products, for example, determine risk events based on machine learning. In this embodiment, risk events include financial, legal, capital, and operating risk events. For example, financial risk events include labels such as changes in capital structure, poor liquidity, and performance losses.

This embodiment pre-constructs a keyword table based on risk events, and the keyword table includes a plurality of keywords related to preset risk events. Keywords related to risk events are characteristic identifiers corresponding to risk events. For example, keywords corresponding to the risk event "poor liquidity" include "liquidity", "poor", etc.

This embodiment considers that the content words obtained by word segmentation of risk information include those related to the corresponding risk event, such as "liquidity", and also include those that are not related to the corresponding risk event, such as some punctuation marks, connectives, etc., and also include Including those related to risk events, this embodiment screens multiple content words obtained by word segmentation of risk events based on the keyword table to determine the target content words that can be used as feature vectors for constructing risk information, thereby speeding up the efficiency of risk assessment. Avoid unnecessary waste of computing resources.

Illustratively, this embodiment can be implemented based on steps S501 to S503. The details are described as follows:

Step S501: Match each content word with the keyword table to obtain the target content word matching the keyword table.

In this embodiment, the content words that match the keyword table are first determined. For example, each content word can be directly compared with the keyword list. If the same keyword as the corresponding content word can be found in the keyword table, the corresponding content word is determined. Content words are matched against the keyword list.

Considering that the content words and the keywords in the keyword list are not exactly the same, there may be relatively strong semantic correlations, such as "liquidity" and "circulation". Illustratively, this embodiment calculates the correlation between each content word and the keyword. If the correlation is greater than the preset threshold, it is determined that the corresponding content word matches the corresponding keyword. If the obtained correlation is less than the preset threshold, and if it is determined that the corresponding content words do not match the keyword list, it means that the corresponding content words do not contribute much to the user's characteristics. Therefore, when determining the feature vector, such content words are discarded. In this embodiment, The above method can fully extract the semantic information in the risk information, and then more accurately extract the features in the risk information, making the obtained feature vector corresponding to the risk information more accurate.

Step S502: Determine the importance parameters of each target content word.

In this embodiment, the importance parameter of the target content word is used to represent the importance of the corresponding target content word to the risk information.

For example, this embodiment can determine the importance parameter of the target content word through the following formula:

Among them, W _{x, y} represents the corresponding importance parameter of the target content word x in the risk information y, tf _{x, y} represents the frequency of the target content word x appearing in the risk information y, N represents the total number of texts included in the risk information y, and df _x represents the number of texts including the target content word x in the total number of texts N.

The inventor of the present application considers that since the importance of content words increases in direct proportion to the number of times they appear in the document, but at the same time decreases inversely proportional to the frequency of their appearance in the corpus, therefore, in this embodiment, tf _{x, y} This parameter is placed in the numerator position of the formula, and represents the importance of the target content word. The parameter is proportional to the frequency of the target content word x appearing in the risk information y; placing the parameter _df The size of the importance parameter is inversely proportional to the number of texts including the target content word x in the total number of texts N. The importance parameter of the content word obtained through the above formula is more accurate.

Step S503: Use a vector composed of importance parameters of each target content word as a feature vector.

For example, the importance parameters of each target content word are arranged according to the order of keywords matching the target content word in the keyword table, thereby obtaining a feature vector.

Exemplarily, the dimensions of the feature vectors corresponding to the risk information are unified. Exemplarily, the dimensions of the feature vectors corresponding to the risk information are preset to be equal to the number of keywords included in the keyword table. According to the number of keywords included in the keyword table, The ranking order sorts the importance parameters corresponding to the target content words to obtain the feature vector. Among them, when the number of target content words corresponding to the risk information is less than the number of keywords included in the keyword table, there will be no target content words and their corresponding keywords. Set the element of the feature vector to 0 at the position of the word.

Step S103: Match the feature vector with the risk events in the preset risk event library to obtain the target risk event that matches the feature vector.

In this embodiment, the risk event library includes risk events of different risk event types. In this step, the server can take known defaulted bonds as examples in advance, analyze the public opinion information of defaulted bonds, and obtain different risk events.

For example, the feature vector corresponding to each risk event is determined based on a text extraction algorithm. Specifically, the label risk information corresponding to multiple risk events is obtained, the label risk information is segmented, the importance parameters corresponding to the multiple content words are counted, and the feature vector corresponding to the risk event is constructed based on the importance parameters corresponding to the multiple content words. .

