Method and system for assessing risks of protecting and inheriting overall asset wealth

Abstract

The application belongs to the technical field of information matching and data evaluation, and proposes a full asset wealth protection and inheritance risk evaluation method and system, specifically: first, a full asset network identification benchmark server and a redistribution server are identified, which are respectively recorded as a benchmark object and an evaluation object, a benchmark word adaptive portrait is constructed through an asset database of each evaluation object, then inheritance execution quality time sequence analysis is performed by using the benchmark word adaptive portrait to obtain an inheritance execution score of each evaluation object, and finally, inheritance risk evaluation is performed in combination with the inheritance execution score of each evaluation object. The coordination between the redistribution server and the related database of the full asset wealth needing to perform inheritance processing and the benchmark server can be effectively quantified, and the risk of data tampering, loss or individual asset data read / write failure of the server group in the inheritance task is reduced.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of information matching and data evaluation, and particularly relates to a full-asset wealth protection and inheritance risk evaluation method and system. BACKGROUND

[0002] Full-asset wealth inheritance plays a vital role in scenarios such as enterprise mergers and acquisitions and family inheritance. The process of full-asset wealth inheritance mainly involves accurately and correctly transferring various types of assets of the inheritance party to the inheriting party. However, the server for asset management in the process of full-asset inheritance is not simply completed by the database reading and writing of the inheritance work, because full-asset is multi-dimensional data, and the different recording and server eras lead to different verification, registration or interaction methods, resulting in the problem of long database reading and writing cycle of service providers, insufficient quality and efficiency of asset data inheritance, and the need for a large number of adaptive adjustments. In addition, the replacement of asset service providers is also a common phenomenon in full-asset inheritance, which further magnifies the problem of insufficient quality and efficiency of asset data inheritance. In the process of performing inheritance work by the asset service party, a server is usually selected as the main storage server for the inheriting party with sufficient data, and another server is selected to verify the quality of the storage server data, including whether the original data is tampered with or the storage logic is contradictory, etc. Therefore, the server for verifying the storage server requires the asset data obtained historically to have sufficient adaptability in storage type and interaction form to the benchmark server, so as to avoid the risk of declining verification quality in the inheritance execution. SUMMARY

[0003] The purpose of the present application is to provide a full-asset wealth protection and inheritance risk evaluation method and system to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0004] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a full-asset wealth protection and inheritance risk evaluation method is provided, which comprises the following steps:

[0005] S100, identifying a benchmark server and a redistribution server from a full-asset network, respectively denoted as a benchmark object and an evaluation object; S200, constructing a benchmark word adaptation portrait through the asset database of each evaluation object;

[0006] S300, performing inheritance execution quality time series analysis using the benchmark word adaptation portrait to obtain an inheritance execution score of each evaluation object;

[0007] S400, combining the inheritance execution score of each evaluation object to perform inheritance risk evaluation.

[0008] Further, in step S100, the method of identifying the benchmark server and the redistribution server from the total asset network, respectively denoted as the benchmark object and the evaluation object, is that the total asset network is composed of a plurality of servers, including a benchmark server and a plurality of redistribution servers, respectively denoted as the benchmark object and the evaluation object.

[0009] Because the total asset wealth inheritance process involves a large amount of data changes and editing, the number of data entries and categories is huge, and the number of servers involved is also large, so in the process of network transmission, it is easy to appear the developer cannot predict the vulnerability, easy to be illegal intrusion, so in addition to the normal work of the redistribution server and the benchmark server, a server is selected from the redistribution server as the deployment server, the benchmark server is used to verify the correctness of the data, and the server with the most deployed data of the inheritor is usually selected. The deployment server directly exchanges data with the verification server, which has a similar backup effect, so the logic of the deployment server in data processing needs relatively high level of intercommunication. The total asset network refers to the server group composed of various servers serving asset management.

[0010] Further, in step S200, the method of constructing the benchmark word adaptation portrait through the asset database of each evaluation object is that each server contains an asset database, the asset database is a database composed of asset documents in JSON format or BSON format, and the stored data is unstructured or semi-structured data; the asset document is a collection composed of text; every 5-10 natural days is taken as an analysis point, and 2-6 analysis points in the reverse time direction of an analysis point are taken as the mapping period of the analysis point; for any analysis point, the benchmark object combines each asset document of the mapping period to form a mapping text set, and the evaluation object forms an analysis text set from each asset document at the analysis point; the redistribution reference score of the evaluation object is calculated according to the mapping text set and the analysis text set of the analysis point, and the sequence composed of the redistribution reference scores of all analysis points is denoted as the benchmark word adaptation portrait.

