CN111260219A - Asset class identification method, device, equipment and computer readable storage medium - Google Patents
Asset class identification method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN111260219A CN111260219A CN202010046271.6A CN202010046271A CN111260219A CN 111260219 A CN111260219 A CN 111260219A CN 202010046271 A CN202010046271 A CN 202010046271A CN 111260219 A CN111260219 A CN 111260219A
- Authority
- CN
- China
- Prior art keywords
- asset
- information
- case information
- identified
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 49
- 239000013598 vector Substances 0.000 claims description 72
- 238000012545 processing Methods 0.000 claims description 37
- 238000012549 training Methods 0.000 claims description 14
- 238000002372 labelling Methods 0.000 claims description 13
- 238000007477 logistic regression Methods 0.000 claims description 6
- 238000012954 risk control Methods 0.000 description 28
- 230000008859 change Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000005457 optimization Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000001737 promoting effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012502 risk assessment Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0645—Rental transactions; Leasing transactions
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/18—Legal services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- General Physics & Mathematics (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Finance (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an asset class identification method, an asset class identification device, asset class identification equipment and a computer readable storage medium, wherein the method comprises the following steps: receiving asset information to be identified; and inputting the asset information to be identified into a preset asset identification model, and obtaining the asset type corresponding to the asset information to be identified, wherein the asset type comprises normal assets and poor assets. By adopting the pre-trained asset identification model to identify the asset information to be identified, the asset type corresponding to the asset information to be identified can be accurately identified, and further unnecessary loss of companies and enterprises can be avoided.
Description
Technical Field
The present invention relates to the field of computers, and in particular, to an asset class identification method, device, apparatus, and computer-readable storage medium.
Background
The bad assets refer to the legal relationship formed by the fact that the rights and interests of the enterprises cannot be recovered or a small amount of rights and interests cannot be recovered after the enterprises borrow or rent the capital, commodities, technologies and the like of the enterprises to other companies. And poor assets tend to cause unnecessary losses to the company enterprise.
Therefore, in order to avoid unnecessary loss to companies and enterprises, it is necessary to discriminate the defective assets. However, in the prior art, the bad assets cannot be effectively distinguished, and the dynamic changes of the assets and the risks to be faced by the assets cannot be analyzed and identified in real time.
Disclosure of Invention
The invention provides an asset type identification method, an asset type identification device, asset type identification equipment and a computer readable storage medium, which are used for solving the technical problem that the asset type cannot be identified in the prior art.
The first aspect of the invention provides an asset class identification method, which comprises the following steps:
acquiring asset case information;
performing data processing on the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
marking the characteristic vectors according to the asset types corresponding to the characteristic vectors to obtain data to be trained;
training a preset model to be trained through the data to be trained to obtain an asset identification model;
receiving asset information to be identified;
inputting the asset information to be identified into the asset identification model, and obtaining an asset type corresponding to the asset information to be identified, wherein the asset type comprises normal assets and poor assets;
the performing data processing on the asset case information to obtain at least one group of feature vectors corresponding to the asset case information includes:
for each set of the property case information, determining a data category of the property case information, the data category comprising discrete data and continuous data;
and performing data processing on the asset case information according to the data type of the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information.
Another aspect of the present invention provides an asset class identification apparatus comprising:
the acquisition module is used for acquiring asset case information;
the processing module is used for carrying out data processing on the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
the marking module is used for marking the characteristic vectors according to the asset types corresponding to the characteristic vectors to obtain data to be trained;
the training module is used for training a preset model to be trained through the data to be trained to obtain an asset identification model;
the to-be-identified asset receiving module is used for receiving the information of the to-be-identified asset;
the identification module is used for inputting the asset information to be identified into a preset asset identification model and acquiring asset types corresponding to the asset information to be identified, wherein the asset types comprise normal assets and poor assets;
the processing module is used for:
for each set of the property case information, determining a data category of the property case information, the data category comprising discrete data and continuous data;
and performing data processing on the asset case information according to the data type of the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information.
Still another aspect of the present invention provides an asset class identification device including: a memory, a processor;
a memory; a memory for storing the processor-executable instructions;
wherein the processor is configured to execute the asset class identification method as described above by the processor.
