Investment product data expansion method and system, electronic equipment and storage medium

Abstract

The embodiment of the invention provides an investment product data expansion method and system, electronic equipment and a storage medium, and relates to the technical field of computer application. The investment product data expansion method comprises the following steps: extracting key features of value representation data of each investment product in a plurality of investment products; calculating the similarity between the key feature corresponding to the target investment product and the key feature corresponding to each other investment product; taking other investment products corresponding to the similarity meeting a preset similarity condition as candidate investment products; calculating a value change parameter of the value representation data of the candidate investment products in a second time range; and calculating predicted value representation data of the target investment product in the second time range based on the value representation data and the value change parameter of the target investment product. The accuracy of data expansion of investment products can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer application, and in particular, to a data expansion method and system for investment products, an electronic device, and a storage medium. BACKGROUND

[0002] Some investment products have relatively little relevant data because they were established relatively late, and so it is difficult to perform investment analysis and decision-making for these investment products based on the existing relevant data. Therefore, in order to better perform investment analysis and decision-making, it is necessary to expand the relevant data of these investment products. In related technologies, artificial operation and simple mathematical models are mainly relied on, and artificial use of simple mathematical models, such as linear interpolation or extrapolation, is used to expand the relevant data of investment products. This method only uses the data of investment products for mathematical operations, which can result in low accuracy of data expansion for investment products. SUMMARY

[0003] The purpose of the embodiments of the present application is to provide a data expansion method and system for investment products, an electronic device, and a storage medium, to improve the accuracy of data expansion for investment products. The specific technical solutions are as follows:

[0004] In a first aspect, a data expansion method for investment products is provided, comprising:

[0005] Obtaining value representation data of a plurality of investment products including a target investment product, the value representation data being used to represent the value of an investment product; the value representation data of the target investment product including a sequence of a plurality of value representation values within a first time range;

[0006] Extracting key features of the value representation data of each investment product in the plurality of investment products;

[0007] Calculating the similarity between the key features corresponding to the target investment product and the key features corresponding to each other investment product, wherein the other investment product includes an investment product other than the target investment product in the plurality of investment products;

[0008] Taking the other investment product corresponding to the similarity satisfying a preset similarity condition as a candidate investment product;

[0009] Calculating a value change parameter of the value representation data of the candidate investment product within a second time range;

[0010] Based on the value representation data of the target investment product and the value change parameter, calculating predicted value representation data of the target investment product within the second time range;

[0011] The value representation data of the target investment product and the predicted value representation data are taken as the extended value representation data corresponding to the target investment product.

[0012] Optionally, after the predicted value representation data of the target investment product in the second time range is calculated based on the value representation data of the target investment product and the value change parameter, the method further comprises:

[0013] The feature indicators corresponding to the value representation data of the target investment product and the predicted value representation data are calculated respectively.

[0014] The value representation data of the target investment product and the predicted value representation data are taken as the extended value representation data corresponding to the target investment product, which comprises:

[0015] In the case where the difference between the feature indicators corresponding to the value representation data of the target investment product and the predicted value representation data is not less than a first preset value, the value representation data of the target investment product and the predicted value representation data are taken as the extended value representation data corresponding to the target investment product.

[0016] Optionally, the key features include key features of multiple feature types.

[0017] The similarity between the key features corresponding to the target investment product and the key features corresponding to each other investment product is calculated, which comprises:

[0018] For the target investment product and each other investment product, the key features of each feature type are weighted and summed based on the influence weight corresponding to each feature type to obtain weighted key features.

[0019] The similarity between the weighted key features corresponding to the target investment product and the weighted key features corresponding to each other investment product is calculated.

[0020] Optionally, after the predicted value representation data of the target investment product in the second time range is calculated based on the value representation data of the target investment product and the value change parameter, the method further comprises:

[0021] After the real value representation data of the target investment product in the second time range is obtained, the real value representation data is compared with the predicted value representation data.

[0022] In a case where a difference between the real value representation data and the predicted value representation data is not less than a second preset value, a first data expansion related parameter is adjusted, the first data expansion related parameter being a parameter used in subsequent expansion of value representation data of the investment product.

[0023] Optionally, before the similarity between the key feature of the target investment product and the key feature of each other investment product is calculated, the method further comprises:

[0024] A plurality of historical data are acquired, the historical data including value representation data of a plurality of sample investment products including a target sample investment product, the value representation data of the target sample investment product including a plurality of value representation values in a third time range and a plurality of value representation values in a fourth time range;

[0025] A key feature of the value representation data of each sample investment product is extracted;

[0026] The similarity between the key feature of the target sample investment product and the key feature of each other sample investment product is calculated, wherein the other sample investment product includes an investment product other than the target sample investment product in the plurality of investment products;

[0027] The other sample investment product corresponding to a similarity satisfying a preset similarity condition is taken as a candidate sample investment product;

[0028] A value change parameter of the value representation data of the candidate sample investment product in the fourth time range is calculated;

[0029] Based on the plurality of value representation values in the third time range included in the value representation data of the target sample investment product and the value change parameter of the value representation data of the candidate sample investment product in the fourth time range, predicted value representation data of the target sample investment product in the fourth time range is calculated;

[0030] The calculated predicted value representation data of the target sample investment product in the fourth time range is verified by using the plurality of value representation values in the fourth time range included in the value representation data of the target sample investment product;

[0031] Based on a verification result, a second data expansion related parameter is adjusted.

[0032] Optionally, after the value representation data of the target investment product and the predicted value representation data are taken as the expanded value representation data corresponding to the target investment product, the method further comprises:

[0033] updating the value representation data of the target investment product as the extended value representation data corresponding to the target investment product.

[0034] Optionally, after the value representation data of the target investment product and the predicted value representation data are updated as the extended value representation data corresponding to the target investment product, the method further comprises:

[0035] displaying a user interaction interface;

[0036] receiving a query parameter input through the user interaction interface;

[0037] searching a target result corresponding to the query parameter from the extended value representation data corresponding to the plurality of target investment products;

[0038] displaying the target result.

