CN117455688A

CN117455688A - Investment object screening method and device, storage medium and electronic device

Info

Publication number: CN117455688A
Application number: CN202311676898.XA
Authority: CN
Inventors: 何辉; 祝放; 杨智康; 林孙镇江
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-12-07
Filing date: 2023-12-07
Publication date: 2024-01-26

Abstract

The application discloses a screening method and device of investment objects, a storage medium and an electronic device. Relates to the field of financial science and technology, and the method comprises the following steps: receiving an object screening request, wherein the object screening request is used for requesting to screen out investment objects which are put into target resources; constructing a first data graph corresponding to each first investment object by using the investment data of N first investment objects in the database, wherein the first data graph comprises M nodes, the nodes in the first data graph are connected through directed edges, and the nodes are used for indicating the investment data of the corresponding first investment object; predicting matching parameters and risk parameters between each first investment object in the N first investment objects and the target resource according to the first data graph; and screening the second investment objects from the N first investment objects according to the matching parameters and the risk parameters. By the method and the device, the problem of low screening efficiency of investment objects in the related technology is solved.

Description

Investment object screening method and device, storage medium and electronic device

Technical financial science and technology field

The present application relates to the field of financial science and technology, and in particular, to a method and apparatus for screening investment objects, a storage medium, and an electronic apparatus.

Background

In the traditional data mining and machine learning technology, under the scene of huge amount of data or multi-source heterogeneous data, useful information needs to be extracted from the huge amount of data, and then analysis or processing of the data is carried out, so that complex relation data cannot be processed well, and particularly under the scene of huge amount of data or multi-source heterogeneous data, the efficiency of data processing is low and the accuracy is poor.

Aiming at the problem of low screening efficiency of investment objects in the related technology, no effective solution is proposed at present.

Disclosure of Invention

The main objective of the present application is to provide a method, an apparatus, a storage medium and an electronic device for screening investment objects, so as to solve the problem of low efficiency of investment object screening in the related art.

In order to achieve the above object, according to one aspect of the present application, there is provided a screening method of investment objects.

The method comprises the following steps:

receiving an object screening request, wherein the object screening request is used for requesting to screen out investment objects which are put into target resources;

constructing a first data graph corresponding to each first investment object by using investment data of N first investment objects in a database, wherein the first data graph comprises M nodes, the nodes in the first data graph are connected through directed edges, the nodes are used for indicating the investment data of the corresponding first investment objects, the directed edges are used for indicating the association relation between one connected node and the other node, the N first investment objects are investment objects allowed to be put into the target resource, N is a positive integer greater than or equal to 1, and M is a positive integer greater than 1;

Predicting a matching parameter and a risk parameter between each first investment object in the N first investment objects and the target resource according to the first data graph, wherein the matching parameter is used for indicating the matching degree between each first investment object and the target resource, and the risk parameter is used for indicating the risk degree of investing the target resource to each first investment object;

and screening a second investment object from the N first investment objects according to the matching parameters and the risk parameters, wherein the second investment object is used for being invested in the target resource.

Optionally, the constructing a first data graph corresponding to each first investment object by using data of N first investment objects in a database includes: screening investment objects allowed to be put into the target resource from all investment objects in the database to obtain the N first investment objects; extracting, for each first investment object, data whose data type matches the resource type of the target resource from the data of each first investment object included in the data in the database as target investment data of each first investment object; and constructing the target investment data into a first data graph corresponding to each first investment object.

Optionally, the constructing the target investment data into a first data map corresponding to each first investment object includes: creating the nodes for each of the target investment data, and recording the data value of each of the target investment data as the node attribute of each of the nodes; and connecting the directed edges among the nodes according to the data conversion relations among the target investment data to obtain a first data graph corresponding to each first investment object, wherein each data conversion relation corresponds to one directed edge.

Optionally, before the first data map corresponding to each first investment object is constructed by using the data of N first investment objects in the database, the method further includes: accessing an initial database into a data interface of a plurality of financial tools; importing financial data of each financial tool in the plurality of financial tools from the data interface to obtain a multi-source heterogeneous data set; extracting investment objects from the multi-source heterogeneous data set, and integrating financial data of each investment object in the plurality of financial tools to obtain investment objects and object data with corresponding relations; normalizing the object data of each investment object to obtain the database, wherein the normalizing comprises: numerical normalization processing and format normalization processing.

Optionally, the predicting, according to the first data map, matching parameters and risk parameters between each of the N first investment objects and the target resource includes: the N first data graphs are used as input data, the target resources are used as decision objects and are input into a target decision model, wherein the target decision model is obtained by training an initial decision model by using a data pattern book marked with matching parameter labels and risk parameter labels of different decision objects; and acquiring a first data graph, matching parameters and risk parameters which are output by the target decision model and have a corresponding relation.

Optionally, the screening a second investment object from the N first investment objects according to the matching parameter and the risk parameter, where the second investment object is used to be put into the target resource, includes: constructing a second data graph corresponding to the funding object by using the investment data of the funding object of the target resource in the database, wherein the second data graph comprises P nodes, the nodes in the second data graph are connected through directed edges, the nodes are used for indicating the investment data of the funding object, the directed edges are used for indicating the association relation between one connected node and the other node, and P is a positive integer greater than 1; determining a risk range corresponding to the target resource according to the second data graph, wherein the risk range is used for indicating a range which can be born by the investment risk of the sponsor for investing the target resource; screening third investment objects with the risk parameters falling within the risk range from the N first investment objects; and screening the second investment object from the third investment objects according to the matching parameters.