Yet another aspect of the present invention is to provide a computer-readable storage medium having stored therein computer-executable instructions for implementing the asset class identification method as described above when executed by a processor.
The asset type identification method, the device, the equipment and the computer readable storage medium provided by the invention receive the asset information to be identified; and inputting the asset information to be identified into a preset asset identification model, and obtaining the asset type corresponding to the asset information to be identified, wherein the asset type comprises normal assets and poor assets. By adopting the pre-trained asset identification model to identify the asset information to be identified, the asset type corresponding to the asset information to be identified can be accurately identified, and further unnecessary loss of companies and enterprises can be avoided. In addition, the asset case information and the asset identification model are stored in the block chain, so that all nodes in the block chain can check the asset case information and call the asset identification model, the transparency of the information is improved, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art according to the drawings.
FIG. 1 is a schematic diagram of a network architecture on which the present invention is based;
FIG. 2 is a schematic flowchart of an asset class identification method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating an asset class identification method according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of an asset class identification device according to a third embodiment of the present invention;
fig. 5 is a schematic structural diagram of an asset class identification device according to a fourth embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other examples obtained based on the examples in the present invention are within the scope of the present invention.
In view of the above-mentioned technical problem that the asset class cannot be identified in the prior art, the present invention provides an asset class identification method, apparatus, device and computer readable storage medium.
It should be noted that the asset class identification method, device, equipment and computer readable storage medium provided by the present application may be applied to a scenario of identifying any asset class.
Fig. 1 is a schematic diagram of a network architecture based on the present invention, and as shown in fig. 1, the network architecture based on the present invention at least includes: an asset class identification device 1 and a terminal device 2. The asset class identification device 1 may be in communication connection with the terminal device 2, so that the asset class identification device 1 may send an identification result to the terminal device 2 after identifying the asset class, so that the user can know the asset class in time. The asset type identification device 1 can be written by C/C + +, Java, Shell or Python languages and the like; the terminal device 2 may be a desktop computer, a tablet computer, or the like.
Fig. 2 is a schematic flowchart of an asset class identification method according to an embodiment of the present invention, and as shown in fig. 2, the method includes:
102, performing data processing on the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
103, marking the characteristic vectors according to the asset types corresponding to the characteristic vectors to obtain data to be trained;
104, training a preset model to be trained through the data to be trained to obtain an asset identification model;
105, receiving asset information to be identified;
for each set of the property case information, determining a data category of the property case information, the data category comprising discrete data and continuous data;
and performing data processing on the asset case information according to the data type of the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information.
The execution subject of the present embodiment is an asset class identification device. In order to identify the asset class, the asset information to be identified needs to be received, wherein the asset information may include, but is not limited to, asset risk control and case management information, asset composition configuration information, negative inventory information, asset cash flow information, asset composition change information, bad asset replacement and update information, asset tracking information, and other asset risk control and management update information in asset securitization. After receiving the asset information to be identified, the asset information to be identified may be input into a preset asset identification model, and the asset information to be identified is identified by the asset identification model, and accordingly, the asset identification model may output the asset type corresponding to the asset information to be identified. It should be noted that the asset identification model is a model obtained by training a large amount of asset case information in advance, and can accurately identify the asset type of the asset information to be identified, where the asset type includes normal assets and bad assets, and the bad assets refer to legal relationships formed by borrowing or leasing funds, commodities, technologies and the like of an enterprise to other companies, and the rights and interests cannot be withdrawn or are withdrawn by a small amount.
In order to realize the identification of the asset information to be identified through the asset identification model, the asset identification model needs to be trained and obtained first. Specifically, data to be trained can be obtained, the asset case information labeled according to the asset type in the data to be trained is trained on a preset model to be trained through the data to be trained until the model converges, and therefore the asset identification model can be obtained.
