Digital economic risk management assessment method and system based on cloud computing

Abstract

The embodiment of the invention provides a digital economic risk management assessment method and system based on cloud computing, and belongs to the technical field of risk assessment. The method comprises the steps of collecting initial behavior data corresponding to a target object and initial news data related to behaviors of the target object according to a cloud computing platform corresponding to the target object; performing association analysis on the initial behavior data to obtain a target association relationship, and performing data filling on the initial behavior data according to the target association relationship to obtain target behavior data; performing exception identification on the target behavior data to obtain target exception data corresponding to the target object, and determining a target behavior feature corresponding to the target object according to the target exception data; performing news viewpoint identification on the initial news data to obtain a target behavior viewpoint related to the target object behavior; and performing distance calculation according to the target behavior characteristics and the target behavior viewpoint to obtain gap information, and performing risk assessment on the target object according to the gap information to obtain a risk assessment result.

Description

Technical Field

[0001] The present invention relates to the field of risk assessment technology, and in particular to a digital economy risk management assessment method and system based on cloud computing. Background Art

[0002] The current risk assessment system mainly relies on transaction data for analysis and judgment. Although this method can reflect market fluctuations and trading behaviors to a certain extent, its limitations are becoming increasingly prominent. Relying solely on transaction data itself, it is often difficult to capture deeper risk factors, such as the macroeconomic environment, industry dynamics, etc. These factors are equally important in their impact on risk, but existing risk assessment technologies cannot fully consider these multi-dimensional information. Therefore, existing technologies have the problem of low accuracy when conducting risk assessments, making it difficult to comprehensively and timely identify potential risks, and thus failing to effectively serve as a warning, affecting the scientificity and accuracy of decision-making. Summary of the invention

[0003] The main purpose of the embodiments of the present invention is to provide a digital economy risk management assessment method and system based on cloud computing, aiming to solve the problem of low accuracy in risk assessment in related technologies.

[0004] In a first aspect, an embodiment of the present invention provides a digital economy risk management assessment method based on cloud computing, comprising:

[0005] Collecting initial behavior data corresponding to the target object and initial news data related to the behavior of the target object according to the cloud computing platform corresponding to the target object;

[0006] Performing association analysis on the initial behavior data to obtain a target association relationship, and performing data filling on the initial behavior data according to the target association relationship to obtain target behavior data;

[0007] Performing abnormality identification on the target behavior data to obtain target abnormality data corresponding to the target object, and determining target behavior features corresponding to the target object according to the target abnormality data;

[0008] Performing news opinion recognition on the initial news data to obtain a target behavior opinion related to the target object behavior;

[0009] Distance calculation is performed based on the target behavior characteristics and the target behavior viewpoint to obtain gap information between the target behavior characteristics and the target behavior viewpoint, and risk assessment is performed on the target object based on the gap information to obtain a risk assessment result corresponding to the target object.

[0010] In a second aspect, an embodiment of the present invention provides a digital economy risk management and assessment system based on cloud computing, including:

[0011] A data collection module, used to collect initial behavior data corresponding to the target object and initial news data related to the behavior of the target object according to the cloud computing platform corresponding to the target object;

[0012] A data processing module, used for performing association analysis on the initial behavior data to obtain a target association relationship, and performing data filling on the initial behavior data according to the target association relationship to obtain target behavior data;

[0013] An anomaly identification module, used to perform anomaly identification on the target behavior data to obtain target anomaly data corresponding to the target object, and determine the target behavior characteristics corresponding to the target object according to the target anomaly data;

[0014] A viewpoint recognition module, used for performing news viewpoint recognition on the initial news data to obtain a target behavior viewpoint related to the target object behavior;

[0015] The risk assessment module is used to perform distance calculation based on the target behavior characteristics and the target behavior viewpoint to obtain the gap information between the target behavior characteristics and the target behavior viewpoint, and perform risk assessment on the target object based on the gap information to obtain the risk assessment result corresponding to the target object.

[0016] The embodiment of the present invention provides a digital economy risk management assessment method and system based on cloud computing, the method comprising: collecting the initial behavior data of the target object and the initial news data related to the initial behavior data through the cloud computing platform, so as to comprehensively capture the behavior characteristics of the target object and whether the behavior characteristics are consistent with the external information. Thus, by performing correlation analysis on the initial behavior data, the correlation relationship between different behaviors is identified, and the target behavior data is further improved by data filling, the integrity and accuracy of the data are improved, and then the target abnormal data in the behavior of the target object can be found through the abnormal identification technology, so as to determine the target behavior characteristics of the target object according to the identified target abnormal data, which can help to understand the behavior pattern of the target object more accurately. Then, by performing news viewpoint identification on the initial news data, the target behavior viewpoint related to the behavior of the target object can be obtained, so as to obtain the gap information between the target behavior characteristics and the target behavior viewpoint by performing distance calculation according to the target behavior characteristics and the target behavior viewpoint, and perform risk assessment on the target object according to the gap information, obtain the risk assessment result corresponding to the target object, and then combine the target behavior characteristics with the target behavior viewpoint to perform risk assessment, so as to more comprehensively judge the risk level of the target object. Behavioral characteristics provide internal behavioral pattern analysis, while target behavioral viewpoints reflect the reference information provided by the outside world on the behavior of the target object. Through comprehensive analysis, the generated risk assessment results can provide a strong reference for decision makers to help them better identify and manage potential risks. It also solves the problem of low accuracy of related technologies in risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 A flowchart of a digital economy risk management assessment method based on cloud computing provided by an embodiment of the present invention;

[0019] Figure 2 A schematic diagram of the module structure of a digital economy risk management and assessment system based on cloud computing provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0022] It should be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0023] The embodiment of the present invention provides a digital economy risk management assessment method and system based on cloud computing. The digital economy risk management assessment method based on cloud computing can be applied to a terminal device, which can be an electronic device such as a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The terminal device can be a server or a server cluster.

[0024] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0025] Please refer to Figure 1 , Figure 1 A flowchart of a digital economy risk management assessment method based on cloud computing provided in an embodiment of the present invention.

