Data processing method and device, computer device and storage medium

Abstract

This application relates to a data processing method, apparatus, computer equipment, storage medium, and computer program product. It acquires profile information of multiple objects to be invested in with virtual resources, and filters out potential investment targets from these objects. Based on the correlation between potential investment targets and automated pooling indicators of already invested objects, it adds potential investment targets to a pool. For target investment targets in the pool, it obtains an operational evaluation score based on the target investment target's virtual resource operation information and due diligence information. Based on the operational evaluation score and due diligence information, it determines the investment judgment result for the target investment target. Then, based on the operational data of the target investment target after the virtual resource investment, it completes risk control and exit investment management, achieving comprehensive online management of the target investment target before, during, and after investment. By automatically and intelligently processing the data of the potential investment targets, it eliminates the need for manual data analysis, improving data processing efficiency and accuracy.

Description

Technical Field

[0001] This application relates to the field of computer technology, and in particular to a data processing method, apparatus, computer equipment, storage medium, and computer program product. Background Technology

[0002] In recent years, with the surge in domestic innovation and entrepreneurship and the development of the capital market, the investment market has continued to heat up and its scale has continued to grow. Financial investment institutions often invest heavily in pre-investment management but lack investment in post-investment management and the establishment of management mechanisms. However, investment projects have relatively long investment cycles (generally 5-8 years) and their investment risks are higher than other investments. Therefore, with the increasing stringency and standardization of the investment market and regulatory environment, coupled with the long-term and high-risk characteristics of investment projects, how to efficiently manage the entire lifecycle of investment projects, ensure long-term effective management and timely detection of project risks, optimize the comprehensive information management capabilities of investment institutions for target companies, reduce investment risks caused by information asymmetry between investment institutions and investees, and increase the profitability and success rate of investment business are major challenges facing investment institutions.

[0003] In related technologies, when determining investment targets, such as equity or funds, data on these targets is typically acquired manually and then analyzed manually to determine which target to invest in. Because this requires manual analysis, labor costs are high. Furthermore, because it is manual analysis, the accuracy of data processing is low, and the efficiency is also inefficient. Summary of the Invention

[0004] Therefore, it is necessary to provide a data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product that can accurately and effectively address the above-mentioned technical problems.

[0005] Firstly, this application provides a data processing method. The method includes:

[0006] For multiple objects that need to be invested with virtual resources, select the objects to be invested with based on the profile information of the multiple objects;

[0007] Based on the correlation between the automated pooling metrics of the target targets and the automated pooling metrics of the already invested targets, add the target targets to the pool of target targets.

[0008] For target targets in the pool of potential investors, an operational evaluation score is obtained based on the virtual resource operation information and due diligence information of the target targets.

[0009] Based on operational evaluation scores and due diligence information, the decision tree is used to determine the investment judgment results for the target investment objects.

[0010] In one embodiment, adding potential targets to the pool of potential targets based on the correlation between the automated pooling metrics of potential targets and the automated pooling metrics of already targeted targets includes:

[0011] Based on the correlation between the automated pooling metrics of the target targets and the automated pooling metrics of the already invested targets, obtain the pooling correlation vector of the target targets;

[0012] Based on the values ​​of each element in the pooling correlation vector, determine the number of elements in the pooling correlation vector that are greater than the corresponding preset threshold.

[0013] If the number of elements is greater than half of the total number of objects already submitted, the objects to be submitted will be added to the pool of objects to be submitted.

[0014] In one embodiment, the number of objects to be invested in and the number of automated pooling indicators are both multiple; the pooling correlation vector of the objects to be invested in is composed of the correlation coefficient between the objects to be invested in and each already invested object, and the process of determining the correlation coefficient between the objects to be invested in and each already invested object includes:

[0015] For the current invested targets and the current automated investment indicators, obtain the first average value of the current automated investment indicators for all targets to be invested and the second average value of the current automated investment indicators for all invested targets. Calculate the first difference between the current automated investment indicator for the current target and the first average value. Calculate the second difference between the current automated investment indicator for the current invested target and the second average value. Calculate the first product between the first difference and the second difference, which is used as the first product of the current automated investment indicator.

[0016] Sum the products of each automation input indicator to obtain the sum value;

[0017] For each automation input indicator, the first difference is summed by squaring, and the first square root of the summation is taken. For each automation input indicator, the second difference is summed by squaring, and the second square root of the summation is taken. The second product between the first square root and the second square root is obtained. The ratio between the sum and the second product is calculated as the correlation coefficient between the target to be invested and the currently invested target.

[0018] In one embodiment, the method further includes:

[0019] If the investment judgment result is a confirmed investment, after investing virtual resources into the target investment object, collect the object operation information generated by the operation of the invested virtual resources into the target investment object according to the preset collection cycle;

[0020] For the target investment object's field, obtain environmental and operational information for that field;

[0021] Based on the custom report template and the object operation information and environmental operation information, generate a periodic operation information report for the target input object.

[0022] In one embodiment, the method further includes:

[0023] After investing virtual resources into the target investment object, calculate the exit investment assessment value based on the virtual resource rate of return generated by the target investment object based on the invested virtual resources, the risk warning index, the investment multiple, the investment duration, and the conversion ratio of investment to return.

[0024] If the exit investment assessment value exceeds the preset threshold, then the investment of virtual resources to the target investment object will be stopped; otherwise, the investment of virtual resources to the target investment object will continue.

[0025] In one embodiment, the process of obtaining the risk warning index includes:

[0026] Obtain risk indicators for the target investment object. Risk indicators should include at least the positive return indicators of virtual resources, the return capability indicators of virtual resources, the operation capability indicators of virtual resources, the risk indicators of changes in the internal architecture of the object, and the risk indicators of the environment in which the object belongs.