[0011] Here, the asset document is usually used to store physical assets, including but not limited to equipment, buildings, vehicles, etc., and the asset document is also used to store digital assets, including but not limited to software, data sets, patents, and copyrights, and each asset content is presented in the asset document in the form of text.

[0012] Further, the method for calculating the redistribution reference score of the evaluation object according to the mapping text set and the parsed text set of the analysis point is: for any analysis point, the text set is preprocessed, including cleaning the text, word segmentation processing and stop word elimination; the key words and corresponding weights are obtained by identifying the key words of the text set through the LDA implicit Dirichlet distribution model, and the key words are classified to obtain nouns and adjectives and are classified into relevant words and fitting words respectively by using the CRF conditional random field algorithm; the weights of the relevant words and the fitting words are normalized respectively;

[0013] The word embedding analysis is performed on the basis of the key words and corresponding weights of the text set to obtain a word vector, wherein the word vector obtained on the basis of the mapping text set analysis is a benchmark image, the word vector obtained on the basis of the parsed text set analysis is an evaluation image, and the cosine similarity between the evaluation image and the benchmark image is calculated as the redistribution reference score of the analysis point.

[0014] The text set includes the mapping text set and the parsed text set; the word embedding method includes one of GloVe, Word2Vec or FastText; the LDA implicit Dirichlet distribution model is referenced from the Gensim library in the python analysis software.

[0015] Further, in step S300, the method for performing inheritance execution quality time series analysis by using the benchmark word adaptation image to obtain the inheritance execution score of each evaluation object is: a time period is set as an evaluation period EVtm, EVtm∈[1, 10] years, and the time scale at which the redistribution reference score is obtained is recorded as an analysis point in the evaluation period; wherein all evaluation objects are required to have an equal number of analysis points in the evaluation period;

[0016] For any evaluation object, the redistribution reference score of each analysis point is obtained, and a benchmark segmentation set is formed; that is, the benchmark segmentation set is a collection of redistribution reference scores;

[0017] The K-means clustering algorithm is used on the benchmark segmentation set to divide all elements into a plurality of clusters; by default, the number of clusters is EVtm / 10;

[0018] The distance of any element to its corresponding cluster center is calculated and recorded as the cluster center distance of the element, and if the cluster center distance of any element is greater than the 70th percentile of all cluster center distances in its corresponding cluster, the analysis point corresponding to the element is recorded as a distant adaptation point;

[0019] The 70th percentile of all distances in the corresponding cluster refers to the value of the 70th position in the ascending order of all element cluster center distances in the cluster.

[0020] The redistribution reference score of each analysis point is normalized by using a sigmoid activation function to obtain an adaptation scale;

[0021] For any evaluation object, the sequence of the adaptation scale of each remote adaptation point is denoted as a remote evaluation sequence LS.PT; the sequence of the adaptation scale of all analysis points of the evaluation object is denoted as a full-range evaluation sequence LS.AP; any adaptation scale is selected from the full-range evaluation sequence, the percentile of all adaptation scales under the analysis point corresponding to the adaptation scale is denoted as Hta, and the percentile corresponding to the adaptation scale in the sequence LS.PT is denoted as Htb, and the adaptation scale value IHT of the adaptation scale is the root mean square value of Hta and Htb;

[0022] In the calculation of the percentile of all adaptation scales under the analysis point corresponding to the adaptation scale, different evaluation objects have adaptation scales under the same analysis point, and therefore any adaptation scale under the same analysis point can obtain the percentile.

[0023] The principle of obtaining the adaptation scale value is actually based on the comparison of the adaptation scale, and the focus is on how to relatively compare the adaptation scale of the remote adaptation point with the adaptation scale of the analysis point. The adaptation scale value is designed to measure the coordination between the relevant database to be inherited and the benchmark server in the storage logic of the redistribution server. The stronger the coordination is, the higher the probability of coincidence of the asset-related type or attribute is, indicating that the redistribution server as a deployment server can more safely and efficiently perform the backup and verification of the wealth information. When the adaptation scale value is low, it indicates that the redistribution server as a deployment server is prone to have insufficient efficiency in the backup and verification steps.

[0024] The inheritance execution score of each evaluation object is calculated according to the remote evaluation sequence and the adaptation scale value.