[0026] like Figure 1 As shown, the digital economy risk management assessment method based on cloud computing includes steps S101 to S105.

[0027] Step S101: collecting initial behavior data corresponding to the target object and initial news data related to the behavior of the target object according to the cloud computing platform corresponding to the target object.

[0028] Exemplarily, the cloud computing platform corresponding to the target object is determined, and initial behavior data corresponding to the target object is collected based on the cloud computing platform. The initial behavior data includes but is not limited to log data, transaction data, user behavior data, etc.

[0029] Exemplarily, based on the initial behavior data of the target object, determine the key topics or specific keywords when collecting news information. These topics or keywords will be closely related to the initial behavior data, and then through the efficient processing capabilities of the cloud computing platform, the initial news data matching these keywords or topics will be screened and collected from a wide range of sources (such as news websites, social media, forums, etc.). These initial news data are relevant news information collected specifically for the initial behavior data of the target object. For example, if the initial behavior data of the target object is expressed as buying the stock of Company A, then the cloud computing platform will automatically collect news reports, market trends or industry analysis related to Company A. These collected initial news data will provide an important basis for subsequent risk assessment, ensuring that the risk assessment based on the initial behavior data is more accurate and comprehensive.

[0030] Step S102: performing association analysis on the initial behavior data to obtain a target association relationship, and performing data filling on the initial behavior data according to the target association relationship to obtain target behavior data.

[0031] Exemplarily, association rule algorithms such as Apriori, FP-Growth, etc. are used to perform association analysis on the initial behavior data to obtain related behaviors with association relationships in the initial behavior data.

[0032] For example, missing or incomplete information is identified in the initial behavior data, and the possible value of the missing data is inferred based on the existing target association relationship, and then the inferred value is filled into the initial behavior data to generate complete target behavior data. In this way, the initial behavior data can be effectively analyzed for association, and the missing data can be filled using the obtained target association relationship, so as to obtain more complete and accurate target behavior data, providing a solid data foundation for subsequent risk assessment and other applications.

[0033] In some embodiments, the data filling of the initial behavior data according to the target association relationship to obtain the target behavior data includes: performing missing detection on the initial behavior data to obtain target missing data corresponding to the first parameter in the initial behavior data; obtaining target adjacent data corresponding to the target missing data under the first parameter from the initial behavior data; obtaining the second parameter corresponding to the first parameter according to the target association relationship, and obtaining the initial associated data corresponding to the target adjacent data under the second parameter from the initial behavior data; establishing a target conversion relationship corresponding to the first parameter and the second parameter according to the target adjacent data and the initial associated data; obtaining the target missing position corresponding to the target missing data, and obtaining the target associated data corresponding to the second parameter at the target missing position from the initial behavior data; performing data prediction on the target missing data according to the target conversion relationship combined with the target association data to obtain target filling data; and performing data filling on the target missing data according to the target filling data to obtain the target behavior data.

[0034] Exemplarily, a comprehensive missing detection is performed on the initial behavior data to find the first parameter where information is missing in the data, and the missing data under the first parameter is identified, which are the target missing data that need to be filled. Under the first parameter, the context data or adjacent data corresponding to the target missing data is found from the initial behavior data to obtain the target adjacent data corresponding to the target missing data under the first parameter.

[0035] Exemplarily, according to the target association relationship, a second parameter associated with the first parameter is identified. From the initial behavior data, corresponding data of the target adjacent data under the second parameter are extracted, and these data are referred to as initial association data.

[0036] Exemplarily, statistical analysis or machine learning methods are used to analyze the conversion relationship between the target adjacent data and the initial associated data, and then the conversion relationship is determined as the target conversion relationship between the first parameter and the second parameter, which will become the basis for predicting the target missing data.

[0037] Exemplarily, in the initial behavior data, the specific location of the target missing data is identified, so that at the target missing location, the target associated data corresponding to the second parameter is extracted, and then the possible value of the target missing data is predicted using the previously established target conversion relationship and target associated data to obtain the target filling data.

[0038] Exemplarily, the predicted target filling data is inserted into the corresponding missing position of the initial behavior data to complete the data filling process, and then after the data filling, the complete target behavior data is finally obtained.

[0039] For example, the missing parts in the initial behavior data are detected, and the target association relationship is used to predict and fill in the missing data, and finally a complete and accurate target behavior data is obtained, thereby providing a solid foundation for subsequent data analysis and risk assessment support.

[0040] Step S103: performing abnormality identification on the target behavior data to obtain target abnormality data corresponding to the target object, and determining target behavior features corresponding to the target object according to the target abnormality data.

[0041] Exemplarily, according to anomaly detection methods, such as statistical methods (such as Z-score, Grubbs' test), machine learning methods (such as isolation forest, One-Class SVM) or deep learning methods (such as Autoencoder), anomalies are identified on the target behavior data to identify anomalies that are significantly different from most data. These anomalies are the target anomaly data.

[0042] Exemplarily, the distribution characteristics of the target abnormal data are analyzed, and then key features that can represent the behavioral characteristics of the target object are extracted from the target abnormal data. The key features include but are not limited to frequency, duration, intensity, change trend, etc., so that the key features are fused to obtain the target behavioral characteristics corresponding to the target object.

[0043] In some embodiments, the target behavior data is identified as abnormal to obtain the target abnormal data corresponding to the target object, including: obtaining any sub-behavior data from the target behavior data, and segmenting the target behavior data according to the sub-behavior data to obtain first behavior data and second behavior data; calculating the data difference between the first behavior data and the second behavior data to obtain a corresponding behavior difference value; obtaining the maximum difference value from all the behavior difference values, and using statistical significance to calculate the target probability corresponding to each behavior difference value when it is less than or equal to the maximum difference value; determining a preset threshold, and segmenting the target behavior data according to the preset threshold and the target probability to obtain target segmented data; and identifying the abnormality of each sub-segmented data in the target segmented data to obtain the target abnormal data corresponding to the target object.

