CN113450229A - Block chain technology-based method for managing deposit duration bonds - Google Patents

Block chain technology-based method for managing deposit duration bonds Download PDF

Info

Publication number
CN113450229A
CN113450229A CN202110775310.0A CN202110775310A CN113450229A CN 113450229 A CN113450229 A CN 113450229A CN 202110775310 A CN202110775310 A CN 202110775310A CN 113450229 A CN113450229 A CN 113450229A
Authority
CN
China
Prior art keywords
current
feature vector
data
weighted
historical
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Withdrawn
Application number
CN202110775310.0A
Other languages
Chinese (zh)
Inventor
王仁杰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hangzhou Xinku Technology Co ltd
Original Assignee
Hangzhou Xinku Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hangzhou Xinku Technology Co ltd filed Critical Hangzhou Xinku Technology Co ltd
Priority to CN202110775310.0A priority Critical patent/CN113450229A/en
Publication of CN113450229A publication Critical patent/CN113450229A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/06—Asset management; Financial planning or analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/27—Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/60—Protecting data
    • G06F21/64—Protecting data integrity, e.g. using checksums, certificates or signatures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
    • G06Q40/03—Credit; Loans; Processing thereof

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Development Economics (AREA)
  • Strategic Management (AREA)
  • Computer Security & Cryptography (AREA)
  • Databases & Information Systems (AREA)
  • Evolutionary Computation (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Economics (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • Technology Law (AREA)
  • General Business, Economics & Management (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Probability & Statistics with Applications (AREA)
  • Bioethics (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Mathematical Physics (AREA)
  • Computer Hardware Design (AREA)
  • Computational Linguistics (AREA)
  • Biophysics (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Biology (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Game Theory and Decision Science (AREA)
  • Human Resources & Organizations (AREA)
  • Operations Research (AREA)

Abstract

The method adopts a semantic understanding model based on a converter to carry out semantic understanding and classification on related events of the deposit bond, enterprise operation data and enterprise external public opinion data aiming at the centralized storage and management functions of distributed data of a block chain and the non-tampering property and real-time property of the data stored by the block chain, thereby obtaining a classification result representing the risk prediction result of the deposit bond. Therefore, risk prediction is carried out by monitoring the relevant information of the deposit bond, whether the deposit bond right has risk or not is determined, and a subsequent management system of the debt financing tool is perfected.