[0027] Under the same risk level system, the corresponding risk level of each risk indicator is determined, and the risk indicator vector of the target input object is composed of the corresponding risk levels of each risk indicator.

[0028] The risk indicator vector is processed in three layers to obtain the risk warning index of the target investment object; each layer of processing includes convolution processing, activation function processing, residual processing and pooling processing.

[0029] Secondly, this application also provides a data processing apparatus. The apparatus includes:

[0030] The filtering module is used to filter out the objects to be invested in from multiple objects based on the profile information of the multiple objects.

[0031] The add module is used to add potential targets to the pool of potential targets based on the correlation between the automated pooling metrics of potential targets and the automated pooling metrics of already invested targets.

[0032] The acquisition module is used to obtain the operational evaluation score of the target target in the target target pool based on the target target's virtual resource operation information and due diligence information.

[0033] The determination module is used to determine the investment judgment result of the target investment object based on the operational evaluation score and due diligence information through a decision tree.

[0034] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0035] For multiple objects that need to be invested with virtual resources, select the objects to be invested with based on the profile information of the multiple objects;

[0036] Based on the correlation between the automated pooling metrics of the target targets and the automated pooling metrics of the already invested targets, add the target targets to the pool of target targets.

[0037] For target targets in the pool of potential investors, an operational evaluation score is obtained based on the virtual resource operation information and due diligence information of the target targets.

[0038] Based on operational evaluation scores and due diligence information, the decision tree is used to determine the investment judgment results for the target investment objects.

[0039] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0040] For multiple objects that need to be invested with virtual resources, select the objects to be invested with based on the profile information of the multiple objects;

[0041] Based on the correlation between the automated pooling metrics of the target targets and the automated pooling metrics of the already invested targets, add the target targets to the pool of target targets.

[0042] For target targets in the pool of potential investors, an operational evaluation score is obtained based on the virtual resource operation information and due diligence information of the target targets.

[0043] Based on operational evaluation scores and due diligence information, the decision tree is used to determine the investment judgment results for the target investment objects.

[0044] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0045] For multiple objects that need to be invested with virtual resources, select the objects to be invested with based on the profile information of the multiple objects;

[0046] Based on the correlation between the automated pooling metrics of the target targets and the automated pooling metrics of the already invested targets, add the target targets to the pool of target targets.

[0047] For target targets in the pool of potential investors, an operational evaluation score is obtained based on the virtual resource operation information and due diligence information of the target targets.

[0048] Based on operational evaluation scores and due diligence information, the decision tree is used to determine the investment judgment results for the target investment objects.

[0049] The aforementioned data processing methods, apparatus, computer equipment, storage media, and computer program products, for multiple objects to be invested in with virtual resources, filter out potential investment objects from multiple objects based on the profile information of these objects; add potential investment objects to the potential investment object pool based on the correlation between the automated pooling indicators of potential investment objects and the automated pooling indicators of already invested objects; for target potential investment objects in the pool, obtain the operational evaluation score of the target potential investment object based on the virtual resource operation information and due diligence information of the target potential investment object; and determine the investment judgment result of the target potential investment object through a decision tree based on the operational evaluation score and due diligence information. For the obtained data information of potential investment objects, the investment judgment result of the potential investment object is automatically identified by comparing it with the data of already invested objects and calculating the operational evaluation score. This eliminates the need for manual data analysis; the computer automatically and intelligently processes the data information of potential investment objects, improving data processing efficiency and accuracy. Attached Figure Description

[0050] Figure 1 This is a diagram illustrating the application environment of a data processing method in one embodiment.

[0051] Figure 2 This is a flowchart illustrating a data processing method in one embodiment;

[0052] Figure 3 This is a schematic diagram illustrating the process of generating a periodic operational information report for a target input object in one embodiment.

[0053] Figure 4 This is a flowchart illustrating the data processing method in another embodiment;

[0054] Figure 5 This is a flowchart illustrating the data processing method in yet another embodiment;

[0055] Figure 6 This is a structural diagram of the risk assessment model training process in one embodiment;

[0056] Figure 7 This is a system physical architecture diagram of the lifecycle management system for objects to be deployed in one embodiment;

[0057] Figure 8 This is a schematic diagram of the lifecycle management system interface for an object to be deployed in one embodiment.

[0058] Figure 9 This is a structural block diagram of a data processing device in one embodiment;

[0059] Figure 10 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0061] The data processing method provided in this application embodiment can be applied to, for example... Figure 1 In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or located in the cloud or on other network servers. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, etc. Portable wearable devices can include smartwatches, smart bracelets, head-mounted devices, etc. Server 104 can be implemented using a standalone server or a server cluster consisting of multiple servers.

[0062] In one embodiment, such as Figure 2 As shown, a data processing method is provided, which can be applied to... Figure 1 Taking server 104 as an example, the following steps are included:

[0063] Step 202: For multiple objects to which virtual resources are to be invested, select the objects to be invested from the multiple objects based on the profile information of the multiple objects;

[0064] Among these, the multiple objects of virtual resources to be invested refer to projects for which relevant information has been obtained and are awaiting confirmation of whether they meet the investment criteria. Virtual resources are used to measure the degree of investment; for example, the objects could be funds or equity. Profile information refers to all information about the company to which the object belongs. For example, profile information could include company profile, company brand profile, business registration information, financing history, comparable listed companies, relevant news, and competitor information. The type of profile information will vary depending on the object. For example, when the object is a target fund, the profile information may also include investment details, shareholder information, business registration changes, institutional news, investment trends, invested companies, and exited companies.

[0065] Specifically, after obtaining profile information for multiple targets, an initial screening can be performed using preset criteria. For example, screening can be conducted based on information such as region, industry, investment round, establishment date, latest investment date, management organization, investment area, investment region, and investment time, improving the efficiency of target screening. Additionally, custom tags can be set for the target profile information, allowing for comparison of these tags across multiple targets to analyze differences in the available virtual resources, facilitating screening and saving time. After profile information screening, a set of targets for investment will be obtained.