[0044] Exemplarily, a sub-behavior data is arbitrarily selected from the target behavior data as a segmentation point. This sub-behavior data can be a specific time point, event or behavior pattern. Then, based on the selected sub-behavior data, the target behavior data is segmented into two parts, namely, the first behavior data and the second behavior data.

[0045] Exemplarily, the first behavior data and the second behavior data are compared using methods such as mean comparison, standard deviation analysis, and feature distance calculation, and their differences in values, features, or behavior patterns are calculated to generate behavior difference values. Then, from all the calculated behavior difference values, the difference value with the largest value is selected as the maximum difference value, which represents the maximum inconsistency between the two parts after the data is segmented.

[0046] Exemplarily, a statistical method is used to calculate the probability that each behavior difference value is less than or equal to the maximum difference value, that is, the target probability. This reflects the significance level of each behavior difference value in the overall data. Therefore, according to business needs or statistical experience, a preset threshold is determined to determine whether the behavior difference value reaches the significance level, and then the target probability is compared with the preset threshold: if the target probability is less than or equal to the preset threshold, the behavior difference value is considered to be significant, and the split point is retained. If the target probability is greater than the preset threshold, the split point is excluded. After screening, a series of significant split points are obtained, which divide the target behavior data into several sub-segmented data, which are then determined as target segmented data.

[0047] Exemplarily, an anomaly recognition method (such as a statistical method or a machine learning method) is applied to each sub-segmented data in the target segmented data to detect abnormal points in each sub-segmented data, and finally obtain target abnormal data corresponding to the target object.

[0048] In some embodiments, the abnormality identification of each sub-segmented data in the target segmented data to obtain the target abnormality data corresponding to the target object includes: performing abnormality scoring on each sub-data in the sub-segmented data to obtain the abnormality score corresponding to the sub-data; clustering all the abnormality scores according to a preset number to obtain first clustering data and second clustering data corresponding to the abnormality score; obtaining a first number corresponding to the first clustering data and a second number corresponding to the second clustering data; calculating the difference between the first number and the second number to obtain a target difference, and obtaining sub-abnormal data corresponding to the sub-segmented data from the first clustering data and the second clustering data according to the target difference; and fusing all the sub-abnormal data to obtain the target abnormality data corresponding to the target object.

[0049] Exemplarily, an anomaly detection algorithm such as Isolation Forest, Local Outlier Factor (LOF) or a statistical method (such as Z-Score or IQR) is used to perform an anomaly scoring on each sub-data in the sub-segmented data to obtain an anomaly score corresponding to the sub-data.

[0050] Exemplarily, K-Means or DBSCAN is used to cluster all abnormal scores according to a preset number to obtain first cluster data and second cluster data corresponding to the abnormal scores. For example, if the preset number is 2, all abnormal scores are clustered according to K-Means to obtain two clustering results, which are respectively recorded as first cluster data and second cluster data.

[0051] Exemplarily, the number of data in the first cluster data is calculated, recorded as the first number, the number of data in the second cluster data is calculated, recorded as the second number, and then the difference between the first number and the second number is calculated to obtain the target difference. When the target difference is less than or equal to the preset number, it means that the data gap between the first cluster data and the second cluster data is small, and there is no abnormal data in the sub-segmented data. When the target difference is greater than the preset number, it means that the cluster with fewer numbers in the first cluster data and the second cluster data is used as an abnormal data cluster, and then data is extracted from the cluster with fewer numbers, and these data are the sub-abnormal data corresponding to the sub-segmented data. All sub-abnormal data are merged to obtain the target abnormal data of the target object.

[0052] In some embodiments, the performing anomaly scoring on each sub-data in the sub-segmented data to obtain an anomaly score corresponding to the sub-data includes: analyzing the sub-segmented data based on an isolation forest algorithm to obtain a target isolated tree corresponding to the sub-segmented data; obtaining a current path length corresponding to the sub-data according to the target isolated tree, and performing mean calculation based on the current path length to obtain an average path length corresponding to the sub-data; determining a reference factor, and performing anomaly scoring based on the average path length and the reference factor to determine the anomaly score corresponding to each sub-data in the sub-segmented data.

[0053] Exemplarily, an anomaly detection model is constructed using an isolation forest algorithm, and a corresponding isolated tree structure is obtained, thereby using the sub-segmentation data to train the isolation forest model and generate multiple target isolated trees.

[0054] Exemplarily, the current path length of each child data in the target isolated tree is calculated, and the average of all current path lengths is calculated to characterize its abnormality. That is, for each child data, each target isolated tree is traversed, and the path length from the root node to the leaf node is recorded. For each child data, the average of its path lengths in all isolated trees, i.e., the average path length, is calculated.

[0055] Exemplarily, the reference factor is used to normalize the path length corresponding to the sub-data. Different average path lengths are used to set different reference factors. For example, if the average path length is less than 2, the reference factor is set to 0; if the average path length is equal to 2, the reference factor is set to 1; if the average path length is greater than 2, the reference factor is obtained according to the following formula:

[0056]

[0057] Where w represents the average path length The corresponding reference factor is greater than 2. represents the average path length, c represents a fixed constant, and ln represents the natural logarithm.

[0058] Exemplarily, after determining the reference factor based on the average path length, the average path length and the reference factor are ratioed and the negative number is taken to obtain the corresponding numerical value, and the data corresponding to the exponential of the numerical value with base 2 is taken to determine the abnormal score corresponding to the sub-data.

[0059] In some embodiments, determining the target behavior characteristics corresponding to the target object based on the target abnormal data includes: obtaining target neighboring data corresponding to the target abnormal data from the target behavior data; determining the target change trend corresponding to the object under the target abnormal data based on the target neighboring data and the target abnormal data; extracting time domain features and frequency domain features of the target abnormal data to obtain target-related characteristics corresponding to the target abnormal data; and performing feature fusion on the target-related characteristics and the target change trend to obtain the target behavior characteristics corresponding to the target object.

