CN115619569A - Data processing method, data processing device, computer equipment and storage medium - Google Patents
Data processing method, data processing device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN115619569A CN115619569A CN202211285844.6A CN202211285844A CN115619569A CN 115619569 A CN115619569 A CN 115619569A CN 202211285844 A CN202211285844 A CN 202211285844A CN 115619569 A CN115619569 A CN 115619569A
- Authority
- CN
- China
- Prior art keywords
- thrown
- index
- input
- pool
- objects
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/06—Asset management; Financial planning or analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Economics (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Technology Law (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Human Resources & Organizations (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application relates to a data processing method, a data processing device, a computer device, a storage medium and a computer program product, which are used for acquiring portrait information of a plurality of objects to be thrown into virtual resources and screening the objects to be thrown out from the objects; adding the object to be thrown into the object pool to be thrown according to the correlation degree between the object to be thrown and the automatic pool-entering index piece of the thrown object; acquiring an operation evaluation score of a target object to be thrown based on virtual resource operation information and full-tone information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown; and determining an input judgment result of the target object to be input based on the operation evaluation score and the full tone information. And then according to the operation data of the target object to be thrown after the virtual resource is thrown, completing risk control and quitting the throw management, and realizing the on-line management of the target object to be thrown before, during and after the throw. By automatically and intelligently processing the data of the object to be thrown, the data does not need to be analyzed manually, and the data processing efficiency and the accuracy are improved.
Description
Technical Field
The present application relates to the field of computer technologies, and in particular, to a data processing method, an apparatus, a computer device, a storage medium, and a computer program product.
Background
In recent years, with the development of the hot tide of domestic innovation and business creation and the development of capital market, the investment market is continuously heated and the scale is continuously increased, and financial investment institutions in the investment field usually invest a large amount of resources before investment, but lack investment and management mechanism construction for post-investment management. However, investment projects have a relatively long investment period (typically up to 5-8 years) and their investment risk is also higher than other investments. Therefore, with the strict and planned investment in the market and supervision environment and the combination of the characteristics of long period and high risk of the investment project, how to efficiently complete the full life cycle management of the investment project, ensure the long-term effective management of the investment project and timely discover the project risk, optimize the comprehensive informatization management capability of the investment organization on the target enterprise, reduce the investment risk caused by the asymmetry of the information of the investment organization and the invested party, and increase the profitability and the success probability of the investment business is a major problem for the investment organization.
In the related art, when determining to invest an object, for example, a product such as a stock right or a fund, data of the related object is manually acquired, and then the data is manually analyzed to determine which object is invested. The manual cost is high due to the need for manual analysis. Meanwhile, because of manual analysis, the accuracy in data processing is not high, and the efficiency is low.
Disclosure of Invention
In view of the above, it is necessary to provide a data processing method, an apparatus, a computer device, a computer readable storage medium and a computer program product, which can accurately and effectively process data.
In a first aspect, the present application provides a data processing method. The method comprises the following steps:
aiming at a plurality of objects to be invested into virtual resources, screening out the objects to be invested from the plurality of objects according to the portrait information of the plurality of objects;
adding the object to be thrown into the object pool to be thrown according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object;
acquiring an operation evaluation score of a target object to be thrown based on virtual resource operation information and scheduling information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown;
and determining the input judgment result of the target object to be input through the decision tree based on the operation evaluation score and the full tone information.
In one embodiment, adding an object to be thrown to an object to be thrown pool according to the degree of correlation between an automatic pool-entering index of the object to be thrown and an automatic pool-entering index piece of a thrown object includes:
acquiring a pool-entering relevancy vector of an object to be thrown according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object;
determining the number of elements larger than a corresponding preset threshold in the pool entry association degree vector based on the numerical value of each element in the pool entry association degree vector;
and if the number of the elements is more than half of the total number of the thrown objects, adding the thrown objects into the to-be-thrown object pool.
In one embodiment, the number of the objects to be thrown and the number of the automatic pool-entering indexes are multiple; the pool-entering relevance vector of the object to be thrown is formed by correlation coefficients between the object to be thrown and each thrown object, and the determination process of the correlation coefficients between the object to be thrown and each thrown object comprises the following steps:
aiming at a current input object and a current automatic input index, acquiring a first average value of the current automatic input index corresponding to all the objects to be input and a second average value of the current automatic input index corresponding to all the objects to be input, calculating a first difference value between the current automatic input index corresponding to the current object to be input and the first average value, calculating a second difference value between the current automatic input index corresponding to the current object to be input and the second average value, and calculating a first product between the first difference value and the second difference value as a first product corresponding to the current automatic input index;
summing the products corresponding to each automatic input index to obtain a sum value;
carrying out square summation on a first difference value corresponding to each automatic input index, taking a first square value as a square summation result, carrying out square summation on a second difference value corresponding to each automatic input index, taking a second square value as the square summation result, and obtaining a second product between the first square value and the second square value; and calculating the ratio of the sum value to the second product as a correlation coefficient between the object to be thrown and the current thrown object.
In one embodiment, the method further comprises:
under the condition that the investment judgment result is that the investment is determined, after virtual resources are invested into the target object to be invested, object operation information generated by the operation of the target object to be invested into the virtual resources is acquired according to a preset acquisition period;
aiming at the field of a target input object, acquiring environment operation information of the field;
and generating a periodic operation information report of the target input object according to the custom report template and the object operation information and the environment operation information.
In one embodiment, the method further comprises:
after the virtual resources are invested into the target investment object, calculating an exit investment evaluation value according to the yield of the virtual resources generated by the target investment object based on the invested virtual resources, a risk early warning index, an investment multiple, investment duration and a conversion ratio of investment to income;
when the quit investment evaluation value is larger than a preset threshold value, quitting the investment of virtual resources to the target investment object; otherwise, the virtual resources are continuously invested into the target investment object.