[0066] Step 204: Add potential investment targets to the pool of potential investment targets based on the correlation between the automated pooling metrics of potential investment targets and the automated pooling metrics of already invested targets.

[0067] Automatic inclusion criteria refer to indicators used to measure whether an entity can be added to the pool of potential investees. There can be one or more indicators, such as operational status, company size, R&D expenditure, certifications, legal involvement, development stage, intellectual property, and investor information. The type of automatic inclusion criterion for already invested entities should be consistent with that for potential investees.

[0068] The relevance level reflects the degree of association between potential targets and already invested targets. Based on the already invested targets, potential targets are screened to determine whether they can be added to the target pool. It's important to note that targets are selected directly from the target pool. Understandably, for a potential target, a higher degree of relevance to already invested targets indicates a greater worthiness of virtual resource investment. Specifically, the correlation coefficient between potential and already invested targets is determined based on multiple automated pooling indicators, and the inclusion of the potential target in the pool is determined based on this correlation coefficient.

[0069] Step 206: For the target targets in the target pool, obtain the operational evaluation score of the target targets based on the virtual resource operation information and due diligence information of the target targets;

[0070] Among them, the target investment object refers to the potential investment objects in the pool of potential investment objects. That is, the potential investment objects are obtained after initial screening based on profile information and correlation with previously invested objects from multiple objects initially acquired for investment. The virtual resource operation information of the target investment object refers to the internal corporate information of the company to which the target investment object belongs, such as basic corporate information, shareholder information, senior management information, financing history, major customers, corporate operation data, and financial data. The due diligence information refers to the information of the company to which the target investment object belongs obtained from other external levels, such as judicial litigation information (civil litigation, criminal litigation, court enforcement), bank statements (overall inflow and outflow, analysis of the top ten fund transaction counterparties), intellectual property (patents, trademarks, copyrights), etc.

[0071] See Figure 3 The intended enterprise is the company to which the target investment object belongs. External data refers to the due diligence information in this embodiment. Collected data refers to virtual resource operation information. After collecting the virtual resource operation information and due diligence information of the target investment object, a due diligence report will be automatically generated. The due diligence report may include the following elements: basic enterprise information (business registration information, business changes, shareholder information, financing information, senior management information, news and public opinion), judicial litigation information (civil litigation, criminal litigation, court enforcement), financial data (balance sheet, cash flow statement, horizontal comparison of quarterly financial statement indicators), bank statements (overall inflow and outflow, analysis of the top ten fund transaction counterparties), invoices and taxes (output / input / difference, analysis of the top ten suppliers), and intellectual property rights (patents, trademarks, copyrights).

[0072] The operational evaluation score is a score obtained by the company owning the target investment target in assessing the target investment target's operational status. It indicates the degree to which the target investment target is worth investing virtual assets in; generally, a higher score is better. Specifically, the pooling correlation vector is determined through the target investment target's automated pooling indicators. Then, based on the target investment target's pooling correlation vector, virtual resource operation information, and due diligence information, the operational evaluation score of the target investment target is calculated using the following formula:

[0073] T(c)=r1P(c)+r2Q(c)+r3M(c)+r4N(c)+r5S(c)

[0074] Where P(c) represents the average value of the correlation vector in the pool, Q(c) represents the debt-to-asset ratio, M(c) represents the loan turnover rate, N(c) represents the year-on-year growth rate of net profit, S(c) represents the number of intellectual property rights, and r1, r2, r3, r4, r5 represent preset weights, and ∑r i =1.

[0075] Step 208: Based on the operational evaluation score and due diligence information, determine the investment judgment result of the target investment object through a decision tree.

[0076] Decision trees, based on known probabilities of various scenarios, are used to calculate the probability that the expected net present value is greater than or equal to zero, thereby evaluating project risk and determining its feasibility. In this embodiment, before processing the data of the target investment object, a trained decision tree, obtained by training on a large amount of historical data, is used to judge the investment outcome of the target investment object. The investment judgment result indicates whether the target investment object is approved for the allocation of virtual resources.

[0077] Specifically, a decision tree can be trained based on information such as the company's relevance to the target investment, operational evaluation value, estimated investment amount, collateral and pledge status, market capacity, and profit level. After multiple training and optimizations, the following results can be obtained:

[0078] pass(i) = h(n)

[0079] Where pass(i) represents the judgment result, which takes the value 1 or 0. If it is 1, the approval is allowed; otherwise, the approval is not allowed and manual processing is required. h(n) represents the trained decision tree function, and n is the number of decision tree parameters.

[0080] In the method provided in the above embodiments, for multiple objects to be invested in with virtual resources, objects to be invested in are selected from multiple objects based on their profile information; objects to be invested in are added to the pool of objects to be invested in based on the correlation between the automated pooling indicators of the objects to be invested in and the automated pooling indicators of the objects already invested in; for the target objects to be invested in the pool of objects to be invested in, an operational evaluation score is obtained based on the virtual resource operation information and due diligence information of the target objects to be invested in; based on the operational evaluation score and due diligence information, the investment judgment result of the target objects to be invested in is determined through a decision tree. For the data information of the objects to be invested in, the investment judgment result of the target objects to be invested in is automatically identified by comparing it with the data information of the objects already invested in and calculating the operational evaluation score. This eliminates the need for a manual data analysis process, as the computer automatically and intelligently processes the data information of the target objects to be invested in, improving data processing efficiency and accuracy.