[0060] Exemplarily, for each identified target abnormal data, its neighboring data points are obtained. These neighboring data points may be the previous and next data points in time, or the close data points in space, so as to obtain the target neighboring data.

[0061] Exemplarily, the target neighboring data and the target abnormal data are compared by calculating the rate of change, trend direction, etc., and the behavior change trend of the target object under the abnormal data is analyzed. For example, the overall change pattern of the target object's behavior before and after the target abnormal data is determined, such as increase, decrease or fluctuation, so as to obtain the target change trend.

[0062] Exemplarily, the time domain and frequency domain features of the target abnormal data are extracted. The time domain features may include mean, variance, peak value, etc., while the frequency domain features may extract frequency components and periodic information through methods such as Fourier transform, and then obtain these features to more comprehensively understand the characteristics of the target abnormal data. The extracted time domain and frequency domain features are then fused with the previously determined target change trend. This can be achieved through feature weighting, combination, etc. to form a comprehensive behavioral feature description to ensure that the fused features can accurately reflect the target behavioral characteristics of the target object under the target abnormal data.

[0063] Exemplarily, based on the fused features and change trends, the target behavior features of the target object under the target abnormal data are determined, and the target behavior features should be able to describe the behavior pattern and potential change rules of the target object under abnormal conditions.

[0064] Step S104: performing news opinion recognition on the initial news data to obtain a target behavior opinion related to the target object behavior.

[0065] Exemplarily, the initial news data is news information closely related to the initial behavior data, and then the opinions in the initial news data related to the initial behavior data, such as transactions with the target object or investments with the target object, are identified to obtain target behavior opinions related to the target object's behavior. That is, the target behavior opinion is information about an object associated with the target object's related behavior.

[0066] For example, algorithms such as topic modeling, sentiment analysis, and opinion mining are used to extract the overall trends and mainstream opinions of objects related to the target object's behaviors from the initial news data, thereby obtaining target behavior opinions related to the target object's behaviors.

[0067] For example, if target object A has large transactions with associated object B, the initial news data will identify news opinions on associated object B, so as to subsequently judge whether there is a risk of target object A having large transactions with associated object B through target behavior opinions.

[0068] In some embodiments, the performing news opinion recognition on the initial news data to obtain the target behavior opinion related to the target object behavior includes: performing event element recognition on the initial news data to obtain the corresponding target event information, and determining the first association information between the initial news data according to the element co-occurrence information between the target event information; screening out the related news data associated with the initial news data according to the first association information, and obtaining the second association information between the initial news data and the related news data from the first association information; performing emotion recognition on the initial news data to obtain the corresponding first emotion information and performing emotion recognition on the related news data to obtain the corresponding second emotion information; and determining the third association information between the initial news data and the related news data according to the distance between the first emotion information and the second emotion information; fusing the second association information and the third association information to determine the target representation information corresponding to the initial news data under the related news data; performing key information recognition on the initial news data according to the target representation information to obtain the target key sentence corresponding to the initial news data; performing behavior classification according to the target key sentence to obtain the target behavior opinion related to the target object behavior; wherein the target representation information is obtained according to the following formula:

[0069]

[0070] in, represents the target representation information corresponding to the i-th initial news data, represents the damping coefficient, num represents the number of news corresponding to the relevant news data, represents weight information corresponding to the second association information, represents the weight information corresponding to the third association information, Indicates second association information between the i-th initial news data and the k-th related news data; represents the third association information between the i-th initial news data and the k-th related news data, Indicates second association information between the kth related news data and the jth related news data; Indicates third association information between the k-th related news data and the j-th related news data; The target representation information corresponding to the k-th related news data under the news data associated with the k-th related news data is represented.

[0071] For example, event elements are identified on the initial news data to extract key information describing the event, which may include time, location, person, event type, event result, etc., and then the extracted event elements are organized into structured target event information.

[0072] Exemplarily, based on the co-occurrence relationship of elements in the target event information (i.e., elements that co-appear in multiple event information), the first association information between the initial news data is determined, and the first association information can reflect the similarity or association of events in different news reports.

[0073] Exemplarily, the related news data that is related to the initial news data is screened out based on the first related information, and then the second related information between the initial news data and the related news data is further extracted from the first related information.

[0074] Exemplarily, emotion recognition is performed on initial news data to extract corresponding first emotion information (such as positive emotion, negative emotion, neutral emotion, etc.), and emotion recognition is performed on related news data to extract corresponding second emotion information.

[0075] Exemplarily, based on the difference between the first emotional information and the second emotional information (such as the similarity of emotional polarity, the change of emotional intensity, etc.), the emotional distance is calculated, and the third association information between the initial news data and the related news data is determined. The third association information can reflect the similarities or differences in emotional expression of different news reports.

[0076] Exemplarily, the second association information (association based on event elements) and the third association information (association based on emotions) are fused according to the following formula to determine the target representation information of the initial news data under the relevant news data. The target representation information may include the core description of the event, the integration of emotional tendencies, etc.:

[0077]

[0078] in, represents the target representation information corresponding to the i-th initial news data, represents the damping coefficient, num represents the number of news corresponding to the relevant news data, represents the weight information corresponding to the second association information, represents the weight information corresponding to the third association information, Indicates the second association information between the i-th initial news data and the k-th related news data; represents the third association information between the i-th initial news data and the k-th related news data, Indicates the second association information between the k-th related news data and the j-th related news data; Indicates third association information between the k-th related news data and the j-th related news data; Indicates target representation information corresponding to the k-th related news data under the news data associated with the k-th related news data.

[0079] For example, by fusing the second associated information based on event elements and the third associated information based on emotions, the characteristics of news data can be fully described from multiple dimensions. This not only takes into account the structural information of the event, but also the expression of emotions, which helps to understand the news content more comprehensively. By fusing multiple associated information, the target representation information can more accurately reflect the core content and emotional tendency of the news data. By fusing the second associated information and the third associated information, richer data support can be provided to help decision makers understand the background, impact and emotional tendency of news events more comprehensively.

