Method, device, apparatus and computer-readable medium for generating value risk information

By obtaining and analyzing the product value flow data sequence and current status information of the target object, screening out the historical data trend change curve of similar objects, solving the problem of inaccurate generation of value risk information in the existing technology, and achieving a more accurate value risk judgment .

CN117993709BActive Publication Date: 2024-11-29PARK DO CREDIT CO LTD
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202410122222.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-29
Publication Date
2024-11-29
Estimated Expiration
2044-01-29

AI Technical Summary

Technical Problem

The analysis of historical value transfer data sequences is large, and the accuracy of the generated value risk information is difficult to guarantee, resulting in large deviations in value risk judgments.

Method used

By obtaining the product value flow data sequence and current status information of the target object, data intercept and curve prediction and expansion are performed on the historical data of similar objects, and data trend change curves that are more matched with the target object are selected to generate more accurate value risk information.

Benefits of technology

It improves the accuracy of value risk information, reduces the amount of analysis work, and enhances the ability to judge the value risk of the target object.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117993709B_ABST
    Figure CN117993709B_ABST
Patent Text Reader

Abstract

The embodiments of the present disclosure disclose a method, device, equipment and computer-readable medium for generating value risk information. A specific implementation of the method includes: obtaining a product value circulation data sequence and product value status information; for each similar object, executing a generation step: performing data interception on the historical product value circulation data sequence; determining a data trend change curve and at least one similar data trend change curve; performing curve prediction expansion on the data trend change curve to generate an expanded data trend change curve, adjusting the curve cross-sectional length of at least one similar data trend change curve to generate at least one adjusted data trend change curve; screening a target adjusted data trend change curve to obtain at least one target adjusted data trend change curve; generating value risk information. This implementation can generate more accurate value risk information for target objects and target products.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a method, apparatus, device, and computer-readable medium for generating value-risk information. Background Art

[0002] At present, value risk detection for target customers / users has become a key development direction for various industries. The generation of value risk information corresponding to the target object is usually done in the following way: first, the historical value flow data sequence of the target object is manually analyzed to generate various value data indicators corresponding to the target object. Then, the value risk information of the target object is determined based on each value data indicator.

[0003] However, the inventors have found that when the above method is adopted, the following technical problem often occurs:

[0004] The workload of analyzing historical value transfer data sequences is large, and the accuracy of the value risk information generated for various value data indicators cannot be effectively guaranteed, resulting in large deviations in the value risk judgment of the target object.

[0005] In the process of adopting technical solutions to solve the above-mentioned technical problem 1, the following technical problem 2 is often accompanied: how to accurately determine the curve whose curve change similarity between the adjusted data trend change curve meets the target preset conditions, so as to supplement the value flow information of similar objects with the target object, so as to ensure the subsequent more accurate generation of value risk information for the target object. For the above-mentioned technical problem 2, the conventional solution is generally: to determine the curve whose curve change similarity between the adjusted data trend change curve meets the target preset conditions by comparing the various curve indicators between the curves. However, the above-mentioned conventional solution still has the following problem: the characteristics of the considered curve are limited, resulting in the lack of accuracy of the missing curve.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the inventive concept and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art. Summary of the invention

[0007] The content of this disclosure is used to introduce concepts in a brief form, which will be described in detail in the detailed implementation section below. The content of this disclosure is not intended to identify the key features or essential features of the technical solution claimed for protection, nor is it intended to limit the scope of the technical solution claimed for protection.

[0008] Some embodiments of the present disclosure propose value risk information generation methods, devices, equipment and computer-readable media to solve one or more of the technical problems mentioned in the above background technology section.

[0009] In a first aspect, some embodiments of the present disclosure provide a method for generating value risk information, including: obtaining a product value circulation data sequence and corresponding product value status information corresponding to a target object and in a target historical time period for a target value product; for each similar object in a similar object set corresponding to the target object, executing the following generation steps: based on the product value status information, performing data interception on the historical product value circulation data sequence corresponding to the similar object to generate at least one historical product value circulation data subsequence, wherein the corresponding duration of the historical product value circulation data sequence is greater than or equal to the corresponding duration of the target historical time period; determining a data trend change curve corresponding to the product value circulation data sequence and the at least one historical product value circulation data According to at least one similar data trend change curve corresponding to the subsequence; performing curve prediction extension on the above data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjusting the curve cross-sectional length of the similar data trend change curve in the above at least one similar data trend change curve to generate at least one adjusted data trend change curve; screening out from the above at least one adjusted data trend change curve a target adjusted data trend change curve whose curve change similarity with the above extended data trend change curve meets a target preset condition, to obtain at least one target adjusted data trend change curve; generating value risk information for the above target object according to the above data trend change curve and the obtained at least one target adjusted data trend change curve set.

[0010] In a second aspect, some embodiments of the present disclosure provide a value risk information generation device, including: an acquisition unit, configured to acquire a product value circulation data sequence and corresponding product value status information corresponding to a target object and in a target historical time period for a target value product; an execution unit, configured to execute the following generation steps for each similar object in a similar object set corresponding to the above target object: based on the above product value status information, data interception is performed on the historical product value circulation data sequence corresponding to the above similar object to generate at least one historical product value circulation data subsequence, wherein the corresponding duration of the above historical product value circulation data sequence is greater than or equal to the corresponding duration of the above target historical time period; determining a data trend change curve corresponding to the above product value circulation data sequence and the above at least one historical product At least one similar data trend change curve corresponding to the value flow data subsequence; performing curve prediction extension on the above data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjusting the curve cross-sectional length of the similar data trend change curve in the above at least one similar data trend change curve to generate at least one adjusted data trend change curve; screening out a target adjusted data trend change curve whose curve change similarity with the above extended data trend change curve meets a target preset condition from the above at least one adjusted data trend change curve, and obtaining at least one target adjusted data trend change curve; a generating unit, configured to generate value risk information for the above target object according to the above data trend change curve and the obtained at least one target adjusted data trend change curve set.

[0011] In a third aspect, some embodiments of the present disclosure provide an electronic device comprising: one or more processors; a storage device on which one or more programs are stored, and when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation manner in the first aspect.

[0012] In a fourth aspect, some embodiments of the present disclosure provide a computer-readable medium having a computer program stored thereon, wherein when the program is executed by a processor, the method described in any implementation manner in the first aspect is implemented.