[0081] In one embodiment, see Figure 4 Based on the correlation between the automated pooling metrics of potential investees and the automated pooling metrics of already invested investors, add potential investees to the pool, including:

[0082] Step 402: Based on the correlation between the automated pooling metrics of the target object and the automated pooling metrics of the already invested objects, obtain the pooling correlation vector of the target object.

[0083] Step 404: Based on the values ​​of each element in the pooling correlation vector, determine the number of elements in the pooling correlation vector that are greater than the corresponding preset threshold.

[0084] Step 406: If the number of elements is greater than half of the total number of objects already submitted, then add the objects to be submitted to the pool of objects to be submitted.

[0085] After initial screening of multiple candidates based on their profile information, a preliminary screening set C can be obtained:

[0086]

[0087] Where C(i) represents the initial screening result of whether the i-th target for investment is included in the pool, E is the set of industries that are manually focused on in the current stage of the investment strategy, v(j) represents the set of industry tags of the current target for investment, and exist i (finance) indicates that the target company currently has financing needs, unexist i (finance) indicates that the target company currently has no financing needs. The set E can be updated periodically by the user based on the investment of virtual resources.

[0088] The automated criteria for pooling potential investment targets can include multiple dimensions such as business status, company size, R&D ratio, qualifications and certifications, legal disputes, development stage, intellectual property, and investor information. The set of invested targets Y represents the set of virtual resource investment targets that have been pooled and initiated. The correlation vector P is calculated between each potential investment target in the initial screening set C and each invested target in the set Y.

[0089] A higher correlation coefficient indicates a higher degree of correlation. In this embodiment, the correlation vector P of each initially screened object c is calculated based on the degree of correlation, and the final set R (the pool of objects to be automatically added to the pool) of objects is obtained by filtering.

[0090]

[0091] Where, p i This represents an element of the correlation vector P, where TH represents the PCC correlation threshold. When the number of elements in vector P that are greater than or equal to the threshold is greater than or equal to half the number of objects in the already invested object set Y, it is added to the set R of objects awaiting investment in the automated investment pool; otherwise, it is not added.

[0092] The method used in the above embodiments calculates the correlation vector between each candidate and the already submitted candidates, and then performs a secondary screening based on the correlation vector to determine the candidates entering the candidate pool. This automatically completes the screening of candidates, and the judgment is made according to a fixed formula, resulting in high accuracy and avoiding the influence of human subjectivity. Furthermore, the automatic screening method is extremely efficient.

[0093] In one embodiment, the number of objects to be invested in and the number of automated pooling indicators are both multiple; the pooling correlation vector of the objects to be invested in is composed of the correlation coefficient between the objects to be invested in and each already invested object, and the process of determining the correlation coefficient between the objects to be invested in and each already invested object includes:

[0094] For the current invested targets and the current automated investment indicators, obtain the first average value of the current automated investment indicators for all targets to be invested and the second average value of the current automated investment indicators for all invested targets. Calculate the first difference between the current automated investment indicator for the current target and the first average value. Calculate the second difference between the current automated investment indicator for the current invested target and the second average value. Calculate the first product between the first difference and the second difference, which is used as the first product of the current automated investment indicator.

[0095] Sum the products of each automation input indicator to obtain the sum value;

[0096] For each automation input indicator, the first difference is summed by squaring, and the first square root of the summation is taken. For each automation input indicator, the second difference is summed by squaring, and the second square root of the summation is taken. The second product between the first square root and the second square root is obtained. The ratio between the sum and the second product is calculated as the correlation coefficient between the target to be invested and the currently invested target.

[0097] For each candidate in the initial screening set C and each candidate in the screening set Y, calculate the Pearson correlation coefficient pcc(c,y) using the following formula to obtain the correlation vector P of the initial screening items:

[0098]

[0099] Where c is the automated pooling index vector of the initial screening objects, y represents the automated pooling index vector of the invested projects, and the absolute value of the calculation result of pcc(c,y) is in the range of [0,1].

[0100] By calculating the correlation vector between each candidate and the already submitted candidates, a second screening is performed on the candidates after the initial screening based on the correlation vector. This determines the candidates to be included in the candidate pool. The screening of candidates is completed automatically, and the judgment is made according to a fixed formula, resulting in high accuracy and avoiding the influence of human subjectivity. Furthermore, the automatic screening method is extremely efficient.

[0101] In one embodiment, the method further includes:

[0102] If the investment judgment result is a confirmed investment, after investing virtual resources into the target investment object, collect the object operation information generated by the operation of the invested virtual resources into the target investment object according to the preset collection cycle;

[0103] For the target investment object's field, obtain environmental and operational information for that field;

[0104] Based on the custom report template and the object operation information and environmental operation information, generate a periodic operation information report for the target input object.

[0105] The target investment object refers to the intended investment object after virtual resources are invested. The object operation information refers to the development status of the target investment object after the investment of virtual resources. For example, if the target investment object is a fund, then the increase in the fund's corresponding virtual resources after virtual resources are invested is considered operation information. The types of information included in the target investment information differ for each target investment entity. For example, when the target investment entity is a direct investment project fund, the target investment information includes basic fund information, investment strategy, key terms, payment information, target projects in the investment portfolio, financial data, post-investment meetings, personnel assignment, regular review checklist, regular reports, fund allocation, other attachments, post-investment value-added services, comprehensive linkage, and financial data of the target projects in the investment portfolio. When the target investment entity is a direct investment fund of funds, the target investment information, in addition to the characteristics of a direct investment project fund, also includes the target fund in the investment portfolio, the projects invested in by the target fund, the financial data of the target fund, and the financial data of the projects invested in by the target fund. When the target investment entity is a direct investment project, the target investment information includes project fund information, financial data, payment information, meeting and board information, company valuation, company equity, post-investment reports, dispatched personnel, regular review checklist, project allocation, post-investment value-added services, comprehensive linkage, and other attachments.