Illustratively, this embodiment matches the feature vector corresponding to the risk information with the feature vector corresponding to each risk event, and determines the target risk event matching the feature vector based on the obtained matching result. Illustratively, this embodiment calculates the correlation between the feature vector corresponding to the risk information and the feature vector corresponding to each risk event, and uses the risk event corresponding to the correlation degree greater than the preset threshold as the target risk event. It is understandable that the target risk event can be one or more depending on the actual application scenario.

Step S104: Provide risk prompts based on target risk events.

The bond risk information processing method based on big data provided in this embodiment performs word segmentation processing on the risk information of the issuance object corresponding to the target bond to obtain multiple corresponding content words. The risk information includes the financial information, credit information and history corresponding to the issuance object. Default information; determine the feature vector of risk information based on the importance parameters of the content words matching the preset keyword table. The keyword table includes multiple keywords related to the preset risk events, where the importance parameter is used to represent Corresponds to the importance of the target content word to the risk information; matches the feature vector with the risk events in the preset risk event library to obtain the target risk event that matches the feature vector. The risk event library includes multiple risk events; based on the target Provide risk reminders for risk events. This embodiment determines the feature vector of the risk information based on the importance parameters of the content words that match the preset keyword table. The above method can fully extract the semantic information in the risk information, and thereby more accurately extract the features in the risk information, so that The feature vector corresponding to the obtained risk information is more accurate, and information related to risk events is extracted to avoid unnecessary waste of computing resources and improve the efficiency of big data risk assessment based on bond information; in addition, this embodiment starts from a smaller granularity Start by analyzing possible risk events in risk information, and provide risk reminders based on risk events, so that users can be more clear about the risks brought by bond products.

For example, the risk event library includes a risk event score value corresponding to each risk event.

For example, count the number of occurrences of risk events for each historical default bond of the issuer, generate a risk event matrix, calculate the probability value of each risk event based on the risk event matrix, and determine the risk of each risk event based on the probability value of each risk event. Event rating value.

For example, after obtaining risk events from the news corpus data of each historical default bond, obtain the risk events corresponding to all historical default bonds, remove duplicate risk events, obtain a risk event table, and count the risk events corresponding to each historical default bond, Corresponding to the number of occurrences of risk events in the risk event table, a risk event matrix is generated. After obtaining the risk event matrix, calculate the probability value of each risk event when the bond is a default bond, and quantify the obtained probability value into each The risk event score value corresponding to the risk event. For example, if the probability value of the risk event "poor liquidity" is 80% to 89%, then the risk event score value corresponding to the risk event is set to 8. By counting the number of risk events in historical default bonds, we can calculate the probability of risk events in the event of a bond default event based on the number of risk events, and then determine the risk event score value of each risk event to achieve the goal of determining the risk event score based on risk events and defaults. The correlation degree of the bond sets the risk event score value of the risk event, improves the accuracy of the risk event score value, and improves the accuracy of the target bond default risk level in the subsequent process of identifying the default risk of the target bond.

For example, the target matching degree is used as the weight of the risk event score value corresponding to the target risk event, the weighted sum of the risk event score values of the target risk event is calculated, and the weighted sum is used as the risk score value of the target bond. It can be understood that if there is one target risk event, the risk event score value corresponding to the target risk event and the target matching degree are directly multiplied to obtain the risk score value. If there are multiple target risk events, multiple target risks are calculated. The weighted sum of the risk event score values corresponding to the event.

In this embodiment, the target matching degree is the matching degree between the target risk event and the feature vector. In this embodiment, the matching degree between the target risk event and the feature vector can be determined in a variety of ways. For example, the Euclidean distance or cosine value between the target risk event and the feature vector is used as the matching between the target risk event and the feature vector. Spend.

This embodiment uses the matching degree between the target risk event and the feature vector as the weight of the risk event score value corresponding to the target risk event to determine the contribution of the corresponding target risk event to the risk assessment of the target bond, which can more accurately determine the risk assessment of the target bond. Risk score value.

Among related technologies, although the bond trading platform has a function to prompt bond risks, the description of the bond risks is cumbersome and there are no key reminders throughout the article, which is not conducive to customers quickly understanding the characteristics of the corresponding bond products and the risks they need to bear, resulting in information utilization The problem of low rates.

In an exemplary embodiment, step S104 includes steps S201-step S202, which are described in detail as follows:

Step S201: In response to the first operation instruction for the target bond triggered in the bond trading page, obtain the target risk event and risk score value.