[0013] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the value risk information generation method of some embodiments of the present disclosure, more accurate value risk information can be generated for the target object and the target product. Specifically, the reason why the relevant value risk information is not accurate enough is that the analysis workload of the historical value circulation data sequence is large, and the accuracy of the value risk information generated for various value data indicators cannot be effectively guaranteed, resulting in a large deviation in the value risk judgment of the target object. Based on this, the value risk information generation method of some embodiments of the present disclosure first obtains the product value circulation data sequence and the corresponding product value status information for the target value product corresponding to the target object and in the target historical time period, as supporting data to determine the subsequent value risk information. Then, for each similar object in the similar object set corresponding to the target object, the following generation steps are performed: First, according to the product value status information, the historical product value flow data sequence corresponding to the similar object is intercepted to generate at least one historical product value flow data subsequence, wherein the corresponding duration of the historical product value flow data sequence is greater than or equal to the corresponding duration of the target historical time period, so as to further supplement the value feature data sequence for the target object, so as to ensure that more accurate value risk information is generated with more data support in the future. Second, determine the data trend change curve corresponding to the product value flow data sequence and at least one similar data trend change curve corresponding to the at least one historical product value flow data subsequence, so as to screen out a more matching data curve corresponding to the target object, so as to generate more accurate value risk information in the future. Third, perform curve prediction and expansion on the data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjust the curve cross-sectional length of the similar data trend change curve in the at least one similar data trend change curve to generate at least one adjusted data trend change curve, so as to facilitate the curve matching combination of the data trend change curve and at least one similar data trend change curve. The fourth step is to select a target adjusted data trend change curve from the at least one adjusted data trend change curve, whose curve change similarity with the extended data trend change curve meets the target preset condition, and obtain at least one target adjusted data trend change curve for subsequent generation of more accurate value risk information. Finally, based on the data trend change curve and the obtained at least one target adjusted data trend change curve set, the value risk information for the target object can be accurately generated based on a large amount of data for the target object. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that components and elements are not necessarily drawn to scale.

[0015] Figure 1 is a flow chart of some embodiments of the value risk information generation method according to the present disclosure;

[0016] Figure 2 is a schematic diagram of the structure of some embodiments of the value risk information generating device according to the present disclosure;

[0017] Figure 3 It is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. DETAILED DESCRIPTION

[0018] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments set forth herein. On the contrary, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0019] It should also be noted that, for ease of description, only the parts related to the invention are shown in the drawings. In the absence of conflict, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0020] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0021] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0022] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0023] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0024] refer to Figure 1, shows a process 100 of some embodiments of the value risk information generation method according to the present disclosure. The value risk information generation method comprises the following steps:

[0025] Step 101, obtaining a product value flow data sequence and corresponding product value status information for a target value product corresponding to a target object and in a target historical time period.

[0026] In some embodiments, the execution subject of the above-mentioned value risk information generation method can obtain the product value flow data sequence and the corresponding product value status information for the target value product in the target historical time period corresponding to the target object through a wired connection method or a wireless connection method. Among them, the target object can be an object to be subjected to value risk detection. In practice, the target object can be a target user or a target enterprise. The target historical time period can be a pre-set historical time period for the current time. For example, the target historical time period can be the first half of the current time period. The target value product can be a product related to value flow. In practice, for the financial field, the target value product can be an investment product or a related credit product. Value flow can be but not limited to at least one of the following: value consumption, value deposit, and value investment. The product value flow data sequence can be a value flow data sequence for the target value product. For example, the product value flow data can be the credit consumption data and credit credit data of the related credit product. The product value status information can characterize the current status of the target object when operating the target value product. For example, the product value status information may include: current investment funds for the target value product, current consumption funds for the target value product, and current object usage credit for the target value product.

[0027] Step 102: for each similar object in the similar object set corresponding to the target object, perform the following generation steps:

[0028] Step 1021: based on the product value status information, data interception is performed on the historical product value circulation data sequence corresponding to the similar object to generate at least one historical product value circulation data subsequence.

[0029] In some embodiments, the execution subject may perform data interception on the historical product value circulation data sequence corresponding to the similar objects according to the product value status information to generate at least one historical product value circulation data subsequence. Among them, the similar objects in the similar object set may be objects that have similar object features with the target object. For example, similar object features may be similar consumption features, or similar product usage experience features. In practice, the generation of similar object sets may be based on the division of object portraits. The specific implementation method will not be repeated. The historical product value circulation data sequence may be a product value circulation data sequence corresponding to similar objects within a predetermined historical time period. Among them, the corresponding duration of the historical product value circulation data sequence is greater than or equal to the corresponding duration of the target historical time period. For example, if the target historical time period is half a year, the corresponding duration of the historical product value circulation data subsequence may be one year.

[0030] As an example, first, the execution subject can determine the product usage status corresponding to each time point according to the historical product value flow data sequence, and obtain at least one product usage status information. Then, the product usage status information whose status similarity with the product value status information reaches a preset degree is screened out from the at least one product usage status information, and at least one target product usage status information is obtained. Next, according to at least one time point corresponding to the at least one target product usage status information, the historical product value flow data sequence is intercepted to obtain at least one candidate historical product value flow data subsequence. Finally, according to the duration corresponding to each candidate historical product value flow data subsequence, each candidate historical product value flow data subsequence in at least one candidate historical product value flow data subsequence is sequence-combined, so that each combined historical product value flow data subsequence corresponds to a duration greater than the corresponding duration of the target historical time period, and at least one historical product value flow data subsequence is obtained. That is, the sequences in at least one candidate historical product value flow data subsequence whose corresponding duration is less than that of the candidate historical product value flow data subsequence are adjacently combined.

[0031] Step 1022: determine the data trend change curve corresponding to the product value circulation data sequence and at least one similar data trend change curve corresponding to the at least one historical product value circulation data subsequence.

[0032] In some embodiments, the above-mentioned execution entity can determine the data trend change curve corresponding to the above-mentioned product value flow data sequence and at least one similar data trend change curve corresponding to the above-mentioned at least one historical product value flow data subsequence. Among them, the data trend change curve can be a curve that characterizes the change of the value flow data corresponding to the product value flow data sequence. In practice, the data trend change curve can be a curve for the target coordinate system. The target coordinate system can be a coordinate system with the actual numerical value corresponding to the product value flow data as the Y-axis and the corresponding time as the X-axis. In practice, a similar data trend change curve can also be a curve for the historical product value flow data subsequence under the above-mentioned target coordinate.

[0033] As an example, the execution subject may explicitly reflect each data and corresponding time in the product value flow data sequence on the target coordinate axis to generate a data trend change curve. The curve generation method of at least one similar data trend change curve may be similar.

[0034] Step 1023, performing curve prediction expansion on the above-mentioned data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjusting the curve cross-sectional length of a similar data trend change curve in the above-mentioned at least one similar data trend change curve to generate at least one adjusted data trend change curve.

[0035] In some embodiments, the above-mentioned execution entity can perform curve prediction expansion on the above-mentioned data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjust the curve cross-sectional length of a similar data trend change curve in the above-mentioned at least one similar data trend change curve to generate at least one adjusted data trend change curve.

[0036] In some optional implementations of some embodiments, the above-mentioned curve prediction extension of the data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and the curve cross-sectional length adjustment of a similar data trend change curve in the at least one similar data trend change curve to generate at least one adjusted data trend change curve may include the following steps:

[0037] The first step is to determine the corresponding ordinate set of the above-mentioned data trend change curve under the predetermined abscissa set in the target coordinate system, and determine the corresponding abscissa set of the above-mentioned data trend change curve under the predetermined ordinate set in the target coordinate system. Among them, the predetermined abscissa in the predetermined abscissa set can be a coordinate value pre-set for the corresponding abscissa value. For example, if the abscissa is time, the time corresponding to each day can be determined as the value corresponding to the predetermined abscissa. The predetermined ordinate in the predetermined ordinate set can be a coordinate value pre-set for the corresponding ordinate value. For example, if the ordinate is time, the preset value corresponding to the product value flow data can be determined as the value corresponding to the predetermined ordinate.

