User behavior simulation test method, device, electronic device and readable medium

Abstract

The embodiments of the present disclosure disclose a user behavior simulation test method, device, electronic device and readable medium. A specific implementation of the method includes: obtaining a user historical feature information set; performing feature division on each user historical feature information in the user historical feature information set to obtain a set of feature information groups after division; generating an order flow simulation operation data sequence set; constructing a user feature signal table set; constructing a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table and a low-frequency information daily integration table; determining the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the user feature signal table set to obtain a user order behavior feature type data set and a user sensitivity sequence; performing a simulated order simulation operation on each user to generate a simulation test result. This implementation can ensure the accuracy of the simulation test results.

Description

Technical Field

[0001] Embodiments of the present disclosure relate to the field of computer technology, and in particular to a user behavior simulation test method, device, electronic device, and readable medium. Background Art

[0002] User behavior simulation testing is convenient for providing technical support for the stability of each securities order. At present, when conducting user behavior simulation testing, the method usually adopted is: for each user, the behavior simulation of his order operation is performed separately.

[0003] However, in practice, it is found that when the above method is used to conduct user behavior simulation testing, the following technical problems often occur:

[0004] First, in reality, each user is easily affected by other users and the order market during the order operation process, which leads to low accuracy of the simulation results of each user's order operation behavior, and further makes it difficult to provide users with suitable order information.

[0005] Second, when conducting simulation tests on a large number of users at the same time, the amount of data corresponding to each user is large, and the data corresponds to a large number of user behavior characteristics, which makes the data dimension high, thus requiring more computing resources to be consumed during the simulation test;

[0006] Third, due to the low accuracy of simulation test results, it is difficult to provide users with more appropriate order change information.

[0007] 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

[0008] 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.

[0009] Some embodiments of the present disclosure propose a user behavior simulation test method, apparatus, electronic device, and readable medium to solve one or more of the technical problems mentioned in the above background technology section.

[0010] In a first aspect, some embodiments of the present disclosure provide a user behavior simulation test method, the method comprising: obtaining a user historical feature information set, wherein each user historical feature information in the user historical feature information set corresponds to a user; performing feature division on each user historical feature information in the user historical feature information set to obtain a set of divided feature information groups; performing order behavior decision simulation on each divided feature information in each divided feature information group in the divided feature information group set to generate an order flow simulation operation data sequence set; based on the order flow simulation operation data sequence set, constructing a user feature signal table set; based on the user feature signal table The user-held data set is collected and preset to construct a daily order entry-and-exit comparison table, an intraday order entry-and-exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table; based on the above-mentioned daily order entry-and-exit comparison table, the above-mentioned intraday order entry-and-exit comparison table, the above-mentioned high-frequency information intraday integration table, and the above-mentioned low-frequency information daily integration table, determine the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the above-mentioned user feature signal table set, and obtain the user order behavior feature type data set and the user sensitivity sequence; use the above-mentioned user sensitivity sequence and the above-mentioned user order behavior feature type data set to perform simulated order simulation operations on each user to generate simulation test results.

[0011] In a second aspect, some embodiments of the present disclosure provide a user behavior simulation test device, which includes: an acquisition unit, configured to acquire a user history feature information set, wherein each user history feature information in the above user history feature information set corresponds to a user; a feature division unit, configured to perform feature division on each user history feature information in the above user history feature information set to obtain a set of divided feature information groups; a behavior decision simulation unit, configured to perform order behavior decision simulation on each divided feature information in each divided feature information group in the above divided feature information group set to generate an order flow simulation operation data sequence set; a first construction unit, configured to construct a user feature signal table set based on the above order flow simulation operation data sequence set; and a second construction unit, configured to perform a feature division on each user history feature information in the above user history feature information set to obtain a set of divided feature information groups. The unit is configured to construct a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table and a low-frequency information daily integration table based on the above-mentioned user feature signal table set and a preset user holding data set; the determination unit is configured to determine the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the above-mentioned user feature signal table set based on the above-mentioned daily order entry and exit comparison table, the above-mentioned intraday order entry and exit comparison table, the above-mentioned high-frequency information intraday integration table and the above-mentioned low-frequency information daily integration table, and obtain the user order behavior feature type data set and the user sensitivity sequence; the simulation test unit is configured to use the above-mentioned user sensitivity sequence and the above-mentioned user order behavior feature type data set to perform simulated order simulation operations on each user to generate simulation test results.

[0012] 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 of the above-mentioned first aspect.

[0013] 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 of the above-mentioned first aspect is implemented.

[0014] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the user behavior simulation test method of some embodiments of the present disclosure, the accuracy of the simulation test of each user behavior can be improved, so as to provide users with adaptive order change information. Specifically, the reason for the low accuracy of the order operation behavior simulation result for each user is that each user in reality is easily affected by other users and the order market during the order operation process. Based on this, the user behavior simulation test method of some embodiments of the present disclosure first obtains a user historical feature information set. Among them, each user historical feature information in the above user historical feature information set corresponds to a user. Then, the feature division of each user historical feature information in the above user historical feature information set is performed to obtain a set of feature information groups after division. Here, through feature division, the historical feature information of multiple users can be preliminarily divided into different feature categories. Afterwards, the order behavior decision simulation is performed on each divided feature information in each divided feature information group in the above divided feature information group set to generate an order flow simulation operation data sequence set. Here, through the order behavior decision simulation, the user behavior operation information can be preliminarily simulated according to the user data after feature division. Next, based on the above-mentioned order flow simulation operation data sequence set, a user feature signal table set is constructed. Then, based on the above-mentioned user feature signal table set and the preset user holding data set, a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table are constructed. Here, the situation of mutual influence between users is taken into account. Therefore, by classifying the different characteristics of each user into a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table, the user's behavior characteristics can be decomposed from multiple dimensions. As a result, the influence between different feature dimensions can be greatly avoided, which is convenient for extracting user behavior characteristics. Then, based on the above-mentioned daily order entry and exit comparison table, the above-mentioned intraday order entry and exit comparison table, the above-mentioned high-frequency information intraday integration table, and the above-mentioned low-frequency information daily integration table, the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the above-mentioned user feature signal table set are determined, and the user order behavior feature type data set and user sensitivity sequence are obtained. In practice, the daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table, and the low-frequency information daily integration table are used to determine the behavior characteristic type data of each user from multiple perspectives. Compared with the unified processing of all the information of each user, it is easier to extract accurate user behavior characteristic type data. Finally, using the above user sensitivity sequence and the above user order behavior characteristic type data set, simulated order simulation operations are performed on each user to generate simulation test results. Therefore, based on a more accurate user order behavior characteristic type data set, the accuracy of the simulation test results can be ensured. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] 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.