In one embodiment, the process of obtaining the risk pre-warning index includes:
acquiring risk indexes of a target input object, wherein the risk indexes at least comprise a virtual resource forward income index, a virtual resource returning capacity index, a virtual resource operation capacity index, an object internal architecture change risk index and an object belonging environment risk index;
determining the risk grade corresponding to each risk index under the same risk grade system, and forming a risk index vector of a target input object by the risk grade corresponding to each risk index;
sequentially carrying out three layers of processing on the risk index vectors to obtain a risk early warning index of the target input object; wherein each layer of processing comprises convolution processing, activation function processing, residual processing and pooling processing.
In a second aspect, the present application further provides a data processing apparatus. The device comprises:
the screening module is used for screening out the objects to be invested from the plurality of objects according to the portrait information of the plurality of objects aiming at the plurality of objects to be invested into the virtual resources;
the adding module is used for adding the object to be thrown into the object pool according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object;
the acquisition module is used for acquiring the operation evaluation score of the target object to be thrown based on the virtual resource operation information and the full-tone information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown;
and the determining module is used for determining the input judgment result of the target object to be input through the decision tree based on the operation evaluation score and the dispatching information.
In a third aspect, the present application also provides a computer device. The computer device comprises a memory storing a computer program and a processor implementing the following steps when executing the computer program:
aiming at a plurality of objects to be invested into virtual resources, screening out the objects to be invested from the plurality of objects according to the portrait information of the plurality of objects;
adding the object to be thrown into the object pool to be thrown according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object;
acquiring an operation evaluation score of a target object to be thrown based on virtual resource operation information and scheduling information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown;
and determining an input judgment result of the target object to be input through a decision tree based on the operation evaluation score and the adjustment information.
In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
aiming at a plurality of objects to be invested into virtual resources, screening out the objects to be invested from the plurality of objects according to the portrait information of the plurality of objects;
adding the object to be thrown into the object pool to be thrown according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object;
acquiring an operation evaluation score of a target object to be thrown based on virtual resource operation information and scheduling information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown;
and determining the input judgment result of the target object to be input through the decision tree based on the operation evaluation score and the full tone information.
In a fifth aspect, the present application further provides a computer program product. The computer program product comprising a computer program which when executed by a processor performs the steps of:
aiming at a plurality of objects to be invested into virtual resources, screening out the objects to be invested from the plurality of objects according to the portrait information of the plurality of objects;
adding the object to be thrown into the object pool according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object;
acquiring an operation evaluation score of a target object to be thrown based on virtual resource operation information and full-tone information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown;
and determining the input judgment result of the target object to be input through the decision tree based on the operation evaluation score and the full tone information.
According to the data processing method, the data processing device, the computer equipment, the storage medium and the computer program product, aiming at a plurality of objects to be invested in virtual resources, the objects to be invested are screened out from the plurality of objects according to the portrait information of the plurality of objects; adding the object to be thrown into the object pool to be thrown according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object; acquiring an operation evaluation score of a target object to be thrown based on virtual resource operation information and scheduling information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown; and determining the input judgment result of the target object to be input through the decision tree based on the operation evaluation score and the full tone information. The acquired data information of the object to be thrown is compared with the thrown object and the operation evaluation score is calculated, the throwing judgment result of the object to be thrown is automatically identified, a manual data analysis process is not needed, the data information of the object to be thrown is automatically and intelligently processed by a computer, and the data processing efficiency and the accuracy are improved.
Drawings
FIG. 1 is a diagram of an application environment of a data processing method in one embodiment;
FIG. 2 is a flow diagram that illustrates a data processing method in one embodiment;
FIG. 3 is a schematic diagram of a process for generating a periodic operational information report of a target investment object in one embodiment;
FIG. 4 is a flow chart illustrating a data processing method according to another embodiment;
FIG. 5 is a flow chart illustrating a data processing method according to still another embodiment;
FIG. 6 is a diagram of a risk assessment model training process in accordance with one embodiment;
FIG. 7 is a diagram of a system physical architecture of a lifecycle management system for an object to be invested in one embodiment;
FIG. 8 is a schematic diagram of a lifecycle management system interface for an object to be placed in one embodiment;
FIG. 9 is a block diagram showing the structure of a data processing apparatus according to an embodiment;
FIG. 10 is a diagram showing an internal structure of a computer device according to an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more clearly understood, the present application is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The data processing method provided by the embodiment of the application can be applied to the application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. The data storage system may store data that the server 104 needs to process. The data storage system may be integrated on the server 104, or may be located on the cloud or other network server. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smart phones, tablet computers, internet of things devices and portable wearable devices, and the internet of things devices may be smart speakers, smart televisions, smart air conditioners, smart car-mounted devices, and the like. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, and the like. The server 104 may be implemented as a stand-alone server or a server cluster comprised of multiple servers.
In one embodiment, as shown in fig. 2, a data processing method is provided, which is described by taking the method as an example applied to the server 104 in fig. 1, and includes the following steps:
the plurality of objects to be invested into the virtual resource refer to items which have acquired the related information and wait for determining whether the invested conditions are met, wherein the virtual resource is used for measuring the invested degree, and for example, the objects may be funds or stock rights. The portrait information is all information of the enterprise to which the object belongs, for example, the portrait information may be company profile, company label portrait, business information, financing process, company on market, related news, competitors, and the like. The type of the image information may be different for different objects, and for example, when the object is a target fund, the image information may include information such as the status of investment, information on shareholders, a change of industry and business, news of institutions, the trend of investment, the investment in a company, and the exit from a company.
Specifically, after the image information of a plurality of objects is acquired, the image information may be primarily screened according to a preset condition, for example, information such as a region, an industry field, an input round, an establishment time, a latest acquisition time, a management organization, an input field, an input region, and an input time may be primarily screened, thereby improving the object screening efficiency. In addition, the user-defined labels can be set for the portrait information of the objects, the user-defined labels of the portrait information of the objects are compared, differences among the objects to be put into the virtual resources are analyzed, screening is facilitated, and screening time is saved. After the portrait information is screened, a set of objects to be thrown is obtained.
the automatic pooling index is an index for measuring whether an object can be added into the pool of the object to be pooled, and may be one or more, for example, the automatic pooling index may include multiple dimensions such as an operation state, an enterprise scale, a research and development proportion, qualification certification, judicial complaints, a development stage, intellectual property rights, and investor conditions. The type of the automatic pool indicator of the dropped object and the automatic pool type of the object to be dropped should be consistent.