[0025] Since the calculation of the inheritance execution score is obtained by processing the remote evaluation sequence and the adaptation scale value, the coordination between the relevant database to be inherited and the benchmark server in the storage logic of the redistribution server can be effectively quantified. However, the dependence of the adaptation scale value on the adaptation scale is too large, which can cause the quantization result to be partially generalized and cause decision bias. This is because the amount of data of the inherited asset data obtained in the server is not always large, and when the amount of data is insufficient, the full-range evaluation sequence data will have a large swing and cause the adaptation scale to be inaccurate. However, the prior art cannot effectively compensate for this generalization phenomenon. In order to eliminate this influence, the present application proposes a more preferred solution as follows:

[0026] Further, in step S300, the method of using the benchmark word adaptation image to perform quality time series analysis to obtain the inheritance execution score of each evaluation object is: set a time period as the evaluation period EVtm, EVtm∈[2, 6] years; wherein all evaluation objects are required to have equal number of analysis points within the evaluation period;

[0027] For any evaluation object, obtain the redistribution reference score of each analysis point, and form a redistribution reference score sequence; in the redistribution reference score sequence, calculate the weighted average of all elements and record it as Mvae, wherein the weight of each element is its percentile in all elements in the redistribution reference score sequence corresponding to it; when any element in the redistribution reference score sequence is greater than Mvae, the analysis point corresponding to the element is recorded as a high adaptation point, and the number of high adaptation points is recorded as RQm;

[0028] A floating point variable is preset for all element corresponding analysis points, recorded as inheritance priority Laor, if the analysis point is a high adaptation point, the inheritance priority takes value 1, otherwise the inheritance priority takes value 0.5; the purpose of setting the inheritance priority is to make the probability of selecting the high adaptation point as the inheritance estimation point higher in the subsequent process, and the value of the non-high adaptation point can also be between 0.3-0.7, the larger the value is, the lower the ability to distinguish from the high adaptation point is;

[0029] The inheritance priority Faor of any analysis point is the ratio of its inheritance priority to the sum of the inheritance priorities of all analysis points;

[0030] In the redistribution reference score sequence, the cumulative inheritance priority FFaor of any element is the cumulative value of the inheritance priority between the element and the first element of the sequence; wherein the first element of the sequence corresponds to the analysis point closest to the current time; write all cumulative inheritance priorities into the sequence as the cumulative sequence;

[0031] Randomly generate RTN random numbers recorded as selection values, the value range of the selection value is RU∈(0, 1); wherein, RTN is a preset integer, RTN∈[500, 2000];

[0032] The serial number of the k2 is taken as the analysis point, and for any selected value RU, the estimation point condition is set as FFaor(k2) < RU < FFaor(k2+1); the analysis point satisfying the estimation point condition is searched and marked as an estimation point event; after marking the analysis points of all selected values that have estimation point events, the total number of estimation point events of the analysis points is recorded as RQm_TH, RQm_TH is arranged in descending order, and the analysis points corresponding to the first RQm elements are selected as the inheritance estimation points; wherein FFaor(k2) and FFaor(k2+1) are the cumulative inheritance probabilities of the analysis points corresponding to the k2th and k2+1th elements in the redistribution reference score sequence; the inheritance execution score of each evaluation object is calculated according to the inheritance estimation points.

[0033] The principle of screening the inheritance estimation points here is actually based on the concepts of weighted average and genetic algorithm. By setting the inheritance priority and the inheritance probability, the influence of each analysis point is quantified, and these quantified values are selected to simulate a process similar to the selection of the best, so as to determine which analysis points are more suitable to become inheritance estimation points, thereby better explaining the relevance distance of the document content between the redistribution server and the benchmark server.

[0034] Beneficial effects: Since the adaptive scale value is a dynamic quantitative tool calculated based on the text word vectors of each evaluation object and the benchmark object, it can effectively quantify the coordination of the redistribution server in the relevant database of the entire asset wealth that needs to perform inheritance processing with the benchmark server, and further explain the synchronization ability and adaptability of each participating redistribution server in the asset content with the benchmark server, thereby reducing the risk of data tampering, loss, or individual asset data read / write failure of the server group in the inheritance task.