[0016] Figure 1 is a flow chart of some embodiments of the user behavior simulation test method according to the present disclosure;

[0017] Figure 2 is a schematic diagram of the structure of some embodiments of the user behavior simulation test device according to the present disclosure;

[0018] 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

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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".

[0023] 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.

[0024] With regard to the collection, storage, and use of user personal information (such as user portraits and historical user behaviors) involved in this disclosure, before performing the corresponding operations, the relevant organizations or individuals shall fulfill their obligations, including conducting personal information security impact assessments, fulfilling the obligation to inform the personal information subject, and obtaining the authorization and consent of the personal information subject in advance.

[0025] The present disclosure will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0026] Figure 1 The process 100 of some embodiments of the user behavior simulation test method according to the present disclosure is shown. The user behavior simulation test method comprises the following steps:

[0027] Step 101: Obtain a user's historical feature information set.

[0028] In some embodiments, the execution subject of the user behavior simulation test method can obtain the user historical feature information set by wired or wireless means. Wherein, each user historical feature information in the above user historical feature information set corresponds to a user. The user historical feature information can be user data within a user historical time period. For example, the user data can include but is not limited to at least one of the following: user unique identification, user historical transfer-out order information, user historical transfer-in order information, etc.

[0029] It should be noted that the above-mentioned wireless connection methods may include but are not limited to 3G / 4G connection, WiFi connection, Bluetooth connection, WiMAX connection, Zigbee connection, UWB (ultra wideband) connection, and other wireless connection methods currently known or to be developed in the future.

[0030] Step 102: perform feature division on each user historical feature information in the user historical feature information set to obtain a set of divided feature information groups.

[0031] In some embodiments, the execution subject may perform feature division on each user historical feature information in the user historical feature information set to obtain a set of divided feature information groups. In particular, each user historical feature information may be divided into a preset number of groups according to the data included in the user historical feature information to obtain a set of divided feature information groups.

[0032] As an example, each user's historical feature information may be divided into 1000 features according to the included data, and each feature corresponds to a divided feature information group.

[0033] Step 103 , performing order behavior decision simulation on each divided feature information in each divided feature information group in the divided feature information group set, so as to generate an order flow simulation operation data sequence set.

[0034] In some embodiments, the execution entity may perform order behavior decision simulation on each divided feature information in each divided feature information group in the divided feature information group set to generate an order flow simulation operation data sequence set.

[0035] In some optional implementations of some embodiments, the execution subject performs order behavior decision simulation on each divided feature information in each divided feature information group in the divided feature information group set to generate an order flow simulation operation data sequence set, which may include the following steps:

[0036] The first step is to label each of the divided feature information in each divided feature information group in the above-mentioned divided feature information group set to generate a user behavior feature label group set and a corresponding user holding feature label group set. Among them, the labeling process can be to convert the data included in the divided feature information into preset labels. Here, each user corresponds to a user behavior feature label group and a user holding feature label group. The preset labels may include but are not limited to at least one of the following: order disposal, order extrapolation, order risk, order splitting, order period, order value, order revenue, order fluctuation and other features. The user behavior feature label group can characterize the behavioral characteristics used. The user holding feature label group can characterize the user's order holding (i.e., position) characteristics.

[0037] The second step is to classify the divided feature information group set based on the above-mentioned user behavior feature label group set and the corresponding user holding feature label group set to generate a feature classification information group set. Among them, each feature classification information in the above-mentioned feature classification information group set can also include: user value level value, user account opening years, user holding data turnover rate, user transfer times. Secondly, feature classification can be to use the user behavior feature label group and user holding feature label group of each user to divide the user and the corresponding label into preset feature categories. Here, the preset feature category can include feature categories with a preset number of features (for example, 30). Each feature classification information group can correspond to a feature category.

[0038] The third step is to measure the number of user turnovers and the feature classification information in the feature classification information group from the three dimensions of user value level value, user account opening years, and user holding data turnover rate included in the feature classification information for each feature classification information in each feature classification information group in the above feature classification information set, so as to generate a user behavior parameter distribution matrix in the user behavior parameter distribution matrix set. Among them, the user value level value can represent the value of the orders owned by the user. The user holding data turnover rate can represent the frequency of the user's order buying and selling within a certain period of time (for example, within one year).

[0039] Specifically, first, in the dimension of user value level value, the value level distribution histogram of the user value level value included in each feature classification information can be determined. Then, in the dimension of user account opening years, the account opening years distribution histogram of the user account opening years included in each feature classification information can be determined. After that, in the dimension of user holding data turnover rate, the turnover rate distribution histogram of the user holding data turnover rate included in each feature classification information can be determined. Finally, the above-mentioned value level distribution histogram, the above-mentioned account opening years distribution histogram and the above-mentioned turnover rate distribution histogram are cross-analyzed to obtain the user behavior parameter distribution matrix.

[0040] The fourth step is to determine the user expected value of each user behavior parameter distribution vector in the above user behavior parameter distribution matrix set based on the preset user behavior deviation data, and obtain the user expected value sequence set. Among them, the user behavior deviation data may include the behavior deviation information of each user. Here, each user behavior parameter distribution matrix may be composed of user behavior parameter distribution vectors. During the user behavior simulation test, the user behavior parameter distribution vector and the user behavior deviation data may be input into a pre-trained logistic regression model to obtain the user expected value. The pre-trained logistic regression model may be pre-trained based on the user data. In this way, it is used to simulate the user expected value for input and realize the user behavior simulation test.

[0041] In practice, the user behavior deviation parameter can be pre-constructed into a signal based on the order disclosure data and the transaction data of the user account, and the measurement model can be used to estimate the sensitivity of the user behavior to the signal as the user behavior deviation data. In addition, in actual scenarios, the user expected value can be: the user behavior deviation data and each user behavior parameter distribution vector are sent to the user terminal for the user to determine the user expected value.