The correlation degree can reflect the correlation degree between the object to be thrown and the thrown object, the object to be thrown is screened according to the thrown object, and whether the object to be thrown can be added into the pool of the object to be thrown is determined. When determining the input object, the input object is directly selected from the pool of objects to be input. It will be appreciated that for an object to be committed, the higher its association with the committed object, the more worthwhile the object to be committed to committing to virtual resources. Specifically, according to a plurality of automatic pool entering indexes, a correlation coefficient between the object to be thrown and the thrown object is determined, and whether the object to be thrown enters the pool or not is determined according to the correlation coefficient.
the target object to be thrown is an object to be thrown in an object to be thrown pool, namely, a plurality of initially acquired objects to be thrown in virtual resources are subjected to primary screening of image information and screening of the association degree of the initially acquired objects to be thrown. The virtual resource operation information of the target object to be invested refers to internal enterprise information of an enterprise to which the target object to be invested belongs, such as enterprise basic information, stockholder information, high management information, financing history, main customers, enterprise operation data and financial data; the exhausted information refers to information of an enterprise to which a target object to be delivered belongs acquired from other external layers, for example, information of judicial litigation (civil litigation, criminal litigation, court execution), bank flow (inflow and outflow overview, analysis of former ten capital trading opponents), intellectual property (patent, trademark, copyright), and the like.
Referring to fig. 3, an intention enterprise is an enterprise to which a target object to be delivered belongs, external data is the scheduling information in this embodiment, collected data is virtual resource operation information, and after the virtual resource operation information and the scheduling information of the target object to be delivered are collected, a scheduling report is automatically generated, where the scheduling report may include the following elements: enterprise basic information (industrial merchant registration information, industrial merchant change, stockholder information, financing information, high management information, news public opinion), judicial litigation information (civil litigation, criminal litigation, court execution), financial data (asset liability statement, cash flow statement, enterprise quarterly financial statement index lateral comparison), banking (incoming and outgoing general view, analysis of the first ten capital trading opponents), invoice tax (sales/advances/differences, analysis of the first ten suppliers), intellectual property (patents, trademarks, copyright).
The operation evaluation score is a score obtained by evaluating the operation condition of the target object to be thrown by the enterprise to which the target object to be thrown belongs, and represents the degree that the target object to be thrown can be worth to throw in the virtual asset, and generally, the higher the score is, the better the score is. Specifically, determining a pool entry association degree vector through an automatic pool entry index of the target object to be posted, and calculating an operation evaluation score of the target object to be posted according to the pool entry association degree vector, virtual resource operation information and dispatching information of the target object to be posted by the following formula:
T(c)＝r 1 P(c)+r 2 Q(c)+r 3 M(c)+r 4 N(c)+r 5 S(c)
wherein P (c) represents the average value of the pooling relevance vector, Q (c) represents the rate of assets and liabilities, M (c) represents the turnover rate of credits, N (c) represents the same-ratio increase rate of net profits, S (c) represents the number of intellectual property rights, r 1 、r 2 、r 3 、r 4 、r 5 Represents a preset weight, and ∑ r i ＝1。
And 208, determining an input judgment result of the target object to be input through a decision tree based on the operation evaluation score and the adjustment information.
The decision tree is a decision analysis method which is used for obtaining the probability that the expected value of the net present value is greater than or equal to zero by forming the decision tree on the basis of the known occurrence probability of various conditions, evaluating the risk of the project and judging the feasibility of the project. In the embodiment of the application, before the data of the target object to be thrown is processed, a large number of historical data pairs are trained, and the input result of the trained decision tree on the target object to be thrown is judged. And the input judgment result is that whether the target object to be input is approved or not and virtual resources can be input.
Specifically, the decision tree can be trained according to information such as the company-to-pool association degree, the operation evaluation value, the estimated investment amount, the pledge condition, the market capacity, the profit level and the like of the target object to be delivered, and the decision tree can be obtained after multiple times of training and tuning:
pass(i)＝h(n)
and b, wherein pass (i) represents a judgment result and takes a value of 1 or 0, if the judgment result is 1, the examination and approval is allowed to pass, otherwise, the examination and approval is not allowed to pass for manual processing, h (n) represents a trained decision tree function, and n is the number of parameters of the decision tree.
In the method provided by the above embodiment, for a plurality of objects to be invested in virtual resources, objects to be invested are screened out from the plurality of objects according to the portrait information of the plurality of objects; adding the object to be thrown into the object pool to be thrown according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object; acquiring an operation evaluation score of a target object to be thrown based on virtual resource operation information and full-tone information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown; and determining the input judgment result of the target object to be input through the decision tree based on the operation evaluation score and the full tone information. The acquired data information of the target to be thrown is compared with the thrown target and the operation evaluation score is calculated, so that the throwing judgment result of the target to be thrown is automatically identified, a manual data analysis process is not needed, the data information of the target to be thrown is automatically and intelligently processed by a computer, and the data processing efficiency and the accuracy are improved.
In one embodiment, referring to fig. 4, adding an object to be posted to an object pool to be posted according to a degree of correlation between an automation pool index of the object to be posted and an automation pool index of a posted object, includes:
and 406, if the number of the elements is more than half of the total number of the thrown objects, adding the thrown objects to the to-be-thrown object pool.
After a plurality of objects to be input are primarily screened through the image information of the objects to be input, a primary screening set C can be obtained:
c (i) represents a preliminary screening result of whether the current ith object to be thrown enters the pool or not, E represents a manually concerned focused industry set in the current stage throwing strategy, v (j) represents an industry label set of the current object to be thrown, exist i (finance) represents that the financing requirement, uniexist, exists in the current object to be delivered i (finence) indicates that no financing requirement exists in the current object to be invested. Wherein the set E can be updated periodically by human according to the virtual resource investment.
The automatic pool-entering index of the object to be put into operation can comprise multiple dimensions such as operation state, enterprise scale, research and development proportion, qualification certification, judicial complaint, development stage, intellectual property, investor condition and the like. And the thrown object set Y represents a set of virtual resource thrown objects which are already put into the pool and started, and the relevance vector P is calculated by each object to be thrown in the primary screening set C and each thrown object in the set Y.