The bond trading page refers to the interactive interface used to display or display bonds and bond-related information in the bond risk warning device. For example, it can be a touch screen interface of a mobile terminal, etc. The bond trading page displays bond information. Customers can trigger the first operation instruction for the bond that the user wants to know about based on their own needs. The first operation instruction includes but is not limited to long press, click, double click, drag.

Step S202: Load the target risk event and risk score value on the bond trading page.

Illustratively, the risk warning method provided by this embodiment also includes steps S301 to S302, which are described in detail as follows:

Step S301: Determine the risk level corresponding to the target bond based on the risk score value.

Preset multiple risk levels and the risk score interval corresponding to each risk level. For example, the risk level includes low risk level, medium risk level, high risk level and the highest risk level. Among them, the risk assessment interval corresponding to the low risk level is [ 0, 0.2), the risk assessment interval corresponding to the medium risk level is [0.2, 0.5), the risk assessment interval corresponding to the high risk level is [0.5, 0.8), and the risk assessment interval corresponding to the highest risk level is [0.8, 1].

This embodiment matches the risk score value of the target bond with the risk score interval corresponding to each risk level to determine the risk level of the target bond.

Step S302: Associate the risk level, target risk event, and risk score value with the target bond, and load the associated risk level, target risk event, and risk score value onto the bond transaction page.

This embodiment takes into account that if the risk level, target risk event, risk score value and target bond are loaded separately on the bond trading page, it may not be possible to clearly indicate to the user the risks that the target bond may bring. For example, if the risk level, target risk The events and risk score values are far apart on the bond trading page, and there are no corresponding explanation fields to explain the relationship between them. It is difficult for users to see the risk events, risk score values and risk levels of the target bonds. Based on this, this embodiment associates the risk level with the target risk event and the risk score value with the target bond, so that the user can see the risks brought by the target bond at a glance, avoid misleading the user's bond transaction process, and improve the user experience.

For example, a risk association table is constructed. The risk association table has bond type as the title column. The risk association table includes multiple bond products displayed on the bond transaction page, as well as the risk events, risk score values and risks corresponding to each bond product. grade. Among them, the risk events, risk score values and risk levels corresponding to multiple bond products each occupy one column of the risk association table, and the risk events, risk score values and risk levels corresponding to each bond product occupy one row of the risk association table.

Illustratively, the risk prompt field template is pre-generated, where the risk prompt field template includes four parameters to be brought in, namely, target bond, risk event, risk score value and risk level. For example, the risk prompt field template is " The risk events that may occur in the target bond include the target risk event, the probability of occurrence is the risk score value, and the risk level is the target risk level." In the actual application scenario, the code or name of the target bond, the specific risk event, and the specific risk score value , the specific risk level is brought into the above risk prompt field template, and the risk prompt field can be obtained. For example, if the target risk event is "poor liquidity", the risk score value is 80%, and the risk level is the highest risk level, after associating the target risk event, risk score value and risk level with the target bond, the risk prompt field "Target Bond" will be obtained. "Poor liquidity, risk score value is 80%, risk level is the highest risk level", load the field "Target bond has poor liquidity, risk score value is 80%, risk level is the highest risk level" on the bond trading page. In response to the first operation instruction for the target bond triggered in the bond trading page, the obtained risk prompt field is loaded into the bond trading page.

In this embodiment, the target risk event corresponding to the target bond is displayed on the bond transaction page, so that the user can clearly understand the risk events that may occur in the target bond in the future, as well as the possibility of the risk event occurring, based on the characteristics of the target bond and the responsibilities that need to be borne. The risks are clear at a glance.

For example, in response to the second operation instruction for the bond information link triggered in the bond transaction page, the information page corresponding to the bond information link is loaded. Considering that some users have a need to further understand the risk information of bond products, this embodiment is a bond information link corresponding to the bond product displayed on the bond transaction page. When the user triggers the bond information link, the bond information link corresponding to the bond information link is loaded. information page, and then display the risk information corresponding to the target bond to users.