Description

Block chain technology-based method for managing deposit duration bonds
Technical Field
The present invention relates to the field of blockchain, and more particularly, to a method for managing a lifetime bond based on blockchain technology, a system for managing a lifetime bond based on blockchain technology, and an electronic device.
Background
The block chain is a distributed shared account book and a database, and has the characteristics of decentralization, no tampering, trace retaining in the whole process, traceability, collective maintenance, openness and transparency and the like. The characteristics ensure the honesty and the transparency of the block chain and lay a foundation for creating trust for the block chain. In recent years, as the technology of blockchain matures and develops, various data management technologies based on blockchain technology and applications thereof are developed due to the unique non-alterable characteristic of blockchain.
The technical scheme is that a supervising center successively launches and revises 'guide of subsequent management work of principal and underwriters of non-financial enterprise debt financing instruments in inter-bank bond market,' guide of emergency management work of non-financial enterprise debt financing instruments in inter-bank bond market and 'conference regulation of holders of non-financial enterprise debt financing instruments in inter-bank bond market' and the like from 2010 after the inter-bank trader deal of China, and a scientific work system is established for the subsequent management of the inter-bank bond market.
However, until now, there is no uniform subsequent management information system for inter-bank market debt financing tool products, and the main underwriters generally adopt an off-line manual maintenance mode to perform information maintenance and dynamic monitoring on the deposit bond and enterprise information, so that the requirements on the labor cost and time cost of subsequent management are high, and the monitoring and investigation of risk events are not facilitated in time.
Therefore, a solution optimized for the management of the lifetime bonds is desired.
Disclosure of Invention
The present application is proposed to solve the above-mentioned technical problems. The embodiment of the application provides a block chain technology-based preservation bond management method, a block chain technology-based preservation bond management system and an electronic device, aiming at the centralized storage and management functions of distributed data of a block chain and the non-tamper-resistance and real-time performance of the data stored by the block chain, a converter-based semantic understanding model is adopted to carry out semantic understanding and classification on related events of the preservation bond, enterprise operation data and enterprise external public opinion data, and therefore a classification result representing the risk prediction result of the preservation bond is obtained. Therefore, risk prediction is carried out by monitoring the relevant information of the deposit bond, whether the deposit bond right has risk or not is determined, and a subsequent management system of the debt financing tool is perfected.
According to one aspect of the application, a method for managing a lifetime bond based on a block chain technology is provided, which comprises the following steps:
acquiring text data of a plurality of current events for storing the renewal bonds, current enterprise operation data and current enterprise external public opinion data;
respectively passing the text data of the current events, the current enterprise operation data and the current enterprise external public opinion data through a converter-based semantic understanding model to obtain a plurality of current event feature vectors, current operation feature vectors and current public opinion feature vectors;
generating an event feature vector based on the plurality of current event feature vectors and one or more historical event feature vectors associated with the plurality of current events, wherein the one or more historical event feature vectors are obtained from text data of one or more historical events respectively through the converter-based semantic understanding model;
obtaining a plurality of historical business operation data and passing the historical business operation data through the semantic understanding model based on the converter to obtain a plurality of historical business characteristic vectors and calculating the average weighted sum of the plurality of historical business characteristic vectors to obtain an average historical business characteristic vector;
calculating a difference between the average historical operating feature vector and the current operating feature vector to obtain a difference operating feature vector;
activating the characteristic value of each position in the current public opinion characteristic vector by a Sigmoid function so as to map the characteristic value of each position in the current public opinion characteristic vector to an interval from 0 to 1 to obtain a probabilistic current public opinion characteristic vector;
calculating the information entropy of the characteristic value of each position in the probabilistic current public opinion characteristic vector, wherein the information entropy is obtained by multiplying the negative value of the logarithmic function value of the characteristic value of each position by the characteristic value of the position;
weighting the current public opinion feature vector by taking the information entropy of each position of the probabilistic current public opinion feature vector as a weight to obtain a weighted public opinion feature vector;
cascading the event feature vector, the differential operation feature vector and the weighted public opinion feature vector to obtain a classification feature vector and enabling the classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for representing a risk prediction result; and
and storing the text data of a plurality of current events of the lifetime bond, the current enterprise business data and the current enterprise external public opinion data in a storage block of a block chain architecture.
According to another aspect of the present application, there is provided a block chain technology-based lifetime bond management system, including:
the data acquisition unit is used for acquiring text data of a plurality of current events for storing the renewal bonds, current enterprise operation data and current enterprise external public opinion data;
a current feature vector generating unit, configured to pass the text data of the multiple current events, the current enterprise business data, and the current enterprise external public opinion data obtained by the data obtaining unit through a converter-based semantic understanding model to obtain multiple current event feature vectors, current business feature vectors, and current public opinion feature vectors, respectively;
an event feature vector generating unit, configured to generate an event feature vector based on the plurality of current event feature vectors obtained by the current feature vector generating unit and one or more historical event feature vectors associated with the plurality of current events, where the one or more historical event feature vectors are obtained by text data of one or more historical events through the converter-based semantic understanding model, respectively;
a historical characteristic vector generating unit, which is used for acquiring a plurality of historical enterprise operation data and passing the historical enterprise operation data through the semantic understanding model based on the converter to obtain a plurality of historical operation characteristic vectors and calculating the average weighted sum of the plurality of historical operation characteristic vectors to obtain an average historical operation characteristic vector;
a differential operation feature vector generation unit configured to calculate a difference between the average historical operation feature vector obtained by the historical feature vector generation unit and the current operation feature vector obtained by the current feature vector generation unit to obtain a differential operation feature vector;
an activation unit, configured to activate, by using a Sigmoid function, the feature value of each position in the current public opinion feature vector obtained by the current feature vector generation unit to map the feature value of each position in the current public opinion feature vector into an interval from 0 to 1, so as to obtain a probabilistic current public opinion feature vector;
the information entropy calculation unit is used for calculating the information entropy of the characteristic value of each position in the probabilistic current public opinion characteristic vector obtained by the activation unit, wherein the information entropy is obtained by multiplying the negative value of the logarithmic function value of the characteristic value of each position by the characteristic value of the position;
a weighting unit configured to weight the current public opinion feature vector obtained by the current feature vector generation unit with the information entropy of each position of the probabilistic current public opinion feature vector obtained by the information entropy calculation unit as a weight to obtain a weighted public opinion feature vector;
a classification result generating unit, configured to cascade the event feature vector obtained by the event feature vector generating unit, the differential operation feature vector obtained by the differential operation feature vector generating unit, and the weighted public opinion feature vector obtained by the weighting unit to obtain a classification feature vector, and pass the classification feature vector through a classifier to obtain a classification result, where the classification result is used to represent a risk prediction result; and
and the storage unit is used for storing the text data of a plurality of current events of the lifetime bonds, the current enterprise business data and the current enterprise external public opinion data which are obtained by the data acquisition unit into a storage block of a block chain architecture.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory having stored therein computer program instructions which, when executed by the processor, cause the processor to perform the method of lifetime bond management based on blockchain techniques as described above.
According to yet another aspect of the present application, there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the method for lifetime bond management based on blockchain techniques as described above.