[0042] The fifth step is to determine the user daily transaction demand information corresponding to each user behavior parameter distribution vector in the user behavior parameter distribution matrix set based on the above user expected value sequence set and the preset user aggressiveness level data, and obtain the user daily transaction demand information sequence set. Among them, the user aggressiveness level data can characterize the degree of the user's order. For each behavior parameter distribution vector, the user daily transaction demand information of the corresponding user expected value and user aggressiveness level data can be selected from the pre-constructed transaction demand table. Here, the transaction demand table can be a correspondence table established in advance according to different user expected values ​​and user aggressiveness level data. The table may include fields for user expected value, fields for user aggressiveness level data, and fields for user daily transaction demand information. In addition, the user daily transaction demand information may include but is not limited to at least one of the following: demand order number, demand order quantity, etc.

[0043] The sixth step is to perform order flow simulation operations on the users corresponding to each user behavior parameter distribution vector in the above user behavior parameter distribution matrix set based on the pre-acquired intraday public information, order flow demand, order flow demand degree value, user intraday preference data and user intraday flow preference data, so as to generate an order flow simulation operation data sequence set. Among them, the order flow simulation operation is to simulate the process of users buying or selling orders based on the pre-acquired intraday public information, order flow demand, order flow demand degree value, user intraday preference data and user intraday flow preference data. Finally, the simulated order information of each user after simulation can be determined as an order flow simulation operation data sequence set. Here, each order flow simulation operation data sequence can be the simulated order information of each user corresponding to the same feature type.

[0044] Optionally, the user aggression level data may be generated by the following steps:

[0045] The first step is to obtain the order buyer-driven quantity sequence, order seller-driven quantity sequence, order buy order ratio mean sequence and order buy order ratio deviation expectation corresponding to each preset order identifier.

[0046] The second step is to generate a user aggressiveness value based on the order buyer driven quantity sequence and the order seller driven quantity sequence corresponding to each order identifier. The user aggressiveness value can be generated by the following formula:

[0047]

[0048] Among them, Herd(i, t) represents the user's aggressiveness value for the i-th order in the t-th month. i represents the order identification number. t represents the month number. B(i, t) represents the order buyer-driven volume for the i-th order in the t-th month. Here, each order buyer-driven volume in the order buyer-driven volume sequence conforms to the binomial distribution. S(i, t) represents the order seller-driven volume for the i-th order in the t-th month. k represents the number. AF(i, t) represents the preset adjustment item for the i-th order in the t-th month, which represents the expected value of the deviation between the buy order ratio of each order and the average buy order ratio of the order. p i represents the probability of placing the i-th order. t represents the probability of placing an order in month t. t k represents the kth p t probability.

[0049] In the third step, the user aggression value corresponding to each order identifier is determined as user aggression level data.

[0050] Optionally, the user sentiment value can also be used as the user aggression level data. Specifically, the closed order discount rate, market order turnover rate, the number of first public orders, the order yield on the listing day, the user information index value, and the number of new users can be obtained. Then, the closed order discount rate, market order turnover rate, the number of first public orders, the order yield on the listing day, the user information index value, and the number of new users can be weighted and summed to obtain the user aggression. Here, the weights of the weighted summation can be obtained by analyzing the closed order discount rate, market order turnover rate, the number of first public orders, the order yield on the listing day, the user information index value, and the number of new users using the principal component analysis algorithm. In addition, the user aggression level data can also be generated in combination with the user sentiment value and the user aggression level value.

[0051] The above steps 102-103 and their related contents and formulas serve as an inventive point of an embodiment of the present disclosure, and solve the second technical problem mentioned in the background technology: "When performing simulation tests on more users at the same time, the amount of data corresponding to each user is large, and the data corresponds to more user behavior characteristics, which makes the data dimension high, thus resulting in the need to consume more computing resources during the simulation test." The factors that lead to the need to consume more computing resources during the simulation test are often as follows: When performing simulation tests on more users at the same time, the amount of data corresponding to each user is large, and the data corresponds to more user behavior characteristics, which makes the data dimension high. If the above factors are solved, the consumption of computing resources can be reduced during the simulation test. In order to achieve this effect, first, through labeling processing, the data of each user can be unified to facilitate feature extraction. Then, through feature classification, it is convenient to measure the feature classification information from three dimensions: user value level value, user account opening years, and user holding data turnover rate. In this way, the data is further unified into data. Afterwards, in order to reduce the data dimension, by introducing user behavior deviation data and user aggressiveness level data, the user expected value sequence set and user daily transaction demand information sequence set required for the simulation test can be detected in advance. In addition, because the user aggressiveness level data is generated by the above formula, more humanized simulation parameters can be provided for order simulation. In this way, the accuracy of the order flow simulation operation is improved. Therefore, through the order flow simulation operation, the order flow simulation operation data sequence set can be preliminarily simulated. Therefore, it can provide data support for subsequent simulation tests, while reducing the data features and accuracy that need to be extracted during the simulation test. Furthermore, the consumption of computing resources can be reduced during the simulation test.

[0052] Step 104: construct a user feature signal table set based on the order flow simulation operation data sequence set.

[0053] In some embodiments, the execution entity may construct a set of user characteristic signal tables based on the order flow simulation operation data sequence set.

[0054] In some optional implementations of some embodiments, the execution subject constructs a user characteristic signal table set based on the order flow simulation operation data sequence set, which may include the following steps:

[0055] The first step is to determine the simulated transaction data, simulated holding data and simulated decision data corresponding to each order flow simulation operation data in the above order flow simulation operation data sequence set. Among them, the simulated transaction data can be the order data of the user's buy or sell. The simulated holding data can be the order data held by the user. The simulated decision data can be the decision information of the user's buy or sell order.

[0056] In the second step, each simulated transaction data, each simulated holding data and each simulated decision data are merged according to different preset time frequencies to obtain a merged user simulation data set. The frequency intervals in the preset different time frequencies can be at the minute level. For example, 10 minutes, 60 minutes, etc. Here, the data merging process can be to merge each simulated transaction data, each simulated holding data and each simulated decision data in the same frequency interval in the time frequency as the merged user simulation data. Specifically, the merging can be to arrange the data in the same field order.

[0057] The third step is to perform standardization processing on each merged user simulation data in the merged user simulation data set to generate a set of user feature signal tables. In particular, the Z-score standardization algorithm can be used to perform standardization processing on each merged user simulation data corresponding to each time frequency in the merged user simulation data set to generate a user feature signal table. A set of user feature signal tables corresponding to each time frequency is obtained.

[0058] Step 105, based on the user feature signal table set and the preset user holding data set, construct a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table and a low-frequency information daily integration table.