Refer to Figure 2. Figure 2 is a schematic diagram of jumping from the bond transaction page to the information page in an exemplary embodiment. As shown in Figure 2, the bond transaction page includes multiple bond products, specifically including bbbb, aaaa, cccc, The numbers of bond products such as eeeee, fffff, ggggg, etc., wherein a corresponding interaction button is configured for each bond product. In this embodiment, the interaction button is the "+" symbol on the right side of the number of each bond product. It can be understood that Yes, you can also configure corresponding interaction buttons for bond products by setting other identifiers, which are not specifically limited here. By triggering the interactive button corresponding to the bond product, the user can trigger the second operation instruction for the bond information link, and then load the information page corresponding to the bond information link to display relevant risk warning information. As shown in Figure 2, the information page corresponding to the bond number aaaaa includes the risk information of the bond product. The user can understand the risk status of the corresponding bond product through the risk information displayed on the information page.

Referring to Figure 3, Figure 3 is a flow chart of a bond risk warning method according to an exemplary embodiment. As shown in Figure 3, the bond risk warning method involved in this embodiment is suitable for a risk warning system. In this embodiment , the risk warning system includes users, clients, products, and servers. The bond risk warning method provided in this embodiment includes steps 1 to 5, which are described in detail as follows;

Step 1: Allocate high-risk bonds.

In this embodiment, the product is a bond trading platform, and users can conduct bond transactions through the bond trading platform. For example, the product evaluates high-risk bonds through multiple risk dimensions such as credit risk, default risk, and liquidation risk of the bond, and configures them on the server side.

In this embodiment, high-risk bonds are bonds whose risk score value is greater than the preset threshold among the bonds displayed on the client. The product determines high-risk bonds and low-risk bonds by evaluating the risk score value of each bond product.

Step 2: View bond information.

In this embodiment, the user requests to view bond information from the client. The bond information represents whether the corresponding target bond is a high-risk bond. For example, the user sends a viewing request to the client, where the viewing request includes the target bond and corresponding bond information.

Step 3: Request bond information.

In this embodiment, the client requests bond information from the server, and the client requests bond information from the server. For example, the client forwards the view request sent by the user to the server, so that the server responds to the view request target. Bond bond information is played to the client.

Step 4: Return bond information.

In this embodiment, the server returns bond information to the client.

Step 5: Display bond information.

In this embodiment, the client displays bond information to the user. For example, if the bond information indicates that the target bond is a high-risk bond, the client will display a high-risk warning mark or a high-risk warning bar.

In this embodiment, the client displays bond information to the user so that the user can intuitively understand the bond information of the target bond, that is, can intuitively understand whether the target bond is a high-risk bond. On the one hand, it can avoid the user from blindly conducting bond transactions. Transactions can lead to unnecessary losses. In addition, it can also prevent users from blaming the platform for losses after trading high-risk products, which helps reduce unnecessary risks.

Referring to Figure 4, Figure 4 is a block diagram of a big data-based bond risk information processing device illustrating an exemplary embodiment of the present application. As shown in Figure 4, the big data-based bond risk information processing device 400 includes a word segmentation processing module 401, Determination module 402, matching module 403 and risk prompt module 404.

Among them, the word segmentation processing module 401 is used to segment the risk information of the issuance object corresponding to the target bond to obtain multiple corresponding content words. The risk information includes the financial information, credit information and historical default information corresponding to the issuance object; the determination module 402 uses The feature vector of the risk information is determined based on the importance parameters of the content words that match the preset keyword table. The keyword table includes a plurality of keywords related to the preset risk event; the matching module 403 is used to match the feature vector with the preset risk event. The risk events in the set risk event library are matched to obtain the target risk event that matches the feature vector. The risk event library includes multiple risk events; the risk prompt module 404 is used to provide risk prompts based on the target risk event.

In another exemplary embodiment, the determination module 402 includes a matching unit, a determination unit and a feature vector acquisition unit, wherein the matching unit is used to match each content word with the keyword table respectively to obtain the target content word; the determination unit is used to determine The importance parameters of each target content word; the feature vector acquisition unit is used to use a vector composed of the importance parameters of each target content word as a feature vector.

In another exemplary embodiment, the big data-based bond risk information processing device 400 provided in this embodiment also includes a calculation module, wherein the calculation module is used to use the target matching degree as the risk event score value corresponding to the target risk event. Weight, calculate the weighted sum of the risk event score values of the target risk event, and use the weighted sum as the risk score value of the target bond. The target matching degree is the matching degree between the target risk event and the feature vector. The risk event library includes risk event score values corresponding to each risk event.

In another exemplary embodiment, the risk prompt module 404 includes a response unit and a loading unit, wherein the response unit is used to obtain the target risk event and risk score in response to the first operation instruction for the target bond triggered in the bond trading page. value; the loading unit is used to load target risk events and risk score values into the bond trading page.