In order to train the model to be trained and obtain the asset identification model, the data to be trained need to be obtained first. Specifically, first, asset case information may be obtained from a blockchain. The system comprises a blockchain, a plurality of nodes and a plurality of database nodes, wherein each node can upload asset case information in the blockchain periodically, and the asset case information comprises asset risk control and case management information, asset composition configuration information, negative list information, asset cash flow information, asset composition change information, poor asset replacement and update information, asset tracking information and other asset risk control and management update information in asset securitization. Accordingly, after the asset case information is acquired, data processing can be performed on the asset case information, and the asset case information is converted into at least one set of feature vectors corresponding to the asset case information. And for each set of feature vectors, the asset type of the asset case information is known in advance, so that for each set of feature vectors, the asset type corresponding to the feature vector can be determined, and the data to be trained is obtained by labeling according to the feature vectors. Specifically, the feature vector may be labeled in any manner, for example, the feature vector corresponding to the undesirable asset may be labeled as an undesirable asset, the feature vector corresponding to the normal asset may be labeled as a normal asset, the feature vector corresponding to the undesirable asset may also be labeled as Failure, and the feature vector corresponding to the normal asset may be labeled as Success, which is not limited herein.
The asset class identification method provided by the invention receives the asset information to be identified; and inputting the asset information to be identified into a preset asset identification model, and obtaining the asset type corresponding to the asset information to be identified, wherein the asset type comprises normal assets and poor assets. By adopting the pre-trained asset identification model to identify the asset information to be identified, the asset type corresponding to the asset information to be identified can be accurately identified, and further unnecessary loss of companies and enterprises can be avoided.
In this example, the pre-stored asset information to be identified may be obtained from the blockchain, or the asset information to be identified may be obtained from an organization (e.g., a company base business organization) that is to identify the asset.
Specifically, on the basis of any of the above embodiments, the model to be trained is a logistic regression model.
In this embodiment, the model to be trained may specifically be a logistic regression model. An important basis or method for regression models is regression analysis, which is a calculation method and theory for studying the specific dependency relationship of one variable (an explained variable) on another variable (an explained variable), and logistic regression is used to calculate the probability of "event ═ Success" and "event ═ Failure". Therefore, in order to accurately identify whether the asset type of the asset information to be identified is a normal asset or a bad asset, the logistic regression model can be selected as the model to be trained, so that the asset type of the asset information to be identified can be accurately identified.
In addition, after the asset recognition model is obtained through training, on the basis of any of the above embodiments, the asset recognition model may be stored in a preset node in a blockchain, so that all nodes participating in the blockchain can obtain and use the asset recognition model, and the transparency of information is improved.
According to the asset class identification method provided by the embodiment, the asset identification model is obtained by obtaining the data to be trained and training the preset model to be trained through the data to be trained, so that a basis is provided for accurate identification of subsequent asset information to be identified.
Further, on the basis of any of the above embodiments, the step 101 specifically includes:
asset case information is obtained from a blockchain.
Further, on the basis of any of the above embodiments, after the step 102, the method further includes:
storing the asset information to be identified and the asset type corresponding to the asset information to be identified to a preset storage path in an associated manner;
and when the asset information to be identified stored in the storage path and the asset type corresponding to the asset information to be identified exceed a preset threshold value, updating the asset identification model according to the asset information to be identified and the asset type corresponding to the asset information to be identified.
In this embodiment, after determining the asset type corresponding to the asset information to be identified, the asset information to be identified and the asset type corresponding to the asset information to be identified may be stored in a node or a storage path preset in the block chain in an associated manner. In order to improve the accuracy of the asset identification model identification, the asset identification model can be updated through the data stored in the storage path as the data stored in the storage path increases. Specifically, when it is detected that the asset information to be identified stored in the storage path and the asset type corresponding to the asset information to be identified exceed a preset threshold value, the asset identification model is trained according to the asset information to be identified and the asset type corresponding to the asset information to be identified, so that the identification accuracy of the asset identification model is improved. As an implementation manner, the asset identification model may also be trained by using the asset information to be identified in the preset storage path and the asset type corresponding to the asset information to be identified according to a preset time period.
According to the asset class identification method provided by the embodiment, the asset identification model is trained according to the asset information to be identified and the asset type corresponding to the asset information to be identified, so that the identification accuracy of the asset identification model can be effectively improved.