Optionally, the screening the second investment object from the third investment object according to the matching parameter includes one of the following: determining the investment object with the highest matching parameter in the third investment objects as the second investment object; screening candidate investment objects with the matching parameters higher than a matching parameter threshold value from the third investment objects; displaying the candidate investment object to the funding object; the candidate investment object selected by the sponsor object is determined to be the second investment object.

In order to achieve the above object, according to another aspect of the present application, there is provided a screening apparatus for investment objects.

The device comprises:

the receiving module is used for receiving an object screening request, wherein the object screening request is used for requesting to screen out investment objects which are put into target resources;

the construction module is used for constructing a first data graph corresponding to each first investment object by using investment data of N first investment objects in a database, wherein the first data graph comprises M nodes, the nodes in the first data graph are connected through directed edges, the nodes are used for indicating the investment data of the corresponding first investment objects, the directed edges are used for indicating the association relation between one connected node and the other node, the N first investment objects are investment objects allowed to be put into the target resource, N is a positive integer greater than or equal to 1, and M is a positive integer greater than 1;

A prediction module, configured to predict, according to the first data map, a matching parameter and a risk parameter between each of the N first investment objects and the target resource, where the matching parameter is used to indicate a degree of matching between each of the first investment objects and the target resource, and the risk parameter is used to indicate a degree of risk of investing the target resource to each of the first investment objects;

and the screening module is used for screening a second investment object from the N first investment objects according to the matching parameters and the risk parameters, wherein the second investment object is used for being invested in the target resource.

According to another aspect of the present application, there is also provided a computer readable storage medium having a computer program stored therein, wherein the computer program is arranged to execute the above-described investment object screening method at run-time.

According to another aspect of an embodiment of the present invention, there is also provided an electronic device including one or more processors; and a memory for storing one or more programs which, when executed by the one or more processors, cause the one or more processors to implement a method for running the program, wherein the program is configured to perform the above-described investment object screening method when run.

Through the application, the following steps are adopted: receiving an object screening request, wherein the object screening request is used for requesting to screen out investment objects which are put into target resources; constructing a first data graph corresponding to each first investment object by using investment data of N first investment objects in a database, wherein the first data graph comprises M nodes, the nodes in the first data graph are connected through directed edges, the nodes are used for indicating the investment data of the corresponding first investment objects, the directed edges are used for indicating the association relation between one connected node and the other node, the N first investment objects are investment objects allowed to be put into the target resource, N is a positive integer greater than or equal to 1, and M is a positive integer greater than 1; predicting a matching parameter and a risk parameter between each first investment object in the N first investment objects and the target resource according to the first data graph, wherein the matching parameter is used for indicating the matching degree between each first investment object and the target resource, and the risk parameter is used for indicating the risk degree of investing the target resource to each first investment object; and screening a second investment object from the N first investment objects according to the matching parameters and the risk parameters, wherein the second investment object is used for being put into the target resource, that is, the matching parameters and the risk parameters between the first investment object and the target resource are obtained by constructing a first data diagram corresponding to the first investment object, so that the second investment object is screened from the N first investment objects according to the matching parameters and the risk parameters. The problem of low efficiency of investment object screening in the related art is solved. Thereby achieving the effect of improving the screening efficiency of investment objects.

Drawings

The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the application and are not to be construed as limiting the application. In the drawings:

FIG. 1 is a flow chart of a method of screening investment objects provided in accordance with an embodiment of the present application;

FIG. 2 is a flow chart of a process of constructing a first data graph according to an embodiment of the present application;

FIG. 3 is a flow chart of a process of screening a second investment object according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a process of constructing a second data graph according to an embodiment of the present application;

FIG. 5 is a schematic diagram I of an investment object screening system according to an embodiment of the present application;

FIG. 6 is a schematic diagram II of an investment object screening system according to an embodiment of the present application;

FIG. 7 is a schematic diagram of an investment object screening apparatus provided in accordance with an embodiment of the present application;

fig. 8 is a schematic diagram of an electronic device according to an embodiment of the application.

Detailed Description

It should be noted that, in the case of no conflict, the embodiments and features in the embodiments may be combined with each other. The present application will be described in detail below with reference to the accompanying drawings in conjunction with embodiments.

In order to better understand the technical solutions of the present application by those skilled in the financial and technological arts, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which are obtained by persons of ordinary skill in the art without creative efforts, based on the embodiments in the application are intended to fall within the protection scope of the application.

It should be noted that the terms "first," "second," and the like in the description and claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe the embodiments of the present application described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

It should be noted that, the method for screening investment objects provided in the present application is applicable to a wide range of scenarios, and may be applied to any scenario that needs to be selected among a plurality of objects, where the investment objects may include, but are not limited to: stock, enterprise, commodity, product, etc. The above-mentioned investment object screening method may be applicable to the scene including, but not limited to: screening among multiple stocks, screening among multiple enterprises, screening among multiple products, etc. The above-described investment object screening method may be applied, but is not limited to, in any scenario where selection among a plurality of objects is desired.

It should be noted that, related information (which may include, but is not limited to, user equipment information, user personal information, etc.) and data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present disclosure are information and data authorized by a user or sufficiently authorized by each party. For example, an interface is provided between the system and the relevant user or institution, before acquiring the relevant information, the system needs to send an acquisition request to the user or institution through the interface, and acquire the relevant information after receiving the consent information fed back by the user or institution.