[0080] Exemplarily, the event elements and sentiment tendencies extracted from the target representation information are used as screening criteria. If the target representation information shows that the core of a news report's event is "conference decision" and the sentiment tendency is "negative", then sentences related to "conference decision" and with "negative" sentiment are screened out. Thus, each sentence in the initial news data is scored, and the scoring criteria include: whether the sentence contains the key elements in the target representation information. Whether the sentence contains the sentiment tendency in the target representation information. Thus, each sentence in the initial news data is analyzed to determine whether it meets the characteristics of the key sentence, and then according to the screening strategy, the sentences that meet the standards are screened out, and the screened out key sentences are sorted, and sentences with high correlation with the target representation information and high information density are given priority to obtain the target key sentence.

[0081] For example, for the extracted target key sentences, a special classification model is used to perform in-depth behavior classification, so as to accurately identify the target behavior viewpoint related to the target object's behavior. The target behavior viewpoint is that the target object involves the associated object to develop positively, such as achieving success, gaining support or achieving growth; or the target object involves the associated object to develop negatively, such as encountering setbacks, being hindered or facing decline; or the target object involves the associated object to develop steadily, that is, the behavior and status of the target object remain the same without significant changes.

[0082] Step S105: performing distance calculation based on the target behavior characteristics and the target behavior viewpoint to obtain gap information between the target behavior characteristics and the target behavior viewpoint, and performing risk assessment on the target object based on the gap information to obtain a risk assessment result corresponding to the target object.

[0083] Exemplarily, the target behavior characteristics are classified into types to obtain the target behavior type corresponding to the target object. For example, the target behavior type is to increase investment, reduce investment or stabilize investment, and then the target behavior type and the target behavior viewpoint, such as positive development (such as support, growth), negative development (such as encountering obstacles, decline) or stable development (such as maintaining the status quo), are compared. When the target behavior type is to increase investment and the target behavior viewpoint is positive development (such as support, growth), the text similarity calculation formula is used to calculate the distance between the target behavior type and the target behavior viewpoint to obtain the gap information between the target behavior characteristics and the target behavior viewpoint. When the gap information is small, it means that the risk assessment result corresponding to the target object is low risk; when the target behavior type is to increase investment and the target behavior viewpoint is negative development (such as encountering obstacles, decline), the text similarity calculation formula is used to calculate the distance between the target behavior type and the target behavior viewpoint to obtain the gap information between the target behavior characteristics and the target behavior viewpoint. When the gap information is large, it means that the risk assessment result corresponding to the target object is high risk.

[0084] In some embodiments, the distance calculation is performed based on the target behavior characteristics and the target behavior viewpoint to obtain the gap information between the target behavior characteristics and the target behavior viewpoint, and the risk assessment is performed on the target object based on the gap information to obtain the risk assessment result corresponding to the target object, including: using the first feature characterization layer of the risk assessment model to feature the target behavior characteristics to obtain first feature information; using the second feature characterization layer of the risk assessment model to feature the target behavior viewpoint to obtain second feature information; using the distance calculation layer of the risk assessment model to perform distance calculation based on the first feature information and the second feature information to obtain the gap information between the target behavior characteristics and the target behavior viewpoint; using the risk classification layer of the risk assessment model to perform data classification based on the gap information to obtain the target risk type between the target behavior characteristics and the target behavior viewpoint; and determining the risk assessment result corresponding to the target object based on the target risk type.

[0085] Exemplarily, the first feature representation layer of the risk assessment model is used to represent the target behavior characteristics. For example, key numerical features are extracted from the target behavior characteristics, such as the frequency, intensity, influence, etc. of the behavior, and the extracted features are then normalized to ensure that the numerical ranges of different features are consistent to facilitate subsequent calculations, thereby representing the normalized features in vector or matrix form as the first feature information.

[0086] Exemplarily, the second feature representation layer is used to represent the target behavior viewpoints, for example, specific positive and negative tendencies, emotional intensity, and viewpoint proportions are extracted from the target behavior viewpoints. The extracted features are normalized to ensure that they have the same numerical range as the first feature information. The normalized viewpoint features are represented in vector or matrix form as the second feature information.

[0087] Exemplarily, the distance calculation layer is used to calculate the gap between the first feature information and the second feature information. For example, the distance between the first feature information and the second feature information is calculated according to a distance measurement method (such as Euclidean distance, cosine similarity, etc.), and the calculation result is converted into a specific gap value to represent the difference between the target behavior characteristics and the target behavior viewpoints to obtain gap information.

[0088] Exemplarily, the risk classification layer is used to classify data according to the gap information. For example, different risk types are defined according to the range or threshold of the gap information, such as: Low risk: the gap is small, and the behavior characteristics are consistent with the behavior viewpoint. Medium risk: the gap is moderate, and there is a certain deviation between the behavior characteristics and the behavior viewpoint. High risk: the gap is large, and the behavior characteristics are significantly inconsistent with the behavior viewpoint. Thus, according to the value of the gap information, it is classified into the target risk type (such as low risk, medium risk, high risk).

[0089] Exemplarily, a risk assessment result of a target object is determined according to a target risk type, the target risk type is associated with the target object, the risk assessment result of the target object is generated, and then the target risk type is determined as the risk assessment result of the target object.

[0090] In some embodiments, after obtaining the risk assessment result, the method further includes: determining preset information, comparing the preset information with the risk assessment result, and when the risk assessment result meets the preset information, generating a risk description statement corresponding to the risk assessment result based on the target behavior characteristics and the target behavior viewpoint; determining a risk reminder result based on the risk description statement and the risk assessment result, and sending the risk reminder result to the target communication device.

[0091] For example, when the preset information is that the risk level is medium risk or high risk, then when the risk assessment result is any of the preset information, it is determined that the risk assessment result meets the preset conditions, thereby extracting key information related to the risk assessment result from the target behavior characteristics and target behavior viewpoints, such as the specific manifestations of the target behavior characteristics (such as frequency, intensity). The specific content of the target behavior viewpoint (such as positive and negative tendencies, emotional intensity). Based on the extracted key information, a concise risk description statement is generated, such as: "The frequency of the target object's behavior has increased significantly, but the proportion of negative evaluations of related objects involved in the target object is too high, and there is a high risk."