The higher the correlation coefficient value is, the higher the correlation degree is, in this embodiment, the correlation degree is taken as a basis, the correlation degree vector P of each preliminarily screened object c is calculated, and a final set R of objects to be thrown (pool of objects to be thrown) automatically entering the pool is obtained by screening.
Wherein p is i Representing one element of the relevance vector P and TH representing the pc relevance threshold. And when the number of elements which are more than or equal to the threshold value in the vector P is more than or equal to half of the number of the objects in the set Y of the objects which are already put into the pool, adding the set R of the objects to be put into the pool automatically, or not adding the set R.
In the method adopted by the embodiment, the relevance vector between each object to be thrown and the thrown object is calculated, the primarily screened object to be thrown is secondarily screened according to the relevance vector, the object to be thrown entering the object pool is determined, the screening of the object to be thrown is automatically completed, the judgment is carried out according to a fixed formula mode, the accuracy rate is high, and the influence of artificial subjective consciousness can be avoided. And the efficiency is extremely high by means of automatic screening.
In one embodiment, the number of the objects to be thrown and the number of the automatic pool-entering indexes are multiple; the pool-entering relevance vector of the object to be thrown is formed by correlation coefficients between the object to be thrown and each thrown object, and the process for determining the correlation coefficients between the object to be thrown and each thrown object comprises the following steps:
aiming at a current input object and a current automatic input index, acquiring a first average value of the current automatic input index corresponding to all the objects to be input and a second average value of the current automatic input index corresponding to all the objects to be input, calculating a first difference value between the current automatic input index corresponding to the current object to be input and the first average value, calculating a second difference value between the current automatic input index corresponding to the current object to be input and the second average value, and calculating a first product between the first difference value and the second difference value as a first product corresponding to the current automatic input index;
summing products corresponding to each automatic input index to obtain a sum value;
carrying out square summation on a first difference value corresponding to each automatic input index, taking a first square value as a square summation result, carrying out square summation on a second difference value corresponding to each automatic input index, taking a second square value as the square summation result, and obtaining a second product between the first square value and the second square value; and calculating the ratio of the sum value to the second product as a correlation coefficient between the object to be thrown and the current thrown object.
Calculating a Pearson correlation coefficient pc (C, Y) for each object to be thrown in the primary screening set C and each thrown object in the Y set, and obtaining a relevance vector P of the primary screening item according to the following formula:
wherein c is an automatic pool-entering index vector of the primary screening object, y represents an automatic pool-entering index vector of the thrown project, and the absolute value of the calculation result of the pc (c, y) is in the range of [0,1 ].
The method comprises the steps of calculating the relevance vector between each object to be thrown and the thrown object, carrying out secondary screening on the primarily screened object to be thrown according to the relevance vector, determining the object to be thrown entering the object pool, automatically completing screening of the object to be thrown, judging according to a fixed formula mode, and being high in accuracy rate and capable of avoiding the influence of artificial subjective consciousness. And the efficiency is extremely high by means of automatic screening.
In one embodiment, the method further comprises:
under the condition that the input judgment result is that the input is determined, after virtual resources are input into a target object to be input, object operation information generated by the operation of the target input object by the input virtual resources is acquired according to a preset acquisition period;
aiming at the field of a target input object, acquiring environment operation information of the field;
and generating a periodic operation information report of the target input object according to the custom report template and the object operation information and the environment operation information.
The target input object refers to a target object to be input after virtual resources are input. The object operation information is development information of the target input object after the virtual resource is input, and for example, if the target input object is a fund, the operation information is the virtual resource increase situation corresponding to the fund after the virtual resource is input into the fund. The type of information included in the object operation information differs for each target investment object, for example: when the target input object is a direct-input project fund, the object operation information relates to fund basic information, input strategies, key terms, payment information, input project of a combined object, financial data, post-input meetings, personnel delegation, periodic check lists, periodic reports, fund distribution, other accessories, post-input value-added services, comprehensive linkage and input project financial data of the combined object; the target investment object is a direct investment mother fund, and the object operation information relates to investment of combined target fund, target fund investment project, target fund financial data and target fund investment project financial data besides the characteristics of the direct investment project fund; the target input object is a direct-throw item, and the object operation information relates to item fund information, financial data, payment information, three-party information, company valuation, company share right, post-throw report, outsourcing personnel, periodic investigation list, item distribution, post-throw value-added service, comprehensive linkage and other accessories.
It should be noted that the object operation information is collected according to a preset period, for example, one month, one quarter, half a year, and the like.
Because the target input object has a long input period in the application, in the method in the embodiment, when data is acquired in a preset period (for example, a quarter), market data including the information of a business, the securitization state, the IPO condition, the financing condition, the stock price on the market, the place on the market, the stockholder change information and the like are automatically captured, the information of the target input object is automatically updated, the updated content is marked, a business manager can sense the market change condition of the input object at the earliest time, and the change details of the input object are rapidly captured.
According to the method provided by the embodiment of the application, after the object operation information and the environment operation information of the target input object are collected and analyzed, the periodic operation information report of the target input object in the preset period can be generated according to the self-defined report template. The operation information of the target input object is monitored and analyzed in real time, so that the periodic management and control of the target input object at the stage after virtual resources are input are realized.
In one embodiment, referring to fig. 5, the method further comprises:
step 502, after the virtual resources are invested into the target investment object, calculating an exit investment evaluation value according to the yield of the virtual resources, the risk early warning index, the investment multiple, the investment duration and the conversion ratio of investment and income generated by the target investment object based on the invested virtual resources;
The virtual resource yield is an Internal yield IRR (Internal Rate of Return), and is a discount Rate when the total current amount of virtual resources is equal to the total current amount of virtual resources, and the net current value is zero. In one embodiment, the internal rate of return IRR, taking into account the time value of the virtual resource, better reflects the investorsWherein T is the investing period, CF t Refers to the net virtual resource amount in the t-th period.