Compared with the prior art, the block chain technology-based preservation bond management method, the block chain technology-based preservation bond management system and the electronic device provided by the application have the advantages that the converter-based semantic understanding model is adopted to carry out semantic understanding and classification on related events of the preservation bond, enterprise operation data and enterprise external public opinion data aiming at the centralized storage and management functions of distributed data of the block chains and the non-tamper-property and real-time property of the data stored in the block chains, so that the classification result representing the risk prediction result of the preservation bond is obtained. Therefore, risk prediction is carried out by monitoring the relevant information of the deposit bond, whether the deposit bond right has risk or not is determined, and a subsequent management system of the debt financing tool is perfected.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing in more detail embodiments of the present application with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the application and are incorporated in and constitute a part of this specification, illustrate embodiments of the application and together with the description serve to explain the principles of the application. In the drawings, like reference numbers generally represent like parts or steps.
Fig. 1 is a schematic diagram of a block chain-based lifetime bond database according to an embodiment of the present application;
fig. 2 is an application scenario diagram of a method for managing a lifetime bond based on a blockchain technique according to an embodiment of the present application;
fig. 3 is a flowchart of a method for managing lifetime bonds based on a block chain technique according to an embodiment of the present application;
fig. 4 is a schematic diagram of a system architecture of a method for managing lifetime bonds based on a block chain technique according to an embodiment of the present application;
fig. 5 is a block diagram of a block chain technology based on a life bond management system according to an embodiment of the present application;
fig. 6 is a block diagram of a current feature vector generation unit in a block chain technology-based lifetime bond management system according to an embodiment of the present application;
fig. 7 is a block diagram of an event feature vector generation unit in a block chain technology-based lifetime bond management system according to an embodiment of the present application;
fig. 8 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be understood that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and that the present application is not limited by the example embodiments described herein.
Block chain architecture overview
Fig. 1 illustrates an architectural diagram of a blockchain-based lifetime bond database according to an embodiment of the present application. As shown in fig. 1, the block chain-based remaining bond database according to the embodiment of the present application employs a typical block chain architecture, and related information of the remaining bonds, such as text data of a plurality of current events of the remaining bonds, current business data, and current business external public opinion data P1, P2, …, Pn, is stored in respective storage blocks B1, B2, …, Bn constructed in a block chain. Of course, those skilled in the art will appreciate that the related information of the different types of the renewal bonds can be stored in separate blocks, for example, one block is dedicated to the business management data of the storage of the renewal bonds, and another block is dedicated to the business external public opinion data of the storage of the renewal bonds.
According to a typical blockchain storage architecture, each block B1, B2, …, Bn includes pointers H1, H2, …, Hn and data portions D1, D2, …, Dn. The pointers H1, H2, …, Hn may be various types of hash pointers, such as SHA-256 hash functions commonly used in blockchain storage architectures, that point to the last chunk.
In the embodiment of the present application, the value of the hash pointer of the next chunk is based on the value of the hash pointer of the previous chunk and the hash function value of the data portion, for example, H2 ═ H1 × H (D1), and H (D1) represents the hash function value of the data portion D1. The value of the hash pointer for the first chunk may be a random value. In this way, any modification to the portion of data within a block will react on the value of the hash pointer of the next block and further change the values of the hash pointers of all subsequent blocks, making modifications to the portion of data virtually impossible.
Here, it can be understood by those skilled in the art that the blockchain-based lifetime bond database according to the embodiment of the present application may adopt any general blockchain architecture, and the embodiment of the present application is not intended to limit the specific implementation of the blockchain architecture. In addition, in the embodiment of the present application, the block chain preferably adopts a private chain or a federation chain, so as to facilitate the storage management of the persistent bonds inside the persistent bond provider or a company or an enterprise of a federation of the persistent bond provider, and accordingly, each storage block for storing the persistent bonds can be configured in advance without being generated based on the consensus algorithm, so that the consumption of computing resources caused by the consensus algorithm can be avoided.
That is to say, the blockchain architecture of the blockchain-based duration bond database according to the embodiment of the present application focuses on storage management of the duration bonds, and does not relate to a blockchain-based value transfer function similar to electronic money, so that the blockchain architecture can be configured in advance in a cloud by a management department inside a company or an enterprise, and accessed from a terminal by each technical department for uploading the duration bonds, and performing unified storage and management in the cloud. Therefore, since the technical departments are likely to be distributed in different geographic locations, the application of the blockchain architecture can conveniently realize the distributed storage of the lifetime bonds.
On the other hand, each block in the block chain architecture according to the embodiment of the present application may also be associated with a block of the public chain, so that each block has time stamp information corresponding to the associated block of the public chain. Thus, when information requiring a time attribute, such as the uploading time of a lifetime bond, needs to be recorded to determine whether the lifetime bond is an early version, the time sequence attribute of each block in the block chain can be utilized.
Overview of a scene
As mentioned above, currently, there is no unified subsequent management information system for inter-bank market debt financing tool products, and the main underwriters generally adopt an offline manual maintenance mode to perform information maintenance and dynamic monitoring on the deposit bond and the enterprise information, which has a large requirement on the labor cost and time cost of subsequent management, and is not beneficial to timely monitoring and troubleshooting of risk events.
Based on the above, the inventor of the present application further considers enterprise business data and enterprise external public opinion data for monitoring relevant information of the lifetime bonds, including major matters monitoring, holder meeting monitoring, insurance clause monitoring, credit event monitoring, and rating adjustment event monitoring, and adopts a block chain-based storage architecture to store and manage the information, because the above information has high requirements for authenticity, and the non-tamper-ability of the block chain technology is required to ensure the authenticity of the data. In addition, as the block chain is a storage framework with a time stamp, the timeliness of the information can be ensured.
In addition, aiming at the above events, namely major matters, holder meetings, insurance terms, credit events and rating adjustment events, enterprise operation data, such as enterprise business tax laws, complaint integrity, association relation and the like, and enterprise external public opinion data, the risk events of the existing debt need to be treated differently when being predicted, so that whether the existing debt is at risk or not is determined in an artificial intelligence manner, and a subsequent management system of the debt financing tool is perfected.
Based on semantic understanding of event data, risk prediction is performed by further considering enterprise business data and enterprise external public opinion data in the technical scheme of the application. Here, the business operation data is easier to process, and only the difference between the business operation data and the historical operation data needs to be processed. As the industry of media, especially the rapid development of various self-media, develops external public sentiments of enterprises, and the external public sentiments of the enterprises become more complex, the external public sentiments must be processed in a proper way.
According to the technical scheme, for enterprise business data and enterprise external public opinion data, the enterprise business data and the enterprise external public opinion data are firstly converted into a series of word vectors through a word embedding model, and then the current business characteristic vectors and the current public opinion characteristic vectors are obtained through a semantic understanding model based on a converter. Then, a plurality of historical operation characteristic vectors are obtained, the average value of the historical operation characteristic vectors is calculated, and the difference between the current operation characteristic vector and the average historical operation characteristic vector is calculated to obtain a difference operation characteristic vector. For the current public opinion feature vector, firstly, the sigmoid function is used for activating each feature value to map between 0 and 1, so that the probability value form is converted, and then the information entropy of each feature value, namely xi [ -log (xi) ], is calculated, namely, for the current public opinion data, the more corresponding the current public opinion data to the small probability event, the more remarkable the current public opinion data is.
Then, weighting the current public opinion feature vector by the information entropy of each feature value to obtain a weighted public opinion feature vector, and further cascading with the event feature vector and the differential operation feature vector to obtain a classification feature vector.
And finally, obtaining a classification result by the classification feature vector through a classifier, wherein the classification result can represent a risk prediction result. In addition, the risk prediction result, the text data of the current event, the current enterprise business data and the external public opinion data of the enterprise are all stored in the storage block of the block chain architecture, so as to realize the risk management of the existing bond.