[0039] In a second aspect, an investment product data extension system is provided, comprising:

[0040] an acquisition module configured to acquire value representation data of a plurality of investment products including a target investment product, the value representation data being used to represent the value of an investment product, and the value representation data of the target investment product comprising a sequence of a plurality of value representation values within a first time range;

[0041] a feature extraction module configured to extract key features of the value representation data of each investment product in the plurality of investment products;

[0042] a calculation module configured to calculate the similarity between the key features corresponding to the target investment product and the key features corresponding to each other investment product, wherein the other investment product comprises an investment product in the plurality of investment products other than the target investment product, to take the other investment product corresponding to a similarity satisfying a preset similarity condition as a candidate investment product, to calculate a value change parameter of the value representation data of the candidate investment product within a second time range, and to calculate predicted value representation data of the target investment product within the second time range based on the value representation data of the target investment product and the value change parameter;

[0043] a data extension module configured to update the value representation data of the target investment product and the predicted value representation data as the extended value representation data corresponding to the target investment product.

[0044] In a third aspect, an electronic device is provided, comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus.

[0045] Memory for storing computer programs;

[0046] The processor is configured to implement any of the method steps described in the first aspect when executing a program stored in the memory.

[0047] In a fourth aspect, a computer-readable storage medium is provided, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, any method step described in the first aspect is implemented.

[0048] An embodiment of the present invention further provides a computer program product comprising instructions, which, when executed on a computer, enables the computer to execute any of the above-mentioned methods for expanding the data of investment products.

[0049] Beneficial effects of the embodiments of the present invention:

[0050] In an embodiment of the present invention, value representation data of multiple investment products, including a target investment product, is obtained, key features of the value representation data of each investment product in the multiple investment products are extracted, and similarities between the key features corresponding to the target investment product and the key features corresponding to each other investment product are calculated to indicate the correlation between the target investment product and each other investment product. Further, other investment products corresponding to similarities that meet a preset similarity condition are selected as candidate investment products, and based on the value representation data and value change parameters of the target investment product, predicted value representation data of the target investment product within a second time range is calculated; the value representation data of the target investment product and the predicted value representation data are used as the expanded value representation data corresponding to the target investment product, thereby implementing data expansion of the value representation data of the target investment product using the value representation data of the candidate investment products. By extracting key features of the value representation data of multiple investment products and calculating similarities, candidate investment products can be more accurately identified, providing a more accurate data source for data expansion of the target investment product, and improving the accuracy of investment product data expansion.

[0051] Of course, it is not necessary to achieve all of the advantages described above simultaneously in order to implement any product or method of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other embodiments can also be obtained based on these drawings.

[0053] Figure 1 A first flow chart of the data expansion method for investment products provided in an embodiment of the present invention;

[0054] Figure 2 A flowchart for calculating the similarity between investment products is provided for the embodiments of the present application.

[0055] Figure 3 A second flowchart of the data augmentation method for investment products is provided for the embodiments of the present application.

[0056] Figure 4 A flowchart for verifying the predicted value representation data is provided for the embodiments of the present application.

[0057] Figure 5 Another flowchart for verifying the predicted value representation data is provided for the embodiments of the present application.

[0058] Figure 6 A schematic diagram for interacting with the predicted value representation data is provided for the embodiments of the present application.

[0059] Figure 7 A structural schematic diagram of the data augmentation system for investment products is provided for the embodiments of the present application.

[0060] Figure 8 A structural schematic diagram of the electronic device is provided for the embodiments of the present application. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art based on the present application belong to the scope of protection of the present application.

[0062] With reference to Figure 1 The embodiments of the present application provide a data augmentation method for investment products, comprising:

[0063] S11, acquiring value representation data of a plurality of investment products including a target investment product, the value representation data being used to represent the value of the investment product; the value representation data of the target investment product including a sequence of a plurality of value representation values in a first time range;

[0064] S12, extracting key features of the value representation data of each investment product in the plurality of investment products;

[0065] S13, calculating the similarity between the key features corresponding to the target investment product and the key features corresponding to each other investment product, wherein the other investment products include investment products other than the target investment product in the plurality of investment products;

[0066] S14, selecting other investment products whose similarities satisfy the preset similarity condition as candidate investment products;

[0067] S15, calculating a value change parameter of the value representation data of the candidate investment product within a second time range;

[0068] S16, calculating predicted value representation data of the target investment product within a second time range based on the value representation data and the value change parameter of the target investment product;

[0069] S17, taking the value representation data of the target investment product and the predicted value representation data as the expanded value representation data corresponding to the target investment product.

[0070] In an embodiment of the present invention, value representation data of multiple investment products, including a target investment product, is obtained, key features of the value representation data of each investment product in the multiple investment products are extracted, and similarities between the key features corresponding to the target investment product and the key features corresponding to each other investment product are calculated to indicate the correlation between the target investment product and each other investment product. Further, other investment products corresponding to similarities that meet a preset similarity condition are selected as candidate investment products, and based on the value representation data and value change parameters of the target investment product, predicted value representation data of the target investment product within a second time range is calculated; the value representation data of the target investment product and the predicted value representation data are used as the expanded value representation data corresponding to the target investment product, thereby implementing data expansion of the value representation data of the target investment product using the value representation data of the candidate investment products. By extracting key features of the value representation data of multiple investment products and calculating similarities, candidate investment products can be more accurately identified, providing a more accurate data source for data expansion of the target investment product, and improving the accuracy of investment product data expansion.

[0071] The data expansion method for investment products provided in the embodiment of the present invention can be applied to electronic devices. Specifically, the electronic device can be a server, for example, an internal server of an enterprise.

[0072] In S11 , for a target investment product, value representation data of the target investment product is acquired, and value representation data of other investment products other than the target investment product is acquired.

[0073] The investment product may be any form of investment product in actual application, and the embodiment of the present invention does not limit this. For example, the investment product may be a private equity fund.

[0074] The value representation of the investment product refers to a value representation used to represent the value of the investment product. For example, when the investment product is a private fund, the value representation of the investment product can be the net value. The value representation data of the investment product can be a sequence of value representations, such as a sequence of net values.

[0075] The first time range refers to a time range of value representations included in the target investment product. The value representation data of the target investment product includes a sequence of multiple value representations in the first time range, and specifically can be understood as including a sequence of value representations of each day in the first time range. For example, when the first time range is from January 1 to March 31, the value representation data of the target investment product includes a sequence of value representations of each day from January 1 to March 31.