[0092] For example, the risk reminder method is determined according to the risk assessment result, and the risk reminder result corresponding to the target object is determined according to the risk reminder method and the risk description statement. Then, the risk description statement is sent to the target communication device corresponding to the target object according to the risk reminder method in the risk reminder result, so that potential risks can be identified in a timely manner, and risk information can be delivered to relevant personnel through effective communication methods to provide support for risk management and decision-making.

[0093] See also Figure 2 , Figure 2 A cloud computing-based digital economy risk management and assessment system 200 is provided for the embodiment of the present application. The cloud computing-based digital economy risk management and assessment system 200 includes a data acquisition module 201, a data processing module 202, an anomaly identification module 203, a viewpoint identification module 204, and a risk assessment module 205, wherein the data acquisition module 201 is used to collect the initial behavior data corresponding to the target object and the initial news data related to the behavior of the target object according to the cloud computing platform corresponding to the target object; the data processing module 202 is used to perform correlation analysis on the initial behavior data to obtain a target correlation relationship, and fill the initial behavior data with data according to the target correlation relationship Obtain target behavior data; an anomaly identification module 203, used to perform anomaly identification on the target behavior data to obtain target anomaly data corresponding to the target object, and determine the target behavior characteristics corresponding to the target object according to the target anomaly data; an opinion identification module 204, used to perform news opinion identification on the initial news data to obtain a target behavior opinion related to the target object behavior; a risk assessment module 205, used to perform distance calculation based on the target behavior characteristics and the target behavior opinion to obtain gap information between the target behavior characteristics and the target behavior opinion, and perform risk assessment on the target object based on the gap information to obtain a risk assessment result corresponding to the target object.

[0094] In some implementations, during the process of filling the initial behavior data with data according to the target association relationship to obtain the target behavior data, the data processing module 202 executes:

[0095] Performing missing detection on the initial behavior data to obtain target missing data corresponding to the first parameter in the initial behavior data;

[0096] Obtaining target adjacent data corresponding to the target missing data under the first parameter from the initial behavior data;

[0097] Obtaining a second parameter corresponding to the first parameter according to the target association relationship, and obtaining initial association data corresponding to the target adjacent data under the second parameter from the initial behavior data;

[0098] Establishing a target conversion relationship corresponding to the first parameter and the second parameter according to the target adjacent data and the initial associated data;

[0099] Obtaining a target missing position corresponding to the target missing data, and obtaining target associated data corresponding to the second parameter at the target missing position from the initial behavior data;

[0100] According to the target conversion relationship and the target associated data, data prediction is performed on the target missing data to obtain target filling data;

[0101] The target missing data is filled in according to the target filling data to obtain the target behavior data.

[0102] In some implementations, the abnormality identification module 203 performs, during the process of identifying abnormalities in the target behavior data to obtain target abnormality data corresponding to the target object:

[0103] Obtain any sub-behavior data from the target behavior data, and segment the target behavior data according to the sub-behavior data to obtain first behavior data and second behavior data;

[0104] Calculating a data difference between the first behavior data and the second behavior data to obtain a corresponding behavior difference value;

[0105] Obtaining a maximum difference value from all the behavior difference values, and using statistical significance to calculate a target probability corresponding to each behavior difference value being less than or equal to the maximum difference value;

[0106] Determine a preset threshold, and segment the target behavior data according to the preset threshold and the target probability to obtain target segmentation data;

[0107] Anomaly identification is performed on each sub-segmented data in the target segmented data to obtain the target abnormal data corresponding to the target object.

[0108] In some implementations, the anomaly identification module 203 performs, during the process of performing anomaly identification on each sub-segmented data in the target segmented data to obtain the target anomaly data corresponding to the target object:

[0109] Performing anomaly scoring on each sub-data in the sub-segmented data to obtain an anomaly score corresponding to the sub-data;

[0110] Performing data clustering on all the abnormal scores according to a preset number to obtain first cluster data and second cluster data corresponding to the abnormal scores;

[0111] Obtaining a first quantity corresponding to the first cluster data and a second quantity corresponding to the second cluster data;

[0112] Calculating a difference between the first quantity and the second quantity to obtain a target difference, and obtaining sub-abnormal data corresponding to the sub-segmented data from the first clustering data and the second clustering data according to the target difference;

[0113] All the sub-abnormal data are fused to obtain the target abnormal data corresponding to the target object.

[0114] In some implementations, the anomaly identification module 203, in the process of performing anomaly scoring on each sub-data in the sub-segmented data to obtain an anomaly score corresponding to the sub-data, performs:

[0115] Analyze the sub-segmentation data based on the isolation forest algorithm to obtain a target isolated tree corresponding to the sub-segmentation data;

[0116] Obtaining a current path length corresponding to the sub-data according to the target isolated tree, and performing mean calculation according to the current path length to obtain an average path length corresponding to the sub-data;

[0117] A reference factor is determined, and an abnormality score is performed according to the average path length and the reference factor to determine the abnormality score corresponding to each sub-data in the sub-segmented data.

[0118] In some implementations, the abnormality identification module 203, in the process of determining the target behavior feature corresponding to the target object according to the target abnormality data, performs:

[0119] Obtaining target neighboring data corresponding to the target abnormal data from the target behavior data;

[0120] Determine, according to the target neighboring data and the target abnormal data, a target change trend corresponding to the object under the target abnormal data;

[0121] Extracting time domain features and frequency domain features of the target abnormal data to obtain target-related features corresponding to the target abnormal data;

[0122] The target-related features and the target change trends are subjected to feature fusion to obtain the target behavior features corresponding to the target object.