Fig. 2 illustrates an application scenario of a method for managing lifetime bonds based on a blockchain technology according to an embodiment of the present application. As shown in fig. 2, in this application scenario, first, text data of a plurality of current events of a lifetime bond, current business management data, current business external public opinion data, and text data of one or more historical events associated with the plurality of current events and historical business management data are acquired through a terminal device (e.g., D as illustrated in fig. 2); then, inputting the text data of the current event, the current business operation data, the current external public opinion data of the business, the text data of the historical event and the historical business operation data into a server (for example, a cloud server S as illustrated in FIG. 2) deployed with a life bond management algorithm based on the blockchain technology, wherein the server is capable of processing the text data of the current event, the current enterprise business data, the current enterprise external public opinion data, the text data of the historical event and the historical enterprise business data based on a life bond management algorithm of a blockchain technology to generate a classification result representing a risk prediction result, then, text data of a plurality of current events of the lifetime bond, current business management data, and current business external public opinion data are stored in a storage block of a block chain architecture (e.g., T as illustrated in fig. 2).
Having described the general principles of the present application, various non-limiting embodiments of the present application will now be described with reference to the accompanying drawings.
Exemplary method
Fig. 3 illustrates a flow chart of a method of life bond management based on blockchain technology. As shown in fig. 3, a method for managing a lifetime bond based on a block chain technology according to an embodiment of the present application includes: s110, acquiring text data of a plurality of current events of the existing bond, current enterprise operation data and current enterprise external public opinion data; s120, respectively enabling the text data of the current events, the current enterprise operation data and the current enterprise external public opinion data to pass through a semantic understanding model based on a converter so as to obtain a plurality of current event feature vectors, current operation feature vectors and current public opinion feature vectors; s130, generating an event feature vector based on the plurality of current event feature vectors and one or more historical event feature vectors associated with the plurality of current events, wherein the one or more historical event feature vectors are obtained by text data of one or more historical events through the converter-based semantic understanding model respectively; s140, acquiring a plurality of historical enterprise operation data, passing the historical enterprise operation data through the semantic understanding model based on the converter to obtain a plurality of historical operation characteristic vectors, and calculating the average weighted sum of the plurality of historical operation characteristic vectors to obtain an average historical operation characteristic vector; s150, calculating the difference between the average historical operation characteristic vector and the current operation characteristic vector to obtain a difference operation characteristic vector; s160, activating the characteristic values of all positions in the current public opinion characteristic vector by a Sigmoid function so as to map the characteristic values of all positions in the current public opinion characteristic vector to an interval from 0 to 1 to obtain a probabilistic current public opinion characteristic vector; s170, calculating the information entropy of the characteristic value of each position in the probabilistic current public opinion characteristic vector, wherein the information entropy is obtained by multiplying the negative value of the logarithmic function value of the characteristic value of each position by the characteristic value of the position; s180, weighting the current public opinion feature vector by taking the information entropy of each position of the probabilistic current public opinion feature vector as a weight to obtain a weighted public opinion feature vector; s190, cascading the event feature vector, the differential operation feature vector and the weighted public opinion feature vector to obtain a classification feature vector, and enabling the classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for representing a risk prediction result; and S200, storing the text data of a plurality of current events of the lifetime bonds, the current enterprise business data and the current enterprise external public opinion data in a storage block of a block chain architecture.
Fig. 4 is a schematic diagram illustrating an architecture of a method for managing lifetime bonds based on a block chain technique according to an embodiment of the present application. As shown IN fig. 4, IN the network architecture of the method for managing a lifetime bond based on the blockchain technique, first, text data (e.g., IN1 as illustrated IN fig. 4), current business management data (e.g., IN2 as illustrated IN fig. 4), and current business external public opinion data (e.g., IN3 as illustrated IN fig. 4) of a plurality of current events of the lifetime bond are acquired; then, passing the text data of the plurality of current events, the current business operations data and the current business external public opinion data through a converter-based semantic understanding model (e.g., SUM as illustrated in fig. 4) to obtain a plurality of current event feature vectors (e.g., V1 as illustrated in fig. 4), a current business feature vector (e.g., V2 as illustrated in fig. 4) and a current public opinion feature vector (e.g., V3 as illustrated in fig. 4), respectively; then, generating an event feature vector (e.g., Vt1 as illustrated IN fig. 4) based on the plurality of current event feature vectors and one or more historical event feature vectors (e.g., V4 as illustrated IN fig. 4) associated with the plurality of current events, wherein the one or more historical event feature vectors are obtained by text data of one or more historical events (e.g., IN4 as illustrated IN fig. 4) respectively through the converter-based semantic understanding model; next, obtaining and passing a plurality of historical business operations data (e.g., IN5 as illustrated IN fig. 4) through the converter-based semantic understanding model to obtain a plurality of historical business feature vectors (e.g., V5 as illustrated IN fig. 4) and calculating an average weighted sum of the plurality of historical business feature vectors to obtain an average historical business feature vector (e.g., Va as illustrated IN fig. 4); then, calculating a difference between the average historical operating signature vector and the current operating signature vector to obtain a differential operating signature vector (e.g., Vt2 as illustrated in fig. 4); then, activating the feature values of the positions in the current public opinion feature vector by a Sigmoid function to map the feature values of the positions in the current public opinion feature vector into an interval from 0 to 1 so as to obtain a probabilistic current public opinion feature vector (for example, Vp3 as illustrated in fig. 4); then, calculating the information entropy of the characteristic value of each position in the probabilistic current public opinion characteristic vector; then, weighting the current public opinion feature vector by taking information entropy of each position of the probabilistic current public opinion feature vector as a weight to obtain a weighted public opinion feature vector (for example, Vt3 as illustrated in fig. 4); then, cascading the event feature vector, the differential business feature vector and the weighted public opinion feature vector to obtain a classification feature vector (for example, Vc as illustrated in fig. 4) and passing the classification feature vector through a classifier (for example, a circle S as illustrated in fig. 4) to obtain a classification result, wherein the classification result is used for representing a risk prediction result; finally, text data of a plurality of current events of the lifetime bond, current business management data, and current business external public opinion data are stored in a storage block of a block chain architecture (e.g., T as illustrated in fig. 4).
In step S110, text data of a plurality of current events of the lifetime bonds, current business management data, and current business external public opinion data are acquired. As described above, in the process of predicting the risk of the long-term bond, the inventor further considers the enterprise business data, such as enterprise tax laws, complaint integrity, association relation and the like, and the influence of the external public opinion data of the enterprise on the risk. Specifically, in the embodiment of the present application, the event includes: major matters, bearer meetings, terms of application, credit events, and rating adjustment events.
In step S120, the text data of the current events, the current business operation data and the current business external public opinion data are respectively passed through a converter-based semantic understanding model to obtain current event feature vectors, current business feature vectors and current public opinion feature vectors.
Specifically, in this embodiment of the present application, a process of passing text data of a plurality of current events, current business operation data, and current business external public opinion data through a converter-based semantic understanding model to obtain a plurality of current event feature vectors, current business feature vectors, and current public opinion feature vectors, respectively, includes: firstly, the text data of the current events are respectively input into a word embedding model to obtain word vectors of the current events. It should be understood that text is a very important type of unstructured data, and text can be converted into structured data by a word embedding model, i.e., text data is represented in the form of vectors. Then, the word vectors of the plurality of current events are respectively input into the converter-based semantic understanding model to obtain the plurality of current event feature vectors. That is, semantic features in the word vector of the current event are obtained through a semantic understanding model to obtain a current event feature vector. In the present application, the semantic understanding model may be a Bert model, which introduces entity word vectors in addition to general word vectors, and is very suitable for semantic understanding and classification in some vertical fields.
Then, the current enterprise business data is input into the word embedding model to obtain a word vector of the current enterprise business data. That is, the enterprise business data is converted into a representation in the form of a vector through the word embedding model. Then, a word vector of the current enterprise business data is input into the converter-based semantic understanding model to obtain the current business feature vector. Then, the current enterprise external public opinion data is input into the word embedding model to obtain a word vector of the current enterprise external public opinion data. That is, the external public opinion data of the enterprise is converted into a representation in a vector form through a word embedding model. Then, inputting the word vector of the current enterprise external public opinion data into the converter-based semantic understanding model to obtain the current public opinion feature vector.