[0106] It should be noted that the object operation information is collected according to a preset cycle, such as once a month, once a quarter, or once every six months.

[0107] Since the target investment object in this application has a long investment period, the method in this embodiment will automatically capture market data, including business information, securitization status, IPO status, financing status, listing price, listing venue, shareholder change information, etc. as environmental operation information when collecting data in a preset period (e.g., quarterly). The target investment object information will be automatically updated and the updated content will be marked, so that the business manager can perceive the market changes of the investment object as early as possible and quickly grasp the details of the changes of the investment object.

[0108] In the method provided in this application embodiment, after collecting and analyzing the object operation information and environmental operation information of the target investment object, a periodic operation information report of the target investment object within a preset period can be generated according to a customized report template. By monitoring and analyzing the operation information of the target investment object in real time, periodic management and control of the target investment object after the investment of virtual resources can be achieved.

[0109] In one embodiment, see Figure 5 The methods also include:

[0110] Step 502: After investing virtual resources into the target investment object, calculate the exit investment evaluation value based on the virtual resource rate of return, risk warning index, investment multiple, investment duration and investment-return conversion ratio generated by the target investment object based on the invested virtual resources.

[0111] Step 504: If the exit investment evaluation value is greater than the preset threshold, then exit the investment of virtual resources to the target investment object; otherwise, continue to invest virtual resources to the target investment object.

[0112] The virtual resource rate of return refers to the internal rate of return (IRR), which is the discount rate at which the total present value of virtual resource inflows equals the total present value of virtual resource outflows, and the net present value equals zero. In a specific embodiment, the IRR considers the time value of virtual resources and can better reflect the investor's return, where T is the investment period and CF... t This refers to the net virtual resource quantity in period t.

[0113]

[0114] The REWI risk warning index indicates the risk status of an investment target. It is based on a risk warning model during the operational phase after virtual resources are invested, and the index is calculated monthly to show the month-on-month growth of the investment target's risk score. The Fscore is also included. j Fscore represents the risk score for month j calculated in the risk warning model based on residual neural networks. j -Fscore j-1This represents the difference in risk scores between month j and month j-1, and n represents the monthly statistical period for REWI.

[0115]

[0116] The Investor Value (TVIP) and the Realization Value (DPI) indicate the return on investment for the investee. TFH represents the allocated return received by the investor, SV represents the residual value, and TZ represents the amount of virtual resources invested.

[0117] TVIP = (TFH + SV) / ​​TZ;

[0118] DPI = TFH / TZ;

[0119] After virtual resources are invested in the target investment object, an exit investment assessment value is calculated based on IRR, TVIP, DPI, and REWI to comprehensively determine whether the virtual resource investment in the target investment object should be withdrawn. If the exit investment assessment value is greater than the set threshold, it is recommended to keep the target investment object running and continue to invest virtual resources in the target investment object without withdrawing; otherwise, it is not recommended, and staff can manually determine whether to withdraw.

[0120]

[0121] It should be noted that when calculating the exit investment valuation, the Public Market Equivalence (PME) can also be used as a reference. The PME indicates the likelihood of acquiring virtual resources after investing in them. When the PME is greater than 1, it means that the return on investment for the current target investment object is greater than the return on investment in the selected public market, making the investment feasible. Where D... t Let C be the total cash outflow during period t. t Let r be the total cash inflow during period t. i It refers to the S&P 500 index.

[0122]

[0123] The method provided in the above embodiments evaluates the operational status of the target investment object after investing virtual resources through multiple indicators, judges whether the target investment object needs to continue investing, realizes comprehensive intelligent supervision of the investment status of the target investment object, improves the processing effect of the target investment object's operational data, and obtains more accurate control over the target investment object.

[0124] In one embodiment, the process of obtaining the risk warning index includes:

[0125] Obtain risk indicators for the target investment object. Risk indicators should include at least the positive return indicators of virtual resources, the return capability indicators of virtual resources, the operation capability indicators of virtual resources, the risk indicators of changes in the internal architecture of the object, and the risk indicators of the environment in which the object belongs.

[0126] Under the same risk level system, the corresponding risk level of each risk indicator is determined, and the risk indicator vector of the target input object is composed of the corresponding risk levels of each risk indicator.

[0127] The risk indicator vector is processed in three layers to obtain the risk warning index of the target investment object; each layer of processing includes convolution processing, activation function processing, residual processing and pooling processing.

[0128] The risk warning index is acquired periodically within a preset period and is used to reflect the risk and return situation of the target investment object after investing virtual resources within the preset period. Combining the investment process, results, and environment of the target investment object, the risk index can include multiple aspects and can be divided into index levels, such as primary indicators and secondary indicators, as shown in Table 1 below.

[0129] Table 1 Description of Risk Indicators

[0130]

[0131] It should be noted that when determining the risk warning index based on risk indicators, it must be determined based on indicators of the same level, that is, within the same risk level system. For example, referring to Table 1, the primary indicators of risk indicators include virtual resource positive return indicators, virtual resource return capability indicators, virtual resource operation capability indicators, internal structure change risk indicators of the object, and environmental risk indicators of the object. Therefore, the risk warning index is determined based on the corresponding risk level of all primary indicators.

[0132] A post-investment intelligent risk assessment model is constructed based on the design principles of convolutional neural networks and residual models. The risk warning index of the target investment object is obtained through the intelligent risk assessment model. The risk warning index [0, 0.2], (0.2, 0.4], (0.4, 0.6], (0.6, 0.8], and (0.8, 1] correspond to the risk levels of low risk, low-medium risk, medium risk, medium-high risk, and high risk.