[0059] In some embodiments, the execution subject may construct a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table based on the user characteristic signal table set and the preset user holding data set.

[0060] In some optional implementations of some embodiments, the execution subject constructs a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table based on the user characteristic signal table set and a preset user holding data set, which may include the following steps:

[0061] The first step is to classify the data in each user feature signal table in the above user feature signal table set to generate a special user data table, a daily user signal table, a daily user signal table, a high-frequency user information table, and a low-frequency user information table. Among them, before the classification, the special user data table, the daily user signal table, the daily user signal table, the high-frequency user information table, and the low-frequency user information table can be preset empty tables, which respectively include corresponding feature fields. Secondly, the classification can be performed according to the pre-classified user reflection difference table. Here, the user reflection difference table can be the degree of user reflection on five categories according to the statistics of various user tags in advance. Therefore, the category of the data in the corresponding user feature signal table can be selected from the user reflection difference table. Thus, the data in each user feature signal table in the user feature signal table set can be filled into the corresponding fields in the table to obtain the special user data table, the daily user signal table, the daily user signal table, the high-frequency user information table, and the low-frequency user information table after classification.

[0062] Optionally, for special user data tables, you can perform the following steps:

[0063] The special user data in the above special user data table are classified to obtain the intraday circulation data group, the extreme return data group, the liquidity demand data group and the order learning user data group. Here, the intraday circulation data group can characterize the user information that conducts order circulation according to the intraday order value. The extreme return data group characterizes the user information that buys and sells according to the order value. The liquidity demand data group characterizes the user information that conducts intraday order circulation according to the demand. The order learning user data group characterizes the user information that adjusts the order trading strategy according to the order change. Therefore, for each user belonging to the intraday circulation data group, the extreme return data group, the liquidity demand data group and the order learning user data group, the corresponding simulation order operation logic is assigned, so as to improve the simulation degree of the simulated special user order operation. Thereby, the simulation test results are further improved.

[0064] The second step is to determine the user daily feature information corresponding to each table record in the above-mentioned daily user signal table, and obtain the user daily feature information set. Among them, each user daily feature in the user daily feature information set may include: user disposition effect value, user risk pursuit deviation value, user confidence value and user extrapolation degree value. Here, the user risk pursuit deviation value can be determined by the characteristic volatility. The user confidence value can be determined by the following method: the difference between the logarithm of the user's monthly turnover rate + 1 and the logarithm of the median of the monthly turnover rate of all users + 1.

[0065] Optionally, the user disposition effect value can be generated by the following steps: First, determine the number of user profit orders sold and the number of user loss orders sold corresponding to each user's daily characteristics. Here, the number of user profit orders sold can represent the number of orders sold by users that have profits. Secondly, the ratio of the number of user profit orders sold to the sum of the number of user profit orders sold and the number of profit orders held by the user can be determined as the willingness to sell profit orders. Then, the ratio of the number of user loss orders sold to the sum of the number of user loss orders sold and the number of user loss orders held by the user can be determined as the willingness to sell loss orders. Finally, the ratio of the willingness to sell profit orders to the willingness to sell loss orders can be determined as the user disposition effect value.

[0066] Optionally, the user extrapolation degree value may be generated by the following steps: First, the user's purchase order value and order history rate of return corresponding to each user's daily characteristics are obtained. Then, the product of the user's purchase order value and order history rate of return corresponding to each order may be determined. After that, the ratio of the sum of the products corresponding to each order to the total purchase order value is determined as the user extrapolation degree value.

[0067] The third step is to construct a daily order entry and exit comparison table corresponding to the daily user signal table based on the above user daily feature information set and the preset user entrustment transaction table, user holding information table and user label table. Among them, the user daily feature information that matches each daily user signal in the daily user signal table can be selected from each user's daily feature information, and then each user's daily feature information can be combined into a daily information control group. Finally, the above daily user signal table and the above daily information control group can be combined into a daily order entry and exit comparison table. Here, the matching can be that the user order purchase volume included in the daily user signal is the same as the order sale volume in the user's daily feature information. Secondly, each control group in the daily order entry and exit comparison table can be in an adjacent position. The daily order entry and exit comparison table may include but is not limited to at least one of the following fields: user unique identification, order identification, order quantity, order purchase or sale time, etc. In addition, the daily order entry and exit comparison table can characterize the order comparison situation of each user between days.

[0068] The fourth step is to determine the user's intraday feature information corresponding to each table record in the above intraday user signal table to obtain the user's intraday feature information set. Among them, each user's intraday feature in the user's intraday feature information set includes: user's intraday risk level value, user's intraday momentum value, user's intraday time value and user's intraday aggressiveness. Secondly, the ratio of the order closing value to the closing value of the previous minute can be used as the user's intraday momentum value. The standard deviation of all minute yields from the opening of the order to the current moment can be used as the user's intraday risk level value. The ratio of the time from the opening of the order to the current time point to the opening time of the whole day can be determined as the user's intraday time value. The ratio of the number of limit orders to the number of market orders in the order can be determined as the user's intraday aggressiveness.

[0069] The fifth step is to construct an intraday order entry and exit comparison table corresponding to the above-mentioned intraday user signal table based on the above-mentioned user intraday feature information set and the preset user entrustment transaction table, user holding information table and user label table. Among them, the user intraday feature information that matches each intraday user signal in the intraday user signal table can be selected from the intraday feature information of each user. Then, the matched intraday feature information of each user can be combined with the intraday user signal table to form an intraday order entry and exit comparison table. The intraday order entry and exit comparison table can characterize the order comparison situation of users between different time periods within the day.

[0070] The sixth step is to obtain the customer announcement date information, customer news date information, customer financial report, customer evaluation information corresponding to the above-mentioned high-frequency user information table, and the customer profit announcement information, industry policy information, customer penalty date information and industry rule information corresponding to the above-mentioned low-frequency user information table. Among them, the customer announcement date information can be the date of the announcement issued by the customer related to the order. The customer news date information can be the date of the news issued related to the customer. The customer financial report can be the financial report of the customer corresponding to a certain order. The customer evaluation information can be the user's evaluation information on the customer's order. The customer profit announcement information can be the customer's public order profit information. The industry policy information can be the policy information issued by the administration on the order value and the like. The customer penalty date information can be the date information on the customer company receiving the penalty. The industry rule information can be the recognized and published industry rule information.