In step S130, an event feature vector is generated based on the plurality of current event feature vectors and one or more historical event feature vectors associated with the plurality of current events, wherein the one or more historical event feature vectors are obtained from text data of one or more historical events respectively through the converter-based semantic understanding model.
Specifically, in this embodiment of the present application, the process of generating an event feature vector based on the plurality of current event feature vectors and one or more historical event feature vectors associated with the plurality of current events includes: first, text data of one or more historical events related to the plurality of current events is obtained. It should be understood that due to the relevance between events, prediction is not performed through a certain event, but through accumulated events, and therefore, in the technical solution of the present application, text data of one or more historical events related to the multiple current events needs to be acquired.
Then, the text data of the one or more historical events are respectively passed through the converter-based semantic understanding model to obtain one or more historical event feature vectors. That is, the text data of the historical events are respectively input into a word embedding model to obtain word vectors of the historical events. Then, the word vector of the historical event is input into the converter-based semantic understanding model to obtain the historical event feature vector. In the embodiment of the present application, the semantic understanding model based on the converter may be a Bert model.
Then, for each feature vector to be weighted in the plurality of current event feature vectors and the one or more historical event feature vectors, one or more reference event feature vectors corresponding to each feature vector to be weighted are obtained, wherein the reference event feature vectors are obtained by the converter-based semantic understanding model for template text data of corresponding events. It should be appreciated that in order to determine the weighted relationship between the current event feature vector and the historical event feature vector, the inventors of the present application employ a classification probability weight expression based on template data, i.e., a reference event feature vector. That is, for each feature vector to be weighted in the current event feature vector and the historical event feature vector, the event type to which it belongs, such as the important item, the holder meeting, the insurance clause, the credit event and the rating adjustment event as described above, is first determined, and then the corresponding reference event feature vector under the event type is determined. Here, the reference event feature vector may be a reference event feature vector obtained by subjecting template text data of the above event to a converter-based semantic understanding model, and since a certain type generally corresponds to a plurality of template texts, also corresponds to a plurality of reference event feature vectors.
Then, for each feature vector to be weighted in the plurality of current event feature vectors and the one or more historical event feature vectors, respectively calculating a classification probability weight expression between each feature vector to be weighted and the one or more reference event feature vectors corresponding to the feature vector to be weighted to obtain a weight value corresponding to each feature vector to be weighted, wherein the weight value is used for calculating the classification probability weight expression of each feature vector to be weightedThe classification probability weight is expressed as a quotient of a weighted sum of natural exponent function values raised to a power of a negative value of the feature value of each position in the feature vector to be weighted divided by a sum of weighted sums of natural exponent function values raised to a power of a negative value of the feature value of each position in the one or more reference event feature vectors. More specifically, in this embodiment of the present application, for each to-be-weighted feature vector in the plurality of current event feature vectors and the one or more historical event feature vectors, a process of respectively calculating a classification probability weight expression between each to-be-weighted feature vector and the one or more reference event feature vectors corresponding thereto to obtain a weight value corresponding to each to-be-weighted feature vector includes: calculating a classification probability weight expression between each feature vector to be weighted and the one or more reference event feature vectors corresponding to the feature vector to be weighted to obtain a weight value corresponding to each feature vector to be weighted, wherein the formula is as follows: p ═ Σiexp(-xi)/∑i，jexp (-yi), xi represents the eigenvalue of each position of the eigenvector to be weighted, yi represents the eigenvalue of each position of the reference event eigenvector, and j is further summed to represent Σ for the plurality of reference event eigenvectorsiThe values of exp (-yi) are summed. In this way, the weight of each feature vector to be weighted can be calculated, and the weight is substantially used for indicating the degree of attention required by the event occurring at this time in the event of the same type.
Then, each feature vector to be weighted is weighted by each weight value to obtain a plurality of weighted feature vectors. It should be understood that, by weighting each of the feature vectors to be weighted, the obtained weighted feature vectors can better reflect the overall features. Then, the plurality of weighted feature vectors are concatenated to obtain the event feature vector. That is, a plurality of weighted feature vectors are spliced into an event feature vector.
In step S140, a plurality of historical business operations data are obtained and passed through the converter-based semantic understanding model to obtain a plurality of historical business feature vectors and an average weighted sum of the plurality of historical business feature vectors is calculated to obtain an average historical business feature vector. It should be understood that since the business operation data has a certain volatility, the business operation data at a certain time is not used as a reference, but is referred to based on a historical average of the business operation data.
In step S150, a difference between the average historical operating feature vector and the current operating feature vector is calculated to obtain a difference operating feature vector. It should be appreciated that calculating the difference between the average historical operational characteristic vector and the current operational characteristic vector may reflect a variance in the historical average of the current business operational data based on which the lifetime bond risk may be predicted.
In step S160, the feature values of the positions in the current public opinion feature vector are activated by a Sigmoid function to map the feature values of the positions in the current public opinion feature vector into an interval from 0 to 1, so as to obtain a probabilistic current public opinion feature vector. That is, the current public opinion feature vector is activated by a Sigmoid function to map the current public opinion feature vector into an interval of 0 to 1, so as to facilitate the calculation of the subsequent probability.
In step S170, an information entropy of the feature value of each position in the probabilistic current public opinion feature vector is calculated, where the information entropy is obtained by multiplying a negative value of a logarithmic function value of the feature value of each position by the feature value of the position. Specifically, in the embodiment of the present application, the process of calculating the information entropy of the feature value of each position in the probabilistic current public opinion feature vector includes: and calculating the information entropy of the characteristic value of each position in the probabilistic current public opinion characteristic vector by the following formula, wherein the formula is p ═ xi [ -log (xi) ], and xi represents the characteristic value of each position in the probabilistic current public opinion characteristic vector. That is, for current public opinion data, the more it corresponds to a small probability event, the more noticeable it is.
In step S180, weighting the current public opinion feature vector by using the information entropy of each position of the probabilistic current public opinion feature vector as a weight to obtain a weighted public opinion feature vector. It should be understood that, the current public opinion feature vector is weighted by taking the information entropy of each position of the probabilistic current public opinion feature vector as a weight, and each position of the obtained weighted public opinion feature vector integrates the weight information which should be noticed by the position.
In step S190, the event feature vector, the differential business feature vector, and the weighted public opinion feature vector are concatenated to obtain a classification feature vector, and the classification feature vector is passed through a classifier to obtain a classification result, where the classification result is used to represent a risk prediction result. Namely, the event feature vector, the differential operation feature vector and the weighted public opinion feature vector are spliced into a classification feature vector, and are classified through a Softmax classification function to obtain a classification result representing a risk prediction result. It should be understood that the classification result is more accurate because the classification feature vector fuses the relevant event information of the lifetime bonds, the enterprise operation data and the enterprise external public opinion data.
In step S200, the text data of a plurality of current events of the lifetime bonds, the current business operation data, and the current business external public opinion data are stored in a storage block of a block chain architecture. Specifically, in the embodiment of the present application, the process of storing text data of a plurality of current events of the lifetime bonds, current business operation data, and current business external public opinion data in a storage block of a block chain architecture includes: and in response to the classification result being risk-free, storing text data of a plurality of current events of the lifetime bonds, current enterprise business data and current enterprise external public opinion data in a storage block of a block chain architecture. That is, by managing the lifetime bond information using the blockchain technique, the data stored in the block is not changeable.
In summary, the method for managing a lifetime bond based on a blockchain technology is disclosed, which is used for semantically understanding and classifying related events of the lifetime bond, enterprise business data and enterprise external public opinion data by using a semantic understanding model based on a converter aiming at the centralized storage and management functions of distributed data of the blockchain and the non-tamper-property and real-time property of the data stored in the blockchain, so as to obtain a classification result representing a risk prediction result of the lifetime bond. Therefore, risk prediction is carried out by monitoring the relevant information of the deposit bond, whether the deposit bond right has risk or not is determined, and a subsequent management system of the debt financing tool is perfected.