[0076] In an implementable manner, the initial value representation data of multiple investment products including the target investment product can be collected first, and the collected initial value representation data can be preprocessed first. The preprocessing process can also be understood as cleaning the collected initial value representation data. This process can also be referred to as a data mining process. The cleaning can include removing outliers, filling missing values, data standardization, and the like, so as to ensure data quality. On this basis, the value representation data after preprocessing is executed in S12 in the embodiment of the application. The preprocessing manner is not limited in the embodiment of the application, and the manner of preprocessing data in related explanations can be used.

[0077] The preprocessing step in the embodiment of the application effectively improves the data quality and provides accurate input for data expansion. Moreover, the automatic data collection and preprocessing process reduces the need for manual operation, and significantly improves the speed and efficiency of data processing.

[0078] In S12, the key features can be used to represent the attributes of the value representation data. For example, the key features can include product type, yield, volatility, Sharpe ratio, and the like.

[0079] In an implementable manner, the key features can be extracted by a neural network or the like. For example, a neural network is pre-trained, the input of the neural network is the value representation data, that is, a sequence of multiple value representations, and the output of the neural network is the key features of the value representation data. The training of the neural network can use the model training manner in related technologies, such as supervised model training or unsupervised model training, and the like, and the embodiment of the application does not limit this.

[0080] In S13, a machine learning algorithm can be used to calculate the similarity between the key features of the target investment product and the key features of each of the other investment products. For example, a neural network can be used to calculate the similarity. For example, a neural network can be pre-trained, and the input of the neural network is the key features of the target investment product and the key features of one of the other investment products; and the output of the neural network is the similarity between the key features of the target investment product and the key features of one of the other investment products.

[0081] In one implementation, in the process of calculating the similarity between the key features of the target investment product and the key features of one of the other investment products, the key features of the target investment product and the key features of one of the other investment products can be first represented in a vector form, and then the similarity between the vector representation of the key features of the target investment product and the vector representation of the key features of one of the other investment products is calculated, and the similarity is taken as the similarity between the key features of the target investment product and the key features of one of the other investment products.

[0082] In an optional embodiment, the other investment products whose value representation data time range is greater than the first time range of the target investment product can be selected, and for the selected other investment products, the similarity between the key features of the target investment product and the key features of the selected other investment products is calculated.

[0083] For example, the value representation data time range is greater than the first time range of the target investment product, and specifically, the value representation data includes the value representation values in the first time range and the value representation values in a second time range. The second time ranges corresponding to different other investment products can be the same or different. The second time range is different from the first time range.

[0084] In this case, in S11, only the value representation data of the other investment products whose data time range is greater than the first time range of the target investment product can be obtained, and in S12, in addition to extracting the key features of the value representation data of the target investment product and the key features of the value representation data of the other investment products whose data time range is greater than the first time range of the target investment product.

[0085] In an optional embodiment, in the process of calculating the similarity, a time interval for which the similarity is calculated can also be selected. The time interval for which the similarity is calculated means that in the process of calculating the similarity, the key features of the value representation data corresponding to the time interval in the value representation data of the investment product are extracted, and the similarity is calculated based on the key features of the value representation data corresponding to the time interval in the value representation data of the investment product.

[0086] Specifically, an overlapping interval of a time range included in the value representation data of the target investment product and a time range included in the value representation data of the other investment product can be selected as the time interval for which the similarity is calculated. Alternatively, a partial range of the overlapping interval can also be selected as the time interval for which the similarity is calculated.

[0087] For example, the value representation data of the target investment product includes a sequence of multiple value representation values in a first time range, and the value representation data of the other investment product includes a sequence of multiple value representation values in the first time range and multiple value representation values in a second time range. The first time range can be selected as the time interval for which the similarity is calculated. Alternatively, a partial range in the first time range can also be selected as the time interval for which the similarity is calculated.

[0088] In an implementation manner, an interval parameter of the time interval for which the similarity is calculated can be preset, for example, a duration of the time interval. In the process of selecting the time interval for which the similarity is calculated, the time interval for which the similarity is calculated that meets the interval parameter can be selected based on the interval parameter.

[0089] In an optional embodiment, the key features can include multiple key features of multiple feature types.

[0090] In this case, as shown in Figure 2 S13 can include:

[0091] S21, for the target investment product and each other investment product, weighting the key features of each feature type based on the influence weight corresponding to each feature type to obtain weighted key features;

[0092] S22, calculating the similarity between the weighted key features corresponding to the target investment product and the weighted key features corresponding to each other investment product.

[0093] The influence weight can be understood as the weight of the feature influencing the similarity, and can be determined according to actual requirements or experience, etc. The influence weights corresponding to different feature types can be the same or different.

[0094] This manner can support giving different weights to the key features of different feature types, adaptively adjusting the consideration of the feature types in the process of calculating the similarity, and can improve the accuracy of the similarity calculated based on the key features of the investment products, and more accurately represent the correlation between the investment products.

[0095] In S14, the similarity between the key features of the target investment product and the key features of each other investment product is used to represent the similarity between the target investment product and each other investment product. The embodiment of the present application selects the candidate investment product for the target investment product based on the similarity.

[0096] In one implementation manner, the other investment product corresponding to the preset similarity condition can be the other investment product with the highest similarity between the key features and the key features of the target investment product.

[0097] The similarity between the key features of the target investment product and the key features of each other investment product can be sorted, and then the other product corresponding to the highest similarity is selected as the candidate investment product. In this case, the similarity satisfying the preset similarity condition can be understood as the highest value among all the similarities calculated in S13. In simple terms, the other investment products are sorted according to the correlation, and the other investment product with the highest correlation is selected as the candidate investment product.

[0098] In another implementation manner, the other investment product corresponding to the similarity not less than the preset similarity threshold can be selected as the candidate investment product, wherein the preset similarity threshold can be determined according to actual demand or experience. In this case, the similarity can be understood as the similarity score, and in simple terms, the candidate investment product with high similarity to the target investment product is selected based on the similarity score.

[0099] In one implementation manner, in addition to considering the correlation, the life of the investment product can also be considered in the process of selecting the candidate investment product. Specifically, for each other investment product, the weighted sum of the similarity between the key features of the target investment product and the key features of the other investment product and the life of the other investment product is calculated, and the other investment product corresponding to the maximum weighted sum is selected as the candidate investment product. The life can be the duration of the investment product, which can be calculated from the establishment time, such as the time from the establishment time to the time of obtaining the value representation data of the investment product in S11.