[0071] The seventh step is to integrate the customer announcement date information, the customer news date information, the customer financial report, and the customer evaluation information within a day to generate a high-frequency information intraday integration table. First, select the user intraday feature information within a certain time period (e.g., 15 minutes) at each time point in the customer announcement date information, the customer news date information, the customer financial report, and the customer evaluation information to obtain the selected intraday feature information group. Then, the selected intraday feature information groups of each time period under the corresponding time frequency can be combined in order to form a high-frequency information intraday integration table.

[0072] In the eighth step, the above-mentioned customer profit announcement information, the above-mentioned industry policy information, the above-mentioned customer penalty date information and the above-mentioned industry rule information are integrated on a daily basis to generate a low-frequency information daily integration table. First, the daily feature information of users within a certain time period (e.g., 1 day) at each time point in the above-mentioned customer profit announcement information, the above-mentioned industry policy information, the above-mentioned customer penalty date information and the above-mentioned industry rule information can be selected to obtain a selected daily feature information group. Then, each selected daily feature information group can be combined in order to form a low-frequency information daily integration table.

[0073] Step 106, based on the daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table and the low-frequency information daily integration table, determine the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the user feature signal table set, and obtain the user order behavior feature type data set and user sensitivity sequence.

[0074] In some embodiments, the above-mentioned execution entity can determine the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the above-mentioned user feature signal table set based on the above-mentioned daily order entry and exit comparison table, the above-mentioned intraday order entry and exit comparison table, the above-mentioned high-frequency information intraday integration table and the above-mentioned low-frequency information daily integration table, and obtain the user order behavior feature type data set and user sensitivity sequence.

[0075] In some optional implementations of some embodiments, the execution subject determines the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the user feature signal table set based on the daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table, and the low-frequency information daily integration table, and obtains the user order behavior feature type data set and the user sensitivity sequence, which may include the following steps:

[0076] The first step is to generate a daily feature sensitivity sequence based on the records in each table in the above-mentioned daily order entry and exit comparison table. Among them, first, the data in the daily order entry and exit comparison table are divided into multiple daily order entry and exit comparison sub-tables according to the preset daily time period. Then, the order buying parameters and order selling parameters of the data in the daily order entry and exit comparison sub-table can be linearly regressed by a multivariate linear regression model to obtain a daily order buying regression equation and a daily order selling regression equation. After that, the fitting means of the daily order buying regression equation and the daily order selling regression equation can be determined respectively as the daily feature sensitivity. Thus, a daily feature sensitivity sequence is obtained. In addition, the order buying parameters may include various parameters of the buying order, such as the identification of the buying order, the buying order quantity, the buying order value, etc. Similarly, the order selling parameters may include various parameters of the selling order, such as the identification of the selling order, the selling order quantity, the selling order value, etc.

[0077] The second step is to generate an intraday feature sensitivity sequence based on the records in each table in the above intraday order entry and exit comparison table. First, the data in the intraday order entry and exit comparison table are divided into multiple intraday order entry and exit comparison sub-tables according to the preset intraday time period. Then, the order buying parameters and order selling parameters of the data in the intraday order entry and exit comparison sub-table can be linearly regressed by the multivariate linear regression model to obtain the intraday order buying regression equation and the intraday order selling regression equation. After that, the fitting means of the intraday order buying regression equation and the intraday order selling regression equation can be determined respectively as the intraday feature sensitivity. Thus, the intraday feature sensitivity sequence is obtained.

[0078] The third step is to generate a high-frequency feature regression sensitivity sequence based on the records of each table in the above-mentioned high-frequency information intraday integration table. Among them, for each selected intraday feature information group in the high-frequency information intraday integration table, the order buying parameters and order selling parameters in the selected intraday feature information group are linearly regressed by the multivariate linear regression model to obtain the high-frequency order buying regression equation and the high-frequency order selling regression equation. Secondly, the high-frequency order buying regression equation and the high-frequency order selling regression equation can be determined as the high-frequency feature regression sensitivity respectively.

[0079] The fourth step is to generate a low-frequency feature sensitivity sequence based on the records in each table in the above-mentioned low-frequency information daily integration table. For each selected daily feature information group in the low-frequency information daily integration table, the order buying parameters and order selling parameters in the selected daily feature information group are linearly regressed by a multivariate linear regression model to obtain a low-frequency order buying regression equation and a low-frequency order selling regression equation. Secondly, the low-frequency order buying regression equation and the low-frequency order selling regression equation can be determined as the low-frequency feature regression sensitivity, respectively.

[0080] The fifth step is to combine the daily feature sensitivity sequence, the intra-day feature sensitivity sequence, the high-frequency feature regression sensitivity sequence, and the low-frequency feature sensitivity sequence into a user sensitivity sequence.

[0081] The sixth step is to cluster the feature labels of each user in each user feature label group based on the daily order entry and exit comparison table, intraday order entry and exit comparison table, high-frequency information intraday integration table and low-frequency information daily integration table to generate a user order behavior feature type data set.

[0082] Step 107, using the user sensitivity sequence and the user ordering behavior feature type data set, perform a simulated ordering operation on each user to generate a simulation test result.

[0083] In some embodiments, the execution subject may use the user sensitivity sequence and the user order behavior feature type data set to perform a simulated order simulation operation on each user to generate a simulation test result. The simulated order logic of each user may be set by the user sensitivity sequence and the user order behavior feature type data set to perform a simulated order simulation operation to generate a simulation test result.

[0084] Optionally, the execution entity may also send corresponding order change information to each user based on the simulation test results. The simulation test results may include order information that each user is going to buy and sell. Therefore, the order information of each order of each user may be sent to the user as order change information.

[0085] The above steps 104 to 107 and their related contents, as an inventive point of an embodiment of the present disclosure, solve the technical problem three mentioned in the background technology, "due to the low accuracy of the simulation test results, it is difficult to provide users with more suitable order change information". The factors that make it difficult to provide users with more suitable order change information are often as follows: the accuracy of the simulation test results is low. If the accuracy of the simulation test results is improved, more suitable order change information can be provided to users. In order to achieve this effect, first, considering the problem of large data time span, the data can be divided into different time periods by setting different time frequencies for data merging processing. Then, in order to facilitate the use of data, the data is further standardized into a user feature signal table. Afterwards, considering that there are many data feature dimensions, a special user data table, a daily user signal table, an intraday user signal table, a high-frequency user information table, and a low-frequency user information table are generated by feature category division. Thus, corresponding calculation methods can be executed for tables of different feature categories. Thus, the mutual influence of data between different feature categories is avoided. Next, since the selling and buying volumes of the order market are the same, the order control group is set to facilitate the association of order circulation features. Then, through the multivariate linear regression model, the feature sensitivity corresponding to each feature category can be determined respectively. At the same time, through clustering processing, users with different order behavior types are classified using user feature labels. Therefore, combining the user order behavior feature type data set and feature sensitivity, the degree of simulation of the simulated order simulation operation on the real order flow scenario can be greatly improved. As a result, the accuracy of the simulation test results is improved. In turn, more suitable order change information can be provided to users.