Further, on the basis of any of the above embodiments, the labeling the feature vector for the asset type corresponding to each feature vector to obtain the data to be trained includes:
if the asset case information corresponding to the feature vector is normal assets, marking the feature vector as a first feature value;
and if the asset case information corresponding to the feature vector is the poor asset, marking the feature vector as a second feature value.
In this embodiment, for each piece of asset case information, the asset case information includes an asset type corresponding to the asset case information, and accordingly, after the asset type of the asset case information is known in advance, for each group of feature vectors, the asset type corresponding to the feature vector may be determined, and the data to be trained is obtained by labeling according to the feature vectors. Specifically, if the asset case information corresponding to the feature vector is a normal asset, the feature vector may be labeled as a first feature value, and the first feature value may be 1. If the asset case information corresponding to the feature vector is an undesirable asset, the feature vector may be labeled as a second feature value, and the second feature value may be specifically 0. It should be noted that the first characteristic value and the second characteristic value may be any values as long as the first characteristic value is ensured to be distinguishable from the second characteristic value, and the present invention is not limited herein.
Correspondingly, after the to-be-trained data formed by the marked feature vectors are trained to obtain the asset identification model, the asset identification model can output the feature values corresponding to the to-be-identified asset information after receiving the to-be-identified asset information, and then the asset type of the to-be-identified asset information can be determined according to the corresponding relation between the feature values and the to-be-identified asset information.
Further, after the data to be trained is obtained, the model to be trained can be trained through the data to be trained.
According to the asset class identification method provided by the embodiment, the asset case information is acquired and is subjected to data processing, the asset case information after the data processing is labeled according to the asset type, so that the data to be trained can be acquired, and the acquired asset identification model can accurately identify the asset intensity after the model to be trained is trained according to the data to be trained because the data to be trained is accurately labeled according to the asset type.
Further, on the basis of any of the above embodiments, the performing data processing on the property case information to obtain at least one set of feature vectors corresponding to the property case information includes:
for each set of the property case information, determining a data category of the property case information, the data category comprising discrete data and continuous data;
and performing data processing on the asset case information according to the data type of the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information.
In this embodiment, the asset case information may be discrete data or continuous data, and for different data categories, different processing methods need to be adopted in the data processing process. Therefore, in order to implement data processing on the asset case information of any data type, firstly, the data type of the asset case information is determined for each group of asset case information, and the asset case information is processed in different data processing modes according to the data type of the asset case information to obtain at least one group of feature vectors corresponding to the asset case information.
Specifically, on the basis of any of the above embodiments, the performing data processing on the property case information according to the data category of the property case information includes:
if the asset case information is discrete data, labeling the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
and if the asset case information is continuous data, discretizing the asset case information to obtain discretized asset case information, labeling the discretized asset case information, and obtaining at least one group of characteristic vectors corresponding to the asset case information.
In this embodiment, different data processing methods may be used to perform data processing on the property case information according to the data type of the property case information. Specifically, if the data type of the asset case information is determined to be discrete data, the discrete data can be directly labeled to obtain at least one group of feature vectors corresponding to the asset case information. Correspondingly, if the data type of the asset case information is determined to be continuous data, the continuous data needs to be converted into discrete data, discretization processing can be performed on the asset case information to obtain discretized asset case information, the discrete data is labeled to obtain at least one group of feature vectors corresponding to the asset case information. It should be noted that any labeling and discretization method can be adopted to realize the labeling and discretization of the asset case information, and the invention is not limited herein.
According to the asset class identification method provided by the embodiment, the data class of the asset case information is determined according to each group of asset case information, the asset case information is subjected to data processing in different data processing modes according to the data class of the asset case information, and at least one group of feature vectors corresponding to the asset case information is obtained, so that a basis can be provided for obtaining the subsequent data to be trained.