[0100] In the embodiment of the present application, the weighted score combining the similarity and the life can be used to develop personalized data expansion strategies for different investment products, realize personalized processing, and improve the flexibility and adaptability of data processing. Moreover, the investment product with the highest weighted score (maximum weighted sum) is selected as the data source for data expansion of the target investment product, which ensures the effectiveness and reliability of the expanded data.

[0101] After the candidate investment product is selected in S14, the value representation data of the candidate investment product can be used as the data source for expanding the data of the target investment product. In this way, the value representation data of the target investment product can be expanded based on the value representation data of the candidate investment product.

[0102] The expansion of the value representation data of the target investment product based on the value representation data of the candidate investment product can be data fusion of the value representation data of the candidate investment product and the value representation data of the target investment product.

[0103] S15, S16 and S17 are the processes of specific data fusion.

[0104] In S15, the value change parameter represents the change rate of the value representation value. For example, when the value representation value is the net value, the value change parameter can be the yield rate, etc.

[0105] The second time range can be a time range adjacent to the first time range, or in other words, the second time range and the first time range constitute a continuous time period. For example, the first time range represents a plurality of consecutive days, and the second time range also represents a plurality of consecutive days, the first day of the second time range and the last day of the first time range are two consecutive days, or the last day of the second time range and the first day of the first time range are two consecutive days.

[0106] In one implementation manner, for the second time range, a value change parameter corresponding to the second time range is calculated. In this case, the difference between the last value representation value and the first value representation value in the plurality of value representation values in the second time range can be calculated first, and then the ratio of the difference to the number of the plurality of value representation values in the second time range is calculated, and the percentage of the ratio is taken as the value change parameter corresponding to the second time range.

[0107] In another implementation manner, the second time range can be further divided into a plurality of time periods, and for each time period, a value change parameter corresponding to the time period is calculated. The division of the time period can be determined according to actual requirements or experience, etc. For each time period, the difference between the last value representation value and the first value representation value in the time period is calculated, and the percentage of the ratio of the difference to the number of the value representation values in the time period is taken as the value change parameter corresponding to the time period.

[0108] For example, 1 day can be divided into 1 time period, and if the second time range contains the value representation values of each day from April 1 to June 30, the percentage of the difference between the value representation values of two adjacent days (e.g., the difference between the value representation value of the next day and the value representation value of the previous day) is calculated as the value change parameter of the corresponding 1 time period of the two days, such as the percentage of the difference between the value representation value of April 2 and the value representation value of April 1, as the value change parameter of the time period from April 2 to April 1.

[0109] In S16, the value representation data of the target investment product includes a sequence of multiple value representation values in the first time range.

[0110] The value representation data of the candidate investment product includes multiple value representation values in the first time range and multiple value representation values in the second time range.

[0111] For example, the first time range is from January 1 to March 31, and the value representation data of the target investment product includes a sequence of value representation values of each day from January 1 to March 31; the second time range is from April 1 to June 30, and the value representation data of the candidate investment product includes a sequence of value representation values of each day from January 1 to March 31 and value representation values of each day from April 1 to June 30.

[0112] The value change parameter of the value representation data of the candidate investment product in the second time range is calculated, i.e., the value change parameter of the value representation data of the candidate investment product in the time range from April 1 to June 30 is calculated, and according to the calculated value change parameter of the time range from April 1 to June 30 and the value representation values of each day from January 1 to March 31 of the target investment product, the value representation values of the target investment product in the time range from April 1 to June 30 are calculated.

[0113] In one implementation, if the value change parameter corresponding to the second time range is calculated in S15, the last value representation value in the first time range, such as the value representation value of the last day in the consecutive days represented in the first time range, is taken as an initial value, and the value representation value of the first day in the second time range is calculated using the initial value and the value change parameter corresponding to the second time range. Then, the value representation value of the second day in the second time range is calculated using the calculated value representation value of the first day in the second time range and the value change parameter corresponding to the second time range, and so on. The value representation value of the last day in the second time range is calculated using the value representation value of the penultimate day in the second time range and the value change parameter corresponding to the second time range. In this way, the predicted value representation data of the target investment product in the second time range, i.e., the sequence of value representation values of the target investment product in the second time range, is obtained.

[0114] The process of calculating the value representation value of the next day using the value representation value of the previous day and the value change parameter corresponding to the second time range can be the inverse process of calculating the value representation value using two value representation values in S15. For example, the value representation value of the first day in the second time range can be calculated using the initial value (the value representation value of the last day in the consecutive days represented in the first time range) and the value change parameter corresponding to the second time range.

[0115]

[0116] In another implementation, in the process of calculating the value representation of the target investment product on the first day of the second time range by using the initial value (the value representation of the last day in the continuous days represented in the first time range) and the value change parameter corresponding to the second time range, the value change parameter can be the value change parameter obtained in S15 by the following method (first calculate the difference between the last value representation and the first value representation in the plurality of value representations in the second time range, then calculate the ratio of the difference to the number of the plurality of value representations in the second time range, and take the percentage of the ratio as the value change parameter corresponding to the second time range); and in the subsequent process of calculating the value representation of the target investment product on the second day of the second time range by using the calculated value representation of the target investment product on the first day of the second time range and the value change parameter corresponding to the second time range, and so on, the value representation of the target investment product on the last day of the second time range is calculated by using the value representation of the target investment product on the first day of the second time range and the value change parameter corresponding to the second time range, and thus the predicted value representation data of the target investment product in the second time range is obtained, and the value change parameter used is the value change parameter obtained in S15 by the following method (for example, if the second time range includes the value representations of each day from April 1 to June 30, the percentage of the difference between the value representations of adjacent days (for example, the difference between the value representation of the next day and the value representation of the previous day) is calculated as the value change parameter of one time period corresponding to the two days, such as the percentage of the difference between the value representation on April 2 and the value representation on April 1, as the value change parameter of the time period from April 2 to April 1). In this case, it can be understood that the first time range is earlier than the second time range, and the first time range is pushed back.

[0117] In S17, the value representation data and the predicted value representation data of the target investment product are taken as the expanded value representation data corresponding to the target investment product.