In the following, the present application will be described in connection with preferred implementation steps, and fig. 1 is a flowchart of a method for screening investment objects according to an embodiment of the present application, as shown in fig. 1, the method includes the following steps:

step S101, receiving an object screening request, wherein the object screening request is used for requesting to screen out investment objects which are put into target resources;

step S102, constructing a first data graph corresponding to each first investment object by using investment data of N first investment objects in a database, wherein the first data graph comprises M nodes, the nodes in the first data graph are connected through directed edges, the nodes are used for indicating the investment data of the corresponding first investment objects, the directed edges are used for indicating the association relation between one connected node and the other node, the N first investment objects are investment objects allowed to be put into the target resource, N is a positive integer greater than or equal to 1, and M is a positive integer greater than 1;

step S103, predicting matching parameters and risk parameters between each first investment object and the target resource in the N first investment objects according to the first data graph, wherein the matching parameters are used for indicating the matching degree between each first investment object and the target resource, and the risk parameters are used for indicating the risk degree of investing the target resource to each first investment object;

Step S104, screening a second investment object from the N first investment objects according to the matching parameters and the risk parameters, wherein the second investment object is used for being invested in the target resource.

Through the steps, receiving an object screening request, wherein the object screening request is used for requesting to screen out investment objects which are put into target resources; constructing a first data graph corresponding to each first investment object by using investment data of N first investment objects in a database, wherein the first data graph comprises M nodes, the nodes in the first data graph are connected through directed edges, the nodes are used for indicating the investment data of the corresponding first investment objects, the directed edges are used for indicating the association relation between one connected node and the other node, the N first investment objects are investment objects allowed to be put into the target resource, N is a positive integer greater than or equal to 1, and M is a positive integer greater than 1; predicting a matching parameter and a risk parameter between each first investment object in the N first investment objects and the target resource according to the first data graph, wherein the matching parameter is used for indicating the matching degree between each first investment object and the target resource, and the risk parameter is used for indicating the risk degree of investing the target resource to each first investment object; and screening a second investment object from the N first investment objects according to the matching parameters and the risk parameters, wherein the second investment object is used for being put into the target resource, that is, the matching parameters and the risk parameters between the first investment object and the target resource are obtained by constructing a first data diagram corresponding to the first investment object, so that the second investment object is screened from the N first investment objects according to the matching parameters and the risk parameters. The problem of low efficiency of investment object screening in the related art is solved. Thereby achieving the effect of improving the screening efficiency of investment objects.

In the solution provided in step S101, the object screening request may be, but not limited to, sent from a client, or may be, but not limited to, using a server to receive and respond to the object screening request, where responding to the object screening request may be, but not limited to, including screening out the most suitable investment object from a plurality of investment objects stored in the server, to input the target resource.

Alternatively, in this embodiment, in the case of receiving the object filtering request, the target resource may be acquired at the same time, for example, but not limited to: receiving an object screening request for indicating that a target resource input to an investment object is a user asset under the condition of screening target stocks from a plurality of stocks; in the case where the object screening request is used to instruct screening of a target company from a plurality of companies, the target resource invested in the investment object may include, but is not limited to, manpower, assets, and the like.

Optionally, in this embodiment, the object screening request may also, but is not limited to, a condition for indicating screening of the investment object, such as: selecting the stock with the highest fluctuation range from a plurality of stocks as an investment object to be put into a target resource, wherein the stock can be determined as the investment object without limitation, and the object screening request can carry the instruction with the highest fluctuation range without limitation; alternatively, the most-historically-effective company is selected from the plurality of companies as the investment target resource, wherein the company may be determined as the investment target, and the most-historically-effective indication may be carried in the target screening request.

In the solution provided in the step S102, the database may, but is not limited to, store a total of N first investment objects and investment data of each first investment object, where the investment data of the first investment object may, but is not limited to, include a plurality of parameters of the first investment object, such as: taking the first investment object as stock as an example, the investment data may include, but is not limited to, stock codes, stock prices, market rates, stock information rates, market values, volume of deals, risk indexes, etc.; taking the first investment object as an example of a company, the investment data may include, but is not limited to, revenue, net profit, liability statement, cash flow, market value, employee number, industry status, etc.; taking the first investment object as an example of a fixed asset, the investment data may include, but is not limited to, monetary amount, deadline, depreciation, lifetime, return on investment, etc.

Alternatively, in this embodiment, the investment object indicated in the object screening request may be obtained by parsing the object screening request, and then N first investment objects related to the object screening request may be obtained from the database, for example: obtaining an object screening request indication according to the object screening request to screen stocks, wherein the stocks are investment objects, and all the stocks can be obtained from a database as a first investment object; alternatively, the object screening request is obtained according to the object screening request to instruct to screen the company, where the company is the investment object, and all the companies may be acquired from the database as the first investment object, but not limited to, and the like.

Alternatively, in this embodiment, the database may be, but is not limited to, a database for storing the first investment objects for which the object screening request may be screened and the investment data of the first investment objects, and in the case where N first investment objects related to the object screening request and the investment data of each first investment object are acquired from the database according to the object screening request, a first data map corresponding to each first investment object may be, but is not limited to, constructed, in which the investment data of the first investment objects may be, but is not limited to, used as nodes, and the directed edge connection of the investment data may be used according to the association relationship between one node connected to another node until the first data map is obtained.

In an exemplary embodiment, before the first data map corresponding to each of the first investment objects is constructed using the data of the N first investment objects in the database, the database may be obtained, but is not limited to, in the following manner: accessing an initial database into a data interface of a plurality of financial tools; importing financial data of each financial tool in the plurality of financial tools from the data interface to obtain a multi-source heterogeneous data set; extracting investment objects from the multi-source heterogeneous data set, and integrating financial data of each investment object in the plurality of financial tools to obtain investment objects and object data with corresponding relations; normalizing the object data of each investment object to obtain the database, wherein the normalizing comprises: numerical normalization processing and format normalization processing.