The risk early warning index REWI represents the risk condition of the input object, is based on a risk early warning model of the input object in the operation stage after the input of virtual resources, and counts the increase condition of the risk score ring ratio of the input object according to the month, wherein Fscore j Represents the calculated j-month risk score, fscore, in the risk early warning model based on the residual neural network j -Fscore j-1 Representing the difference in risk scores between month j and month j-1, and n representing the monthly statistical period for REWI.
The investment multiple TVIP and the variation multiple DPI indicate investment return of investment objects, wherein TFH represents allocated return obtained by investors, SV represents residual value, and TZ represents the amount of invested virtual resources.
TVIP＝(TFH+SV)/TZ；
DPI＝TFH/TZ；
After the target input object inputs the virtual resource, calculating a quit input evaluation value according to IRR, TVIP, DPI and REWI, and comprehensively judging whether the virtual resource input of the target input object quits. If the quit investment evaluation value is larger than the set threshold value, recommending to keep the target investment object running, continuously investing virtual resources into the target investment object, and not quitting; otherwise, the recommendation is not carried out, and whether the quitting is carried out or not can be judged by staff.
It should be noted that, when calculating the quit investment evaluation value, the calculation can be performed by referring to the public market equivalence coefficient PME; public market equivalence factor PMEShowing the observability of acquiring the virtual resources after the virtual resources are input, when the PME is more than 1, showing that the input income of the current target input object is more than the input income of the selected public market, and the input is feasible, wherein D t For total cash flow in t period, C t For the total cash inflow during t period, r i Is S&P500 index.
In the method provided by the embodiment, the operation condition of the target input object after virtual resources are input is evaluated through various indexes, whether the target input object needs to be input continuously is judged, the input condition of the target input object is intelligently monitored in an all-around manner, the processing effect of the operation data of the target input object is improved, and the target input object is controlled more accurately.
In one embodiment, the process of obtaining the risk pre-warning index includes:
acquiring risk indexes of a target input object, wherein the risk indexes at least comprise a virtual resource forward income index, a virtual resource returning capacity index, a virtual resource operation capacity index, an object internal architecture change risk index and an object belonging environment risk index;
determining the risk grade corresponding to each risk index under the same risk grade system, and forming a risk index vector of the target input object by the risk grade corresponding to each risk index;
sequentially carrying out three layers of processing on the risk index vectors to obtain a risk early warning index of a target input object; wherein each layer of processing comprises convolution processing, activation function processing, residual processing and pooling processing.
The risk early warning index is obtained periodically in a preset period and is used for reflecting the income risk condition of the target input object in the preset period after the virtual resource is input. The risk indicator may include a plurality of aspects in connection with the target subject input process, outcome and environment, and may be graded, such as a primary indicator and a secondary indicator, see table 1 below.
TABLE 1 Risk index description
It should be noted that, when determining the risk early warning index according to the risk index, the risk early warning index needs to be determined according to the index of the same grade, that is, in the same risk grade system. For example, referring to table 1, the primary indexes of the risk indexes include a virtual resource forward income index, a virtual resource returning capability index, a virtual resource operation capability index, an object internal architecture change risk index, and an object belonging environment risk index, and the risk early warning index is determined according to the risk levels corresponding to all the primary indexes.
An intelligent risk assessment model after the target is put into an object is constructed through a convolutional neural network design principle and a residual error model, and risk early warning indexes of the target put into the object are obtained through the intelligent risk assessment model, wherein the risk early warning indexes [0,0.2], (0.2, 0.4], (0.4, 0.6], (0.6, 0.8], (0.8, 1) correspond to low risk, medium and low risk, medium and high risk levels.
Specifically, a training index data set is obtained, and the intelligent risk assessment model is trained using the training index data set, see fig. 6: inputting risk index data x into a first-layer network, outputting F1 (x) after convolution operation, a Batch Normalization function and ReLu function operation, inputting residual error items F1 (x) + x into a second-layer network after being used as F2 (x) and passing through a pooling layer (pooling operation), outputting F3 (x) after convolution, batch Normalization and Relu operation, inputting residual error items F3 (x) + pooling (F2 (x)) into a third-layer network after being used as F4 (x) and passing through pooling operation, outputting F5 (x) after similarly passing through convolution, batch Normalization and Relu operation, and obtaining a risk early warning index by using residual error items F5 (x) + pooling (F4 (x)) as F6 (x) and passing through a Sigmoid active layer and a full connection layer. And marking a risk early warning index Y (x) corresponding to the training data as input x, and continuously adjusting the parameters of the residual neural network in the training process to make the risk early warning index tend to mark Y (x).
In the method provided by the embodiment, the intelligent risk assessment model is constructed according to the convolutional neural network principle, the risk of the target input object is assessed according to the trained intelligent risk, the risk early warning index of the target input object is obtained, and the intelligent management of the input process of the target input object is realized.
In one embodiment, the method provided herein further comprises: and after quitting the virtual resource input to the target input object, acquiring the copy characteristics of the target input object, and judging whether the virtual resource can be input to the target input object again. The double-disk characteristics comprise the current state of a target input object and the market data change condition of the target input object, wherein the current state of the target input object mainly counts the input states (before input, during input, after input, stop and exit) of all input objects managed by a current manager; the market data change condition is determined according to the type of the input object, for example, when the target input object is a target project, the project review can count the financing condition, media reports, wage changes, competitors and judicial complaints of the project input in the previous day; when the target investment object is the target fund, the project replication statistics is carried out on investment events, quit events, new established funds, a new round of financing started by the invested project and a new round of financing change situation completed by the invested project compared with the fund invested in the previous day. The project reply disk enables a manager to easily acquire the latest market data of the input objects every day by means of the market data.
In addition, after virtual resources are invested into the target investment object, multi-dimensional operation data of the target investment object after the investment is obtained, and the data is visualized in forms of a table, a pie chart, a broken line chart, a bar chart and the like, wherein the data is processed to obtain various information display modes of the target investment object, such as a regional concentration statistical chart of the target investment object, an investment industry distribution situation pie chart, a balance statistical situation, an overall evaluation situation, a cash flow situation, a securitization situation, an analysis comparison report form of bottom layer virtual resources and the like.