[0118] In simple terms, the data expansion in the embodiments of the present application can also be called data extension.

[0119] In the embodiments of the present application, the correlation between investment products is considered, the market performance and investment strategy of the candidate investment product are accurately reflected, and the investment products with high similarity in the market are automatically identified and analyzed as candidate investment products for value representation data expansion. Not only the value trend of the investment product is considered, but also the market correlation, thereby improving the relevance and accuracy of data expansion, and enabling investors and researchers to more accurately evaluate and analyze the long-term performance and investment value of the investment product. In simple terms, the intelligent extension of the value representation data of the investment product based on similarity analysis is realized.

[0120] And, the related art lacks consideration of the characteristics of investment products, and the data augmentation can be personalized for different investment products. In addition, the automated data processing process reduces the dependence on manual operation and significantly improves the efficiency of data processing. At the same time, the data can be updated in real time to ensure that the value representation data augmentation result can timely reflect the latest market dynamics. Further, the value representation data of the investment product is effectively augmented, providing more complete and continuous data sequences for investors and researchers. This not only optimizes the display effect of the data, but also provides solid data support for in-depth investment research and decision-making. In addition, during the data augmentation process, strict compliance with data security and privacy protection principles, such as all data and operations being carried out on the company's intranet, and different users being isolated from each other, access permissions being managed by user roles, meeting the relevant requirements of the Data Security Law, and ensuring that all processing processes are carried out in a safe environment, thereby ensuring the security and reliability of the data.

[0121] One implementation manner can update the value representation data of the target investment product to the augmented value representation data corresponding to the target investment product after S17.

[0122] In this way, the augmented value representation data of the target investment product can be automatically updated, and real-time updating can be realized to ensure the timeliness of the data.

[0123] In addition, a data analysis report can be automatically generated for users to download and share. For example, a data report containing the augmented value representation data corresponding to the target investment product is generated, and an interface is displayed, which can display download, sharing and other options. When detecting that the user clicks the download or sharing option, the data report is sent to the user terminal or sent to the shared address.

[0124] In the embodiment of the application, the predicted value representation data of the target investment product in the second time range is calculated based on the value representation data and the value change parameter of the target investment product, and the value representation data and the predicted value representation data of the target investment product are used as the augmented value representation data corresponding to the target investment product to realize data fusion. The value representation data of the candidate investment product can be effectively selected to be fused with the value representation data of the target investment product to form continuous value representation data, such as forming a continuous net value sequence, thereby improving the continuity and integrity of the augmented value representation data.

[0125] In the embodiment of the present application, by feature extraction and similarity calculation, investment products with high similarity to the target investment product, such as private placement products, are accurately identified, and relevant candidate investment products, such as funds, are provided for data expansion. Moreover, the similarity analysis not only considers the value trend of the investment product, such as the net value trend, but also considers market correlation, thereby enhancing the depth and accuracy of data analysis.

[0126] In an optional embodiment, in order to improve the accuracy of the obtained predicted value representation data of the target investment product in the second time range, such as Figure 3 As shown in FIG. 16, after S16, the method can further include:

[0127] S31, calculating the feature indicators corresponding to the value representation data and the predicted value representation data of the target investment product, respectively.

[0128] In this case, S17 includes:

[0129] S32, in the case where the difference between the feature indicators corresponding to the value representation data and the predicted value representation data of the target investment product is not less than the first preset value, the value representation data and the predicted value representation data of the target investment product are taken as the expanded value representation data corresponding to the target investment product.

[0130] The feature indicators can be the same as the key features described above, or can be different features. For example, the feature indicators can be volatility, Barra style exposure (wide index), and the like.

[0131] The first preset value can be determined according to actual requirements or experience, etc. The difference between the feature indicators corresponding to the value representation data and the predicted value representation data of the target investment product being not less than the first preset value can be understood as the difference between the feature indicators corresponding to the value representation data and the predicted value representation data of the target investment product being large, and in this case, it can be considered that the obtained predicted value representation data is reasonable.

[0132] In simple terms, the trend verification analysis is performed on the fused data, such as calculating some feature indicators of the original part (the value representation data of the target investment product described above) and the fused part (the predicted value representation data), to determine whether the difference before and after fusion is reasonable, so as to ensure the rationality of the expanded data.

[0133] In one possible implementation, the obtained predicted value representation data of the target investment product within the second timeframe can be smoothed to reduce possible abnormal fluctuations. For example, an abnormality threshold can be pre-stored, which indicates the theoretically possible deviation of the value representation value. The obtained predicted value representation data is compared with the abnormality threshold. If the predicted value representation data exceeds the abnormality threshold, the predicted value representation data is smoothed. Specifically, the smoothing method can adopt existing smoothing methods in the related art.

[0134] In one possible implementation, the obtained predicted value representation data can be further verified. Specifically, the predicted value representation data can be compared with historical data, or the predicted value representation data can be presented to market experts, who can verify the accuracy of the predicted value representation data through their professional knowledge.

[0135] The accuracy of the augmentation results is verified by historical data and the knowledge of market experts, ensuring the credibility and accuracy of the data augmentation results.

[0136] In actual application, the target investment product may not have a value representation value in the historical period, but it may be generated after a period of time. Figure 1 The process shown is based on the value representation data and value change parameters of the target investment product to obtain the predicted value representation data of the target investment product within the second time range. After a period of time, the real value representation data of the target investment product within the second time range may be obtained. In this case, the real value representation data of the target investment product within the second time range can be used to verify the data expansion method provided by the embodiment of the present invention, so that when the data expansion method provided by the embodiment of the present invention is used later, data expansion can be performed more accurately. Based on the above embodiment, as Figure 4 As shown, after S16, the following may also be included:

[0137] S41, after obtaining the real value representation data of the target investment product within the second time range, comparing the real value representation data with the predicted value representation data;

[0138] S42: When the difference between the real value representation data and the predicted value representation data is not less than a second preset value, adjust the first data expansion related parameters.

[0139] The first data expansion related parameters are parameters used for subsequent expansion of the value representation data of the investment product.

[0140] The first data augmentation related parameter can include a time interval for which the similarity is calculated, a preset similarity threshold, and an influence weight corresponding to each feature type, etc.

[0141] The second preset value can be determined according to actual needs or experience, etc.