[0133] Specifically, obtain the training metric dataset, and use the training metric dataset to train the intelligent risk assessment model. See [link to relevant documentation]. Figure 6Risk indicator data x is input into the first layer of the network. After convolution, Batch Normalization, and ReLU operations, it outputs F1(x). The residual term F1(x) + x is used as F2(x), which is then processed through a pooling layer and input into the second layer. After convolution, Batch Normalization, and ReLU operations, it outputs F3(x). The residual term F3(x) + pooling(F2(x)) is used as F4(x), which is then processed through a pooling layer and input into the third layer. Similarly, after convolution, Batch Normalization, and ReLU operations, it outputs F5(x). The residual term F5(x) + pooling(F4(x)) is used as F6(x), which is then processed through a Sigmoid activation layer and a fully connected layer to obtain the risk warning index. As input x, the risk warning index Y(x) corresponding to the training data is labeled. During training, the parameters of the residual neural network are continuously adjusted so that the risk warning index tends to the labeled Y(x).

[0134] In the method provided in the above embodiments, an intelligent risk assessment model is constructed using the principle of convolutional neural networks. The trained intelligent risk assessment model is used to evaluate the risk of the target investment object, thereby obtaining the risk warning index of the target investment object and realizing intelligent management of the investment process of the target investment object.

[0135] In one embodiment, the method provided in this application further includes: after withdrawing the investment of virtual resources into the target investment object, obtaining the post-investment characteristics of the target investment object to determine whether virtual resources can be reinvested into the target investment object. The post-investment characteristics include the current status of the target investment object and changes in market data related to the target investment object. The current status of the target investment object mainly includes statistics on the investment status (pre-investment, during investment, post-investment, termination, exit) of all investment objects currently managed by the manager. Changes in market data are determined according to the type of investment object. For example, when the target investment object is a project, the project post-investment review will include statistics on the financing situation, media reports, business registration changes, competitors, and legal disputes of the invested project compared to the previous day. When the target investment object is a fund, the project post-investment review will include statistics on investment events, exit events, newly established funds, new rounds of financing for invested projects, and new rounds of financing for invested projects compared to the previous day. The project post-investment review, leveraging market data, allows managers to easily obtain the latest market data of the investment objects daily.

[0136] In addition, after investing virtual resources in the target investment object, multi-dimensional operational data of the target investment object after the investment is obtained, and the data is visualized in the form of tables, pie charts, line charts, bar charts, etc. This includes processing the data to obtain various information display methods of the target investment object, such as the regional concentration statistics chart of the target investment object, the pie chart of the industry distribution of investment, the balance statistics, the overall valuation, the cash flow, the securitization status, and the analysis and comparison report of the underlying virtual resources, etc.

[0137] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0138] In one embodiment, a lifecycle management system for investment targets is provided. This system executes the steps in the data processing method described above to achieve full lifecycle management of investment targets, encompassing pre-investment, investment, and post-investment stages. The lifecycle management system for investment targets employs the following... Figure 7 The system physical architecture is shown. For the visualization interface of the lifecycle management system for the objects to be deployed, please refer to [link / reference needed]. Figure 8 The lifecycle management system for potential investment targets includes:

[0139] The Penetration Management module is used to filter multiple objects for virtual resource investment, aiming to help investment managers discover primary market investment targets more efficiently.

[0140] The project pool module is primarily used for adding potential investment targets to the database and initiating projects. It can also utilize an automated pooling model to calculate pooling relevance, automatically selecting potential investment targets from the market investment targets provided in the penetration management module for automated pooling.

[0141] The enterprise reporting module is primarily used for collecting data on the companies to which the target companies belong, and generating due diligence reports on potential companies by combining external market data. Based on this, an operational evaluation model is used to calculate the operational evaluation score of the target companies, where the operational evaluation value = fun(pool relevance, operational value).

[0142] The investment management module is primarily used for the pre-investment business approval process for potential investments. Approval can be done manually or through a multi-factor automated approval model based on decision trees. Whether a project passes approval depends on the automated model's judgment, which combines evaluation values ​​from previous steps, including the investment target's company's relevance to the investment pool and operational evaluation values.

[0143] The post-investment management module is primarily used to manage the target entities for virtual resource investment, including sub-modules such as quarterly data collection, quarterly data review, and intelligent post-investment reporting. Simultaneously, during the post-investment management phase, the project review and risk management sub-modules within the risk control management module are used for risk analysis and management of the target entities. The risk management module primarily uses a residual neural network-based risk warning model for risk analysis of the target entities.

[0144] The exit management module is mainly used for exit management of target investment objects after they have invested virtual resources. It can manage the investment and exit of target investment objects through an exit mechanism model.

[0145] Based on the same inventive concept, this application also provides a data processing apparatus for implementing the data processing method described above. The solution provided by this apparatus is similar to the implementation scheme described in the above method; therefore, the specific limitations in one or more data processing apparatus embodiments provided below can be found in the limitations of the data processing method described above, and will not be repeated here.

[0146] In one embodiment, such as Figure 9 As shown, a data processing apparatus is provided, including: a filtering module 901, an adding module 902, an acquiring module 903, and a determining module 904, wherein:

[0147] The filtering module 901 is used to filter out the objects to be invested in from multiple objects based on the profile information of the multiple objects;

[0148] Add module 902, which is used to add objects to the pool of objects to be invested in based on the correlation between the automated pooling indicators of the objects to be invested in and the automated pooling indicators of the objects already invested in.

[0149] The acquisition module 903 is used to obtain the operational evaluation score of the target target in the target target pool based on the virtual resource operation information and due diligence information of the target target;

[0150] Module 904 is used to determine the investment judgment result of the target investment object based on the operational evaluation score and due diligence information through a decision tree.

[0151] In one embodiment, the adding module 902 is further configured to:

[0152] Based on the correlation between the automated pooling metrics of the target targets and the automated pooling metrics of the already invested targets, obtain the pooling correlation vector of the target targets;

[0153] Based on the values ​​of each element in the pooling correlation vector, determine the number of elements in the pooling correlation vector that are greater than the corresponding preset threshold.