[0038] The second step is to coordinately combine the predetermined horizontal coordinate set and the vertical coordinate set to generate a first coordinate set, and coordinately combine the horizontal coordinate set and the predetermined vertical coordinate set to generate a second coordinate set.

[0039] The third step is to determine the concave point coordinate set and the convex point coordinate set in the data trend change curve. The concave point coordinates in the concave point coordinate set can be the coordinates corresponding to the concave points in the data trend change curve. The convex point coordinates in the convex point coordinate set can be the coordinates corresponding to the convex points in the data trend change curve.

[0040] The fourth step is to sequentially combine the first coordinate set, the second coordinate set, the concave point coordinate set and the convex point coordinate set according to the order in which the horizontal coordinates are sorted, so as to generate a first coordinate sequence.

[0041] The fifth step is to determine the historical time period to be predicted and the future time period to be predicted for the above data trend change curve. The historical time period to be predicted can be a pre-set historical time period for the corresponding product value flow prediction. The future time period to be predicted can be a pre-set future time period for the corresponding product value flow prediction.

[0042] Step 6: Based on the first coordinate sequence, the historical product value flow information prediction model is used to generate a first historical product value flow prediction information sequence for the historical time period to be predicted. The historical product value flow information prediction model can be a model for predicting product value flow information within a historical time period. In practice, the historical product value flow information prediction model can be a multi-layer serially connected LSTM model.

[0043] As an example, first, the execution subject may perform coordinate data conversion on each first coordinate in the first coordinate sequence to generate a data sequence. Then, each data in the data sequence is preprocessed to obtain a preprocessed data sequence. Finally, the preprocessed data sequence is input into the historical product value circulation information prediction model to generate a first historical product value circulation prediction information sequence.

[0044] The seventh step is to generate a first historical prediction data trend change curve for the above-mentioned first historical product value circulation prediction information sequence.

[0045] As an example, the execution entity may explicitly display each data and corresponding time in the first historical product value flow prediction information sequence on the target coordinate axis to generate a first historical prediction data trend change curve.

[0046] Step 8: Generate a second coordinate sequence for the trend change curve of the first historical forecast data. For specific implementation methods, refer to the generation of the first coordinate sequence.

[0047] In the ninth step, based on the first coordinate sequence and the second coordinate sequence, the future product value flow information prediction model is used to generate a first future product value flow prediction information sequence for the future time period to be predicted. The future product value flow information prediction model may be a prediction model for future product value flow information for future time periods. In practice, the future product value flow information prediction model may be a plurality of LSTM models connected in series. Specifically, the specific implementation method of the first future product value flow prediction information sequence may be referred to.

[0048] The tenth step is to generate a first future prediction data trend change curve for the first future product value flow prediction information sequence. The specific implementation method can refer to the generation of the first historical prediction data trend change curve.

[0049] In the eleventh step, the extended data trend change curve is generated based on the first historical prediction data trend change curve, the data trend change curve and the first future prediction data trend change curve.

[0050] Optionally, generating the extended data trend change curve according to the first historical predicted data trend change curve, the data trend change curve and the first future predicted data trend change curve may include the following steps:

[0051] The first step is to generate a second future product value flow prediction information sequence for the above-mentioned future time period to be predicted based on the above-mentioned first coordinate sequence and using the above-mentioned future product value flow prediction information model. The specific implementation method can refer to the generation of the first future product value flow prediction information sequence. The difference is that the input here is the first coordinate sequence.

[0052] The second step is to generate a second future prediction data trend change curve for the second future product value flow prediction information sequence. The specific implementation method will not be repeated here.

[0053] The third step is to generate a third coordinate sequence for the second future prediction data trend change curve. The specific implementation method will not be described in detail.

[0054] The fourth step is to generate a second historical product value flow prediction information sequence for the historical time period to be predicted based on the first coordinate sequence and the third coordinate sequence and using the historical product value flow prediction model. The specific implementation method will not be described in detail.

[0055] The fifth step is to generate a second historical prediction data trend change curve for the second historical product value circulation prediction information sequence. The specific implementation method will not be repeated here.

[0056] The sixth step is to determine the model precision information corresponding to the above-mentioned future product value flow information prediction model and the model precision information corresponding to the above-mentioned historical product value flow information prediction model, as the first model precision information and the second model precision information respectively. Among them, the model precision information can be the accuracy of the model prediction output result. In practice, the model precision information corresponding to the future product value flow information prediction model and the model precision information corresponding to the above-mentioned historical product value flow information prediction model can be determined by a pre-acquired data set. The first model precision information and the second model precision information can be values ​​between 0 and 1. The larger the value, the higher the accuracy of the corresponding model.

[0057] The seventh step is to generate the first curve importance corresponding to the first historical prediction data trend change curve, the second curve importance corresponding to the second historical prediction data trend change curve, the third curve importance corresponding to the first future prediction data trend change curve, and the fourth curve importance corresponding to the second future prediction data trend change curve based on the first model precision information and the second model precision information.

[0058] As an example, first, the execution entity may determine the second model precision information as the first curve importance. Then, the second model precision information may be multiplied by the first numerical value to obtain a first multiplication result, and the first model precision information may be multiplied by the second numerical value to obtain a second multiplication result. The first numerical value is greater than the second numerical value. The first multiplication numerical value and the second multiplication numerical value are added to obtain a first addition result as the second curve importance. Next, the first model precision information is determined as the third curve importance. Finally, the first model precision information may be multiplied by the first numerical value to obtain a third multiplication result, and the second model precision information may be multiplied by the second numerical value to obtain a fourth multiplication result. The first numerical value is greater than the second numerical value. The third multiplication numerical value and the fourth multiplication numerical value are added to obtain a second addition result as the fourth curve importance.

[0059] Step 8. Generate the extended data trend change curve based on the importance of the first curve, the importance of the second curve, the importance of the third curve, the importance of the fourth curve, the first historical prediction data trend change curve, the second historical prediction data trend change curve, the first future prediction data trend change curve, and the second future prediction data trend change curve.

[0060] Optionally, generating the extended data trend change curve according to the first curve importance, the second curve importance, the third curve importance, the fourth curve importance, the first historical forecast data trend change curve, the second historical forecast data trend change curve, the first future forecast data trend change curve, and the second future forecast data trend change curve may include the following steps:

[0061] The first step is to determine a fourth coordinate sequence for the second historical forecast data trend change curve and a fifth coordinate sequence for the first future forecast data trend change curve.

[0062] The second step is to multiply each coordinate in the second coordinate sequence by the importance of the first curve to obtain a first corresponding coordinate sequence.

[0063] The third step is to multiply each coordinate in the fourth coordinate sequence by the importance of the second curve to obtain a second coordinate sequence.

[0064] The fourth step is to add the coordinate values ​​of the first phase coordinate in the first phase coordinate sequence and the second phase coordinate in the second phase coordinate sequence to obtain a first added coordinate sequence.

[0065] The fifth step is to multiply each coordinate in the fifth coordinate sequence by the importance of the third curve to obtain a third coordinate sequence.

[0066] The sixth step is to multiply each coordinate in the third coordinate sequence by the importance of the fourth curve to obtain a fourth coordinate sequence.