[0086] The above-mentioned embodiments of the present disclosure have the following beneficial effects: through the user behavior simulation test method of some embodiments of the present disclosure, the accuracy of the simulation test of each user behavior can be improved, so as to provide users with adaptive order change information. Specifically, the reason for the low accuracy of the order operation behavior simulation result for each user is that each user in reality is easily affected by other users and the order market during the order operation process. Based on this, the user behavior simulation test method of some embodiments of the present disclosure first obtains a user historical feature information set. Among them, each user historical feature information in the above user historical feature information set corresponds to a user. Then, the feature division of each user historical feature information in the above user historical feature information set is performed to obtain a set of feature information groups after division. Here, through feature division, the historical feature information of multiple users can be preliminarily divided into different feature categories. Afterwards, the order behavior decision simulation is performed on each divided feature information in each divided feature information group in the above divided feature information group set to generate an order flow simulation operation data sequence set. Here, through the order behavior decision simulation, the user behavior operation information can be preliminarily simulated according to the user data after feature division. Next, based on the above-mentioned order flow simulation operation data sequence set, a user feature signal table set is constructed. Then, based on the above-mentioned user feature signal table set and the preset user holding data set, a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table are constructed. Here, the situation of mutual influence between users is taken into account. Therefore, by classifying the different characteristics of each user into a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table, the user's behavior characteristics can be decomposed from multiple dimensions. As a result, the influence between different feature dimensions can be greatly avoided, which is convenient for extracting user behavior characteristics. Then, based on the above-mentioned daily order entry and exit comparison table, the above-mentioned intraday order entry and exit comparison table, the above-mentioned high-frequency information intraday integration table, and the above-mentioned low-frequency information daily integration table, the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the above-mentioned user feature signal table set are determined, and the user order behavior feature type data set and user sensitivity sequence are obtained. In practice, the daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table, and the low-frequency information daily integration table are used to determine the behavior characteristic type data of each user from multiple perspectives. Compared with the unified processing of all the information of each user, it is easier to extract accurate user behavior characteristic type data. Finally, using the above user sensitivity sequence and the above user order behavior characteristic type data set, simulated order simulation operations are performed on each user to generate simulation test results. Therefore, based on a more accurate user order behavior characteristic type data set, the accuracy of the simulation test results can be ensured.

[0087] Further references Figure 2 As an implementation of the methods shown in the above figures, the present disclosure provides some embodiments of a user behavior simulation test device. These device embodiments are similar to Figure 1 Corresponding to the method embodiments shown, the device can be specifically applied to various electronic devices.

[0088] like Figure 2 As shown, the user behavior simulation test device 200 of some embodiments includes: an acquisition unit 201, a feature division unit 202, a behavior decision simulation unit 203, a first construction unit 204, a second construction unit 205, a determination unit 206 and a simulation test unit 207. The acquisition unit 201 is configured to acquire a user history feature information set, wherein each user history feature information in the user history feature information set corresponds to a user; the feature division unit 202 is configured to perform feature division on each user history feature information in the user history feature information set to obtain a set of divided feature information groups; the behavior decision simulation unit 203 is configured to perform order behavior decision simulation on each divided feature information in each divided feature information group in the divided feature information group set to generate an order flow simulation operation data sequence set; the first construction unit 204 is configured to construct a user feature signal table set based on the order flow simulation operation data sequence set; the second construction unit 205 is configured to construct a user feature signal table set based on the user history feature information set; A user characteristic signal table set and a preset user holding data set are used to construct a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table and a low-frequency information daily integration table; a determination unit 206 is configured to determine the user order behavior characteristic type data and user sensitivity corresponding to each user characteristic signal table in the above user characteristic signal table set based on the above daily order entry and exit comparison table, the above intraday order entry and exit comparison table, the above high-frequency information intraday integration table and the above low-frequency information daily integration table, and obtain the user order behavior characteristic type data set and the user sensitivity sequence; a simulation test unit 207 is configured to use the above user sensitivity sequence and the above user order behavior characteristic type data set to perform simulated order simulation operations on each user to generate a simulation test result.

[0089] It is understood that the units described in the device 200 are similar to those described in the reference Figure 1 Therefore, the operations, features and beneficial effects described above for the method are also applicable to the device 200 and the units included therein, and will not be described in detail here.

[0090] Reference below Figure 3 , which shows a structural schematic diagram of an electronic device 300 suitable for implementing some embodiments of the present disclosure. Figure 3The 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.

[0091] like Figure 3 As shown, the electronic device 300 may include a processing device 301 (e.g., a central processing unit, a graphics processing unit, etc.), 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 into 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.

[0092] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although 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.

[0093] 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.

[0094] It should be noted that the computer-readable medium 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 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 that can 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, in which a computer-readable program code is carried. 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. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, 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 suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0095] In some embodiments, the client and the server may communicate using any currently known or future developed network protocol such as HTTP (Hyper Text 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.

[0096] The above-mentioned computer-readable medium may be included in the above-mentioned device; or it may exist independently without being assembled into 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 a user historical feature information set, wherein each user historical feature information in the above-mentioned user historical feature information set corresponds to one user; performs feature division on each user historical feature information in the above-mentioned user historical feature information set to obtain a set of divided feature information groups; performs order behavior decision simulation on each divided feature information in each divided feature information group in the above-mentioned divided feature information group set to generate an order flow simulation operation data sequence set; based on the above-mentioned order flow simulation operation data sequence set, constructs a user feature signal table set; based on the above A set of user feature signal tables and a preset user-held data set are used to construct a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table; based on the above-mentioned daily order entry and exit comparison table, the above-mentioned intraday order entry and exit comparison table, the above-mentioned high-frequency information intraday integration table, and the above-mentioned low-frequency information daily integration table, the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the above-mentioned user feature signal table set are determined to obtain a user order behavior feature type data set and a user sensitivity sequence; using the above-mentioned user sensitivity sequence and the above-mentioned user order behavior feature type data set, simulated order simulation operations are performed on each user to generate simulation test results.