[0154] If the number of elements is greater than half of the total number of objects already submitted, the objects to be submitted will be added to the pool of objects to be submitted.

[0155] In one embodiment, the adding module 902 is further configured to:

[0156] For the current invested targets and the current automated investment indicators, obtain the first average value of the current automated investment indicators for all targets to be invested and the second average value of the current automated investment indicators for all invested targets. Calculate the first difference between the current automated investment indicator for the current target and the first average value. Calculate the second difference between the current automated investment indicator for the current invested target and the second average value. Calculate the first product between the first difference and the second difference, which is used as the first product of the current automated investment indicator.

[0157] Sum the products of each automation input indicator to obtain the sum value;

[0158] For each automation input indicator, the first difference is summed by squaring, and the first square root of the summation is taken. For each automation input indicator, the second difference is summed by squaring, and the second square root of the summation is taken. The second product between the first square root and the second square root is obtained. The ratio between the sum and the second product is calculated as the correlation coefficient between the target to be invested and the currently invested target.

[0159] In one embodiment, the data processing apparatus further includes an operations report generation module:

[0160] If the investment judgment result is a confirmed investment, after investing virtual resources into the target investment object, collect the object operation information generated by the operation of the invested virtual resources into the target investment object according to the preset collection cycle;

[0161] For the target investment object's field, obtain environmental and operational information for that field;

[0162] Based on the custom report template and the object operation information and environmental operation information, generate a periodic operation information report for the target input object.

[0163] In one embodiment, the data processing apparatus further includes an exit module:

[0164] After investing virtual resources into the target investment object, the exit investment assessment value is calculated based on the virtual resource rate of return, risk warning index, investment multiple, investment duration and investment-return conversion ratio generated by the target investment object based on the invested virtual resources.

[0165] If the exit investment assessment value exceeds the preset threshold, then the investment of virtual resources to the target investment object will be stopped; otherwise, the investment of virtual resources to the target investment object will continue.

[0166] In one embodiment, the exit module is further configured to:

[0167] Obtain risk indicators for the target investment object. Risk indicators should include at least the positive return indicators of virtual resources, the return capability indicators of virtual resources, the operation capability indicators of virtual resources, the risk indicators of changes in the internal architecture of the object, and the risk indicators of the environment in which the object belongs.

[0168] Under the same risk level system, the corresponding risk level of each risk indicator is determined, and the risk indicator vector of the target input object is composed of the corresponding risk levels of each risk indicator.

[0169] The risk indicator vector is processed in three layers to obtain the risk warning index of the target investment object; each layer of processing includes convolution processing, activation function processing, residual processing and pooling processing.

[0170] Each module in the aforementioned data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0171] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 10 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database stores multi-dimensional data of the objects to be processed. The network interface communicates with external terminals via a network connection. When the computer program is executed by the processor, it implements a data processing method.

[0172] Those skilled in the art will understand that Figure 10The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0173] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0174] For multiple objects that need to be invested with virtual resources, select the objects to be invested with based on the profile information of the multiple objects;

[0175] Based on the correlation between the automated pooling metrics of the target targets and the automated pooling metrics of the already invested targets, add the target targets to the pool of target targets.

[0176] For target targets in the pool of potential investors, an operational evaluation score is obtained based on the virtual resource operation information and due diligence information of the target targets.

[0177] Based on operational evaluation scores and due diligence information, the decision tree is used to determine the investment judgment results for the target investment objects.

[0178] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0179] Based on the correlation between the automated pooling metrics of the target targets and the automated pooling metrics of the already invested targets, obtain the pooling correlation vector of the target targets;

[0180] Based on the values ​​of each element in the pooling correlation vector, determine the number of elements in the pooling correlation vector that are greater than the corresponding preset threshold.

[0181] If the number of elements is greater than half of the total number of objects already submitted, the objects to be submitted will be added to the pool of objects to be submitted.

[0182] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0183] For the current invested targets and the current automated investment indicators, obtain the first average value of the current automated investment indicators for all targets to be invested and the second average value of the current automated investment indicators for all invested targets. Calculate the first difference between the current automated investment indicator for the current target and the first average value. Calculate the second difference between the current automated investment indicator for the current invested target and the second average value. Calculate the first product between the first difference and the second difference, which is used as the first product of the current automated investment indicator.

[0184] Sum the products of each automation input indicator to obtain the sum value;

[0185] For each automation input indicator, the first difference is summed by squaring, and the first square root of the summation is taken. For each automation input indicator, the second difference is summed by squaring, and the second square root of the summation is taken. The second product between the first square root and the second square root is obtained. The ratio between the sum and the second product is calculated as the correlation coefficient between the target to be invested and the currently invested target.

[0186] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0187] If the investment judgment result is a confirmed investment, after investing virtual resources into the target investment object, collect the object operation information generated by the operation of the invested virtual resources into the target investment object according to the preset collection cycle;

[0188] For the target investment object's field, obtain environmental and operational information for that field;

[0189] Based on the custom report template and the object operation information and environmental operation information, generate a periodic operation information report for the target input object.

[0190] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0191] After investing virtual resources into the target investment object, the exit investment assessment value is calculated based on the virtual resource rate of return, risk warning index, investment multiple, investment duration and investment-return conversion ratio generated by the target investment object based on the invested virtual resources.

[0192] If the exit investment assessment value exceeds the preset threshold, then the investment of virtual resources to the target investment object will be stopped; otherwise, the investment of virtual resources to the target investment object will continue.

[0193] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0194] Obtain risk indicators for the target investment object. Risk indicators should include at least the positive return indicators of virtual resources, the return capability indicators of virtual resources, the operation capability indicators of virtual resources, the risk indicators of changes in the internal architecture of the object, and the risk indicators of the environment in which the object belongs.