[0067] In the seventh step, the coordinate values ​​of the third phase coordinates in the third phase coordinate sequence and the fourth phase coordinates in the fourth phase coordinate sequence are added to obtain a second added coordinate sequence.

[0068] The eighth step is to generate a third historical prediction data trend change curve for the first added coordinate sequence and a third future prediction data trend change curve for the second added coordinate sequence.

[0069] The ninth step is to splice the above data trend change curve, the above third historical prediction data trend change curve and the above third future prediction data trend change curve to generate a spliced ​​curve as the above third historical prediction data trend change curve.

[0070] Step 1024 , selecting a target adjusted data trend change curve whose curve change similarity with the extended data trend change curve meets a target preset condition from the at least one adjusted data trend change curve, and obtaining at least one target adjusted data trend change curve.

[0071] In some embodiments, the execution subject may select a target adjusted data trend change curve from the at least one adjusted data trend change curve, the target adjusted data trend change curve having a curve change similarity degree with the extended data trend change curve that satisfies a target preset condition, and obtain at least one target adjusted data trend change curve. The target preset condition may be a curve having a curve change similarity degree between the target adjusted data trend change curve and the extended data trend change curve that is greater than a target value.

[0072] In some optional implementations of some embodiments, the step of selecting a target adjusted data trend change curve whose curve change similarity with the extended data trend change curve satisfies a target preset condition from the at least one adjusted data trend change curve to obtain at least one target adjusted data trend change curve may include the following steps:

[0073] The first step is to generate an enhanced data trend change curve set for the above-mentioned extended data trend change curve. The above-mentioned enhanced data trend change curve set includes: a positive enhanced data trend change curve set and a negative enhanced data trend change curve set. The positive enhanced data trend change curve can be a curve with the same data change trend direction as the extended data trend change curve. The negative enhanced data trend change curve can be a curve with a data change trend direction inconsistent with the extended data trend change curve.

[0074] In the second step, the at least one adjusted data trend change curve, the enhanced data trend change curve set and the extended data trend change curve are combined to generate a change curve set.

[0075] The third step is to perform curve clustering on each curve in the above change curve set to generate a curve cluster set.

[0076] In the fourth step, a target adjusted data trend change curve that is in the same curve cluster as the extended data trend change curve is selected from the at least one adjusted data trend change curve to obtain at least one target adjusted data trend change curve.

[0077] Optionally, the step of performing curve clustering on each curve in the change curve set to generate a curve cluster set may include the following steps:

[0078] The first step is to determine the curve indicator information group corresponding to each change curve in the above change curve set. The curve indicator information in the curve indicator information set may be an indicator value corresponding to the curve indicator. Specifically, the curve indicator set for the curve may be pre-set. For example, the curve indicator set may include but is not limited to at least one of the following: MA indicator (moving average), MACD indicator (moving average convergence divergence), KDJ indicator (stochastic indicator).

[0079] In the second step, according to the obtained curve index information set, curve clustering is performed on each curve in the above-mentioned change curve set to generate an initial curve cluster set.

[0080] As an example, the execution entity may use the curve indicator information set as a clustering data source to perform curve clustering on each curve in the change curve set to generate an initial curve cluster set.

[0081] Step 3: For each initial curve cluster in the initial curve cluster set, perform the following verification steps:

[0082] In the first sub-step, two curves are randomly obtained from the initial curve cluster as the first curve and the second curve respectively.

[0083] The second sub-step is to determine the trend change difference information between the first curve, the second curve and the first target curve. The first target curve is the curve at the cluster center corresponding to the initial curve cluster. The trend change difference information may include: information characterizing the curve trend change difference between the first curve and the first target curve and information characterizing the curve trend change difference between the second curve and the first target curve. The curve trend change difference may characterize the development trend change between the two curves.

[0084] The third sub-step is to determine the vertical coordinate interval range difference and the horizontal coordinate interval range difference between the first curve, the second curve and the first target curve. The vertical coordinate interval range difference may include: the difference value between the vertical coordinate interval size range between the first curve and the first target curve and the difference value between the vertical coordinate interval size range between the second curve and the first target curve.

[0085] The fourth sub-step is to determine a curve cluster whose corresponding cluster distance with the above initial curve cluster is smaller than the target cluster, and obtain at least one curve cluster. The cluster distance may be the curve distance between the two curves that are closest to each other in the two curve clusters. The specific curve distance between the two curves may be obtained by weighting the corresponding curve index information of the curves.

[0086] The fifth sub-step is to determine at least one second target curve corresponding to the at least one curve cluster, wherein the second target curve is a cluster center curve corresponding to the curve cluster.

[0087] In a sixth sub-step, for each of the at least one second target curve, a curve difference distance between the first curve, the second curve and the second target curve is determined to obtain a first difference distance and a second difference distance.

[0088] The seventh sub-step is to determine the curve difference distances between the first curve, the second curve and the first target curve to obtain a third difference distance and a fourth difference distance.

[0089] In an eighth sub-step, in response to determining that the trend change difference information satisfies a first difference condition, the vertical axis interval range difference and the horizontal axis interval range difference satisfy a second difference condition, the third difference distance is less than at least one first difference distance, and the fourth difference distance is less than at least one second difference distance, generating confirmation information indicating that the initial curve cluster is correct. The first difference condition may be information that the trend change difference information is within a first difference interval. The second difference condition may be information that the vertical axis interval range difference and the horizontal axis interval range difference are within a second difference interval.

[0090] The fourth step is to generate a curve cluster based on the obtained confirmation information set.

[0091] As an example, in response to determining that all confirmation information in the confirmation information set indicates that all difference information satisfies corresponding conditions, the initial curve cluster is determined as the curve cluster.

[0092] Considering the problems of the above conventional solutions, facing the above technical problem 2: the characteristics of the considered curve are limited, resulting in the lack of accuracy of the missing curve. Combining the advantages / technical status, it can be decided to adopt the following solution.

[0093] In some optional implementations of some embodiments, the step of selecting a target adjusted data trend change curve whose curve change similarity with the extended data trend change curve satisfies a target preset condition from the at least one adjusted data trend change curve to obtain at least one target adjusted data trend change curve may include the following steps:

[0094] The first step is to determine the convex curve time period corresponding to the extended data trend change curve to obtain a convex curve time period set, wherein the convex curve time period may be a time period in which the corresponding curve trend is a convex trend.

[0095] The second step is to perform curve cutting on the extended data trend change curve according to the convex curve time period set to generate a first cut curve set, wherein the first cut curve set includes a curve segment set corresponding to the convex curve time period set and belonging to the extended data trend change curve.

[0096] In the third step, for each of the at least one adjustment data change curve, the following first information generation step is performed:

[0097] The first sub-step is to perform curve cutting on the adjustment data change curve according to the convex curve time period set to generate a second cut curve set.

[0098] The second sub-step is to generate similar information of the rising and falling trends of the curves corresponding to the first post-cutting curve set and the second post-cutting curve set. The similar information of the rising and falling trends of the curves can be a value between 0 and 1. The larger the value is, the more similar the rising and falling trends of the curves corresponding to the first post-cutting curve set and the second post-cutting curve set are. That is, the ratio between the same rising and falling trends of the curves and the different rising and falling trends of the curves between the first post-cutting curves in each convex curve time period and the second post-cutting curves in each convex curve time period is the similar information of the rising and falling trends of the curves.