The invention further provides an asset type identification device, which specifically comprises a blockchain network construction subsystem, an information storage and information authentication data format definition subsystem, an asset risk control and management information storage subsystem in asset securitization, an asset risk control and management subsystem in asset securitization and a system performance evaluation subsystem. The block chain network construction subsystem is used for constructing a block chain network for asset risk control and management trading in asset securitization by taking a company basic business organization as a minimum node and one or more groups/companies; the information storage and information authentication data format definition subsystem is used for storing and authenticating shared information and the like according to the data structure mode, the information storage mode and the protocol defined by the invention so as to ensure the high efficiency of information storage and information processing; the asset risk control and management information storage subsystem in asset securitization is used for uploading asset risk control and management update information in asset securitization, such as asset risk control and management cases, asset composition configuration information, negative inventory information, asset cash flow information, asset composition change information, bad asset replacement and update information, asset tracking information and the like, to a block chain by an enterprise or an individual registered in the system, so that the related materials such as audio, video, images and the like of the related materials can be proved to be uploaded to the block chain; the asset risk control and management subsystem in asset securitization is used for protecting privacy (authority management, watermarking, encryption and the like), disclosing transparency, traceability, being not easy to be tampered and the like) according to asset risk control and management information and the like in asset securitization stored in a block chain; the system performance evaluation subsystem is used for evaluating timeliness, effectiveness and accuracy of an asset risk control and management system in asset securitization, and continuously adjusting and optimizing system parameters based on a combined optimization and risk prediction method of real-time asset configuration information dynamic change conditions and real-time asset transparent tracking information so as to effectively realize asset risk control and management in asset securitization in a block chain network, thereby effectively promoting effective popularization of the block chain technology in the aspect of asset risk control and management in asset securitization.
Table 1 shows an example of storing asset risk control and management information in asset securitization based on a data structure of a blockchain technique:
TABLE 1
Table 2 is an example of a data structure for the asset securitization risk analysis and identification model stored in the blockchain:
TABLE 3
Fig. 3 is a schematic structural diagram of an asset class identification device according to a third embodiment of the present invention, and as shown in fig. 3, the asset class identification device includes:
the to-be-identified asset receiving module 31 is configured to receive asset information to be identified;
and the identification module 32 is configured to input the asset information to be identified to a preset asset identification model, and obtain an asset type corresponding to the asset information to be identified, where the asset type includes a normal asset and an undesirable asset.
The asset type identification device provided by the embodiment receives the asset information to be identified; and inputting the asset information to be identified into a preset asset identification model, and obtaining the asset type corresponding to the asset information to be identified, wherein the asset type comprises normal assets and poor assets. By adopting the pre-trained asset identification model to identify the asset information to be identified, the asset type corresponding to the asset information to be identified can be accurately identified, and further unnecessary loss of companies and enterprises can be avoided.
Further, on the basis of any one of the above embodiments, the apparatus further includes:
the training data acquisition module is used for acquiring training data;
the training module is used for training a preset model to be trained through the data to be trained to obtain the asset identification model, wherein the model to be trained is a logistic regression model;
and storing the asset identification model to a preset node in a block chain.
Further, on the basis of any of the above embodiments, the to-be-trained data acquisition module includes:
the acquisition unit is used for acquiring the asset case information from the block chain;
the data processing unit is used for carrying out data processing on the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
and the marking unit is used for marking the characteristic vectors according to the asset types corresponding to the characteristic vectors to obtain the data to be trained.
Further, on the basis of any of the above embodiments, the data processing unit is specifically configured to:
for each set of the property case information, determining a data category of the property case information, the data category comprising discrete data and continuous data;
and performing data processing on the asset case information according to the data type of the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information.
Further, on the basis of any of the above embodiments, the data processing unit is specifically configured to:
if the asset case information is discrete data, labeling the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
and if the asset case information is continuous data, discretizing the asset case information to obtain discretized asset case information, labeling the discretized asset case information, and obtaining at least one group of characteristic vectors corresponding to the asset case information.
Further, on the basis of any of the above embodiments, the labeling unit is specifically configured to:
if the asset case information corresponding to the feature vector is normal assets, marking the feature vector as a first feature value;
and if the asset case information corresponding to the feature vector is the poor asset, marking the feature vector as a second feature value.
Further, on the basis of any of the above embodiments, after the asset information to be identified is input to a preset asset identification model and an asset type corresponding to the asset information to be identified is obtained, the method further includes:
storing the asset information to be identified and the asset type corresponding to the asset information to be identified to a preset storage path in an associated manner;
and when the asset information to be identified stored in the storage path and the asset type corresponding to the asset information to be identified exceed a preset threshold value, updating the asset identification model according to the asset information to be identified and the asset type corresponding to the asset information to be identified.