[0035] Further, in step S400, the method of performing inheritance risk assessment in combination with the inheritance execution score of each evaluation object is: the length of the benchmark word adaptation image is recorded as the analysis amount, that is, the number of analysis points of the evaluation object. The evaluation object with the maximum value in the analysis amount in each evaluation object is searched as the first evaluation object. Under any analysis point, if one evaluation object is greater than the redistribution reference score of the first evaluation object, it is defined that the evaluation object occurs once high adaptation event, and the ratio of the number of high adaptation events of the evaluation object to its analysis amount is the high adaptation efficiency; the lower quartile value in the set composed of all high adaptation efficiencies is the adaptation efficiency threshold; record the median value and the standard deviation of all inheritance execution scores as MER and STDER respectively, and preset the evaluation risk overflow rate ERSR, ERSR ∈ [1.5, 3.5]; if the high adaptation efficiency of an evaluation object is less than the adaptation efficiency threshold and the inheritance execution score of the evaluation object is less than MER-ERSR×STDER, it is evaluated that the evaluation object has inheritance abnormal risk, and is not selected as the allocation server, and each evaluation object with inheritance abnormal risk is sent to the server of the client as an evaluation report.

[0036] Preferably, in the present application, all undefined variables can be manually set thresholds if not specifically defined.

[0037] The present application also provides a full asset wealth protection and inheritance risk assessment system, which comprises a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the full asset wealth protection and inheritance risk assessment method when executing the computer program. The full asset wealth protection and inheritance risk assessment system can run on desktop computers, laptops, palmtop computers, and cloud data centers, and the executable system can include, but is not limited to, a processor, a memory, a server cluster, and the processor executing the computer program running in the following system units:

[0038] A full asset network storage object identification unit is used to identify benchmark servers and redistribution servers from a full asset network, which are recorded as benchmark objects and evaluation objects respectively;

[0039] A benchmark word adaptation image construction unit is used to construct a benchmark word adaptation image through an asset database of each evaluation object;

[0040] A heritage execution quality time sequence analysis unit is used to perform heritage execution quality time sequence analysis using the benchmark word adaptation image to obtain the inheritance execution score of each evaluation object;

[0041] A heritage risk assessment unit is used to perform inheritance risk assessment in combination with the inheritance execution score of each evaluation object.

[0042] The present application provides a full asset wealth protection and inheritance risk assessment method and system, which can effectively quantify the coordination between the relevant database of the redistribution server in the full asset wealth that needs to perform inheritance processing and the benchmark server, and further explain the synchronization ability and adaptability between the asset content of each participating redistribution server in the inheritance and the benchmark server, thereby reducing the risk of data tampering, loss or individual asset data read / write failure of the server group in the inheritance task. BRIEF DESCRIPTION OF DRAWINGS

[0043] The above and other features of the present application will become more apparent by describing in detail the embodiments thereof with reference to the attached drawings in which like reference numerals refer to like elements throughout the several views, of which:

[0044] Figure 1 a flowchart of a full asset wealth protection and inheritance risk assessment method is shown;

[0045] Figure 2 a full asset wealth protection and inheritance risk assessment system structure diagram is shown. DETAILED DESCRIPTION

[0046] The concept, specific structure and technical effects of the present application will be described clearly and completely in combination with the embodiments and drawings to fully understand the purpose, scheme and effects of the present application. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0047] As Figure 1 a flowchart of a full asset wealth protection and inheritance risk assessment method is shown, and the full asset wealth protection and inheritance risk assessment method according to the embodiments of the present application will be described below in combination with Figure 1 The method comprises the following steps:

[0048] Embodiment, 1

[0049] S100, identifying a benchmark server and a redistribution server from a full asset network, respectively denoted as a benchmark object and an evaluation object; S200, constructing a benchmark word adaptation portrait through the asset database of each evaluation object;

[0050] S300, performing inheritance execution quality time sequence analysis using the benchmark word adaptation portrait to obtain an inheritance execution score of each evaluation object;

[0051] S400, the inheritance risk assessment is performed in combination with the inheritance execution score of each evaluation object.

[0052] Further, in step S100, the method for identifying the benchmark server and the redistribution server from the whole asset network, respectively denoted as the benchmark object and the evaluation object, is that the whole asset network is composed of a plurality of servers, the servers include a benchmark server and a plurality of redistribution servers, respectively denoted as the benchmark object and the evaluation object.