Alternatively, in this embodiment, the initial database is a system for storing and organizing data, and may, but not limited to, use different kinds of databases according to the structure and type of the stored data, and the databases may, but not limited to, include: relational Databases (RDBMS) use structures of tables and rows to store data, and use SQL (structured query language) to manage and retrieve data, such as: mySQL, oracle, SQL, server, etc. Non-relational databases (NOSQL) use documents, key-value pairs, column families or graphs to store data, and are suitable for large-scale distributed data storage, such as: mongoDB, cassandra, redis, etc. Data warehouse: database systems that are dedicated to storing and analyzing large amounts of data, such as: teradata, vertica, etc. Object database: databases with objects as the basic unit of storage allow for the storage of complex data structures suitable for use in object-oriented applications such as: db4o, objectDB, etc. Graphic database: databases for storing graphic structures are suitable for use with complex relational networks such as: neo4j, arangondb, etc.

Alternatively, in this embodiment, the initial database may include, but is not limited to, a plurality of components, which may include, but are not limited to, a data interface for accessing the initial database into a plurality of financial instruments, and acquiring corresponding financial data from the plurality of financial instruments for storage. The data interface may be, but is not limited to, an interface disposed on a financial instrument for outputting financial data, which may include, but is not limited to, stocks, bonds, futures, foreign exchange, etc.

Alternatively, in the present embodiment, the multi-source heterogeneous data set may include, but is not limited to, financial data of a plurality of financial instruments acquired through a data interface. Financial data for multiple investment objects in the same aspect may be acquired, but is not limited to, by the same financial instrument, such as: financial data of the investment object A and the investment object B in the aspect A is acquired through the financial tool A, financial data of the investment object A and the investment object B in the aspect B is acquired through the financial tool B, and the like.

Alternatively, financial data of multiple investment objects in different aspects may be acquired, but not limited to, through the same financial instrument, such as: financial data of the investment object a in the aspect a, financial data of the investment object B in the aspect B, and the like are acquired through the financial tool a. Alternatively, financial data for multiple investment objects in different aspects may be acquired by, but not limited to, different financial instruments, such as: financial data of the investment object a in the aspect a, financial data of the investment object B in the aspect B, and the like are acquired through the financial tool a.

Alternatively, in the present embodiment, in the case where a multi-source heterogeneous data set composed of financial data of each of a plurality of financial instruments is obtained, an investment object that may be indicated by an object screening request may be extracted from the multi-source heterogeneous data set, and financial data of each investment object in the plurality of financial instruments may be integrated to obtain an investment object and object data having a correspondence relationship.

Alternatively, in this embodiment, operations such as adding, deleting, querying, modifying, etc. may be performed, but not limited to, adding, deleting, querying, modifying, etc. may be performed by using components of the micro-computing service such as querying and filtering, etc., for example: the service database provides services such as adding, deleting, querying, modifying, online algorithm and the like of partial data in the database through an API (Application Programming Interface ).

Alternatively, in the present embodiment, in the case of obtaining the investment object and the object data having the correspondence relationship, the numerical normalization processing and the format normalization processing may be performed on the investment object and the object data, and the numerical normalization processing may include, but is not limited to, mapping the object data of different value ranges into a uniform range. The format normalization process may, but is not limited to, include converting the object data into a uniform format, and may, but is not limited to, include: date format normalization, text format normalization, etc.

In one exemplary embodiment, the first data map corresponding to each of the N first investment objects in the database may be constructed using, but is not limited to, the data of the first investment objects in the database in the following manner: screening investment objects allowed to be put into the target resource from all investment objects in the database to obtain the N first investment objects; extracting, for each first investment object, data whose data type matches the resource type of the target resource from the data of each first investment object included in the data in the database as target investment data of each first investment object; and constructing the target investment data into a first data graph corresponding to each first investment object.

Alternatively, in this embodiment, the investment object stored in the database may be, but is not limited to, a target resource into which it can be put, such as: target resources to which stocks can be put include, for investment targets: funds, etc.; the target resources that can be invested in a company as an investment target include: stock, funds, manpower, goods, etc.

Alternatively, in this embodiment, in the case of receiving the object screening request, the target resource may be determined according to the object screening request, but not limited to, so as to screen out investment objects allowed to be put into the target resource from all investment objects in the database.

Alternatively, in this embodiment, the first investment object may, but is not limited to, have a plurality of data types of financial data, and may, but is not limited to, obtain the target investment data of the first investment object from the financial data of the first investment object according to the resource type of the target resource, for example: taking the first investment object as a stock as an example, the financial data of the first investment object may include, but is not limited to, stock codes, stock prices, market rates, stock information rates, market values, volume of deals, risk indexes, etc., and may include, but is not limited to, acquiring stock prices, market information rates, market values, risk indexes, etc., as target investment data.

Alternatively, in this embodiment, the first data map is constructed for each first investment object using the target investment data, and the target investment data is mapped to the state space, which may be, but is not limited to, represented by a vector, and the first data map is represented by a matrix.

In one exemplary embodiment, the target investment data may be constructed as a first data map corresponding to each of the first investment objects in the following manner, but is not limited to: creating the nodes for each of the target investment data, and recording the data value of each of the target investment data as the node attribute of each of the nodes; and connecting the directed edges among the nodes according to the data conversion relations among the target investment data to obtain a first data graph corresponding to each first investment object, wherein each data conversion relation corresponds to one directed edge.

Alternatively, in this embodiment, but not limited to, each target investment data of the first investment object may be used as a node of the first data graph, a data value of each target investment data is recorded as a node attribute of each node, and directed edges between the nodes are connected according to a data conversion relationship between the target investment data, so as to obtain the first data graph corresponding to each first investment object.