Exemplary System
Fig. 5 illustrates a block diagram of a block chain technology based on a life cycle bond management system according to an embodiment of the application. As shown in fig. 5, a system 700 for managing lifetime bonds based on a block chain technology according to an embodiment of the present application includes: a data obtaining unit 710 for obtaining text data of a plurality of current events of the lifetime bonds, current enterprise operation data, and current enterprise external public opinion data; a current feature vector generating unit 720, configured to pass the text data of the multiple current events, the current enterprise business data, and the current enterprise external public opinion data obtained by the data obtaining unit 710 through a converter-based semantic understanding model to obtain multiple current event feature vectors, current business feature vectors, and current public opinion feature vectors, respectively; an event feature vector generating unit 730, configured to generate an event feature vector based on the plurality of current event feature vectors obtained by the current feature vector generating unit 720 and one or more historical event feature vectors associated with the plurality of current events, where the one or more historical event feature vectors are obtained by text data of one or more historical events through the converter-based semantic understanding model, respectively; a historical eigenvector generating unit 740, configured to obtain a plurality of historical enterprise operation data and pass the plurality of historical enterprise operation data through the converter-based semantic understanding model to obtain a plurality of historical operation eigenvectors, and calculate an average weighted sum of the plurality of historical operation eigenvectors to obtain an average historical operation eigenvector; a difference operation feature vector generation unit 750 configured to calculate a difference between the average historical operation feature vector obtained by the historical feature vector generation unit 740 and the current operation feature vector obtained by the current feature vector generation unit to obtain a difference operation feature vector; an activating unit 760, configured to activate, by using a Sigmoid function, the feature value of each location in the current public opinion feature vector obtained by the current feature vector generating unit 720 to map the feature value of each location in the current public opinion feature vector into an interval from 0 to 1, so as to obtain a probabilistic current public opinion feature vector; an information entropy calculating unit 770, configured to calculate an information entropy of the feature value of each location in the probabilistic current public opinion feature vector obtained by the activating unit 760, where the information entropy is a product of a negative value of a logarithmic function value of the feature value of each location and the feature value of the location; a weighting unit 780 configured to weight the current public opinion feature vector obtained by the current feature vector generation unit 720 with the information entropy of each position of the probabilistic current public opinion feature vector obtained by the information entropy calculation unit 770 as a weight to obtain a weighted public opinion feature vector; a classification result generating unit 790 for concatenating the event feature vector obtained by the event feature vector generating unit 730, the differential business feature vector obtained by the differential business feature vector generating unit 750, and the weighted public opinion feature vector obtained by the weighting unit 780 to obtain a classification feature vector, and passing the classification feature vector through a classifier to obtain a classification result, wherein the classification result is used for representing a risk prediction result; and a storage unit 800, configured to store the text data of the multiple current events of the lifetime bonds, the current business operation data, and the current business external public opinion data obtained by the data obtaining unit 710 in a storage block of a block chain architecture.
In one example, in the lifetime bond management system 700 described above, as shown in fig. 6, the current feature vector generation unit 720 includes: a first word vector generating subunit 721, configured to input text data of the plurality of current events into a word embedding model respectively to obtain word vectors of the plurality of current events; a current event feature vector generating subunit 722, configured to input the word vectors of the plurality of current events obtained by the first word vector generating subunit 721 into the converter-based semantic understanding model respectively to obtain a plurality of current event feature vectors; a second word vector generating subunit 723, configured to input the current enterprise operation data into the word embedding model to obtain a word vector of the current enterprise operation data; a current business feature vector generating subunit 724, configured to input the word vector of the current enterprise business data obtained by the second word vector generating subunit 723 into the converter-based semantic understanding model to obtain the current business feature vector; a third word vector generating subunit 725, configured to input the current enterprise external public opinion data into the word embedding model to obtain a word vector of the current enterprise external public opinion data; and a current public opinion feature vector generating sub-unit 726 for inputting the word vector of the current enterprise external public opinion data obtained by the third word vector generating sub-unit 725 into the converter-based semantic understanding model to obtain the current public opinion feature vector.
In an example, in the lifetime bond management system 700 described above, as shown in fig. 7, the event feature vector generation unit 730 includes: a history data acquiring subunit 731 configured to acquire text data of one or more history events related to the plurality of current events; a historical event feature vector generating subunit 732, configured to pass the text data of the one or more historical events obtained by the historical data obtaining subunit 731 through the converter-based semantic understanding model respectively to obtain one or more historical event feature vectors; a reference event feature vector generation subunit 733, configured to, for each to-be-weighted feature vector in the plurality of current event feature vectors and the one or more historical event feature vectors obtained by the historical event feature vector generation subunit 732, obtain one or more reference event feature vectors corresponding to each to-be-weighted feature vector, where the reference event feature vectors are obtained by passing through the converter-based semantic understanding model for template text data of corresponding events; a weight value generating sub-unit 734, configured to, for each to-be-weighted feature vector in the plurality of current event feature vectors and the one or more historical event feature vectors obtained by the historical event feature vector generating sub-unit 732, respectively calculate a classification probability weight expression between each to-be-weighted feature vector and the one or more reference event feature vectors obtained by the reference event feature vector generating sub-unit 733 corresponding to the to-be-weighted feature vector to obtain a weight value corresponding to each to-be-weighted feature vector, wherein the classification probability weight is expressed as a quotient of a weighted sum of natural exponent function values raised to a power of a negative value of the feature value at each position in the feature vector to be weighted divided by a sum of weighted sums of natural exponent function values raised to a power of a negative value of the feature value at each position in the one or more reference event feature vectors; a weighting subunit 735, configured to weight each to-be-weighted feature vector with the weight value obtained by each weight value generating subunit 734 to obtain a plurality of weighted feature vectors; and a concatenation subunit 736, configured to concatenate the weighted feature vectors obtained by the weighting subunit 735 to obtain the event feature vector.
Here, it can be understood by those skilled in the art that the detailed functions and operations of the respective units and modules in the above-described renewal bond management system 700 have been described in detail in the above description of the renewal bond management method based on the block chain technology with reference to fig. 1 to 4, and thus, the repeated description thereof will be omitted.
As described above, the present invention can be implemented in various terminal devices, such as a server for use in the deposit bond management, and the like. In one example, the lifetime bond management system 700 according to embodiments of the present application may be integrated into the terminal device as one software module and/or hardware module. For example, the lifetime bond management system 700 may be a software module in the operating system of the terminal device, or may be an application developed for the terminal device; of course, the lifetime bond management system 700 may also be one of many hardware modules of the terminal device.
Alternatively, in another example, the deposit bond management system 700 and the terminal device may be separate devices, and the deposit bond management system 700 may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information according to an agreed data format.
Exemplary electronic device
Next, an electronic apparatus according to an embodiment of the present application is described with reference to fig. 8. As shown in fig. 8, the electronic device 10 includes one or more processors 11 and memory 12. The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium and executed by the processor 11 to implement the functions of the method for blockchain technology-based lifetime bond management of the various embodiments of the present application described above and/or other desired functions. Various contents such as a differential management feature vector, a weighted public opinion feature vector, etc. may also be stored in the computer readable storage medium.
In one example, the electronic device 10 may further include: an input system 13 and an output system 14, which are interconnected by a bus system and/or other form of connection mechanism (not shown).
The input system 13 may comprise, for example, a keyboard, a mouse, etc.
The output system 14 may output various information including classification results and the like to the outside. The output system 14 may include, for example, a display, speakers, a printer, and a communication network and its connected remote output devices, among others.
Of course, for simplicity, only some of the components of the electronic device 10 relevant to the present application are shown in fig. 8, and components such as buses, input/output interfaces, and the like are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.