In another exemplary embodiment, the loading unit is also used to associate the risk level, target risk event, and risk score value of the target bond with the target bond, and load the associated risk level, target risk event, and risk score value into On the bond trading page, the risk level is determined based on the risk score value.

In another exemplary embodiment, the loading unit is also used to bring the risk level, target risk event, risk score value and target bond into the pre-generated risk prompt field template to obtain the corresponding risk prompt field.

In another exemplary embodiment, the big data-based bond risk information processing device 400 provided in this embodiment also includes an identification adding module, configured to display the target bond on the bond transaction page if the risk level is determined to be the highest risk level. , add an exclamation point mark at the default position on the bond trading page.

In another exemplary embodiment, the big data-based bond risk information processing device 400 provided in this embodiment also includes a response module, configured to load, in response to the second operation instruction for the bond information link triggered in the bond transaction page, The information page corresponding to the bond information link. The information page is used to display risk information. The target bond is associated with the bond information link for the target bond.

It should be noted that the device provided by the above embodiments and the method provided by the above embodiments belong to the same concept. The specific manner in which each module and unit performs operations has been described in detail in the method embodiments and will not be described again here. .

In another exemplary embodiment, the present application provides an electronic device, including a processor and a memory, wherein computer readable instructions are stored on the memory, and when the computer readable instructions are executed by the processor, the above large-scale based on Data processing methods for bond risk information.

It should be noted that the computer system 1000 of the electronic device shown in FIG. 5 is only an example, and should not impose any restrictions on the functions and scope of use of the embodiments of the present application.

As shown in Figure 5, the computer system 1000 includes a central processing unit (Central Processing Unit, CPU) 1001, which can be loaded into a random computer according to a program stored in a read-only memory (Read-Only Memory, ROM) 1002 or from a storage part 1008. Access the program in the memory (Random Access Memory, RAM) 1003 to perform various appropriate actions and processing, such as performing the information recommendation method in the above embodiment. In RAM 1003, various programs and data required for system operation are also stored. CPU 1001, ROM 1002 and RAM 1003 are connected to each other through bus 1004. An input/output (I/O) interface 1005 is also connected to bus 1004.

The following components are connected to the I/O interface 1005: an input part 1006 including a keyboard, a mouse, etc.; an output part 1007 including a cathode ray tube (Cathode Ray Tube, CRT), a liquid crystal display (Liquid Crystal Display, LCD), etc., and a speaker, etc. ; a storage part 1008 including a hard disk, etc.; and a communication part 1009 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 1009 performs communication processing via a network such as the Internet. Driver 1010 is also connected to I/O interface 1005 as needed. Removable media 1011, such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc., are installed on the drive 1010 as needed, so that a computer program read therefrom is installed into the storage portion 1008 as needed.

In particular, according to embodiments of the present application, the process described above with reference to the flowchart may be implemented as a computer software program. For example, embodiments of the present application include a computer program product including a computer program carried on a computer-readable medium, the computer program including a computer program for performing the method shown in the flowchart. In such embodiments, the computer program may be downloaded and installed from the network via communication portion 1009 and/or installed from removable media 1011. When the computer program is executed by the central processing unit (CPU) 1001, various functions defined in the system of the present application are executed.

It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), removable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash memory, optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any of the above suitable The combination. As used herein, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which a computer-readable computer program is carried. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device . Computer programs embodied on computer-readable media may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of systems, methods and computer program products according to various embodiments of the present application. Each block in the flow chart or block diagram may represent a module, program segment, or part of the code. The above-mentioned module, program segment, or part of the code includes one or more executable components for implementing the specified logical function. instruction. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown one after another may actually execute substantially in parallel, or they may sometimes execute in the reverse order, depending on the functionality involved. It will also be noted that each block in the block diagram or flowchart illustration, and combinations of blocks in the block diagram or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or operations, or may be implemented by special purpose hardware-based systems that perform the specified functions or operations. Achieved by a combination of specialized hardware and computer instructions.

The units involved in the embodiments of this application can be implemented in software or hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation on the unit itself under certain circumstances.

Another aspect of the present application also provides a computer-readable storage medium on which computer-readable instructions are stored. When the computer-readable instructions are executed by a processor, the big data-based method in any one of the previous embodiments is implemented. Bond risk information processing methods.