Optionally, in this embodiment, fig. 2 is a flowchart of a process for constructing a first data map according to an embodiment of the present application, and as shown in fig. 2, the corresponding first data map may be constructed for the first investment object by, but not limited to, the following steps:

step S202: receiving an object screening request;

step S204: screening a database for a first investment object allowed to be invested in a target resource;

step S206: extracting data with the data type matched with the resource type of the target resource from the database as target investment data of the first investment object;

step S208: creating a node for each target investment data, and recording a data value of each target investment data as a node attribute of each node;

step S210: connecting directed edges among the nodes according to the data conversion relation among the target investment data;

step S212: and obtaining a first data graph corresponding to each first investment object.

In the technical solution provided in the above step S103, the matching degree between each first investment object and the target resource may be detected through, but not limited to, the first data map, where the matching degree may include, but is not limited to, a matching parameter and a risk parameter. The degree of matching between the first investment object and the target resource may be, but is not limited to, determined as a matching parameter between the first investment object and the target resource, such as: the degree of compliance of the first investment object with the target resource under a plurality of parameters, which may include, but are not limited to, funds, market prospects, investment deadlines, expected returns, etc., is determined from the first data map. The matching degree of the first investment object and the target resource under the multiple parameters can be calculated as the matching degree, and then the matching parameters of the first investment object and the target resource can be comprehensively evaluated according to the matching degree of the multiple parameters.

Alternatively, in this embodiment, the risk level of the target resource investment to each first investment object may be determined as a risk parameter between the first investment object and the target resource, such as: and obtaining market conditions, predicting volatility and maximum withdrawal of the target resource from the target resource investment to the first investment object, predicting loss possibility of the target resource investment to the first investment object, and further measuring indexes of the target resource relative to the market integral fluctuation by using Beta coefficients so as to determine risk parameters between the first investment object and the target resource.

In one exemplary embodiment, the matching parameters and risk parameters between each of the N first investment objects and the target resource may be predicted from the first data map, but are not limited to, in the following manner: the N first data graphs are used as input data, the target resources are used as decision objects and are input into a target decision model, wherein the target decision model is obtained by training an initial decision model by using a data pattern book marked with matching parameter labels and risk parameter labels of different decision objects; and acquiring a first data graph, matching parameters and risk parameters which are output by the target decision model and have a corresponding relation.

Optionally, in this embodiment, N first data graphs may be, but not limited to, sequentially input into the target decision model as input data, and the target resource is input into the target decision model as a decision object, where for N first data graphs, the target decision model may be, but not limited to, used to calculate matching parameters and risk parameters between different first data graphs and the same target resource. That is, for the target decision model, the target decision model is used to determine matching parameters and risk parameters between each first investment object and the same target resource.

Optionally, in this embodiment, the target decision model is obtained by training an initial decision model using a data pattern book labeled with matching parameter labels and risk parameter labels of different decision objects, and may, but not limited to, use a different initial model as the initial decision model, where the initial model may, but not limited to, include: decision trees, neural networks, deep learning models, and the like.

Further, taking the initial decision model as an example of a decision tree, the initial decision model may be, but is not limited to, trained to obtain a target decision model by:

Step one: obtaining data graph samples marked with matching parameter labels and risk parameter labels of different decision objects, and using the different decision objects as features;

step two: selecting the optimal dividing characteristic, so that the purity of the divided subsets is higher;

step three: constructing a decision tree recursively according to the selected partitioning characteristics from the root node;

step four: in order to prevent overfitting, pruning is carried out on the constructed decision tree;

step five: and testing the trained decision tree by using the test data pattern book and adjusting the depth of the decision tree to obtain a target decision model.

In the solution provided in step S104, the matching parameter may be, but is not limited to, used to indicate the degree of matching between the first investment object and the target resource, and may be, but is not limited to, considered that the higher the matching parameter is, the higher the degree of matching between the first investment object and the target resource is. The risk parameter may be, but is not limited to, a risk indicating a target resource to be invested in the first investment object, and may be, but is not limited to, a higher degree of matching between the first investment object and the target resource as the risk parameter is considered to be higher. Thus, an investment object with the highest matching parameter and the lowest risk parameter may be selected from the N first investment objects as the second investment object, or an investment object with both matching parameters and risk parameters within the target range may be selected as the second investment object.

In one exemplary embodiment, a second investment object may be selected from the N first investment objects according to the matching parameters and the risk parameters, in the following manner, wherein the second investment object is used to be invested in the target resource: constructing a second data graph corresponding to the funding object by using the investment data of the funding object of the target resource in the database, wherein the second data graph comprises P nodes, the nodes in the second data graph are connected through directed edges, the nodes are used for indicating the investment data of the funding object, the directed edges are used for indicating the association relation between one connected node and the other node, and P is a positive integer greater than 1; determining a risk range corresponding to the target resource according to the second data graph, wherein the risk range is used for indicating a range which can be born by the investment risk of the sponsor for investing the target resource; screening third investment objects with the risk parameters falling within the risk range from the N first investment objects; and screening the second investment object from the third investment objects according to the matching parameters.

Alternatively, in this embodiment, the investment data of the sponsored object may be used as a node, the association relationship between the investment data is used as a directed edge of the connection node to construct a second data map corresponding to the sponsored object, and the risk range corresponding to the target resource may be obtained by determining, according to the second data map, the range that the sponsored object can bear for the investment risk of the investment target resource.