[0099] In the fourth step, an adjusted data change curve having a corresponding curve rising and falling trend similarity information greater than a first fixed value is selected from the at least one adjusted data change curve as a predetermined data change curve to obtain at least one predetermined data change curve.

[0100] Step 5: for each of the at least one adjustment data change curve, perform the following second information generation step:

[0101] The first sub-step is to set the time period weight information corresponding to each convex curve time period in the convex curve time period set to obtain a time period weight information set, wherein the time period weight information can represent the importance of the curve corresponding to the first cut curve.

[0102] The second sub-step is to perform the following third information generation step for each second post-cutting curve in the second post-cutting curve set corresponding to the above adjustment data change curve:

[0103] Sub-step 1, sampling the key points of the second post-cut curve and the corresponding first post-cut curve to generate a second post-cut key point set and a first post-cut key point set. There is a time correspondence between the second post-cut key point in the second post-cut key point set and the first post-cut key point in the first post-cut key point set. The time period between the second post-cut curve and the corresponding first post-cut curve is the same.

[0104] Sub-step 2: Input the second post-cut key point set and the first post-cut key point set into the temporal neural network model to generate curve similarity information. The temporal neural network model can be a Transformer model. The curve similarity information can characterize the curve similarity between the second post-cut curve and the corresponding first post-cut curve.

[0105] The third sub-step is to correspondingly multiply the obtained curve similarities in the curve similarity set with the time period weight information in the above time period weight information set to generate a multiplication result set.

[0106] The fourth sub-step is to add the multiplication results in the multiplication result set to generate an addition result.

[0107] In a sixth step, the addition result whose corresponding addition result is greater than the second fixed value is selected from the at least one addition result obtained to obtain an addition result set.

[0108] In the seventh step, the adjustment data trend change curve set corresponding to the addition result set is determined as at least one target adjustment data trend change curve.

[0109] The above-mentioned optional implementation methods and optional contents in some embodiments, as an inventive point of the present disclosure, solve the technical problem mentioned in Background Technology 2 that "the characteristics of the considered curve are limited, resulting in the lack of accuracy of the missing curve". Based on this, first of all, the present disclosure, first of all, determines a set of concave curve time periods, so as to compare the various curve segments in at least one adjusted data change curve with the various curve segments in the extended data trend change curve, to obtain at least one predetermined data change curve. Then, through the time period weight information set and the time series neural network model, the curve feature information on each time segment is further refined to match, and considering the importance of the features on each time segment, at least one target adjusted data trend change curve whose curve change similarity with the above-mentioned extended data trend change curve meets the target preset conditions is subsequently screened out more accurately, so as to ensure the subsequent generation of more accurate value risk information.

[0110] Step 103: adjusting the data trend change curve set according to the data trend change curve and the at least one target, and generating value risk information for the target object.

[0111] In some embodiments, the execution subject may adjust the data trend change curve set according to the data trend change curve and the at least one target to generate value risk information for the target object. The value risk information may represent the risk information of the target object using the target value product to perform the corresponding value operation. In practice, the value risk information may be score information. The larger the score value, the greater the risk.

[0112] As an example, first, extract the first predetermined trend data set corresponding to the predetermined time point set in the above data trend change curve. And extract the second predetermined trend data set corresponding to each target adjustment data trend change curve in at least one target adjustment data trend change curve set to obtain at least one second predetermined trend data set. Then, combine the first predetermined trend data set and at least one second predetermined trend data set at corresponding time points to generate a predetermined trend data triple set, wherein the predetermined trend triple includes: the first predetermined trend data and at least one second predetermined trend data corresponding to the time. Finally, the predetermined trend data triple set is sequentially input into the first recurrent neural network model to output value risk information.

[0113] As another example, first, the execution entity may input the first predetermined trend data set corresponding to the data trend change curve into the second recurrent neural network model to generate the first candidate risk information. Then, each second predetermined trend data set in at least one second predetermined trend data set is input into the second recurrent neural network model to generate the second candidate risk information, and at least one second candidate risk information is obtained. Finally, the first candidate risk information and at least one second candidate risk information are weighted and summed to generate a weighted sum value as the value risk information.

[0114] In some optional implementations of some embodiments, after step 103, the steps further include:

[0115] The first step is to package the value risk information, the object information corresponding to the target object, the product value flow data sequence and the product value status information to generate object packaging data in response to determining that the value risk information indicates the existence of risk.

[0116] The second step is to import the above object packaging data into the storage space of the target storage device, wherein the target storage device may be a device connected to the execution subject and used to store risk data.

[0117] The third step is to use the preset space detection process to detect in real time whether the data storage bytes corresponding to the target storage space have changed. The space detection process can monitor the data volume change information stored in the target storage device in real time.

[0118] In the fourth step, in response to the determined change, the object package data is marked, and a warning message for the object package data is sent to the relevant value risk monitoring user terminal. The object package data is marked in red. The value risk monitoring user terminal can be a terminal for real-time monitoring of the occurrence of value risks.

[0119] The above-mentioned various embodiments of the present disclosure have the following beneficial effects: through the value risk information generation method of some embodiments of the present disclosure, more accurate value risk information can be generated for the target object and the target product. Specifically, the reason why the relevant value risk information is not accurate enough is that the analysis workload of the historical value circulation data sequence is large, and the accuracy of the value risk information generated for various value data indicators cannot be effectively guaranteed, resulting in a large deviation in the value risk judgment of the target object. Based on this, the value risk information generation method of some embodiments of the present disclosure first obtains the product value circulation data sequence and the corresponding product value status information for the target value product corresponding to the target object and in the target historical time period, as supporting data to determine the subsequent value risk information. Then, for each similar object in the similar object set corresponding to the target object, the following generation steps are performed: First, according to the product value status information, the historical product value flow data sequence corresponding to the similar object is intercepted to generate at least one historical product value flow data subsequence, wherein the corresponding duration of the historical product value flow data sequence is greater than or equal to the corresponding duration of the target historical time period, so as to further supplement the value feature data sequence for the target object, so as to ensure that more accurate value risk information is generated with more data support in the future. Second, determine the data trend change curve corresponding to the product value flow data sequence and at least one similar data trend change curve corresponding to the at least one historical product value flow data subsequence, so as to screen out a more matching data curve corresponding to the target object, so as to generate more accurate value risk information in the future. Third, perform curve prediction and expansion on the data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjust the curve cross-sectional length of the similar data trend change curve in the at least one similar data trend change curve to generate at least one adjusted data trend change curve, so as to facilitate the curve matching combination of the data trend change curve and at least one similar data trend change curve. The fourth step is to select a target adjusted data trend change curve from the at least one adjusted data trend change curve, whose curve change similarity with the extended data trend change curve meets the target preset condition, and obtain at least one target adjusted data trend change curve for subsequent generation of more accurate value risk information. Finally, based on the data trend change curve and the obtained at least one target adjusted data trend change curve set, the value risk information for the target object can be accurately generated based on a large amount of data for the target object.

[0120] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a value risk information generating device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the value risk information generating device can be specifically applied to various electronic devices.