[0053] Further, in step S200, the method for constructing the benchmark word adaptation portrait through the asset database of each evaluation object is that each server contains an asset database, the asset database is a database composed of asset documents in JSON format or BSON format, and the asset document is a collection composed of texts; every 5 natural days is taken as an analysis point, and one analysis point and three analysis points in the reverse time direction thereof are taken as a mapping period of the analysis point; for any analysis point, the benchmark object combines each asset document of the mapping period to form a mapping text set, and each asset document of the evaluation object at the analysis point forms an analysis text set; the redistribution reference score of the evaluation object is calculated according to the mapping text set and the analysis text set of the analysis point, and a sequence composed of the redistribution reference scores of all analysis points is denoted as the benchmark word adaptation portrait.

[0054] Further, the method for calculating the redistribution reference score of the evaluation object according to the mapping text set and the analysis text set of the analysis point is that, for any analysis point, the text set is preprocessed, including text cleaning, word segmentation processing and stop word elimination; the LDA implicit Dirichlet distribution model is used to identify the keywords of the text set, to obtain the keywords and corresponding weights, and the CRF conditional random field algorithm is used to classify the keywords to obtain nouns and adjectives, which are classified as relevant words and fitting words respectively; the weights of the relevant words and the fitting words are normalized respectively;

[0055] The word embedding analysis is performed on each keyword and corresponding weight of the text set to obtain a word vector, wherein the word vector obtained based on the mapping text set analysis is the benchmark portrait, the word vector obtained based on the analysis of the analysis text set is the evaluation portrait, and the cosine similarity between the evaluation portrait and the benchmark portrait is calculated as the redistribution reference score of the analysis point.

[0056] Further, in step S300, the method for obtaining the inheritance execution score of each evaluation object by using the benchmark word adaptation portrait to perform inheritance execution quality time sequence analysis is that a time period is taken as an evaluation period, the value of which is 2 years, and the time scale for obtaining the redistribution reference score is denoted as an analysis point in the evaluation period.

[0057] For any evaluation object, the redistribution reference scores of each analysis point are obtained, and a benchmark segmentation set is formed.

[0058] K-means clustering algorithm is used to divide all elements into 10 clusters as the benchmark partition set;

[0059] The distance of any element to its corresponding cluster center is calculated and recorded as the cluster center distance of the element, and if the cluster center distance of any element is greater than the 70th percentile of all cluster center distances in its corresponding cluster, the corresponding analysis point of the element is recorded as a far-distance adaptive point;

[0060] The reassignment reference score of each analysis point is normalized by a sigmoid activation function to obtain an adaptive scale;

[0061] For any evaluation object, the adaptive scales of each far-distance adaptive point are arranged in sequence to form a far-distance evaluation sequence LS.PT, and the adaptive scales of all analysis points of the evaluation object are written in sequence to form a full-distance evaluation sequence LS.AP, the percentile of all adaptive scales under the corresponding analysis point of any adaptive scale in the full-distance evaluation sequence is recorded as Hta, and the percentile corresponding to the placement of the adaptive scale in the sequence LS.PT is recorded as Htb, then the adaptive scale value IHT of the adaptive scale is the root mean square value of Hta and Htb, specifically: IHT = sqrt(Hta x Htb), where sqrt() is the square root function,

[0062] According to the far-distance evaluation sequence and the adaptive scale value, the inheritance execution score IURN of each evaluation object is calculated: Where i1 is an accumulation variable, SnL is the number of elements in the far-distance evaluation sequence, LS.PT(i1) is the adaptive scale corresponding to the i1th element in the far-distance evaluation sequence, min.PT is the minimum value of the adaptive scales corresponding to each element in the far-distance evaluation sequence, exp() is the exponential function with base e, hs<> is the harmonic mean function, lg() is the logarithmic function with base 10, and IHT i1 is the adaptive scale value corresponding to the i1th element in the far-distance evaluation sequence.

[0063] Further, in step S400, the method of performing inheritance risk assessment in combination with the inheritance execution scores of each evaluation object is: the length of the benchmark word adaptation image is recorded as the analysis amount, the evaluation object with the maximum value in the analysis amount in each evaluation object is searched as the first evaluation object, under any analysis point, if one evaluation object is greater than the redistribution reference score of the first evaluation object, it is defined that the evaluation object occurs an adaptation event, the ratio of the number of high adaptation events of the evaluation object to the analysis amount is the high adaptation efficiency; the lower quartile value in the set composed of all high adaptation efficiencies is the adaptation efficiency threshold; record the median value and the standard deviation of all inheritance execution scores as MER and STDER respectively, preset the evaluation risk overflow rate ERSR, ERSR ∈ [1.5, 3.5]; if the high adaptation efficiency of an evaluation object is less than the adaptation efficiency threshold and the inheritance execution score of the evaluation object is less than MER-ERSR×STDER, it is evaluated that the evaluation object has inheritance abnormal risk, and is not selected as the allocation server, and each evaluation object with inheritance abnormal risk is sent to the server of the client as an evaluation report.