It should be understood that the above division of the modules of the asset class identification apparatus shown in fig. 3 is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity or may be physically separated. And these modules can be realized in the form of software called by processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling by the processing element in software, and part of the modules can be realized in the form of hardware.
Fig. 4 is a schematic structural diagram of an asset class identification system according to still another embodiment of the present invention, and as shown in fig. 4, the asset class identification system specifically includes an asset risk control and management information storage subsystem 41 in asset securitization, an asset risk control and management subsystem 42 in asset securitization, and a system performance evaluation subsystem 43. Specifically, the asset risk control and management information storage subsystem 41 in asset securitization is specifically configured to upload, to a blockchain, asset risk control and management update information in asset securitization, such as asset risk control and management cases, asset composition configuration information, negative inventory information, asset cash flow information, asset composition change information, bad asset replacement and update information, asset tracking information, and the like, of an enterprise or an individual registered in the system, and may prove that related materials, such as audio, video, images, and the like, of the related materials may also be uploaded to the blockchain. The asset risk control and management subsystem 42 in asset securitization is particularly used for providing a combined optimization and risk prediction method based on the dynamic change condition of real-time asset configuration information and real-time asset transparent tracking information according to the characteristics of privacy protection (authority management, watermarking, encryption and the like), open transparency, traceability, difficult tampering and the like of asset risk control and management information and the like in asset securitization stored in a block chain, according to the historical data of asset risk control and management information in the asset securitization in the block chain, the system automatically analyzes and identifies the risk (becoming bad asset) possibly faced by the real-time dynamic change of the asset and sends prompt information and recommendation of a solution to related personnel (asset management personnel, security investors and the like), therefore, the effective popularization of the block chain technology applied to the aspect of asset risk control and management in asset securitization is powerfully promoted. Accordingly, the asset class identification method is not described herein in detail in any of the above embodiments. The system performance evaluation subsystem 43 is specifically configured to evaluate timeliness, effectiveness and accuracy of an asset risk control and management system in asset securitization, and continuously adjust and optimize system parameters based on a combined optimization and risk prediction method of a dynamic change condition of real-time asset configuration information and real-time asset transparent tracking information, so as to effectively realize asset risk control and management in asset securitization in a block chain network, thereby powerfully promoting effective popularization of application of a block chain technology to asset risk control and management in asset securitization.
Fig. 5 is a schematic structural diagram of an asset class identification device according to a fourth embodiment of the present invention, and as shown in fig. 5, the asset class identification device includes: a memory 51, a processor 52;
a memory 51; a memory 51 for storing instructions executable by the processor 52;
wherein the processor 52 is configured to execute the asset class identification method according to any of the above embodiments by the processor 52.
Yet another embodiment of the present invention provides a computer-readable storage medium, having stored therein computer-executable instructions for implementing the asset class identification method according to any one of the above embodiments when executed by a processor.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working process of the apparatus described above may refer to the corresponding process in the foregoing method embodiment, and is not described herein again.
Those of ordinary skill in the art will understand that: all or a portion of the steps of implementing the above-described method embodiments may be performed by hardware associated with program instructions. The program may be stored in a computer-readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. An asset class identification method, comprising:
acquiring asset case information;
performing data processing on the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
marking the characteristic vectors according to the asset types corresponding to the characteristic vectors to obtain data to be trained;
training a preset model to be trained through the data to be trained to obtain an asset identification model;
receiving asset information to be identified;
inputting the asset information to be identified into the asset identification model, and obtaining an asset type corresponding to the asset information to be identified, wherein the asset type comprises normal assets and poor assets;
the performing data processing on the asset case information to obtain at least one group of feature vectors corresponding to the asset case information includes:
for each set of the property case information, determining a data category of the property case information, the data category comprising discrete data and continuous data;
and performing data processing on the asset case information according to the data type of the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information.