[0121] like Figure 2 As shown, a value risk information generating device 200 includes: an acquisition unit 201, an execution unit 202 and a generation unit 203. The acquisition unit 201 is configured to acquire a product value circulation data sequence and corresponding product value status information corresponding to a target object and in a target historical time period for a target value product; the execution unit 202 is configured to perform the following generation steps for each similar object in a similar object set corresponding to the target object: based on the product value status information, data interception is performed on the historical product value circulation data sequence corresponding to the similar object to generate at least one historical product value circulation data subsequence, wherein the corresponding duration of the historical product value circulation data sequence is greater than or equal to the corresponding duration of the target historical time period; determining the data trend change curve corresponding to the product value circulation data sequence and the corresponding to the at least one historical product value circulation data subsequence; at least one similar data trend change curve; performing curve prediction extension on the above data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjusting the curve cross-sectional length of the similar data trend change curve in the above at least one similar data trend change curve to generate at least one adjusted data trend change curve; screening out from the above at least one adjusted data trend change curve a target adjusted data trend change curve whose curve change similarity with the above extended data trend change curve meets the target preset condition, and obtaining at least one target adjusted data trend change curve; a generating unit 203 is configured to generate value risk information for the above target object according to the above data trend change curve and the above at least one target adjusted data trend change curve set.

[0122] It can be understood that the various units recorded in the value risk information generating device 200 and the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the value risk information generating device 200 and the units included therein, and will not be described in detail here.

[0123] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device (eg, an electronic device) 300 suitable for implementing some embodiments of the present disclosure. Figure 3 The electronic device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0124] like Figure 3As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0125] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0126] In particular, according to some embodiments of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, some embodiments of the present disclosure include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In some such embodiments, the computer program can be downloaded and installed from the network through the communication device 309, or installed from the storage device 308, or installed from the ROM 302. When the computer program is executed by the processing device 301, the above-mentioned functions defined in the method of some embodiments of the present disclosure are executed.

[0127] It should be noted that the computer-readable medium mentioned above in some embodiments of the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In some embodiments of the present disclosure, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. In some embodiments of the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer readable signal media may also be any computer readable medium other than computer readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0128] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (HyperText Transfer Protocol), and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0129] The above-mentioned computer-readable medium may be included in the above-mentioned electronic device; or it may exist independently without being installed in the electronic device. The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device: obtains the product value circulation data sequence and the corresponding product value status information corresponding to the target object and in the target historical time period for the target value product; for each similar object in the similar object set corresponding to the above-mentioned target object, executes the following generation steps: according to the above-mentioned product value status information, data is intercepted for the historical product value circulation data sequence corresponding to the above-mentioned similar object to generate at least one historical product value circulation data subsequence, wherein the corresponding duration of the above-mentioned historical product value circulation data sequence is greater than or equal to the corresponding duration of the above-mentioned target historical time period; determines the data trend change curve corresponding to the above-mentioned product value circulation data sequence and the above-mentioned at least one at least one similar data trend change curve corresponding to a historical product value circulation data subsequence; performing curve prediction and extension on the above data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjusting the curve cross-sectional length of the similar data trend change curve in the above at least one similar data trend change curve to generate at least one adjusted data trend change curve; screening out a target adjusted data trend change curve whose curve change similarity with the above extended data trend change curve meets a target preset condition from the above at least one adjusted data trend change curve to obtain at least one target adjusted data trend change curve; generating value risk information for the above target object according to the above data trend change curve and the above at least one target adjusted data trend change curve set.

[0130] Computer program code for performing the operations of some embodiments of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0132] The units described in some embodiments of the present disclosure may be implemented by software or by hardware. The described units may also be provided in a processor, for example, may be described as: a processor including an acquisition unit, an execution unit, and a generation unit. Among them, the names of these units do not constitute a limitation on the unit itself in certain cases, for example, the acquisition unit may also be described as "a unit for acquiring a product value flow data sequence and corresponding product value status information for a target value product corresponding to a target object and in a target historical time period".

[0133] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0134] The above descriptions are only some preferred embodiments of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present disclosure.