[0064] Embodiment 2

[0065] Embodiment 2 adopts the same evaluation method as Embodiment 1, the difference is that in step S300, the method of obtaining the inheritance execution score of each evaluation object by using the benchmark word adaptation image to perform inheritance execution quality timing analysis is: set a time period as the evaluation period EVtm, the value is 2 years;

[0066] For any evaluation object, obtain the redistribution reference score of each analysis point, and form a redistribution reference score sequence; in the redistribution reference score sequence, calculate the weighted average of all elements and record it as Mvae, where the weight of each element is its percentile in all elements in the redistribution reference score sequence corresponding to it; when any element in the redistribution reference score sequence is greater than Mvae, the analysis point corresponding to the element is recorded as a high adaptation point, and the number of high adaptation points is recorded as RQm;

[0067] A floating point variable is preset for all element corresponding analysis points, recorded as inheritance seniority Laor, if the analysis point is a high adaptation point, the inheritance seniority takes the value 1, otherwise the inheritance seniority takes the value 0.5; the inheritance seniority of any analysis point is the ratio of its inheritance seniority to the sum of the inheritance seniorities of all analysis points, which is as follows.

[0068] Calculate the inheritance seniority of any analysis point Faor: Where k1 is an accumulation variable, and Tn is the number of analysis points.

[0069] In the redistribution reference score sequence, the cumulative predecessor probability FFaor of any element is the cumulative value of each predecessor probability between the element and the first element of the sequence; wherein the first element of the sequence corresponds to the analysis point closest to the current time; write all cumulative predecessor probabilities into the sequence as a cumulative sequence;

[0070] Randomly generate RTN random numbers as selected values, the value range of the selected value is RU∈(0,1); wherein, RTN is a preset integer, RTN∈[500,2000];

[0071] Take k2 as the serial number of the analysis point, for any selected value RU, set its estimation point condition as FFaor(k2)<RU≤FFaor(k2+1); search for the analysis point that satisfies the estimation point condition and mark that the analysis point occurs an estimation point event; after marking the analysis points that occur estimation point events for all selected values, take the total number of analysis points that occur estimation point events as RQm_TH, arrange RQm_TH from large to small and select the analysis points corresponding to the first RQm elements as the inheritance estimation points; wherein FFaor(k2) and FFaor(k2+1) are the cumulative predecessor probabilities of the analysis points corresponding to the k2th and k2+1th elements in the redistribution reference score sequence;

[0072] According to the inheritance estimation points, calculate the inheritance execution scores IURN of each evaluation object:

[0073]

[0074] Wherein k3 is an accumulation variable, BCMF k3 and Faor k3 are the redistribution reference score and the predecessor probability of the k3th inheritance estimation point, Avae is the average value of the redistribution reference scores corresponding to all non-inheritance estimation points, ln() is the logarithmic function with e as the base number; the non-inheritance estimation point refers to the analysis point that does not belong to the inheritance estimation point.

[0075] The embodiment of the present application provides a whole asset wealth protection and inheritance risk assessment system, as shown in Figure 2 The whole asset wealth protection and inheritance risk assessment system of the embodiment includes a processor, a memory, and a computer program stored in the memory and executable on the processor, and the processor implements the steps in the above whole asset wealth protection and inheritance risk assessment method embodiment when executing the computer program.

[0076] The system includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor executes the computer program running in the following system units:

[0077] The whole asset network storage object identification unit is used to identify the benchmark server and the redistribution server from the whole asset network, and is respectively recorded as a benchmark object and an evaluation object;

[0078] The benchmark word adaptation portrait construction unit is used to construct the benchmark word adaptation portrait through the asset database of each evaluation object;

[0079] The inheritance execution quality time sequence analysis unit is used to perform inheritance execution quality time sequence analysis by using the benchmark word adaptation portrait to obtain the inheritance execution score of each evaluation object;

[0080] The inheritance risk assessment unit is used to perform inheritance risk assessment in combination with the inheritance execution score of each evaluation object.