It should be understood that, although the steps in the flowcharts related to the embodiments are shown in sequence as indicated by the arrows, the steps are not necessarily executed in sequence as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated herein, may be performed in other orders. Moreover, at least a part of the steps in the flowcharts related to the above embodiments may include multiple steps or multiple stages, which are not necessarily performed at the same time, but may be performed at different times, and the order of performing the steps or stages is not necessarily sequential, but may be performed alternately or alternately with other steps or at least a part of the steps or stages in other steps.
In an embodiment, a lifecycle management system for an object to be launched is provided, and the steps in the data processing method are executed to implement "before-launch, during-launch, and after-launch" full lifecycle management for the object to be launched, where the lifecycle management system for the object to be launched adopts a system physical framework as shown in fig. 7. Referring to fig. 8, a visual interface of the lifecycle management system for the object to be delivered includes:
and the penetration management module is used for screening a plurality of objects to be input into the virtual resources, and is used for helping an input manager to more efficiently discover a first-level market input target.
And the project pool module is mainly used for warehousing of the objects to be thrown and project starting. Meanwhile, the automatic pool entering model can be used for calculating the pool entering association degree, and part of objects to be thrown are screened out from the market input targets provided by the penetration management module to be automatically entered into the pool.
And the enterprise reporting module is mainly used for collecting data of an enterprise to which the object to be thrown belongs and generating an intention enterprise intonation report by combining external market data. And calculating an operation evaluation score of the object to be delivered by an operation evaluation model based thereon, wherein the operation evaluation value = fun (pool-in association degree, operation value).
And the middle-throwing management module is mainly used for examining and approving the business before the throwing of the object to be thrown. The project can be approved through manual approval or a multi-factor automatic approval model based on a decision tree, whether the project can normally pass the approval or not depends on the judgment result of the automatic approval model, and the judgment model combines the evaluation values of the preorder steps, including the pool entry association degree and the operation evaluation value of the enterprise to which the object to be delivered belongs.
And the post-investment management module is mainly used for managing target investment objects invested in the virtual resources and comprises submodules for post-investment quarter data acquisition, quarter data audit, intelligent post-investment report and the like. And in the post-investment management stage, risk analysis and management of the target investment object are performed through a project replication and risk management submodule in the wind control management module. The risk management module is mainly used for carrying out risk analysis on the target input object based on a risk early warning model of the residual error neural network.
And the quit management module is mainly used for quit management after the target input object inputs the virtual resources, and can carry out input and quit of the target input object through the quit mechanism model.
Based on the same inventive concept, the embodiment of the present application further provides a data processing apparatus for implementing the above-mentioned data processing method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more embodiments of the data processing device provided below may refer to the limitations on the data processing method in the above description, and are not described herein again.
In one embodiment, as shown in fig. 9, there is provided a data processing apparatus including: a filtering module 901, an adding module 902, an obtaining module 903 and a determining module 904, wherein:
the screening module 901 is configured to screen, for a plurality of objects to be invested in virtual resources, the objects to be invested from the plurality of objects according to portrait information of the plurality of objects;
an adding module 902, configured to add an object to be posted to an object pool to be posted according to a correlation degree between an automatic pool entry index of the object to be posted and an automatic pool entry index of a posted object;
an obtaining module 903, configured to obtain, for a target object to be cast in the object to be cast pool, an operation evaluation score of the target object to be cast based on virtual resource operation information and scheduling information of the target object to be cast;
and a determining module 904, configured to determine, based on the operation evaluation score and the tone exhaustion information, an input judgment result of the target object to be input through the decision tree.
In one embodiment, the adding module 902 is further configured to:
acquiring a pool entry association degree vector of the object to be thrown according to the correlation degree of the automatic pool entry index of the object to be thrown and the automatic pool entry index part of the thrown object;
determining the number of elements larger than a corresponding preset threshold in the pool-entering association degree vector based on the numerical value of each element in the pool-entering association degree vector;
and if the number of the elements is more than half of the total number of the thrown objects, adding the thrown objects into the to-be-thrown object pool.
In one embodiment, the adding module 902 is further configured to:
aiming at a current input object and a current automatic input index, acquiring a first average value of the current automatic input index corresponding to all the objects to be input and a second average value of the current automatic input index corresponding to all the objects to be input, calculating a first difference value between the current automatic input index corresponding to the current object to be input and the first average value, calculating a second difference value between the current automatic input index corresponding to the current object to be input and the second average value, and calculating a first product between the first difference value and the second difference value as a first product corresponding to the current automatic input index;
summing the products corresponding to each automatic input index to obtain a sum value;
carrying out square summation on a first difference value corresponding to each automatic input index, taking a first square value as a square summation result, carrying out square summation on a second difference value corresponding to each automatic input index, taking a second square value as the square summation result, and obtaining a second product between the first square value and the second square value; and calculating the ratio of the sum value to the second product as a correlation coefficient between the object to be shot and the current shot object.
In one embodiment, the data processing apparatus further comprises an operation report generation module:
under the condition that the input judgment result is that the input is determined, after virtual resources are input into a target object to be input, object operation information generated by the operation of the target input object by the input virtual resources is acquired according to a preset acquisition period;
aiming at the field of a target input object, acquiring environment operation information of the field;
and generating a periodic operation information report of the target input object according to the custom report template and the object operation information and the environment operation information.
In one embodiment, the data processing apparatus further comprises an exit module:
after virtual resources are input into a target object to be input, calculating an exit input evaluation value according to the virtual resource yield, the risk early warning index, the input multiple, the input duration and the input-to-benefit conversion ratio generated by the target input object based on the input virtual resources;
when the quit investment evaluation value is larger than a preset threshold value, quitting investment of virtual resources on the target investment object; otherwise, the virtual resource is continuously invested into the target invested object.
In one embodiment, the exit module is further configured to:
acquiring risk indexes of a target input object, wherein the risk indexes at least comprise a virtual resource forward income index, a virtual resource returning capacity index, a virtual resource operation capacity index, an object internal architecture change risk index and an object belonging environment risk index;
determining the risk grade corresponding to each risk index under the same risk grade system, and forming a risk index vector of a target input object by the risk grade corresponding to each risk index;
sequentially carrying out three layers of processing on the risk index vectors to obtain a risk early warning index of a target input object; wherein each layer process comprises a convolution process, an activation function process, a residual process and a pooling process.