2. The method of claim 1, wherein the model to be trained is a logistic regression model.
3. The method according to claim 1, wherein after the preset model to be trained is trained through the data to be trained to obtain an asset recognition model, the method further comprises:
and storing the asset identification model to a preset node in a block chain.
4. The method of claim 1, wherein the obtaining of the asset-case information comprises:
asset case information is obtained from a blockchain.
5. The method of claim 4, wherein the data processing the asset-case information according to the data categories of the asset-case information comprises:
if the asset case information is discrete data, labeling the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
and if the asset case information is continuous data, discretizing the asset case information to obtain discretized asset case information, labeling the discretized asset case information, and obtaining at least one group of characteristic vectors corresponding to the asset case information.
6. The method according to any one of claims 2 to 5, wherein the labeling the feature vectors for the asset type corresponding to each feature vector to obtain the data to be trained comprises:
if the asset case information corresponding to the feature vector is normal assets, marking the feature vector as a first feature value;
and if the asset case information corresponding to the feature vector is the poor asset, marking the feature vector as a second feature value.
7. The method according to any one of claims 1 to 5, wherein after the asset information to be identified is input into a preset asset identification model and an asset type corresponding to the asset information to be identified is obtained, the method further comprises:
storing the asset information to be identified and the asset type corresponding to the asset information to be identified to a preset storage path in an associated manner;
and when the asset information to be identified stored in the storage path and the asset type corresponding to the asset information to be identified exceed a preset threshold value, updating the asset identification model according to the asset information to be identified and the asset type corresponding to the asset information to be identified.
8. An asset class identification device, comprising:
the acquisition module is used for acquiring asset case information;
the processing module is used for carrying out data processing on the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information;
the marking module is used for marking the characteristic vectors according to the asset types corresponding to the characteristic vectors to obtain data to be trained;
the training module is used for training a preset model to be trained through the data to be trained to obtain an asset identification model;
the to-be-identified asset receiving module is used for receiving the information of the to-be-identified asset;
the identification module is used for inputting the asset information to be identified into a preset asset identification model and acquiring asset types corresponding to the asset information to be identified, wherein the asset types comprise normal assets and poor assets;
the processing module is used for:
for each set of the property case information, determining a data category of the property case information, the data category comprising discrete data and continuous data;
and performing data processing on the asset case information according to the data type of the asset case information to obtain at least one group of characteristic vectors corresponding to the asset case information.
9. An asset class identification device, comprising: a memory, a processor;
a memory; a memory for storing the processor-executable instructions;
wherein the processor is configured to perform the asset class identification method of any of claims 1-7 by the processor.
10. A computer-readable storage medium having computer-executable instructions stored thereon, which when executed by a processor, are configured to implement the asset class identification method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010046271.6A CN111260219A (en) | 2020-01-16 | 2020-01-16 | Asset class identification method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010046271.6A CN111260219A (en) | 2020-01-16 | 2020-01-16 | Asset class identification method, device, equipment and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111260219A true CN111260219A (en) | 2020-06-09 |
Family
ID=70950580
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010046271.6A Pending CN111260219A (en) | 2020-01-16 | 2020-01-16 | Asset class identification method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111260219A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112822208A (en) * | 2021-02-01 | 2021-05-18 | 北京邮电大学 | Internet of things equipment identification method and system based on block chain |