[0123] In some implementations, the opinion recognition module 204 performs, during the process of performing news opinion recognition on the initial news data to obtain a target behavior opinion related to the target object behavior:

[0124] Performing event element recognition on the initial news data to obtain corresponding target event information, and determining first association information between the initial news data according to element co-occurrence information between the target event information;

[0125] Filter out related news data associated with the initial news data according to the first associated information, and obtain second associated information between the initial news data and the related news data from the first associated information;

[0126] Performing emotion recognition on the initial news data to obtain corresponding first emotion information and performing emotion recognition on the related news data to obtain corresponding second emotion information;

[0127] and determining third association information between the initial news data and the related news data according to the distance between the first emotion information and the second emotion information;

[0128] The second association information and the third association information are integrated to determine the target representation information corresponding to the initial news data under the related news data;

[0129] Performing key information identification on the initial news data according to the target representation information to obtain target key sentences corresponding to the initial news data;

[0130] Performing behavior classification according to the target key sentence to obtain the target behavior viewpoint related to the target object behavior;

[0131] The target characterization information is obtained according to the following formula:

[0132]

[0133] in, represents the target representation information corresponding to the i-th initial news data, represents the damping coefficient, num represents the number of news corresponding to the relevant news data, represents weight information corresponding to the second association information, represents the weight information corresponding to the third association information, Indicates second association information between the i-th initial news data and the k-th related news data; represents the third association information between the i-th initial news data and the k-th related news data, Indicates second association information between the kth related news data and the jth related news data; Indicates third association information between the k-th related news data and the j-th related news data; The target representation information corresponding to the k-th related news data under the news data associated with the k-th related news data is represented.

[0134] In some implementations, the risk assessment module 205 performs the following steps during the process of performing distance calculation based on the target behavior feature and the target behavior viewpoint to obtain the gap information between the target behavior feature and the target behavior viewpoint, and performing risk assessment on the target object based on the gap information to obtain the risk assessment result corresponding to the target object:

[0135] Using a first feature representation layer of a risk assessment model to represent the target behavior feature to obtain first feature information;

[0136] Using the second feature representation layer of the risk assessment model to perform feature representation on the target behavior viewpoint to obtain second feature information;

[0137] Using the distance calculation layer of the risk assessment model to perform distance calculation based on the first feature information and the second feature information to obtain the gap information between the target behavior feature and the target behavior viewpoint;

[0138] Using the risk classification layer of the risk assessment model to perform data classification according to the gap information to obtain the target risk type between the target behavior characteristics and the target behavior viewpoints;

[0139] The risk assessment result corresponding to the target object is determined according to the target risk type.

[0140] In some implementations, after obtaining the risk assessment result, the risk assessment module 205 further performs:

[0141] Determine preset information, compare the preset information with the risk assessment result, and when the risk assessment result meets the preset information, generate a risk description statement corresponding to the risk assessment result according to the target behavior characteristics and the target behavior viewpoint;

[0142] A risk reminder result is determined according to the risk description statement and the risk assessment result, and the risk reminder result is sent to a target communication device.

[0143] In some embodiments, the cloud computing-based digital economy risk management assessment system 200 can be applied to a terminal device.

[0144] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the cloud computing-based digital economic risk management assessment system 200 described above can refer to the corresponding process in the aforementioned cloud computing-based digital economic risk management assessment method embodiment, and will not be repeated here.

[0145] An embodiment of the present invention also provides a storage medium for computer-readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of any one of the cloud computing-based digital economy risk management assessment methods provided in the description of the embodiments of the present invention.

[0146] The storage medium may be an internal storage unit of the terminal device described in the foregoing embodiment, such as a hard disk or memory of the terminal device. The storage medium may also be an external storage device of the terminal device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc., equipped on the terminal device.

[0147] It will be appreciated by those skilled in the art that all or some of the steps, systems, and functional modules / units in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. In a hardware embodiment, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed by several physical components in cooperation. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or implemented as hardware, or implemented as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium that can be used to store the desired information and can be accessed by a computer. In addition, it is well known to those skilled in the art that communication media typically contain computer-readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0148] It should be understood that the term "and / or" used in the present specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0149] The serial numbers of the embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present invention, and these modifications or replacements should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A digital economy risk management assessment method based on cloud computing, characterized in that: The method comprises: Collecting initial behavior data corresponding to the target object and initial news data related to the behavior of the target object according to the cloud computing platform corresponding to the target object; Performing association analysis on the initial behavior data to obtain a target association relationship, and performing data filling on the initial behavior data according to the target association relationship to obtain target behavior data; Performing abnormality identification on the target behavior data to obtain target abnormality data corresponding to the target object, and determining target behavior features corresponding to the target object according to the target abnormality data; Performing news opinion recognition on the initial news data to obtain a target behavior opinion related to the target object behavior; Distance calculation is performed based on the target behavior characteristics and the target behavior viewpoint to obtain gap information between the target behavior characteristics and the target behavior viewpoint, and risk assessment is performed on the target object based on the gap information to obtain a risk assessment result corresponding to the target object.

2. The method according to claim 1, characterized in that The step of filling the initial behavior data according to the target association relationship to obtain target behavior data includes: Performing missing detection on the initial behavior data to obtain target missing data corresponding to the first parameter in the initial behavior data; Obtaining target adjacent data corresponding to the target missing data under the first parameter from the initial behavior data; Obtaining a second parameter corresponding to the first parameter according to the target association relationship, and obtaining initial association data corresponding to the target adjacent data under the second parameter from the initial behavior data; Establishing a target conversion relationship corresponding to the first parameter and the second parameter according to the target adjacent data and the initial associated data; Obtaining a target missing position corresponding to the target missing data, and obtaining target associated data corresponding to the second parameter at the target missing position from the initial behavior data; According to the target conversion relationship and the target associated data, data prediction is performed on the target missing data to obtain target filling data; The target missing data is filled in according to the target filling data to obtain the target behavior data.

3. The method according to claim 1, characterized in that The performing abnormality identification on the target behavior data to obtain target abnormality data corresponding to the target object includes: Obtain any sub-behavior data from the target behavior data, and segment the target behavior data according to the sub-behavior data to obtain first behavior data and second behavior data; Calculating a data difference between the first behavior data and the second behavior data to obtain a corresponding behavior difference value; Obtaining a maximum difference value from all the behavior difference values, and using statistical significance to calculate a target probability corresponding to each behavior difference value being less than or equal to the maximum difference value; Determine a preset threshold, and segment the target behavior data according to the preset threshold and the target probability to obtain target segmentation data; Anomaly identification is performed on each sub-segmented data in the target segmented data to obtain the target abnormal data corresponding to the target object.