Claims

1. A method for generating value risk information, comprising: Obtain product value flow data sequence and corresponding product value status information for target value products corresponding to the target object and in the target historical time period; For each similar object in the similar object set corresponding to the target object, the following generation steps are performed: According to the product value status information, data interception is performed on the historical product value circulation data sequence corresponding to the similar object to generate at least one historical product value circulation data subsequence, wherein the corresponding duration of the historical product value circulation data sequence is greater than or equal to the corresponding duration of the target historical time period; Determine a data trend change curve corresponding to the product value circulation data sequence and at least one similar data trend change curve corresponding to the at least one historical product value circulation data subsequence; The data trend change curve is subjected to curve prediction extension within a predetermined time period before and after to generate an extended data trend change curve, and a curve cross-sectional length adjustment is performed on a similar data trend change curve in at least one similar data trend change curve to generate at least one adjusted data trend change curve, wherein the curve prediction extension is performed within a predetermined time period before and after to generate an extended data trend change curve, and the curve cross-sectional length adjustment is performed on a similar data trend change curve in at least one similar data trend change curve to generate at least one adjusted data trend change curve, comprising: determining the data trend change curve under a predetermined set of horizontal coordinates in a target coordinate system. The target coordinate system comprises a plurality of coordinate systems, a plurality of coordinate systems, and a plurality of coordinate systems. The plurality of coordinate systems are respectively configured to determine a corresponding ordinate set, and a corresponding abscissa set of the data trend change curve under a predetermined ordinate set in the target coordinate system; the predetermined abscissa set and the ordinate set are coordinately combined to generate a first coordinate set, and the abscissa set and the predetermined ordinate set are coordinately combined to generate a second coordinate set; a concave point coordinate set and a convex point coordinate set in the data trend change curve are determined; according to the order in which the abscissas are sequentially sorted, the first coordinate set, the second coordinate set, the concave point coordinate set and the convex point coordinate set are coordinately combined in sequence to generate a first coordinate sequence; a historical time period to be predicted and a future time period to be predicted for the data trend change curve are determined; according to the first coordinate sequence, , using the historical product value flow information prediction model, generate a first historical product value flow prediction information sequence for the historical time period to be predicted; generate a first historical prediction data trend change curve for the first historical product value flow prediction information sequence; generate a second coordinate sequence for the first historical prediction data trend change curve; based on the first coordinate sequence and the second coordinate sequence, using the future product value flow information prediction model, generate a first future product value flow prediction information sequence for the future time period to be predicted; generate a first future prediction data trend change curve for the first future product value flow prediction information sequence; based on the first historical prediction data trend change curve , the data trend change curve and the first future predicted data trend change curve, generate the extended data trend change curve, wherein the generation of the extended data trend change curve according to the first historical predicted data trend change curve, the data trend change curve and the first future predicted data trend change curve includes: according to the first coordinate sequence, using the future product value flow information prediction model, generating a second future product value flow prediction information sequence for the future time period to be predicted; generating a second future prediction data trend change curve for the second future product value flow prediction information sequence; generating a third coordinate sequence for the second future prediction data trend change curve;According to the first coordinate sequence and the third coordinate sequence, using the historical product value flow information prediction model, generate a second historical product value flow prediction information sequence for the historical time period to be predicted; generate a second historical prediction data trend change curve for the second historical product value flow prediction information sequence; determine the model precision information corresponding to the future product value flow information prediction model and the model precision information corresponding to the historical product value flow information prediction model, as the first model precision information and the second model precision information respectively; according to the first model precision information and the second model precision information, generate the first curve importance corresponding to the first historical prediction data trend change curve, the second curve importance corresponding to the second historical prediction data trend change curve, the third curve importance corresponding to the first future prediction data trend change curve, and the fourth curve importance corresponding to the second future prediction data trend change curve; according to the first curve importance, the second curve importance, the third curve importance, the fourth curve importance, the first historical prediction data trend change curve, the second historical prediction data trend change curve, the first future prediction data trend change curve, and the second future prediction data trend change curve, generate the extended data trend change curve, wherein the first curve importance, the second curve importance, the third curve importance, the fourth curve importance, the first historical prediction data trend change curve, the second historical prediction data trend change curve, the first future prediction data trend change curve, and the second future prediction data trend change curve are used to generate the extended data trend change curve. , the fourth curve importance, the first historical forecast data trend change curve, the second historical forecast data trend change curve, the first future forecast data trend change curve, the second future forecast data trend change curve, generate the extended data trend change curve, including: determining a fourth coordinate sequence for the second historical forecast data trend change curve and a fifth coordinate sequence for the first future forecast data trend change curve; multiplying each coordinate in the second coordinate sequence by the first curve importance to obtain a first corresponding coordinate sequence; multiplying each coordinate in the fourth coordinate sequence by the second curve importance to obtain a second corresponding coordinate sequence; multiplying the first corresponding coordinate sequence by the first curve importance to obtain a second corresponding coordinate sequence The first phase coordinate in the column is added with the second phase coordinate in the second phase coordinate sequence to obtain a first added coordinate sequence; each coordinate in the fifth coordinate sequence is multiplied by the importance of the third curve to obtain a third phase coordinate sequence; each coordinate in the third coordinate sequence is multiplied by the importance of the fourth curve to obtain a fourth phase coordinate sequence; the third phase coordinate in the third phase coordinate sequence is added with the fourth phase coordinate in the fourth phase coordinate sequence to obtain a second added coordinate sequence; a third historical prediction data trend change curve for the first added coordinate sequence and a third future prediction data trend change curve for the second added coordinate sequence are generated;Splicing the data trend change curve, the third historical prediction data trend change curve and the third future prediction data trend change curve to generate a spliced ​​curve as the third historical prediction data trend change curve; Filtering out a target adjusted data trend change curve whose curve change similarity degree with the extended data trend change curve meets a target preset condition from the at least one adjusted data trend change curve, and obtaining at least one target adjusted data trend change curve, wherein filtering out a target adjusted data trend change curve whose curve change similarity degree with the extended data trend change curve meets a target preset condition from the at least one adjusted data trend change curve, and obtaining at least one target adjusted data trend change curve, comprises: generating an enhanced data trend change curve set for the extended data trend change curve, wherein the enhanced data trend change curve set comprises: a positive enhanced data trend change curve set and a negative enhanced data trend change curve set. The method comprises the steps of: combining the at least one adjusted data trend change curve, the enhanced data trend change curve set and the extended data trend change curve to generate a change curve set; clustering the curves in the change curve set to generate a curve cluster set; selecting a target adjusted data trend change curve in the same curve cluster as the extended data trend change curve from the at least one adjusted data trend change curve to obtain at least one target adjusted data trend change curve, wherein clustering the curves in the change curve set to generate a curve cluster set comprises: determining a curve indicator information group corresponding to each change curve in the change curve set; clustering the curves in the change curve set according to the obtained curve indicator information group set. Each curve in the change curve set is clustered to generate an initial curve cluster set; for each initial curve cluster in the initial curve cluster set, the following verification steps are performed: two curves are randomly obtained from the initial curve cluster, as the first curve and the second curve respectively; the trend change difference information between the first curve, the second curve and the first target curve is determined, wherein the first target curve is the curve at the cluster center corresponding to the initial curve cluster; the vertical coordinate interval range difference and the horizontal coordinate interval range difference between the first curve, the second curve and the first target curve are determined; the curve cluster whose corresponding cluster distance with the initial curve cluster is less than the target cluster is determined to obtain at least one curve cluster; the at least one curve cluster is determined to correspond to at least one second target curve of the at least one second target curve; for each of the at least one second target curve, determining the curve difference distances between the first curve, the second curve and the second target curve to obtain a first difference distance and a second difference distance; determining the curve difference distances between the first curve, the second curve and the first target curve to obtain a third difference distance and a fourth difference distance; in response to determining that the trend change difference information satisfies the first difference condition, the ordinate interval range difference and the abscissa interval range difference satisfy the second difference condition, the third difference distance is less than at least one first difference distance, and the fourth difference distance is less than at least one second difference distance, generating confirmation information characterizing that the initial curve cluster is correct;Generate a curve cluster according to the obtained confirmation information set; According to the data trend change curve and the obtained at least one target adjustment data trend change curve set, value risk information for the target object is generated.

2. The method according to claim 1, characterized in that The method further comprises: In response to determining that the value risk information indicates that there is a risk, the value risk information, the object information corresponding to the target object, the product value flow data sequence and the product value status information are packaged to generate object packaging data; Importing the object packaging data into the storage space of the target storage device; Using the pre-set space detection process, real-time detection is performed to determine whether the data storage bytes corresponding to the target storage space have changed; In response to determining the change, the object packaging data is marked, and warning information for the object packaging data is sent to a related value risk monitoring user terminal.