The various modules in the data processing apparatus described above may be implemented in whole or in part by software, hardware, and combinations thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as shown in fig. 10. The computer device includes a processor, a memory, and a network interface connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The database of the computer device is used for storing multidimensional data of the objects to be invested. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a data processing method.
Those skilled in the art will appreciate that the architecture shown in fig. 10 is merely a block diagram of some of the structures associated with the disclosed aspects and is not intended to limit the computing devices to which the disclosed aspects apply, as particular computing devices may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, a computer device is provided, comprising a memory having a computer program stored therein and a processor that when executing the computer program performs the steps of:
aiming at a plurality of objects to be invested into virtual resources, screening out the objects to be invested from the plurality of objects according to the portrait information of the plurality of objects;
adding the object to be thrown into the object pool to be thrown according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object;
acquiring an operation evaluation score of a target object to be thrown based on virtual resource operation information and scheduling information of the target object to be thrown, aiming at the target object to be thrown in the object pool to be thrown;
and determining the input judgment result of the target object to be input through the decision tree based on the operation evaluation score and the full tone information.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring a pool entry association degree vector of the object to be thrown according to the correlation degree of the automatic pool entry index of the object to be thrown and the automatic pool entry index part of the thrown object;
determining the number of elements larger than a corresponding preset threshold in the pool-entering association degree vector based on the numerical value of each element in the pool-entering association degree vector;
and if the number of the elements is more than half of the total number of the thrown objects, adding the thrown objects into the to-be-thrown object pool.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
aiming at a current thrown object and a current automatic throw-in index, acquiring a first average value of the current automatic throw-in index corresponding to all objects to be thrown and a second average value of the current automatic throw-in index corresponding to all thrown objects, calculating a first difference value between the current automatic throw-in index corresponding to the current objects to be thrown and the first average value, calculating a second difference value between the current automatic throw-in index corresponding to the current objects to be thrown and the second average value, and calculating a first product between the first difference value and the second difference value to serve as a first product corresponding to the current automatic throw-in index;
summing products corresponding to each automatic input index to obtain a sum value;
carrying out square summation on a first difference value corresponding to each automatic input index, taking a first square value as a square summation result, carrying out square summation on a second difference value corresponding to each automatic input index, taking a second square value as the square summation result, and obtaining a second product between the first square value and the second square value; and calculating the ratio of the sum value to the second product as a correlation coefficient between the object to be thrown and the current thrown object.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
under the condition that the investment judgment result is that the investment is determined, after virtual resources are invested into the target object to be invested, object operation information generated by the operation of the target object to be invested into the virtual resources is acquired according to a preset acquisition period;
aiming at the field of a target input object, acquiring environment operation information of the field;
and generating a periodic operation information report of the target input object according to the custom report template and the object operation information and the environment operation information.
In one embodiment, the processor when executing the computer program further performs the steps of:
after virtual resources are input into a target object to be input, calculating an exit input evaluation value according to the virtual resource yield, the risk early warning index, the input multiple, the input duration and the input-to-benefit conversion ratio generated by the target input object based on the input virtual resources;
when the quit investment evaluation value is larger than a preset threshold value, quitting investment of virtual resources on the target investment object; otherwise, the virtual resources are continuously invested into the target investment object.
In one embodiment, the processor, when executing the computer program, further performs the steps of:
acquiring risk indexes of a target input object, wherein the risk indexes at least comprise a virtual resource forward income index, a virtual resource returning capacity index, a virtual resource operation capacity index, an object internal architecture change risk index and an object belonging environment risk index;
determining the risk grade corresponding to each risk index under the same risk grade system, and forming a risk index vector of a target input object by the risk grade corresponding to each risk index;
sequentially carrying out three layers of processing on the risk index vectors to obtain a risk early warning index of a target input object; wherein each layer process comprises a convolution process, an activation function process, a residual process and a pooling process.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, is adapted to carry out the method steps of all embodiments mentioned above.
In an embodiment, a computer program product is provided, comprising a computer program which, when being executed by a processor, carries out the method steps mentioned in all the above embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include a Read-Only Memory (ROM), a magnetic tape, a floppy disk, a flash Memory, an optical Memory, a high-density embedded nonvolatile Memory, a resistive Random Access Memory (ReRAM), a Magnetic Random Access Memory (MRAM), a Ferroelectric Random Access Memory (FRAM), a Phase Change Memory (PCM), a graphene Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), among others. The databases involved in the embodiments provided herein may include at least one of relational and non-relational databases. The non-relational database may include, but is not limited to, a block chain based distributed database, and the like. The processors referred to in the embodiments provided herein may be general purpose processors, central processing units, graphics processors, digital signal processors, programmable logic devices, quantum computing based data processing logic devices, etc., without limitation.
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is specific and detailed, but not construed as limiting the scope of the present application. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, and these are all within the scope of protection of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.
Claims (10)
1. A method of data processing, the method comprising:
aiming at a plurality of objects to be invested into virtual resources, screening out the objects to be invested from the plurality of objects according to the portrait information of the plurality of objects;
adding the object to be thrown into the object pool according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index of the thrown object;
aiming at a target object to be thrown in the object pool, acquiring an operation evaluation score of the target object to be thrown based on virtual resource operation information and full-tone information of the target object to be thrown;
and determining an input judgment result of the target object to be input through a decision tree based on the operation evaluation score and the dispatching information.
2. The method according to claim 1, wherein the adding the object to be thrown to the pool of objects to be thrown according to the degree of correlation between the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object comprises:
acquiring a pool-entering relevancy vector of the object to be thrown according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index piece of the thrown object;
determining the number of elements, which are greater than a corresponding preset threshold value, in the in-pool association degree vector based on the numerical value of each element in the in-pool association degree vector;
and if the number of the elements is more than half of the total number of the objects which are already thrown, adding the objects to be thrown into the pool of the objects to be thrown.