| CN117312833A (en) * | 2023-11-29 | 2023-12-29 | 北京冠群信息技术股份有限公司 | Data identification method and system applied to digital asset environment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140030724A (en) * | 2012-09-03 | 2014-03-12 | 주식회사 신한은행 | Method for providing asset management service and portfolio report by bank server and the same bank server |
| CN109033471A (en) * | 2018-09-05 | 2018-12-18 | 中国信息安全测评中心 | A kind of information assets recognition methods and device |
| CN109657894A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium |
| CN109726763A (en) * | 2018-12-29 | 2019-05-07 | 北京神州绿盟信息安全科技股份有限公司 | A kind of information assets recognition methods, device, equipment and medium |
| CN109862037A (en) * | 2019-03-22 | 2019-06-07 | 泰康保险集团股份有限公司 | Data equipment management method, device, medium and electronic equipment based on block chain |
| CN110033159A (en) * | 2019-02-27 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Risk Identification Method, device and equipment |
| CN110364257A (en) * | 2019-07-18 | 2019-10-22 | 泰康保险集团股份有限公司 | People's vehicle Risk Forecast Method, device, medium and electronic equipment |
-
2020
- 2020-01-16 CN CN202010046271.6A patent/CN111260219A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140030724A (en) * | 2012-09-03 | 2014-03-12 | 주식회사 신한은행 | Method for providing asset management service and portfolio report by bank server and the same bank server |
| CN109033471A (en) * | 2018-09-05 | 2018-12-18 | 中国信息安全测评中心 | A kind of information assets recognition methods and device |
| CN109657894A (en) * | 2018-09-27 | 2019-04-19 | 深圳壹账通智能科技有限公司 | Credit Risk Assessment of Enterprise method for early warning, device, equipment and storage medium |
| CN109726763A (en) * | 2018-12-29 | 2019-05-07 | 北京神州绿盟信息安全科技股份有限公司 | A kind of information assets recognition methods, device, equipment and medium |
| CN110033159A (en) * | 2019-02-27 | 2019-07-19 | 阿里巴巴集团控股有限公司 | Risk Identification Method, device and equipment |
| CN109862037A (en) * | 2019-03-22 | 2019-06-07 | 泰康保险集团股份有限公司 | Data equipment management method, device, medium and electronic equipment based on block chain |
| CN110364257A (en) * | 2019-07-18 | 2019-10-22 | 泰康保险集团股份有限公司 | People's vehicle Risk Forecast Method, device, medium and electronic equipment |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112822208A (en) * | 2021-02-01 | 2021-05-18 | 北京邮电大学 | Internet of things equipment identification method and system based on block chain |
| CN117312833A (en) * | 2023-11-29 | 2023-12-29 | 北京冠群信息技术股份有限公司 | Data identification method and system applied to digital asset environment |
| CN117312833B (en) * | 2023-11-29 | 2024-02-27 | 北京冠群信息技术股份有限公司 | Data identification method and system applied to digital asset environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107945024B (en) | Method for identifying internet financial loan enterprise operation abnormity, terminal equipment and storage medium | |
| US10346782B2 (en) | Adaptive augmented decision engine | |
| JP2019519021A (en) | Performance model bad influence correction | |
| CN113011646B (en) | Data processing method, device and readable storage medium | |
| US20210112101A1 (en) | Data set and algorithm validation, bias characterization, and valuation | |
| Abril et al. | Improving record linkage with supervised learning for disclosure risk assessment | |
| Liu et al. | Can listing information indicate borrower credit risk in online peer-to-peer lending? | |
| Popchev et al. | Aspects of the evolution from risk management to enterprise global risk management | |
| CN111260219A (en) | Asset class identification method, device, equipment and computer readable storage medium | |
| CN110009371B (en) | Abnormal behavior determination method, device, equipment and computer readable storage medium | |
| US20160086122A1 (en) | System and method for providing multi objective multi criteria vendor management | |
| US20240086736A1 (en) | Fault detection and mitigation for aggregate models using artificial intelligence | |
| CN112702410B (en) | Evaluation system, method and related equipment based on blockchain network | |
| US20220058554A1 (en) | Risk management | |
| US11314892B2 (en) | Mitigating governance impact on machine learning | |
| US20190303781A1 (en) | System and method for implementing a trust discretionary distribution tool | |
| CN112686762B (en) | Policy data violation detection method and device, computer equipment and storage medium | |
| CN112712270B (en) | Information processing method, device, equipment and storage medium | |
| CN114493853A (en) | Credit rating evaluation method, credit rating evaluation device, electronic device and storage medium | |
| EP3751500B1 (en) | System and method for technology recommendations | |
| WO2021158984A1 (en) | Methods and systems for facilitating analysis of a model | |
| CN112818235A (en) | Violation user identification method and device based on associated features and computer equipment | |
| US20240161117A1 (en) | Trigger-Based Electronic Fund Transfers | |
| WO2024039017A1 (en) | Method and apparatus for managing quality of data | |
| Treleaven et al. | Future Data-Driven Regulation |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200609 |