[0081] The whole asset wealth protection and inheritance risk assessment system can run in a desktop computer, a notebook computer, a palm computer, and a cloud server, and the like. The whole asset wealth protection and inheritance risk assessment system can run in a system that can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the example is only an example of the whole asset wealth protection and inheritance risk assessment system, and does not constitute a limitation on the whole asset wealth protection and inheritance risk assessment system, and can include more or less components, or combine certain components, or different components, for example, the whole asset wealth protection and inheritance risk assessment system can also include an input and output device, a network access device, a bus, and the like.

[0082] The processor can be a central processing unit (CPU), and can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, and the like. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, and the like. The processor is a control center of the whole asset wealth protection and inheritance risk assessment system running system, and connects each part of the whole asset wealth protection and inheritance risk assessment system running system by using various interfaces and lines.

[0083] The memory can be used to store the computer program and / or modules, and the processor realizes various functions of the full asset wealth protection and inheritance risk assessment system by running or executing the computer program and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application program required by a function (such as a sound playing function, an image playing function, etc.), and the like; and the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.). In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, for example, a hard disk, a memory, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, at least one disk storage device, a flash memory device, or other volatile solid-state memory devices.

[0084] Although the description of the present application has been quite detailed and particularly described with respect to several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, so as to effectively cover the intended scope of the present application. Furthermore, the present application is described above in embodiments that the inventors can foresee, and the purpose is to provide a useful description, and non-essential modifications to the present application that have not yet been foreseen can still represent equivalent modifications of the present application.

Claims

1. A comprehensive asset wealth protection and inheritance risk assessment method, characterized in that, The method includes the following steps: S100 identifies the baseline server and the reallocation server from the full asset network, and denots them as the baseline object and the evaluation object, respectively. S200 constructs a benchmark word adaptation profile through the asset database of each evaluation object; S300: Use benchmark words to adapt to the profile and perform time-series analysis of inheritance execution quality to obtain the inheritance execution score of each evaluation object; S400, combining the inheritance execution scores of each evaluation object to conduct inheritance risk assessment; Specifically, the method in step S300 involves calculating the inheritance execution score of each evaluation object based on the long-range evaluation sequence and the adaptive scaling criterion; or calculating the inheritance execution score of each evaluation object based on the redistribution reference score and the inheritance priority. In step S200, the method for constructing a benchmark word adaptation profile using the asset database of each evaluation object is as follows: each server contains an asset database, which is a database composed of asset documents in JSON or BSON format, and each asset document is a collection of text; every 5-10 natural days is considered a parsing point, and a parsing point and 2-6 parsing points in the reverse time direction are considered as the mapping period for that parsing point; for any parsing point, the benchmark object merges the asset documents of the corresponding mapping period to form a mapping text set, and the evaluation object's asset documents at that parsing point form a parsed text set; the redistribution reference score of the evaluation object is calculated based on the mapping text set and the parsed text set of the parsing point, and the sequence composed of the redistribution reference scores of all parsing points is denoted as the benchmark word adaptation profile; The method for calculating the redistribution reference score of the evaluation object based on the mapping text set and the parsed text set of the parsing point is as follows: For any parsing point, the text set is preprocessed, including text cleaning, word segmentation, and stop word removal; keywords are identified in the text set using the LDA (Latent Dirichlet Algorithm) model to obtain keywords and their corresponding weights; the CRF (Conditional Random Field) algorithm is used to classify the keywords into nouns and adjectives, and then classify them into related words and fitting words respectively; the weights of related words and fitting words are normalized respectively. Word embedding analysis is performed by combining each keyword and its corresponding weight in the text set to obtain word vectors. The word vectors obtained based on the analysis of the mapped text set are the baseline profiles, and the word vectors obtained based on the analysis of the parsed text set are the evaluation profiles. The cosine similarity between the evaluation profile and the baseline profile is calculated as the reference score for the redistribution of parsing points. In step S300, the method for calculating the inheritance execution score of each evaluation object based on the remote evaluation sequence and the adaptation scale value is as follows: set a time period as the evaluation period, and within the evaluation period, record the time scale at which the redistribution reference score is obtained as the parsing point; For any evaluation object, obtain the redistribution reference scores for each parse point and construct a baseline split set; use the K-means clustering algorithm to divide all elements into several clusters in the baseline split set; calculate the distance from any element to its corresponding cluster center and record it as the cluster center distance of the element; if the cluster center distance of any element is greater than the 70th percentile of all cluster center distances in its corresponding cluster, then the parse point corresponding to the element is recorded as a distant fitness point; normalize the redistribution reference scores of each parse point using the sigmoid activation function to obtain the fitness scale. The fitness scales of each remote fitness point are compiled into a sequence and denoted as the remote evaluation sequence LS.PT; the fitness scales of all parse points of the evaluated object are written into a sequence and denoted as the global evaluation sequence LS.AP; any fitness scale is selected from the global evaluation sequence, and the percentile of all fitness scales at its corresponding parse point is denoted as Hta, and the percentile of the fitness scale when placed in the sequence LS.PT is denoted as Htb. Then the fitness scale criterion value IHT of the fitness scale is the root mean square value of Hta and Htb; the inheritance execution score of each evaluated object is calculated based on the remote evaluation sequence and the fitness scale criterion value. In step S300, the method for calculating the inheritance execution score of each evaluation object based on the redistribution reference score and inheritance priority is as follows: A time period is set as the evaluation period EVtm; for any evaluation object, the redistribution reference score of each parsing point is obtained, and a redistribution reference score sequence is constructed; in the redistribution reference score sequence, the weighted average of all elements is calculated and denoted as Mvae, where the weight of each element is its percentile among all elements in its corresponding redistribution reference score sequence; when any element in the redistribution reference score sequence is greater than Mvae, the parsing point corresponding to that element is denoted as a high-fit point, and the number of high-fit points is denoted as RQm; A floating-point variable, denoted as Laor, is pre-defined for the parse points corresponding to all elements. If the parse point is a high-fit point, the inheritance priority is 1; otherwise, the inheritance priority is 0.