3. The method of claim 2, wherein the number of objects to be delivered and the number of automated pooling indicators are both multiple; the pool-entering relevancy vector of the object to be thrown is formed by correlation coefficients between the object to be thrown and each thrown object, and the process of determining the correlation coefficients between the object to be thrown and each thrown object comprises the following steps:
aiming at a current thrown object and a current automatic throwing index, acquiring a first average value of the current automatic throwing index corresponding to all objects to be thrown and a second average value of the current automatic throwing index corresponding to all thrown objects, calculating a first difference value between the current automatic throwing index corresponding to the current objects to be thrown and the first average value, calculating a second difference value between the current automatic throwing index corresponding to the current objects to be thrown and the second average value, and calculating a first product between the first difference value and the second difference value as a first product corresponding to the current automatic throwing index;
summing the products corresponding to each automatic input index to obtain a sum value;
carrying out square summation on a first difference value corresponding to each automatic input index, taking a first square value as a square summation result, carrying out square summation on a second difference value corresponding to each automatic input index, taking a second square value as the square summation result, and obtaining a second product between the first square value and the second square value; and calculating the ratio of the sum value to the second product as a correlation coefficient between the object to be shot and the current shot object.
4. The method of claim 1, further comprising:
under the condition that the investment judgment result is that the investment is determined, after virtual resources are invested into the target object to be invested, object operation information generated by the operation of the target object to be invested into the virtual resources is acquired according to a preset acquisition period;
aiming at the field of the target input object, acquiring environment operation information of the field;
and generating a periodic operation information report of the target input object according to the user-defined report template and the object operation information and the environment operation information.
5. The method of claim 4, further comprising:
after the virtual resources are input into the target object to be input, calculating an exit input evaluation value according to the yield of the virtual resources, a risk early warning index, an input multiple, input duration and a conversion ratio of input and yield generated by the target input object based on the input virtual resources;
when the quit input evaluation value is larger than a preset threshold value, quitting inputting virtual resources to the target input object; otherwise, the virtual resources are continuously invested into the target investment object.
6. The method of claim 5, wherein the obtaining of the risk pre-warning index comprises:
acquiring risk indexes of the target input object, wherein the risk indexes at least comprise a virtual resource forward income index, a virtual resource returning capacity index, a virtual resource operation capacity index, an object internal architecture change risk index and an object belonging environment risk index;
determining the risk grade corresponding to each risk index under the same risk grade system, and forming a risk index vector of the target input object by the risk grade corresponding to each risk index;
sequentially carrying out three layers of processing on the risk index vector to obtain a risk early warning index of the target input object; wherein each layer of processing comprises convolution processing, activation function processing, residual processing and pooling processing.
7. A data processing apparatus, characterized in that the apparatus comprises:
the screening module is used for screening out objects to be invested from a plurality of objects according to portrait information of the objects aiming at the objects to be invested into virtual resources;
the adding module is used for adding the object to be thrown into the object pool according to the correlation degree of the automatic pool-entering index of the object to be thrown and the automatic pool-entering index of the thrown object;
the acquisition module is used for acquiring the operation evaluation score of the target object to be thrown according to the virtual resource operation information and the full-tone information of the target object to be thrown aiming at the target object to be thrown in the object pool to be thrown;
and the determining module is used for determining the input judgment result of the target object to be input through a decision tree based on the operation evaluation score and the dispatching information.
8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method of any of claims 1 to 6.
9. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
10. A computer program product comprising a computer program, characterized in that the computer program realizes the steps of the method of any one of claims 1 to 6 when executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211285844.6A CN115619569A (en) | 2022-10-20 | 2022-10-20 | Data processing method, data processing device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211285844.6A CN115619569A (en) | 2022-10-20 | 2022-10-20 | Data processing method, data processing device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115619569A true CN115619569A (en) | 2023-01-17 |
Family
ID=84863655
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211285844.6A Pending CN115619569A (en) | 2022-10-20 | 2022-10-20 | Data processing method, data processing device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115619569A (en) |
-
2022
- 2022-10-20 CN CN202211285844.6A patent/CN115619569A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20220343432A1 (en) | Machine learning architecture for risk modelling and analytics | |
| US10325222B2 (en) | Decision tree machine learning | |
| US7720732B2 (en) | System and method for generating transaction based recommendations | |
| Bojö et al. | Environment and development: an economic approach | |
| US7664693B1 (en) | Financial methodology for the examination and explanation of spread between analyst targets and market share prices | |
| US20100030799A1 (en) | Method for Generating a Computer-Processed Financial Tradable Index | |
| Wilson et al. | Company failure prediction with limited information: Newly incorporated companies | |
| Lehmann | The role of corporate governance in shaping accruals manipulation prior to acquisitions | |
| Lu et al. | Fintech and the future of financial service: A literature review and research agenda | |
| Klieštik et al. | Prediction of financial health of business entities in transition economies | |
| Li et al. | Pricing derivatives with modeling CO2 emission allowance using a regime-switching jump diffusion model: with regime-switching risk premium | |
| Chen et al. | Explaining cryptocurrency returns: A prospect theory perspective | |
| Chen et al. | Forecasting PGR of the financial industry using a rough sets classifier based on attribute-granularity | |
| Nuthalapati | Optimizing Lending Risk Analysis & Management with Machine Learning, Big Data, and Cloud Computing | |
| CN115619569A (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN113850609A (en) | Customer management system, method, computer equipment and storage medium | |
| CN115221212A (en) | Fund investment data management system and method | |
| Kuznietsova et al. | Risks of innovative activity: economic and legal analysis | |
| Baboyan | New solutions for assessing insolvency risk in comercial organizations | |
| Karami et al. | Accounting Disclosure Quality and Bankruptcy Prediction | |
| Reintjes | Automatic Identification and Classification of Share Buybacks and their Effect on Short-, Mid-and Long-Term Returns | |
| Yatskevych et al. | The Efficiency of the Venture Investment Process | |
| Kushwaha et al. | Prospective Stock Analysis Model to improve the investment chances using Machine Learning | |
| Vinogradova et al. | About the Structural Aspects of Investment | |
| Konno | Default or exit? Empirical study on SMEs in the Japanese construction industry |
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 |