Claims (9)

1. A method for managing a deposit duration bond based on a block chain technology is characterized by comprising the following steps:
acquiring text data of a plurality of current events for storing the renewal bonds, current enterprise operation data and current enterprise external public opinion data;
respectively passing the text data of the current events, the current enterprise operation data and the current enterprise external public opinion data through a converter-based semantic understanding model to obtain a plurality of current event feature vectors, current operation feature vectors and current public opinion feature vectors;
generating an event feature vector based on the plurality of current event feature vectors and one or more historical event feature vectors associated with the plurality of current events, wherein the one or more historical event feature vectors are obtained from text data of one or more historical events respectively through the converter-based semantic understanding model;
obtaining a plurality of historical business operation data and passing the historical business operation data through the semantic understanding model based on the converter to obtain a plurality of historical business characteristic vectors and calculating the average weighted sum of the plurality of historical business characteristic vectors to obtain an average historical business characteristic vector;
calculating a difference between the average historical operating feature vector and the current operating feature vector to obtain a difference operating feature vector;
activating the characteristic value of each position in the current public opinion characteristic vector by a Sigmoid function so as to map the characteristic value of each position in the current public opinion characteristic vector to an interval from 0 to 1 to obtain a probabilistic current public opinion characteristic vector;
calculating the information entropy of the characteristic value of each position in the probabilistic current public opinion characteristic vector, wherein the information entropy is obtained by multiplying the negative value of the logarithmic function value of the characteristic value of each position by the characteristic value of the position;
weighting the current public opinion feature vector by taking the information entropy of each position of the probabilistic current public opinion feature vector as a weight to obtain a weighted public opinion feature vector;
cascading the event feature vector, the differential operation feature vector and the weighted public opinion feature vector to obtain a classification feature vector and enabling the classification feature vector to pass through a classifier to obtain a classification result, wherein the classification result is used for representing a risk prediction result; and
and storing the text data of a plurality of current events of the lifetime bond, the current enterprise business data and the current enterprise external public opinion data in a storage block of a block chain architecture.
2. The method for blockchain technology-based lifetime bond management according to claim 1, wherein generating an event feature vector based on the plurality of current event feature vectors and one or more historical event feature vectors associated with the plurality of current events comprises:
acquiring text data of one or more historical events related to the plurality of current events;
respectively passing the text data of the one or more historical events through the converter-based semantic understanding model to obtain one or more historical event feature vectors;
for each feature vector to be weighted in the plurality of current event feature vectors and the one or more historical event feature vectors, acquiring one or more reference event feature vectors corresponding to each feature vector to be weighted, wherein the reference event feature vectors are obtained by passing template text data of corresponding events through the converter-based semantic understanding model;
for each to-be-weighted feature vector in the plurality of current event feature vectors and the one or more historical event feature vectors, respectively calculating a classification probability weight expression between each to-be-weighted feature vector and the one or more reference event feature vectors corresponding to the to-be-weighted feature vector to obtain a weight value corresponding to each to-be-weighted feature vector, wherein the classification probability weight expression is a quotient of a weighted sum of natural exponent function values raised to the negative of the feature value of each position in the to-be-weighted feature vector and a sum of weighted sums of natural exponent function values raised to the negative of the feature value of each position in the one or more reference event feature vectors;
weighting each feature vector to be weighted by each weight value to obtain a plurality of weighted feature vectors; and
concatenating the plurality of weighted feature vectors to obtain the event feature vector.
3. The method for managing the lifetime bonds based on the block chain technique according to claim 2, wherein for each feature vector to be weighted in the plurality of current event feature vectors and the one or more historical event feature vectors, respectively calculating a classification probability weight expression between each feature vector to be weighted and the one or more reference event feature vectors corresponding to the feature vector to be weighted to obtain a weight value corresponding to each feature vector to be weighted comprises:
calculating a classification probability weight expression between each feature vector to be weighted and the one or more reference event feature vectors corresponding to the feature vector to be weighted to obtain a weight value corresponding to each feature vector to be weighted, wherein the formula is as follows: p ═ Σiexp(-xi)/∑i，jexp (-yi), xi represents the feature value of each position of the feature vector to be weighted, and yi represents the feature value of each position of the reference event feature vector.
4. The method for managing lifetime bonds based on the blockchain technology as claimed in claim 2, wherein passing the text data of the current events, the current business operation data and the current business external public opinion data through a converter-based semantic understanding model to obtain current event feature vectors, current business feature vectors and current public opinion feature vectors, respectively, comprises:
respectively inputting the text data of the current events into a word embedding model to obtain word vectors of the current events;
respectively inputting the word vectors of the plurality of current events into the converter-based semantic understanding model to obtain a plurality of current event feature vectors;
inputting the current enterprise business data into the word embedding model to obtain a word vector of the current enterprise business data;
inputting a word vector of the current enterprise business data into the converter-based semantic understanding model to obtain the current business feature vector;
inputting the current enterprise external public opinion data into the word embedding model to obtain a word vector of the current enterprise external public opinion data; and
inputting the word vector of the current enterprise external public opinion data into the converter-based semantic understanding model to obtain the current public opinion feature vector.
5. The method for managing the existing bond based on the blockchain technology as claimed in claim 2, wherein the calculating of the information entropy of the feature value of each position in the probabilistic current public opinion feature vector comprises:
and calculating the information entropy of the characteristic value of each position in the probabilistic current public opinion characteristic vector by the following formula, wherein the formula is p ═ xi [ -log (xi) ], and xi represents the characteristic value of each position in the probabilistic current public opinion characteristic vector.
6. The method for managing a lifetime bond based on a blockchain technique according to claim 1, wherein storing text data of a plurality of current events of the lifetime bond, current business management data, and current business external public opinion data in a storage block of a blockchain architecture comprises:
and in response to the classification result being risk-free, storing text data of a plurality of current events of the lifetime bonds, current enterprise business data and current enterprise external public opinion data in a storage block of a block chain architecture.
7. The method for life cycle bond management based on block chain technology of claim 1, wherein the event comprises: major matters, bearer meetings, terms of application, credit events, and rating adjustment events.
8. A system for managing a life-cycle bond based on a block chain technique, comprising:
the data acquisition unit is used for acquiring text data of a plurality of current events for storing the renewal bonds, current enterprise operation data and current enterprise external public opinion data;
a current feature vector generating unit, configured to pass the text data of the multiple current events, the current enterprise business data, and the current enterprise external public opinion data obtained by the data obtaining unit through a converter-based semantic understanding model to obtain multiple current event feature vectors, current business feature vectors, and current public opinion feature vectors, respectively;
an event feature vector generating unit, configured to generate an event feature vector based on the plurality of current event feature vectors obtained by the current feature vector generating unit and one or more historical event feature vectors associated with the plurality of current events, where the one or more historical event feature vectors are obtained by text data of one or more historical events through the converter-based semantic understanding model, respectively;
a historical characteristic vector generating unit, which is used for acquiring a plurality of historical enterprise operation data and passing the historical enterprise operation data through the semantic understanding model based on the converter to obtain a plurality of historical operation characteristic vectors and calculating the average weighted sum of the plurality of historical operation characteristic vectors to obtain an average historical operation characteristic vector;
a differential operation feature vector generation unit configured to calculate a difference between the average historical operation feature vector obtained by the historical feature vector generation unit and the current operation feature vector obtained by the current feature vector generation unit to obtain a differential operation feature vector;
an activation unit, configured to activate, by using a Sigmoid function, the feature value of each position in the current public opinion feature vector obtained by the current feature vector generation unit to map the feature value of each position in the current public opinion feature vector into an interval from 0 to 1, so as to obtain a probabilistic current public opinion feature vector;
the information entropy calculation unit is used for calculating the information entropy of the characteristic value of each position in the probabilistic current public opinion characteristic vector obtained by the activation unit, wherein the information entropy is obtained by multiplying the negative value of the logarithmic function value of the characteristic value of each position by the characteristic value of the position;
a weighting unit configured to weight the current public opinion feature vector obtained by the current feature vector generation unit with the information entropy of each position of the probabilistic current public opinion feature vector obtained by the information entropy calculation unit as a weight to obtain a weighted public opinion feature vector;
a classification result generating unit, configured to cascade the event feature vector obtained by the event feature vector generating unit, the differential operation feature vector obtained by the differential operation feature vector generating unit, and the weighted public opinion feature vector obtained by the weighting unit to obtain a classification feature vector, and pass the classification feature vector through a classifier to obtain a classification result, where the classification result is used to represent a risk prediction result; and
and the storage unit is used for storing the text data of a plurality of current events of the lifetime bonds, the current enterprise business data and the current enterprise external public opinion data which are obtained by the data acquisition unit into a storage block of a block chain architecture.
9. The system for managing the lifetime bonds based on the block chain technology as claimed in claim 8, wherein said event feature vector generating unit comprises:
a historical data acquiring subunit, configured to acquire text data of one or more historical events related to the plurality of current events;
a historical event feature vector generating subunit, configured to pass the text data of the one or more historical events obtained by the historical data obtaining subunit through the converter-based semantic understanding model respectively to obtain one or more historical event feature vectors;
a reference event feature vector generating subunit, configured to obtain, for each to-be-weighted feature vector in the multiple current event feature vectors and the one or more historical event feature vectors obtained by the historical event feature vector generating subunit, one or more reference event feature vectors corresponding to each to-be-weighted feature vector, where the reference event feature vectors are obtained by passing template text data of corresponding events through the converter-based semantic understanding model;
a weighted value generating subunit, configured to, for each to-be-weighted feature vector in the plurality of current event feature vectors and the one or more historical event feature vectors obtained by the historical event feature vector generating subunit, respectively calculate a classification probability weight expression between each to-be-weighted feature vector and the one or more reference event feature vectors obtained by the reference event feature vector generating subunit corresponding to the to-be-weighted feature vector to obtain a weighted value corresponding to each to-be-weighted feature vector, wherein the classification probability weight is expressed as a quotient of a weighted sum of natural exponent function values raised to a power of a negative value of the feature value at each position in the feature vector to be weighted divided by a sum of weighted sums of natural exponent function values raised to a power of a negative value of the feature value at each position in the one or more reference event feature vectors;
the weighting subunit is configured to weight each to-be-weighted feature vector with the weight value obtained by each weight value generation subunit to obtain a plurality of weighted feature vectors; and
a cascade subunit, configured to cascade the weighted feature vectors obtained by the weighting subunit to obtain the event feature vector.
CN202110775310.0A 2021-07-08 2021-07-08 Block chain technology-based method for managing deposit duration bonds Withdrawn CN113450229A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110775310.0A CN113450229A (en) 2021-07-08 2021-07-08 Block chain technology-based method for managing deposit duration bonds