5. The inheritance priority Faor of any parse point is the ratio of its inheritance priority to the sum of the inheritance priorities of all parse points. In the redistribution reference score sequence, the cumulative inheritance priority FFaor of any element is the sum of the inheritance priorities of that element and the first element of the sequence. All cumulative inheritance priorities are written into the sequence, which is called the cumulative sequence. RTN random numbers are generated and denoted as selected values, with the range of selected values ​​being RU∈(0,1). Using k2 as the index of the parsing point, for any selected value RU, the estimation condition is set as FFaor(k2)<RU≤FFaor(k2+1). Parsing points that satisfy the estimation condition are searched, and each parsing point is marked as having experienced an estimation event. The total number of estimation events occurring at a parsing point is denoted as RQm_TH. RQm_TH is sorted from largest to smallest, and the parsing points corresponding to the first RQm elements are selected as the inheritance estimation points. The inheritance execution score of each evaluation object is calculated based on the redistribution reference score and inheritance priority. In step S400, the method for assessing inheritance risk by combining the inheritance execution scores of each evaluation object is as follows: the length of the baseline word adaptation profile is denoted as the resolution; the evaluation object with the maximum resolution among all evaluation objects is selected as the first evaluation object; at any resolution point, if an evaluation object has a larger redistribution reference score than the first evaluation object, then the evaluation object is defined as having experienced a high adaptation event; the ratio of the number of high adaptation events to the resolution of the evaluation object is the high adaptation efficiency; the lower quartile of the set of all high adaptation efficiencies is the adaptation efficiency threshold; the median and standard deviation of all inheritance execution scores are denoted as MER and STDER, respectively; the preset evaluation risk spillover rate ERSR is set, ERSR∈[1.5,3.5]; if the high adaptation efficiency of an evaluation object is less than the adaptation efficiency threshold and the inheritance execution score of the evaluation object is less than MER-ERSR×STDER, then the evaluation object is assessed as having inheritance abnormal risk and is not selected as a reassignment server; all evaluation objects with inheritance abnormal risk are sent to the client's server as an evaluation report.

2. The method for assessing the risk of comprehensive asset protection and inheritance according to claim 1, characterized in that, In step S100, the method for identifying the baseline server and the redistribution server from the full asset network and denoting them as the baseline object and the evaluation object, respectively, is as follows: the full asset network consists of several servers, including one baseline server and several redistribution servers, which are denoted as the baseline object and the evaluation object, respectively.

3. A comprehensive asset wealth protection and inheritance risk assessment system, characterized in that: The comprehensive asset protection and inheritance risk assessment system includes: a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the comprehensive asset protection and inheritance risk assessment method according to any one of claims 1-2. The comprehensive asset protection and inheritance risk assessment system runs on a desktop computer, a laptop computer, a handheld computer, or a cloud data center computing device.

Images