[0142] The difference between the real value representation data and the predicted value representation data being not less than the second preset value can mean that the difference between the real value representation data and the predicted value representation data is relatively large, in which case, the data augmentation related parameter is adjusted. Specifically, the preset similarity threshold can be increased, or the time interval for which the similarity is calculated can be increased, or the influence weight corresponding to any feature type or multiple feature types can be increased or decreased.

[0143] In this embodiment, the key features corresponding to the real value representation data and the predicted value representation data can also be extracted, and the difference between the real value representation data and the predicted value representation data is represented by the difference between the key features corresponding to the real value representation data and the predicted value representation data.

[0144] According to the verification result, the similarity calculation and data fusion related parameters can be adjusted to realize continuous optimization and improvement, improve the accuracy of subsequent data augmentation, and further adapt to market changes.

[0145] On the basis of the above-mentioned embodiments, before the data augmentation method shown in Figure 1 Before the data augmentation method shown in Figure 5 Before calculating the similarity between the key features of the target investment product and the key features of each other investment product, the following steps can also be included:

[0146] S51, obtaining a plurality of historical data, the historical data containing value representation data of a plurality of sample investment products including a target sample investment product, the value representation data of the target sample investment product including a plurality of value representation values in a third time range and a plurality of value representation values in a fourth time range;

[0147] In this embodiment, the plurality of value representation values in the fourth time range included in the value representation data of the target sample investment product can be understood as the true value of the verification.

[0148] S52, extracting key features of the value representation data of each sample investment product;

[0149] S53, calculate the similarity between the key features of the target sample investment product and the key features of each of the other sample investment products, wherein the other sample investment products include investment products other than the target sample investment product in the plurality of investment products;

[0150] S54, take the other sample investment product corresponding to the similarity satisfying the preset similarity condition as a candidate sample investment product;

[0151] S55, calculate a value change parameter of the value representation data of the candidate sample investment product in the fourth time range;

[0152] S56, based on the plurality of value representation values in the third time range included in the value representation data of the target sample investment product and the value change parameter of the value representation data of the candidate sample investment product in the fourth time range, calculate the predicted value representation data of the target sample investment product in the fourth time range;

[0153] S57, verify the predicted value representation data of the target sample investment product in the fourth time range calculated by using the plurality of value representation values in the fourth time range included in the value representation data of the target sample investment product;

[0154] S58, adjust the second data augmentation related parameter based on the verification result.

[0155] Figure 5 The process shown can also be understood as a testing or verification process of the data augmentation related parameters before using the data augmentation method shown. Figure 1 The data augmentation method shown.

[0156] The second data augmentation related parameter is to distinguish between adjusting the second data augmentation related parameter and adjusting the first data augmentation related parameter described above, which is in a different stage. The second data augmentation related parameter is also a data augmentation parameter, which can include the time interval for calculating the similarity, the preset similarity threshold, and the influence weight corresponding to each feature type, etc.

[0157] S51 to S56 are similar to S11 to S16, and in the process of executing S51 to S56, the investment products in S11 to S16 are replaced by sample investment products. For specific execution process, refer to the above S11 to S16, which will not be repeated here.

[0158] The fourth time range is different from the third time range. For example, the fourth time range can be a time range adjacent to the third time range, or in other words, the fourth time range and the third time range constitute a continuous time period. For example, the third time range represents a plurality of consecutive days, and the fourth time range also represents a plurality of consecutive days, the third day of the fourth time range is two days connected with the last day of the third time range, or the last day of the fourth time range is two days connected with the third day of the third time range.

[0159] In an implementation manner, the third time range can be the same as the first time range, and the fourth time range can be the same as the second time range.

[0160] In this embodiment, the data augmentation related parameters can be verified based on the expansion result of the sample investment product, the adaptability of the data augmentation related parameters is improved, so that the accuracy of data augmentation is improved when the target investment product is augmented by using the data augmentation related parameters in the subsequent, and it can be understood that the data augmentation result is optimized.

[0161] In an optional embodiment, as shown in FIG. 17, after S17, the method can further include: Figure 6

[0162] S61, displaying a user interaction interface;

[0163] S62, receiving a query parameter input through the user interaction interface;

[0164] S63, searching a target result corresponding to the query parameter from the expanded value representation data corresponding to the plurality of target investment products;

[0165] S64, displaying the target result.

[0166] The query parameter can include a data time range, a data augmentation result, and the like.

[0167] In addition, the query parameter can also be a parameter corresponding to an interactive option displayed by the user interaction interface. For example, the interactive option can include preview, download, sharing, and the like.

[0168] Displaying the target result can include generating a data analysis report of the target result.

[0169] In this way, the user can easily input the query parameter and the like through the intuitive user interaction interface, and the user experience is improved. In addition, the data analysis report can be automatically generated, the report preparation process is simplified, the work efficiency is improved, and the user's understanding and sharing are facilitated.

[0170] ​Overall, the value representation data of the investment product is effectively expanded, and the efficiency, accuracy and practicability of data processing are significantly improved. Through the similarity analysis algorithm of the above key features, investment products with high correlation can be accurately identified and selected for value representation data expansion, and the efficient data processing flow ensures the accuracy and real-time performance of the value representation data expansion. There are beneficial effects in terms of comprehensiveness, quality improvement, processing efficiency, correlation identification, analysis depth enhancement, personalized processing, data continuity, accuracy verification, user experience improvement and report automation. These effects not only provide strong support for investment research and investment decision-making of investment products, but also provide new ideas and methods for data management and application of investment product industry. Through the embodiments of the present application, investors and researchers can more accurately and efficiently conduct investment research and analysis, creating greater value for investors.

[0171] In one example, the investment product can be a private fund, and the value representation data can be a net value sequence. The embodiments of the present application can solve the problem of short net value data in the private market, improve the availability and practicability of private product net value data. Not only improve the accuracy and correlation of data extension, but also through the automatic and intelligent data processing flow, significantly improve the efficiency and real-time performance of data processing. In addition, the personalized and flexible design of the embodiments of the present application makes the net value data extension result more in line with the actual needs of users, providing strong support for investment analysis and decision-making of private products. For the private fund industry, it is an innovative progress, which not only solves the long-standing problem of the industry, but also provides strong data support and decision-making tools for the future development of private funds. Through the embodiments of the present application, investors and researchers will be able to more accurately and efficiently conduct investment research and analysis, creating greater value for investors.