Optionally, in this embodiment, in the case of obtaining the risk range corresponding to the target resource, the risk range corresponding to the target resource may be, but not limited to, taken as a reference object, and the third investment object whose risk parameter falls within the risk range may be screened from the N first investment objects.

Alternatively, in the present embodiment, the investment object falling within the range of the matching parameter may be selected as the second investment object from the third investment objects according to the matching parameter, but is not limited to the present embodiment.

In one exemplary embodiment, the second investment object may be screened from the third investment object according to the matching parameters in one of, but not limited to: determining the investment object with the highest matching parameter in the third investment objects as the second investment object; screening candidate investment objects with the matching parameters higher than a matching parameter threshold value from the third investment objects; displaying the candidate investment object to the funding object; the candidate investment object selected by the sponsor object is determined to be the second investment object.

Alternatively, in the present embodiment, the investment object with the highest matching parameter among the third investment objects may be determined as the second investment object, but is not limited to the first investment object. Alternatively, candidate investment objects with matching parameters higher than the matching parameter threshold value are selected from the third investment objects, and in the case that the candidate investment objects are determined, the candidate investment objects may be, but are not limited to, presented to the investment object, selected by the investment object, and the candidate investment object selected by the investment object is determined as the second investment object.

Alternatively, in this embodiment, the matching parameter threshold may be, but is not limited to, a predetermined fixed value, or a value that varies from one investment object to another.

Alternatively, in the present embodiment, fig. 3 is a flowchart of a process for screening a second investment object according to an embodiment of the present application, as shown in fig. 3, the second investment object may be, but is not limited to, screened from N first investment objects by:

step S302: constructing a first data graph corresponding to each first investment object by using the investment data of N first investment objects in the database;

step S304: predicting matching parameters and risk parameters between each first investment object and the target resource according to the first data graph;

Step S306: constructing a second data graph corresponding to the funding object by using the investment data of the funding object of the target resource in the database;

step S308: determining a risk range corresponding to the target resource according to the second data graph;

step S310: screening third investment objects with risk parameters falling into a risk range from the N first investment objects;

step S312: determining the investment object with the highest matching parameter in the third investment object as a second investment object;

step S314: screening candidate investment objects with the matching parameters higher than the matching parameter threshold value from the third investment objects; displaying the candidate investment object to the investment object; the candidate investment object selected by the sponsor object is determined to be the second investment object.

Alternatively, in the present embodiment, fig. 4 is a schematic diagram of a process of constructing a second data map according to an embodiment of the present application, as shown in fig. 4, the second data map may be constructed by, but not limited to, the following method: investment data may be, but is not limited to, previously acquired from a plurality of financial instruments and stored in a database, and the investment data may be, but is not limited to, loaded into a database under a corresponding server using loaders (loader 1 and loader 2) during the acquisition of the investment data.

In constructing the second data map, investment data corresponding to the sponsored object of the target resource is obtained from databases (which may include, but are not limited to, database 1, database 2, database 3, and database 4) and the second data map is constructed.

Optionally, in this embodiment, fig. 5 is a schematic diagram of an investment object screening system according to an embodiment of the present application, as shown in fig. 5, where the investment object screening system may, but is not limited to, include a data preprocessing module, a prediction module, a result output module, and a loading module and a storage module for storing data, and the investment object screening system may, but is not limited to, screen the second investment object from N first investment objects according to an object screening request by:

the data (data) preprocessing module can be used for accessing a plurality of financial tools, importing financial data of each financial tool to obtain a multi-source heterogeneous data set, carrying out normalization processing on each data in the multi-source heterogeneous data set, and loading the data into the storage module in the server through the loading module.

In the case of receiving the object screening request, the prediction module may, but is not limited to, obtain investment data of N first investment objects from the storage module through the loading module and construct a first data map corresponding to each first investment object using the investment data.

The prediction module may also, but is not limited to, be configured to predict a matching parameter and a risk parameter between each of the N first investment objects and the target resource according to the first data map, and then screen the second investment object from the N first investment objects according to the matching parameter and the risk parameter.

Optionally, in this embodiment, fig. 6 is a schematic diagram two of an investment object screening system according to an embodiment of the present application, as shown in fig. 6, the investment object screening system may, but is not limited to, include a data preprocessing module, a prediction module, a result output module, and a loading module and a storage module for storing data, where the prediction module deploys a target decision model, and the investment object screening system may, but is not limited to, screen a second investment object from N first investment objects according to an object screening request by:

The prediction module may be further, but not limited to, configured to train the initial decision model by using the data pattern book labeled with the matching parameter label and the risk parameter label of the different decision objects in advance to obtain a target decision model, and in the case of obtaining the first data map corresponding to each first investment object, may be, but not limited to, output the first data map, the matching parameter and the risk parameter having a corresponding relationship by using the target decision model with the first data map as input data, and then screen the second investment object by using the first data map, the matching parameter and the risk parameter.

According to the investment object screening method, the matching parameters and the risk parameters between the first investment object and the target resource are obtained by constructing the first data diagram corresponding to the first investment object, so that the second investment object is screened out of N first investment objects according to the matching parameters and the risk parameters. The problem of low efficiency of investment object screening in the related art is solved. Thereby achieving the effect of improving the screening efficiency of investment objects.

It should be noted that the steps illustrated in the flowcharts of the figures may be performed in a computer system such as a set of computer executable instructions, and that although a logical order is illustrated in the flowcharts, in some cases the steps illustrated or described may be performed in an order other than that illustrated herein.

The embodiment of the application also provides a screening device for investment objects, and it should be noted that the screening device for investment objects of the embodiment of the application can be used for executing the screening method for investment objects provided by the embodiment of the application. The following describes a screening apparatus for investment objects provided in the embodiments of the present application.