[0195] Under the same risk level system, the corresponding risk level of each risk indicator is determined, and the risk indicator vector of the target input object is composed of the corresponding risk levels of each risk indicator.

[0196] The risk indicator vector is processed in three layers to obtain the risk warning index of the target investment object; each layer of processing includes convolution processing, activation function processing, residual processing and pooling processing.

[0197] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method steps mentioned in all the above embodiments.

[0198] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the method steps mentioned in all the above embodiments.

[0199] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. 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). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0200] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0201] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A data processing method, characterized in that, The method includes: For multiple objects that need to be invested with virtual resources, select the objects to be invested with based on the profile information of the multiple objects; Based on the correlation between the automated pooling indicators of the target objects and the automated pooling indicators of the already invested objects, the target objects are added to the pool of target objects. For the target targets in the target target pool, based on the virtual resource operation information and due diligence information of the target targets, obtain the operation evaluation score of the target targets; Based on the operational evaluation score and the due diligence information, the investment judgment result of the target investment object is determined by a decision tree; The process of determining the correlation coefficient between the target object and each already invested object includes: For the current invested objects and the current automated investment indicators, obtain the first average value of the current automated investment indicators of all objects to be invested and the second average value of the current automated investment indicators of all invested objects. Calculate the first difference between the current automated investment indicator of the current object to be invested and the first average value. Calculate the second difference between the current automated investment indicator of the current object to be invested and the second average value. Calculate the first product between the first difference and the second difference, which is taken as the first product of the current automated investment indicator. Sum the products of each automation input indicator to obtain the sum value; For each automation input indicator, the first difference is squared and summed, and the first square root of the sum is taken. For each automation input indicator, the second difference is squared and summed, and the second square root of the sum is taken. The second product between the first square root and the second square root is obtained. The ratio between the sum and the second product is calculated as the correlation coefficient between the target to be invested and the currently invested target.

2. The method according to claim 1, characterized in that, The step of adding the target object to the pool of target objects based on the correlation between the automated pooling indicators of the target object and the automated pooling indicators of the already invested objects includes: Based on the correlation between the automated pool entry indicators of the target object and the automated pool entry indicators of the already invested objects, obtain the pool entry correlation vector of the target object; Based on the values ​​of each element in the pooling correlation vector, determine the number of elements in the pooling correlation vector that are greater than the corresponding preset threshold. If the number of elements is greater than half of the total number of objects already cast, then the object to be cast is added to the pool of objects to be cast.

3. The method according to claim 2, characterized in that, The number of objects to be invested in and the number of automated pooling indicators are both multiple; the pooling correlation vector of the objects to be invested in is composed of the correlation coefficient between the objects to be invested in and each already invested object.

4. The method according to claim 1, characterized in that, The method further includes: If the investment judgment result is a confirmed investment, after investing virtual resources into the target investment object, the target investment object's operation information generated by operating the invested virtual resources is collected according to a preset collection cycle. For the field to which the target investment object belongs, obtain the environmental operation information of that field; Based on the custom report template and the object operation information and the environment operation information, a periodic operation information report for the target investment object is generated.

5. The method according to claim 4, characterized in that, The method further includes: After investing virtual resources into the target investment object, the exit investment evaluation value is calculated based on the virtual resource rate of return, risk warning index, investment multiple, investment duration and investment-return conversion ratio generated by the target investment object based on the invested virtual resources. If the exit investment evaluation value is greater than a preset threshold, then the investment of virtual resources into the target investment object is stopped; otherwise, the investment of virtual resources into the target investment object continues.

6. The method according to claim 5, characterized in that, The process of obtaining the risk warning index includes: Obtain the risk indicators of the target investment object, which include at least the positive return indicators of virtual resources, the return capability indicators of virtual resources, the operation capability indicators of virtual resources, the risk indicators of changes in the internal architecture of the object, and the risk indicators of the environment to which the object belongs; Under the same risk level system, the corresponding risk level of each risk indicator is determined, and the risk indicator vector of the target investment object is composed of the corresponding risk levels of each risk indicator. The risk indicator vector is processed in three layers to obtain the risk warning index of the target investment object; wherein each layer of processing includes convolution processing, activation function processing, residual processing and pooling processing.

7. A data processing apparatus, characterized in that, The device includes: The filtering module is used to filter out objects to be invested in from multiple objects based on the profile information of the multiple objects; The addition module is used to add the target object to the target object pool based on the correlation between the automated pool entry indicators of the target object and the automated pool entry indicators of the already invested objects; wherein, the process of determining the correlation coefficient between the target object and each already invested object includes: for the current already invested object and the current automated input indicator, obtaining the first average value of the current automated input indicator of all target objects and the second average value of the current automated input indicator of all already invested objects, calculating the first difference between the current automated input indicator of the current target object and the first average value, and calculating the correlation coefficient between the current automated input indicator of the current already invested object and the current automated input indicator of the current already invested object. The second difference between the second average values ​​is used to calculate the first product between the first difference and the second difference, which is taken as the first product corresponding to the current automation input index. The products corresponding to each automation input index are summed to obtain a sum. The first difference corresponding to each automation input index is squared and summed, and the first square root of the sum is taken. The second difference corresponding to each automation input index is squared and summed, and the second square root of the sum is taken. The second product between the first and second square roots is obtained. The ratio between the sum and the second product is calculated as the correlation coefficient between the target to be invested in and the currently invested target. The acquisition module is used to acquire the operational evaluation score of the target target in the target target pool based on the virtual resource operation information and due diligence information of the target target; The determination module is used to determine the investment judgment result of the target investment object based on the operational evaluation score and the due diligence information through a decision tree.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements 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, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images