[0097] 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 cases involving a remote computer, the remote computer may be connected to the user's computer via 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).

[0098] 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.

[0099] 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 comprising: an acquisition unit, a feature division unit, a behavior decision simulation unit, a first construction unit, a second construction unit, a determination unit, and a simulation test unit. The names of these units do not, in some cases, constitute limitations on the units themselves, for example, the acquisition unit may also be described as a "unit for acquiring a user historical feature information set".

[0100] 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.

[0101] 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-mentioned technical features, but should also cover other technical solutions formed by any combination of the above-mentioned technical features or their equivalent features without departing from the above-mentioned inventive concept. For example, the above-mentioned features are replaced with the technical features with similar functions disclosed in the embodiments of the present disclosure (but not limited to) and the technical solutions formed.

Claims

1. A user behavior simulation test method, comprising: Acquire a user historical feature information set, wherein each user historical feature information in the user historical feature information set corresponds to a user; Performing feature division on each user historical feature information in the user historical feature information set to obtain a set of divided feature information groups; Performing order behavior decision simulation on each divided feature information in each divided feature information group in the divided feature information group set to generate an order flow simulation operation data sequence set; Based on the order flow simulation operation data sequence set, construct a user feature signal table set; Based on the user feature signal table set and the preset user holding data set, construct a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table; Based on the daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table, and the low-frequency information daily integration table, determine the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the user feature signal table set, and obtain the user order behavior feature type data set and the user sensitivity sequence; Using the user sensitivity sequence and the user ordering behavior feature type data set, a simulated ordering simulation operation is performed on each user to generate a simulation test result; The daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table and the low-frequency information daily integration table are constructed based on the user feature signal table set and the preset user holding data set, including: Classify the data in each user characteristic signal table in the user characteristic signal table set to generate a special user data table, a daily user signal table, an intraday user signal table, a high-frequency user information table, and a low-frequency user information table; Determine the user daily feature information corresponding to each table record in the daily user signal table to obtain a user daily feature information set, wherein each user daily feature in the user daily feature information set includes: a user disposition effect value, a user risk pursuit deviation value, a user confidence level value, and a user extrapolation level value; Based on the user daily characteristic information set and the preset user entrustment transaction table, user holding information table and user label table, a daily order entry and exit comparison table corresponding to the daily user signal table is constructed, wherein the user daily characteristic information matching each daily user signal in the daily user signal table is selected from each user daily characteristic information, each user daily characteristic information is combined into a daily information control group, and the above-mentioned daily user signal table and the above-mentioned daily information control group are combined into a daily order entry and exit comparison table, and the matching means that the user order buy quantity included in the daily user signal is the same as the order sell quantity in the user daily characteristic information, each control group in the daily order entry and exit comparison table is in an adjacent position, and the daily order entry and exit comparison table includes at least one of the following fields: user unique identification, order identification, order quantity, and the daily order entry and exit comparison table represents the order comparison situation of each user between days; Determine the user intraday feature information corresponding to each table record in the intraday user signal table to obtain a user intraday feature information set, wherein each user intraday feature in the user intraday feature information set includes: a user intraday risk level value, a user intraday momentum value, a user intraday time value, and a user intraday aggressiveness; Based on the user intraday feature information set and the preset user entrustment transaction table, user holding information table and user label table, an intraday order entry and exit comparison table corresponding to the intraday user signal table is constructed, wherein the user intraday feature information that matches each intraday user signal in the intraday user signal table is selected from each user intraday feature information, and each matched user intraday feature information is combined with the intraday user signal table to form an intraday order entry and exit comparison table, which represents the order comparison status of users between various time periods within the day; Acquire customer announcement date information, customer news date information, customer financial report, customer evaluation information corresponding to the high-frequency user information table, and customer profit announcement information, industry policy information, customer penalty date information and industry rule information corresponding to the low-frequency user information table; The customer announcement date information, the customer news date information, the customer financial report, and the customer evaluation information are integrated intraday to generate a high-frequency information intraday integration table, wherein the user intraday feature information within a certain time period is selected to obtain a selected intraday feature information group, and the selected intraday feature information groups of each time period under the corresponding time frequency are sequentially combined into a high-frequency information intraday integration table; The customer profit announcement information, the industry policy information, the customer penalty date information and the industry rule information are integrated on a daily basis to generate a daily integration table of low-frequency information, wherein daily characteristic information of users within a certain time period is selected to obtain selected daily characteristic information groups, and each selected daily characteristic information group is combined in sequence into a daily integration table of low-frequency information.

2. The method according to claim 1, wherein: The method further comprises: Based on the simulation test results, corresponding order change information is sent to each user.

3. The method according to claim 1, wherein: The step of performing order behavior decision simulation on each of the divided feature information in each of the divided feature information groups in the divided feature information group set to generate an order flow simulation operation data sequence set includes: Labeling each of the divided feature information in each divided feature information group in the divided feature information group set to generate a user behavior feature label group set and a corresponding user holding feature label group set; Based on the user behavior feature tag group set and the corresponding user holding feature tag group set, feature classification is performed on the divided feature information group set to generate a feature classification information group set, wherein each feature classification information in the feature classification information group set includes: user value level value, user account opening years, user holding data turnover rate, and user transfer times; For each feature classification information in each feature classification information group in the feature classification information group set, the number of user turnovers and the feature classification information in the feature classification information group are measured from three dimensions, including the user value level value, the user account opening years, and the user holding data turnover rate, so as to generate a user behavior parameter distribution matrix in the user behavior parameter distribution matrix set; Based on preset user behavior deviation data, determining the user expected value of each user behavior parameter distribution vector in the user behavior parameter distribution matrix set, and obtaining a user expected value sequence set; Based on the user expected value sequence set and preset user aggressiveness level data, determine the user daily transaction demand information corresponding to each user behavior parameter distribution vector in the user behavior parameter distribution matrix set to obtain the user daily transaction demand information sequence set; Based on the pre-acquired intraday public information, order flow demand, order flow demand degree value, user intraday preference data and user intraday flow preference data, order flow simulation operations are performed on the users corresponding to each user behavior parameter distribution vector in the user behavior parameter distribution matrix set to generate an order flow simulation operation data sequence set.