[0172] Based on the same inventive concept as the above data expansion method of investment product, the embodiments of the present application also provide a data expansion system of investment product, as shown in Figure 7 comprises:

[0173] The acquisition module 701 is configured to acquire value representation data of a plurality of investment products including a target investment product, the value representation data being used to represent the value of the investment product; the value representation data of the target investment product includes a sequence of a plurality of value representation values within a first time range;

[0174] The feature extraction module 702 is configured to extract key features of the value representation data of each investment product in the plurality of investment products;

[0175] The similarity calculation module 703 is configured to calculate similarities between the key features corresponding to the target investment product and the key features corresponding to each of the other investment products, wherein the other investment products include investment products other than the target investment product in the plurality of investment products; take the other investment products corresponding to the similarities satisfying a preset similarity condition as candidate investment products; calculate a value change parameter of the value representation data of the candidate investment products in the second time range; and calculate, based on the value representation data of the target investment product and the value change parameter, the predicted value representation data of the target investment product in the second time range.

[0176] The data expansion module 704 is configured to take the value representation data and the predicted value representation data of the target investment product as the expanded value representation data corresponding to the target investment product.

[0177] Optionally, the system further includes:

[0178] The index calculation module is configured to calculate, after calculating the predicted value representation data of the target investment product in the second time range based on the value representation data of the target investment product and the value change parameter, feature indexes corresponding to the value representation data and the predicted value representation data of the target investment product, respectively.

[0179] The data expansion module 704 is specifically configured to, in a case where a difference between the feature indexes corresponding to the value representation data and the predicted value representation data of the target investment product is not less than a first preset value, take the value representation data and the predicted value representation data of the target investment product as the expanded value representation data corresponding to the target investment product.

[0180] Optionally, the key features include key features of multiple feature types.

[0181] The similarity calculation module 703 is specifically configured to, for the target investment product and each of the other investment products, weight and sum the key features of each feature type based on an influence weight corresponding to each feature type to obtain weighted key features; and calculate similarities between the weighted key features corresponding to the target investment product and the weighted key features corresponding to each of the other investment products.

[0182] Optionally, the system further includes:

[0183] The first adjusting module is configured to, after calculating the predicted value representation data of the target investment product in the second time range based on the value representation data of the target investment product and the value change parameter, and after obtaining the real value representation data of the target investment product in the second time range, compare the real value representation data with the predicted value representation data; and in a case where a difference between the real value representation data and the predicted value representation data is not less than a second preset value, adjust the first data expansion related parameter, which is a parameter used in subsequent expansion of the value representation data of the investment product.

[0184] Optionally, the system further comprises:

[0185] The second adjusting module is configured to, before calculating the similarity between the key feature corresponding to the target sample investment product and the key feature corresponding to each other sample investment product, obtain historical data including value representation data of a plurality of sample investment products including the target sample investment product, the value representation data of the target sample investment product including a plurality of value representation values in a third time range and a plurality of value representation values in a fourth time range; extract the key feature of the value representation data of each sample investment product; calculate the similarity between the key feature corresponding to the target sample investment product and the key feature corresponding to each other sample investment product, wherein the other sample investment product includes an investment product other than the target sample investment product in the plurality of investment products; take the other sample investment product corresponding to a similarity satisfying a preset similarity condition as a candidate sample investment product; calculate a value change parameter of the value representation data of the candidate sample investment product in the fourth time range; calculate predicted value representation data of the target sample investment product in the fourth time range based on the plurality of value representation values in the third time range included in the value representation data of the target sample investment product and the value change parameter of the value representation data of the candidate sample investment product in the fourth time range; verify the predicted value representation data of the target sample investment product in the fourth time range calculated based on the plurality of value representation values in the fourth time range included in the value representation data of the target sample investment product; and adjust the second data expansion related parameter based on the verification result.

[0186] Optionally, the system further comprises:

[0187] The updating module is configured to, after taking the value representation data of the target investment product and the predicted value representation data as the expanded value representation data corresponding to the target investment product, update the value representation data of the target investment product to the expanded value representation data corresponding to the target investment product.

[0188] Optionally, the system further comprises:

[0189] The interaction module is configured to display a user interaction interface after the value representation data of the target investment product and the predicted value representation data are displayed as the extended value representation data corresponding to the target investment product, receive a query parameter input through the user interaction interface, search a target result corresponding to the query parameter from the extended value representation data corresponding to the plurality of target investment products, and display the target result.

[0190] The embodiment of the present application further provides an electronic device, as shown in the figure, comprising a processor 801, a communication interface 802, a memory 803 and a communication bus 804, wherein the processor 801, the communication interface 802 and the memory 803 complete mutual communication through the communication bus 804. Figure 8

[0191] The memory 803 is configured to store a computer program.

[0192] The processor 801 is configured to execute the program stored in the memory 803, and realize the method steps of the investment product data extension method.

[0193] The communication bus of the electronic device mentioned above can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0194] The communication interface is configured to realize communication between the electronic device and other devices.

[0195] The memory can comprise a random access memory (RAM) and can also comprise a non-volatile memory (NVM), for example at least one disk memory. Optionally, the memory can also be at least one storage device located away from the aforementioned processor.

[0196] ​The processor described above can be a general processor, including a central processing unit (CPU), a network processor (NP), etc.; can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0197] In yet another embodiment provided by the present application, a computer readable storage medium is provided, and the computer readable storage medium stores a computer program. The computer program is executed by a processor to implement the steps of the data expansion method of any of the investment products.

[0198] In yet another embodiment provided by the present application, a computer program product is provided, and the computer program product includes instructions. When the computer program product is executed on a computer, the computer is caused to perform the data expansion method of any of the investment products in the above embodiments.

[0199] In the above embodiments, the implementation can be achieved by software, hardware, firmware or any combination thereof, entirely or partially. When the implementation is achieved by software, the implementation can be achieved in the form of a computer program product, entirely or partially. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the flow or function described in the embodiments of the present application is generated, entirely or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer readable storage medium or transferred from one computer readable storage medium to another computer readable storage medium, for example, the computer instructions can be transferred from one website, computer, server or data center to another website, computer, server or data center through a wired (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. integrated with one or more available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid state disk (SSD)), etc.