4. The method according to claim 3, characterized in that The performing abnormality identification on each sub-segmented data in the target segmented data to obtain the target abnormal data corresponding to the target object includes: Performing anomaly scoring on each sub-data in the sub-segmented data to obtain an anomaly score corresponding to the sub-data; Performing data clustering on all the abnormal scores according to a preset number to obtain first cluster data and second cluster data corresponding to the abnormal scores; Obtaining a first quantity corresponding to the first cluster data and a second quantity corresponding to the second cluster data; Calculating a difference between the first quantity and the second quantity to obtain a target difference, and obtaining sub-abnormal data corresponding to the sub-segmented data from the first clustering data and the second clustering data according to the target difference; All the sub-abnormal data are fused to obtain the target abnormal data corresponding to the target object.

5. The method according to claim 4, characterized in that The step of performing anomaly scoring on each sub-data in the sub-segmented data to obtain an anomaly score corresponding to the sub-data includes: Analyze the sub-segmentation data based on the isolation forest algorithm to obtain a target isolated tree corresponding to the sub-segmentation data; Obtaining a current path length corresponding to the sub-data according to the target isolated tree, and performing mean calculation according to the current path length to obtain an average path length corresponding to the sub-data; A reference factor is determined, and an abnormality score is performed according to the average path length and the reference factor to determine the abnormality score corresponding to each sub-data in the sub-segmented data.

6. The method according to claim 1, characterized in that The determining, according to the target abnormal data, a target behavior feature corresponding to the target object includes: Obtaining target neighboring data corresponding to the target abnormal data from the target behavior data; Determine, according to the target neighboring data and the target abnormal data, a target change trend corresponding to the object under the target abnormal data; Extracting time domain features and frequency domain features of the target abnormal data to obtain target-related features corresponding to the target abnormal data; The target-related features and the target change trends are subjected to feature fusion to obtain the target behavior features corresponding to the target object.

7. The method according to claim 1, characterized in that The step of performing news viewpoint recognition on the initial news data to obtain a target behavior viewpoint related to the target object behavior includes: Performing event element recognition on the initial news data to obtain corresponding target event information, and determining first association information between the initial news data according to element co-occurrence information between the target event information; Filter out related news data associated with the initial news data according to the first associated information, and obtain second associated information between the initial news data and the related news data from the first associated information; Performing emotion recognition on the initial news data to obtain corresponding first emotion information and performing emotion recognition on the related news data to obtain corresponding second emotion information; and determining third association information between the initial news data and the related news data according to the distance between the first emotion information and the second emotion information; The second association information and the third association information are integrated to determine the target representation information corresponding to the initial news data under the related news data; Performing key information identification on the initial news data according to the target representation information to obtain target key sentences corresponding to the initial news data; Performing behavior classification according to the target key sentence to obtain the target behavior viewpoint related to the target object behavior; The target characterization information is obtained according to the following formula: ; in, represents the target representation information corresponding to the i-th initial news data, represents the damping coefficient, num represents the number of news corresponding to the relevant news data, represents weight information corresponding to the second association information, represents the weight information corresponding to the third association information, Indicates second association information between the i-th initial news data and the k-th related news data; represents the third association information between the i-th initial news data and the k-th related news data, Indicates second association information between the kth related news data and the jth related news data; Indicates third association information between the k-th related news data and the j-th related news data; The target representation information corresponding to the k-th related news data under the news data associated with the k-th related news data is represented.

8. The method according to claim 1, characterized in that The step of performing distance calculation based on the target behavior feature and the target behavior viewpoint to obtain gap information between the target behavior feature and the target behavior viewpoint, and performing risk assessment on the target object based on the gap information to obtain a risk assessment result corresponding to the target object includes: Using a first feature representation layer of a risk assessment model to represent the target behavior feature to obtain first feature information; Using the second feature representation layer of the risk assessment model to perform feature representation on the target behavior viewpoint to obtain second feature information; Using the distance calculation layer of the risk assessment model to perform distance calculation based on the first feature information and the second feature information to obtain the gap information between the target behavior feature and the target behavior viewpoint; Using the risk classification layer of the risk assessment model to perform data classification according to the gap information to obtain the target risk type between the target behavior characteristics and the target behavior viewpoints; The risk assessment result corresponding to the target object is determined according to the target risk type.

9. The method according to claim 8, characterized in that After obtaining the risk assessment result, the method further includes: Determine preset information, compare the preset information with the risk assessment result, and when the risk assessment result meets the preset information, generate a risk description statement corresponding to the risk assessment result according to the target behavior characteristics and the target behavior viewpoint; A risk reminder result is determined according to the risk description statement and the risk assessment result, and the risk reminder result is sent to a target communication device.

10. A digital economy risk management and assessment system based on cloud computing, characterized in that: include: A data collection module, used to collect initial behavior data corresponding to the target object and initial news data related to the behavior of the target object according to the cloud computing platform corresponding to the target object; A data processing module, used for performing association analysis on the initial behavior data to obtain a target association relationship, and performing data filling on the initial behavior data according to the target association relationship to obtain target behavior data; An anomaly identification module, used to perform anomaly identification on the target behavior data to obtain target anomaly data corresponding to the target object, and determine the target behavior characteristics corresponding to the target object according to the target anomaly data; A viewpoint recognition module, used for performing news viewpoint recognition on the initial news data to obtain a target behavior viewpoint related to the target object behavior; The risk assessment module is used to perform distance calculation based on the target behavior characteristics and the target behavior viewpoint to obtain the gap information between the target behavior characteristics and the target behavior viewpoint, and perform risk assessment on the target object based on the gap information to obtain the risk assessment result corresponding to the target object.

Images