3. A value risk information generating device, comprising: An acquisition unit is configured to acquire a product value circulation data sequence and corresponding product value status information for a target value product corresponding to a target object and in a target historical time period; The execution unit is configured to perform the following generation steps for each similar object in the similar object set corresponding to the target object: according to the product value status information, data interception is performed on the historical product value circulation data sequence corresponding to the similar object to generate at least one historical product value circulation data subsequence, wherein the corresponding duration of the historical product value circulation data sequence is greater than or equal to the corresponding duration of the target historical time period; determine the data trend change curve corresponding to the product value circulation data sequence and at least one similar data trend change curve corresponding to the at least one historical product value circulation data subsequence; and the data trend change curve is determined within a predetermined time period. Performing curve prediction extension to generate an extended data trend change curve, and adjusting the curve cross-sectional length of a similar data trend change curve in the at least one similar data trend change curve to generate at least one adjusted data trend change curve, wherein the curve prediction extension of the data trend change curve within a predetermined time period before and after to generate an extended data trend change curve, and adjusting the curve cross-sectional length of a similar data trend change curve in the at least one similar data trend change curve to generate at least one adjusted data trend change curve, comprises: determining a corresponding vertical coordinate set of the data trend change curve under a predetermined horizontal coordinate set in a target coordinate system, and determining the corresponding horizontal coordinate set of the data trend change curve under the predetermined vertical coordinate set in the target coordinate system; combining the predetermined horizontal coordinate set and the vertical coordinate set to generate a first coordinate set, and combining the horizontal coordinate set and the predetermined vertical coordinate set to generate a second coordinate set; determining the concave point coordinate set and the convex point coordinate set in the data trend change curve; combining the first coordinate set, the second coordinate set, the concave point coordinate set and the convex point coordinate set in the order in which the horizontal coordinates are sorted in sequence to generate a first coordinate sequence; determining the historical time period to be predicted and the future time period to be predicted for the data trend change curve; according to the A first coordinate sequence, using a historical product value flow information prediction model to generate a first historical product value flow prediction information sequence for the historical time period to be predicted; generating a first historical prediction data trend change curve for the first historical product value flow prediction information sequence; generating a second coordinate sequence for the first historical prediction data trend change curve; based on the first coordinate sequence and the second coordinate sequence, using a future product value flow information prediction model to generate a first future product value flow prediction information sequence for the future time period to be predicted; generating a first future prediction data trend change curve for the first future product value flow prediction information sequence;The extended data trend change curve is generated according to the first historical forecast data trend change curve, the data trend change curve and the first future forecast data trend change curve, wherein the extended data trend change curve is generated according to the first historical forecast data trend change curve, the data trend change curve and the first future forecast data trend change curve, including: according to the first coordinate sequence, using the future product value flow information prediction model, generating a second future product value flow prediction information sequence for the future time period to be predicted; generating a second future prediction data trend change curve for the second future product value flow prediction information sequence; generating a second future prediction data trend change curve for the second future prediction data a third coordinate sequence of a trend change curve; based on the first coordinate sequence and the third coordinate sequence, using the historical product value flow information prediction model, generate a second historical product value flow prediction information sequence for the historical time period to be predicted; generate a second historical prediction data trend change curve for the second historical product value flow prediction information sequence; determine the model precision information corresponding to the future product value flow information prediction model and the model precision information corresponding to the historical product value flow information prediction model, as the first model precision information and the second model precision information, respectively; generate the first curve corresponding to the first historical prediction data trend change curve based on the first model precision information and the second model precision information The importance of the first curve, the importance of the second curve corresponding to the second historical forecast data trend change curve, the importance of the third curve corresponding to the first future forecast data trend change curve, and the importance of the fourth curve corresponding to the second future forecast data trend change curve; according to the importance of the first curve, the importance of the second curve, the importance of the third curve, the importance of the fourth curve, the first historical forecast data trend change curve, the second historical forecast data trend change curve, the first future forecast data trend change curve, and the second future forecast data trend change curve, the extended data trend change curve is generated, wherein the importance of the first curve, the importance of the second curve, the importance of the third curve, the importance of the fourth curve, the first historical forecast data trend change curve, the second historical forecast data trend change curve, the first future forecast data trend change curve, and the second future forecast data trend change curve are used to generate the extended data trend change curve. , the third curve importance, the fourth curve importance, the first historical forecast data trend change curve, the second historical forecast data trend change curve, the first future forecast data trend change curve, the second future forecast data trend change curve, to generate the extended data trend change curve, including: determining a fourth coordinate sequence for the second historical forecast data trend change curve and a fifth coordinate sequence for the first future forecast data trend change curve; multiplying each coordinate in the second coordinate sequence by the first curve importance to obtain a first corresponding coordinate sequence; multiplying each coordinate in the fourth coordinate sequence by the second curve importance to obtain a second corresponding coordinate sequence;Add the coordinate values ​​of the first phase coordinate in the first phase coordinate sequence and the second phase coordinate in the second phase coordinate sequence to obtain a first added coordinate sequence; multiply each coordinate in the fifth coordinate sequence by the importance of the third curve to obtain a third phase coordinate sequence; multiply each coordinate in the third coordinate sequence by the importance of the fourth curve to obtain a fourth phase coordinate sequence; add the coordinate values ​​of the third phase coordinate in the third phase coordinate sequence and the fourth phase coordinate in the fourth phase coordinate sequence to obtain a second added coordinate sequence; generate a third historical prediction data trend change curve for the first added coordinate sequence and a third future prediction data trend change curve for the second added coordinate sequence. The method comprises the steps of: measuring a data trend change curve; splicing the data trend change curve, the third historical prediction data trend change curve and the third future prediction data trend change curve to generate a spliced ​​curve as the third historical prediction data trend change curve; screening out a target adjusted data trend change curve whose curve change similarity degree with the extended data trend change curve meets a target preset condition from the at least one adjusted data trend change curve, and obtaining at least one target adjusted data trend change curve, wherein the target adjusted data trend change curve whose curve change similarity degree with the extended data trend change curve meets a target preset condition is screened out from the at least one adjusted data trend change curve, and obtaining At least one target adjustment data trend change curve comprises: generating an enhanced data trend change curve set for the extended data trend change curve, wherein the enhanced data trend change curve set comprises: a positive enhanced data trend change curve set and a negative enhanced data trend change curve set; performing curve combination on the at least one adjustment data trend change curve, the enhanced data trend change curve set and the extended data trend change curve to generate a change curve set; performing curve clustering on each curve in the change curve set to generate a curve cluster set; screening out a target adjustment data trend change curve in the same curve cluster as the extended data trend change curve from the at least one adjustment data trend change curve to obtain at least one target The method comprises the following steps: adjusting the trend change curve of the data, wherein the curves in the change curve set are clustered to generate a curve cluster set, including: determining a curve index information group corresponding to each change curve in the change curve set; clustering the curves in the change curve set according to the obtained curve index information group set to generate an initial curve cluster set; for each initial curve cluster in the initial curve cluster set, performing the following verification steps: randomly obtaining two curves from the initial curve cluster, respectively as a first curve and a second curve; determining trend change difference information between the first curve, the second curve and a first target curve, wherein the first target curve is a curve at the cluster center corresponding to the initial curve cluster;Determine the vertical coordinate interval range difference and the horizontal coordinate interval range difference between the first curve, the second curve and the first target curve; determine the curve cluster whose corresponding cluster distance between the initial curve cluster is less than the target cluster, and obtain at least one curve cluster; determine at least one second target curve corresponding to the at least one curve cluster; for each second target curve in the at least one second target curve, determine the curve difference distance between the first curve, the second curve and the second target curve, and obtain a first difference distance and a second difference distance; determine the curve difference distance between the first curve, the second curve and the first target curve, and obtain a third difference distance and a fourth difference distance; in response to determining that the trend change difference information satisfies the first difference condition, the vertical coordinate interval range difference and the horizontal coordinate interval range difference meet the second difference condition, the third difference distance is less than at least one first difference distance, and the fourth difference distance is less than at least one second difference distance, generate confirmation information characterizing that the initial curve cluster is correct; generate a curve cluster set according to the obtained confirmation information set; A generating unit is configured to adjust a data trend change curve set according to the data trend change curve and at least one obtained target, and generate value risk information for the target object.

4. An electronic device comprising: one or more processors; a storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1-2.

5. A computer readable medium having a computer program stored thereon, wherein: When the program is executed by a processor, the method according to any one of claims 1 to 2 is implemented.

Citation Information

Patent Citations

  • Information generation method and device, electronic equipment and computer readable medium

    CN116882591A

  • Risk identification method, device and equipment and readable storage medium

    CN116957329A