[0200] It is to be noted that, in the present document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily implying any actual relationship or order between such entities or actions. Also, the terms "comprises", "comprising", or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the presence of additional identical elements in the process, method, article, or apparatus that comprises the element.

[0201] Each of the embodiments in the present specification is described in a related manner, and the same or similar parts between the embodiments can be mutually referred to. Each of the embodiments focuses on the difference from other embodiments. In particular, for the system, electronic device, computer-readable storage medium, and computer program product embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the part of the description of the method embodiments.

[0202] The preferred embodiments of the present application are described above with reference to the drawings, but the present application is not limited to the above examples. Any modification, equivalent replacement, improvement and the like within the spirit and principle of the present application are included in the scope of the present application.

Claims

1. A data expansion method for investment products, characterized in that: include: Acquiring value representation data of a plurality of investment products including a target investment product, wherein the value representation data is used to represent the value of the investment products; the value representation data of the target investment product includes a sequence of a plurality of value representation values ​​within a first time range; extracting key features of the value representation data of each of the plurality of investment products; Calculating similarities between the key features corresponding to the target investment product and the key features corresponding to each other investment product, wherein the other investment products include investment products other than the target investment product among the multiple investment products; Other investment products whose similarity meets the preset similarity conditions are selected as candidate investment products; Calculating a value change parameter of the value representation data of the candidate investment product within a second time range; Calculating predicted value representation data of the target investment product within the second time range based on the value representation data of the target investment product and the value change parameter; The value representation data of the target investment product and the predicted value representation data are used as the expanded value representation data corresponding to the target investment product.

2. The data expansion method for investment products according to claim 1, characterized in that: After calculating the predicted value representation data of the target investment product within the second time range based on the value representation data of the target investment product and the value change parameter, the method further includes: Calculating characteristic indicators corresponding to the value representation data of the target investment product and the predicted value representation data respectively; The step of using the value representation data of the target investment product and the predicted value representation data as the expanded value representation data corresponding to the target investment product includes: When the difference between the characteristic indicators corresponding to the value representation data of the target investment product and the predicted value representation data is not less than a first preset value, the value representation data of the target investment product and the predicted value representation data are used as the expanded value representation data corresponding to the target investment product.

3. The data expansion method for investment products according to claim 1, characterized in that: The key features include multiple key features of multiple feature types; Calculating the similarity between the key features corresponding to the target investment product and the key features corresponding to each other investment product includes: For the target investment product and each other investment product, based on the impact weight corresponding to each feature type, perform a weighted sum of the key features of each feature type to obtain a weighted key feature; Calculate the similarity between the weighted key features corresponding to the target investment product and the weighted key features corresponding to each other investment product.

4. The data expansion method for investment products according to claim 1, characterized in that: After calculating the predicted value representation data of the target investment product within the second time range based on the value representation data of the target investment product and the value change parameter, the method further includes: After obtaining the real value representation data of the target investment product within the second time range, comparing the real value representation data with the predicted value representation data; When the difference between the real value representation data and the predicted value representation data is not less than a second preset value, adjust the first data expansion related parameters, which are used as parameters for subsequent expansion of the value representation data of the investment product.

5. The data expansion method for investment products according to claim 1, characterized in that: Before calculating the similarity between the key features corresponding to the target investment product and the key features corresponding to each other investment product, the method further includes: Acquire a plurality of historical data, the historical data including value representation data of a plurality of sample investment products including a target sample investment product, the value representation data of the target sample investment product including a plurality of value representation values ​​within a third time range and a plurality of value representation values ​​within a fourth time range; Extract the key features of the value representation data of each sample investment product; Calculating similarities between the key features corresponding to the target sample investment product and the key features corresponding to each other sample investment product, wherein the other sample investment products include investment products other than the target sample investment product among the multiple investment products; Other sample investment products whose similarity meets the preset similarity conditions are used as candidate sample investment products; Calculating a value change parameter of the value representation data of the candidate sample investment product within a fourth time range; Calculating predicted value representation data of the target sample investment product within the fourth time range based on a plurality of value representation values ​​within a third time range included in the value representation data of the target sample investment product and a value change parameter of the value representation data of the candidate sample investment product within a fourth time range; Verifying the calculated predicted value representation data of the target sample investment product within the fourth time range by using a plurality of value representation values ​​within the fourth time range included in the value representation data of the target sample investment product; Based on the verification result, the second data expansion related parameters are adjusted.

6. The data expansion method for investment products according to any one of claims 1 to 5, characterized in that: After using the value representation data of the target investment product and the predicted value representation data as the expanded value representation data corresponding to the target investment product, the method further includes: The value representation data of the target investment product is updated to the expanded value representation data corresponding to the target investment product.

7. The data expansion method for investment products according to any one of claims 1 to 5, characterized in that: After using the value representation data of the target investment product and the predicted value representation data as the expanded value representation data corresponding to the target investment product, the method further includes: Display the user interaction interface; receiving query parameters input through the user interaction interface; Searching for a target result corresponding to the query parameter from the expanded value representation data corresponding to the plurality of target investment products; The target result is displayed.

8. A data expansion system for investment products, characterized in that: include: an acquisition module, configured to acquire value representation data of a plurality of investment products including a target investment product, wherein the value representation data is used to represent the value of the investment products; the value representation data of the target investment product comprises a sequence of a plurality of value representation values ​​within a first time range; a feature extraction module, configured to extract key features of the value representation data of each of the plurality of investment products; a calculation module configured to calculate similarities between the key features corresponding to the target investment product and the key features corresponding to each other investment product, wherein the other investment products include investment products among the multiple investment products other than the target investment product; select the other investment products corresponding to the products whose similarities satisfy a preset similarity condition as candidate investment products; calculate a value change parameter of the value representation data of the candidate investment products within a second time range; and calculate predicted value representation data of the target investment product within the second time range based on the value representation data of the target investment product and the value change parameter; The data expansion module is used to use the value representation data of the target investment product and the predicted value representation data as the expanded value representation data corresponding to the target investment product.

9. An electronic device, characterized in that: It includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory for storing computer programs; A processor, configured to implement the method steps described in any one of claims 1 to 7 when executing a program stored in a memory.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method steps according to any one of claims 1 to 7 are implemented.

Images