4. The method according to claim 3, wherein: The step of constructing a user characteristic signal table set based on the order flow simulation operation data sequence set includes: Determine the simulated transaction data, simulated holding data and simulated decision data corresponding to each order flow simulation operation data in the order flow simulation operation data sequence set; Each simulated transaction data, each simulated holding data and each simulated decision data are merged and processed according to different preset time frequencies to obtain a merged user simulation data set; Each merged user simulation data in the merged user simulation data set is standardized to generate a set of user characteristic signal tables.

5. The method according to claim 1, wherein: The method of determining the user order behavior feature type data and user sensitivity corresponding to each user feature signal table in the user feature signal table set based on the daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table, and the low-frequency information daily integration table, and obtaining the user order behavior feature type data set and the user sensitivity sequence, includes: Generate a daily feature sensitivity sequence based on each table record in the daily order entry and exit comparison table; Generate an intraday feature sensitivity sequence based on each table record in the intraday order entry and exit comparison table; Generate a high-frequency feature regression sensitivity sequence based on each table record in the high-frequency information intraday integration table; Based on each table record in the low-frequency information daily integration table, a low-frequency feature sensitivity sequence is generated; Combining the daily feature sensitivity sequence, the intra-day feature sensitivity sequence, the high-frequency feature regression sensitivity sequence, and the low-frequency feature sensitivity sequence into a user sensitivity sequence; Based on the daily order in / out comparison table, the intraday order in / out comparison table, the high-frequency information intraday integration table and the low-frequency information daily integration table, the feature labels held by each user in each user feature label group are clustered to generate a user order behavior feature type data set.

6. The method according to claim 3, wherein: The user aggression level data is generated by the following steps: Obtain the order buyer-driven quantity sequence, order seller-driven quantity sequence, order buy order ratio mean sequence and order buy order ratio deviation expectation corresponding to each preset order identifier; Generate a user aggressiveness value based on the order buyer driven volume sequence and the order seller driven volume sequence corresponding to each order identifier; The user aggression degree value corresponding to each order identifier is determined as user aggression level data.

7. A user behavior simulation test device, comprising: an acquisition unit, configured to acquire a user historical feature information set, wherein each user historical feature information in the user historical feature information set corresponds to a user; A feature division unit is configured to perform feature division on each user historical feature information in the user historical feature information set to obtain a set of divided feature information groups; A behavior decision simulation unit is configured to perform order behavior decision simulation on each divided feature information in each divided feature information group in the divided feature information group set to generate an order flow simulation operation data sequence set; A first construction unit is configured to construct a user characteristic signal table set based on the order flow simulation operation data sequence set; A second construction unit is configured to construct a daily order entry and exit comparison table, an intraday order entry and exit comparison table, a high-frequency information intraday integration table, and a low-frequency information daily integration table based on the user feature signal table set and a preset user holding data set; a determining unit configured to determine the user ordering behavior feature type data and user sensitivity corresponding to each user feature signal table in the user feature signal table set based on the daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table, and the low-frequency information daily integration table, and obtain the user ordering behavior feature type data set and the user sensitivity sequence; A simulation test unit is configured to perform a simulated ordering operation on each user by using the user sensitivity sequence and the user ordering behavior feature type data set to generate a simulation test result; The daily order entry and exit comparison table, the intraday order entry and exit comparison table, the high-frequency information intraday integration table and the low-frequency information daily integration table are constructed based on the user feature signal table set and the preset user holding data set, including: Classify the data in each user characteristic signal table in the user characteristic signal table set to generate a special user data table, a daily user signal table, an intraday user signal table, a high-frequency user information table, and a low-frequency user information table; Determine the user daily feature information corresponding to each table record in the daily user signal table to obtain a user daily feature information set, wherein each user daily feature in the user daily feature information set includes: a user disposition effect value, a user risk pursuit deviation value, a user confidence level value, and a user extrapolation level value; Based on the user daily characteristic information set and the preset user entrustment transaction table, user holding information table and user label table, a daily order entry and exit comparison table corresponding to the daily user signal table is constructed, wherein the user daily characteristic information matching each daily user signal in the daily user signal table is selected from each user daily characteristic information, each user daily characteristic information is combined into a daily information control group, and the above-mentioned daily user signal table and the above-mentioned daily information control group are combined into a daily order entry and exit comparison table, and the matching means that the user order buy quantity included in the daily user signal is the same as the order sell quantity in the user daily characteristic information, each control group in the daily order entry and exit comparison table is in an adjacent position, and the daily order entry and exit comparison table includes at least one of the following fields: user unique identification, order identification, order quantity, and the daily order entry and exit comparison table represents the order comparison situation of each user between days; Determine the user intraday feature information corresponding to each table record in the intraday user signal table to obtain a user intraday feature information set, wherein each user intraday feature in the user intraday feature information set includes: a user intraday risk level value, a user intraday momentum value, a user intraday time value, and a user intraday aggressiveness; Based on the user intraday feature information set and the preset user entrustment transaction table, user holding information table and user label table, an intraday order entry and exit comparison table corresponding to the intraday user signal table is constructed, wherein the user intraday feature information that matches each intraday user signal in the intraday user signal table is selected from each user intraday feature information, and each matched user intraday feature information is combined with the intraday user signal table to form an intraday order entry and exit comparison table, which represents the order comparison status of users between various time periods within the day; Acquire customer announcement date information, customer news date information, customer financial report, customer evaluation information corresponding to the high-frequency user information table, and customer profit announcement information, industry policy information, customer penalty date information and industry rule information corresponding to the low-frequency user information table; The customer announcement date information, the customer news date information, the customer financial report, and the customer evaluation information are integrated intraday to generate a high-frequency information intraday integration table, wherein the user intraday feature information within a certain time period is selected to obtain a selected intraday feature information group, and the selected intraday feature information groups of each time period under the corresponding time frequency are sequentially combined into a high-frequency information intraday integration table; The customer profit announcement information, the industry policy information, the customer penalty date information and the industry rule information are integrated on a daily basis to generate a daily integration table of low-frequency information, wherein daily characteristic information of users within a certain time period is selected to obtain selected daily characteristic information groups, and each selected daily characteristic information group is combined in sequence into a daily integration table of low-frequency information.

8. 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 to 6.

Images