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110775310.0A CN113450229A (en) 2021-07-08 2021-07-08 Block chain technology-based method for managing deposit duration bonds

Publications (1)

Publication Number Publication Date
CN113450229A true CN113450229A (en) 2021-09-28

Family

ID=77815543

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110775310.0A Withdrawn CN113450229A (en) 2021-07-08 2021-07-08 Block chain technology-based method for managing deposit duration bonds

Country Status (1)

Country Link
CN (1) CN113450229A (en)

Similar Documents

Publication Publication Date Title
Kim et al. Financial series prediction using Attention LSTM
US20210264272A1 (en) Training method and system of neural network model and prediction method and system
US11468239B2 (en) Joint intent and entity recognition using transformer models
US11720615B2 (en) Self-executing protocol generation from natural language text
WO2021196954A1 (en) Serialized data processing method and device, and text processing method and device
CN110751286A (en) Training method and training system of neural network model
CN112084334B (en) Label classification method and device for corpus, computer equipment and storage medium
CN112256886B (en) Probability calculation method and device in atlas, computer equipment and storage medium
WO2018040067A1 (en) User guidance system and method
CN115392237B (en) Emotion analysis model training method, device, equipment and storage medium
CN110826315B (en) Method for identifying timeliness of short text by using neural network system
Zhang et al. Modeling and prediction of stock price with convolutional neural network based on blockchain interactive information
Cheng et al. Regulating systemic crises: Stemming the contagion risk in networked-loans through deep graph learning
CN113157853B (en) Problem mining method, device, electronic equipment and storage medium
US20230360421A1 (en) Natural language processing and text analytics for audit testing with documentation prioritization and selection
US11461616B2 (en) Method and system for analyzing documents
CN117033431A (en) Work order processing method, device, electronic equipment and medium
CN113379432B (en) Sales system customer matching method based on machine learning
CN113450229A (en) Block chain technology-based method for managing deposit duration bonds
CN115841365A (en) Model selection and quotation method, system, equipment and medium based on natural language processing
Temnov et al. A comparison of loss aggregation methods for operational risk
KR20230059364A (en) Public opinion poll system using language model and method thereof
Sehrawat Learning word embeddings from 10-K filings for financial NLP tasks
CN113450222A (en) Block chain technology-based method for managing deposit duration bonds
Meng et al. Classification of customer service tickets in power system based on character and word level semantic understanding

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
WW01 Invention patent application withdrawn after publication

Application publication date: 20210928

WW01 Invention patent application withdrawn after publication