Fig. 7 is a schematic diagram of an investment object screening apparatus provided in accordance with an embodiment of the present application. As shown in fig. 7, the apparatus includes:

A receiving module 702, configured to receive an object screening request, where the object screening request is used to request screening of an investment object that is put into a target resource;

a building module 704, configured to build a first data graph corresponding to each first investment object by using investment data of N first investment objects in a database, where the first data graph includes M nodes, the nodes in the first data graph are connected by a directed edge, the nodes are used to indicate investment data that the corresponding first investment objects have, the directed edge is used to indicate an association relationship between one connected node and another node, the N first investment objects are investment objects allowed to be put into the target resource, N is a positive integer greater than or equal to 1, and M is a positive integer greater than 1;

a prediction module 706, configured to predict, according to the first data map, a matching parameter and a risk parameter between each of the N first investment objects and the target resource, where the matching parameter is used to indicate a degree of matching between each of the first investment objects and the target resource, and the risk parameter is used to indicate a degree of risk of investing the target resource to each of the first investment objects;

A screening module 708, configured to screen a second investment object from the N first investment objects according to the matching parameter and the risk parameter, where the second investment object is used to be invested in the target resource.

Optionally, in the investment object screening apparatus provided in the embodiment of the present application, the building module includes:

a first screening unit, configured to screen out investment objects allowed to be put into the target resource from all investment objects in the database, so as to obtain the N first investment objects;

an extracting unit configured to extract, for each first investment object, data whose data type matches a resource type of the target resource from among data of each first investment object included in the data in the database as target investment data of each first investment object;

and the first construction unit is used for constructing the target investment data into a first data diagram corresponding to each first investment object.

Optionally, in the investment object screening apparatus provided in the embodiment of the present application, the first construction unit is further configured to: creating the nodes for each of the target investment data, and recording the data value of each of the target investment data as the node attribute of each of the nodes; and connecting the directed edges among the nodes according to the data conversion relations among the target investment data to obtain a first data graph corresponding to each first investment object, wherein each data conversion relation corresponds to one directed edge.

Optionally, in the investment object screening apparatus provided in the embodiment of the present application, the apparatus further includes:

the access module is used for accessing the initial database into the data interfaces of a plurality of financial tools;

the importing module is used for importing financial data of each financial tool in the plurality of financial tools from the data interface to obtain a multi-source heterogeneous data set;

the first processing module is used for extracting investment objects from the multi-source heterogeneous data set and integrating financial data of each investment object in the plurality of financial tools to obtain investment objects and object data with corresponding relations;

the second processing module is used for carrying out normalization processing on the object data of each investment object to obtain the database, wherein the normalization processing comprises the following steps: numerical normalization processing and format normalization processing.

Optionally, in the investment object screening apparatus provided in the embodiment of the present application, the prediction module includes:

the input unit is used for taking N first data graphs as input data, and the target resources are taken as decision objects to be input into a target decision model, wherein the target decision model is obtained by training an initial decision model by using a data pattern book marked with matching parameter labels and risk parameter labels of different decision objects;

The acquisition unit is used for acquiring the first data graph, the matching parameters and the risk parameters which are output by the target decision model and have the corresponding relation.

Optionally, in the investment object screening apparatus provided in the embodiments of the present application, the screening module includes:

a second construction unit, configured to construct a second data graph corresponding to a sponsor object of the target resource by using investment data of the sponsor object in the database, where the second data graph includes P nodes, and the nodes in the second data graph are connected by a directed edge, where the nodes are used to indicate investment data that the sponsor object has, and the directed edge is used to indicate an association relationship between one connected node and another node, and P is a positive integer greater than 1;

the determining unit is used for determining a risk range corresponding to the target resource according to the second data graph, wherein the risk range is used for indicating a range which the investment risk of the funding object for investing the target resource can bear;

the second screening unit is used for screening third investment objects with the risk parameters falling within the risk range from the N first investment objects;

And the third screening unit is used for screening the second investment object from the third investment objects according to the matching parameters.

Optionally, in the investment object screening apparatus provided in the embodiment of the present application, the third screening unit is further configured to: determining the investment object with the highest matching parameter in the third investment objects as the second investment object; screening candidate investment objects with the matching parameters higher than a matching parameter threshold value from the third investment objects; displaying the candidate investment object to the funding object; the candidate investment object selected by the sponsor object is determined to be the second investment object.

The investment object screening device provided by the embodiment of the application receives an object screening request, wherein the object screening request is used for requesting to screen out an investment object which is put into a target resource; constructing a first data graph corresponding to each first investment object by using investment data of N first investment objects in a database, wherein the first data graph comprises M nodes, the nodes in the first data graph are connected through directed edges, the nodes are used for indicating the investment data of the corresponding first investment objects, the directed edges are used for indicating the association relation between one connected node and the other node, the N first investment objects are investment objects allowed to be put into the target resource, N is a positive integer greater than or equal to 1, and M is a positive integer greater than 1; predicting a matching parameter and a risk parameter between each first investment object in the N first investment objects and the target resource according to the first data graph, wherein the matching parameter is used for indicating the matching degree between each first investment object and the target resource, and the risk parameter is used for indicating the risk degree of investing the target resource to each first investment object; and screening a second investment object from the N first investment objects according to the matching parameters and the risk parameters, wherein the second investment object is used for being put into the target resource, that is, the matching parameters and the risk parameters between the first investment object and the target resource are obtained by constructing a first data diagram corresponding to the first investment object, so that the second investment object is screened from the N first investment objects according to the matching parameters and the risk parameters. The problem of low efficiency of investment object screening in the related art is solved. Thereby achieving the effect of improving the screening efficiency of investment objects.