Another aspect of the present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the big data-based bond risk information processing method provided in the above embodiments.

It should be noted that the computer-readable medium shown in the embodiments of the present application may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium may be, for example, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard drive, random access memory (RAM), read only memory (ROM), removable Programmable Read-Only Memory (Erasable Programmable Read Only Memory, EPROM), flash memory, optical fiber, portable compact disk read-only memory (Compact Disc Read-Only Memory, CD-ROM), optical storage device, magnetic storage device, or any of the above suitable The combination. As used herein, a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, in which a computer-readable computer program is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device . Computer programs embodied on computer-readable media may be transmitted using any suitable medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

The above content is only a preferred exemplary embodiment of the present application and is not intended to limit the implementation of the present application. Those of ordinary skill in the art can easily make corresponding modifications or modifications based on the main concept and spirit of the present application. Therefore, the protection scope of this application should be subject to the protection scope required by the claims.

Claims

A bond risk information processing method based on big data, including:

Perform word segmentation processing on the risk information of the issuance object corresponding to the target bond to obtain multiple corresponding content words. The risk information includes the financial information, credit information and historical default information corresponding to the issuance object;

The feature vector of the risk information is determined based on the importance parameter of the target content word that matches a preset keyword table. The keyword table includes a plurality of keywords related to the preset risk event, wherein the importance level Parameters are used to represent the importance of the corresponding target content words to the risk information;

Match the feature vector with risk events in a preset risk event library to obtain a target risk event that matches the feature vector, where the risk event library includes multiple risk events;

Risk prompts are made based on the target risk events.
The method according to claim 1, wherein determining the feature vector of the risk information based on the importance parameter of the target content word matching the preset keyword table includes:

Match each content word with the keyword list to obtain the target content word;

Determine the importance parameters of each target content word;

A vector composed of importance parameters of each target content word is used as the feature vector.
The method according to claim 1, wherein the risk event library includes a risk event score value corresponding to each risk event; the method further includes:

The target matching degree is used as the weight of the risk event score value corresponding to the target risk event, the weighted sum of the risk event score values of the target risk event is calculated, and the weighted sum is used as the risk score value of the target bond, so The target matching degree is the matching degree between the target risk event and the feature vector.
The method according to claim 3, wherein the risk prompt based on the target risk event includes:

In response to the first operation instruction for the target bond triggered in the bond trading page, obtain the target risk event and the risk score value;

Load the target risk event and the risk score value into the bond trading page.
The method according to claim 4, wherein loading the target risk event and the risk score value onto the bond trading page includes:

Associating the risk level of the target bond, the target risk event, and the risk score value with the target bond;

The associated risk level, the target risk event, and the risk score value are loaded onto the bond transaction page, and the risk level is determined based on the risk score value.
The method of claim 5, wherein associating the risk level, the target risk event, the risk score value with the target bond includes:

The risk level, the target risk event, the risk score value and the target bond are brought into the pre-generated risk prompt field template to obtain the corresponding risk prompt field.
The method according to claim 3, wherein the target bond is associated with a bond information link for the target bond; the method further includes:

In response to the second operation instruction for the bond information link triggered in the bond transaction page, the information page corresponding to the bond information link is loaded, and the information page is used to display the risk information.
A bond risk information processing device based on big data, including:

The word segmentation processing module is used to segment the risk information of the issuance object corresponding to the target bond to obtain multiple corresponding content words. The risk information includes the financial information, credit information and historical default information corresponding to the issuance object;

A determination module configured to determine the feature vector of the risk information based on the importance parameters of content words that match a preset keyword table, where the keyword table includes a plurality of keywords related to preset risk events, wherein, The importance parameter is used to represent the importance of the corresponding target content word to the risk information;

A matching module, configured to match the feature vector with risk events in a preset risk event library to obtain a target risk event that matches the feature vector, where the risk event library includes multiple risk events;

A risk warning module is used to provide risk warning based on the target risk event.
An electronic device including:

A memory storing computer-readable instructions;

The processor reads the computer-readable instructions stored in the memory to execute the method according to any one of claims 1-7.
A computer-readable storage medium having computer-readable instructions stored thereon. When the computer-readable instructions are executed by a processor of a computer, the computer is caused to perform the method described in any one of claims 1-7.
A computer program product. The computer program product includes computer instructions. When a processor of a computer device executes the computer instructions, the computer device performs the method described in any one of claims 1-7.