The screening device of the investment object comprises a processor and a memory, wherein the modules, the units and the like are stored in the memory as program units, and the processor executes the program units stored in the memory to realize corresponding functions.

The processor includes a kernel, and the kernel fetches the corresponding program unit from the memory. The kernel can be provided with one or more than one kernel, and the efficiency of screening the objects is improved by adjusting kernel parameters.

The memory may include volatile memory, random Access Memory (RAM), and/or nonvolatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM), among other forms in computer readable media, the memory including at least one memory chip.

Embodiments of the present application provide a computer-readable storage medium having stored thereon a program that, when executed by a processor, implements a method of screening an investment object.

The embodiment of the application provides a processor which is used for running a program, wherein the program runs to execute the screening method of the investment objects.

As shown in fig. 8, an embodiment of the present application provides an electronic device, where the device includes a processor, a memory, and a program stored on the memory and executable on the processor, and when the processor executes the program, the following steps are implemented:

The device herein may be a server, PC, PAD, cell phone, etc.

The present application also provides a computer program product adapted to perform, when executed on a data processing device, a program initialized with the method steps of:

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

In one typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.

The memory may include volatile memory in a computer-readable medium, random Access Memory (RAM) and/or nonvolatile memory, etc., such as Read Only Memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

Computer readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium, which can be used to store information that can be accessed by a computing device. Computer-readable media, as defined herein, does not include transitory computer-readable media (transmission media), such as modulated data signals and carrier waves.

It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article or apparatus that comprises an element.

It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.

The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations will be apparent to those skilled in the art. Any modifications, equivalent substitutions, improvements, etc. which are within the spirit and principles of the present application are intended to be included within the scope of the claims of the present application.

Claims

1. A method for screening an investment object, comprising:

2. The method of claim 1, wherein constructing a first data map corresponding to each of the first investment objects using the data of the N first investment objects in the database comprises:

screening investment objects allowed to be put into the target resource from all investment objects in the database to obtain the N first investment objects;

extracting, for each first investment object, data whose data type matches the resource type of the target resource from the data of each first investment object included in the data in the database as target investment data of each first investment object;

And constructing the target investment data into a first data graph corresponding to each first investment object.

3. The method of claim 2, wherein said constructing said target investment data as a first data map for each of said first investment objects comprises:

creating the nodes for each of the target investment data, and recording the data value of each of the target investment data as the node attribute of each of the nodes;

and connecting the directed edges among the nodes according to the data conversion relations among the target investment data to obtain a first data graph corresponding to each first investment object, wherein each data conversion relation corresponds to one directed edge.

4. The method of claim 1, wherein prior to constructing a first data map for each of the first investment objects using the data for the N first investment objects in the database, the method further comprises:

accessing an initial database into a data interface of a plurality of financial tools;

importing financial data of each financial tool in the plurality of financial tools from the data interface to obtain a multi-source heterogeneous data set;

Extracting investment objects from the multi-source heterogeneous data set, and integrating financial data of each investment object in the plurality of financial tools to obtain investment objects and object data with corresponding relations;

normalizing the object data of each investment object to obtain the database, wherein the normalizing comprises: numerical normalization processing and format normalization processing.

5. The method of claim 1, wherein predicting matching parameters and risk parameters between each of the N first investment objects and the target resource from the first data map comprises:

the N first data graphs are used as input data, the target resources are used as decision objects and are input into a target decision model, wherein the target decision model is obtained by training an initial decision model by using a data pattern book marked with matching parameter labels and risk parameter labels of different decision objects;

and acquiring a first data graph, matching parameters and risk parameters which are output by the target decision model and have a corresponding relation.

6. The method of claim 1, wherein the screening a second investment object from the N first investment objects based on the matching parameters and the risk parameters, wherein the second investment object is for being devoted to the target resource, comprises:

Constructing a second data graph corresponding to the funding object by using the investment data of the funding object of the target resource in the database, wherein the second data graph comprises P nodes, the nodes in the second data graph are connected through directed edges, the nodes are used for indicating the investment data of the funding object, the directed edges are used for indicating the association relation between one connected node and the other node, and P is a positive integer greater than 1;

determining a risk range corresponding to the target resource according to the second data graph, wherein the risk range is used for indicating a range which can be born by the investment risk of the sponsor for investing the target resource;

screening third investment objects with the risk parameters falling within the risk range from the N first investment objects;

and screening the second investment object from the third investment objects according to the matching parameters.

7. The method of claim 6, wherein said screening said second investment object from said third investment objects based on said matching parameters comprises one of:

determining the investment object with the highest matching parameter in the third investment objects as the second investment object;

Screening candidate investment objects with the matching parameters higher than a matching parameter threshold value from the third investment objects; displaying the candidate investment object to the funding object; the candidate investment object selected by the sponsor object is determined to be the second investment object.

8. A screening apparatus for investment objects, comprising:

a construction module, configured to construct a first data graph corresponding to each first investment object by using investment data of N first investment objects in a database, where the first data graph includes M nodes, and the nodes in the first data graph are connected by a directed edge, where the nodes are used to indicate investment data that the corresponding first investment object has, and the directed edge is used to indicate an association relationship between one connected node and another node, where the N first investment objects are investment objects allowed to be put into the target resource,

n is a positive integer greater than or equal to 1, M is a positive integer greater than 1;

9. A processor for running a program, wherein the program when run performs the method of any one of claims 1 to 7.

10. An electronic device comprising one or more processors and memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of any of claims 1-7.