A method and device for setting transfer limit

Abstract

The present invention discloses a method and device for setting a transfer limit, including: obtaining historical data of multiple target influencing factors from account information of different users as training samples, training the limit analysis model with the purpose of making the output result of the limit analysis model for the training samples close to the standard transfer limit, and analyzing the user's transfer limit according to the data of the user's current multiple target influencing factors through the pre-trained limit analysis model. Thus, the transfer limit that meets the user's actual situation can be analyzed through the pre-trained limit analysis model, and the user's transfer limit is updated according to the relationship between the predicted second transfer limit of the user and the preset safety limit, thereby further ensuring the user's fund security.

Description

Technical Field

[0001] The present invention relates to the field of data processing, and in particular to a method and device for setting a transfer limit. Background Art

[0002] Currently, in order to ensure the safety of funds, users will set transfer limits for their fund accounts. However, in general, the transfer limits are set randomly by users. However, as the user's funds change, the fund limits initially set by the user may not be applicable to the user's current fund status. In addition, the transfer limits used to set are also very subjective and may not be applicable to the user's current fund status. Therefore, there is an urgent need for a mechanism that can analyze the user's fund limits in the current state. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides a method and device for setting a transfer limit, which realizes the intelligent setting of the user's transfer limit while ensuring the safety of the user's funds.

[0004] An embodiment of the present invention discloses a method for setting a transfer limit, comprising:

[0005] Acquire data of a plurality of preset target influencing factors from the target user's account information; the plurality of preset influencing factors at least include: consumption information, a first transfer limit, an account balance, and transfer limit adjustment information; the first transfer limit is a transfer limit actually set by the user;

[0006] Extracting a first target feature from the data of the plurality of target impact factors;

[0007] The extracted target features are input into a pre-trained limit analysis model to predict the user's second transfer limit; the limit analysis model is obtained through the following training method: historical data of multiple target influencing factors are obtained from the account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output results of the limit analysis model for the training samples close to the standard transfer limit.

[0008] The user's transfer limit is updated based on the relationship between the predicted second transfer limit of the user and the preset safety limit.

[0009] Optionally, the training process of the quota analysis model includes:

[0010] Obtaining a second target feature of historical data of multiple target influencing factors of the user account;

[0011] Inputting the second target feature of the historical data of multiple target influencing factors of the user account into the quota analysis model as a training sample;

[0012] The limit analysis model is trained with the goal of making the output results of the limit analysis model for training samples close to the standard transfer limit; wherein the standard limit is the user's expected limit that matches the user's financial situation.

[0013] Optionally, the step of obtaining the second target feature of the historical data of multiple target influencing factors of the user account includes:

[0014] Obtaining historical data of multiple preset influencing factors from the user's account information;

[0015] Obtaining the second target feature from the historical data of each impact factor;

[0016] Determine the weight of the second target feature for each influencing factor;

[0017] According to the weight of each historical data influencing the second target characteristics of multiple target influencing factors, the second target characteristics of multiple target influencing factors are screened out from the multiple influencing factors.

[0018] Optionally, updating the user's transfer limit according to the predicted relationship between the user's second transfer limit and a preset safety limit includes:

[0019] If the second transfer limit is less than the preset safety limit, setting the transfer limit of the user to the second transfer limit;

[0020] If the second transfer limit is greater than the preset safety limit, the transfer limit of the user is set to the preset safety transfer limit.

[0021] Optionally, updating the user's transfer limit according to the relationship between the preset second transfer limit of the user and the preset safety limit includes:

[0022] If the second transfer limit is greater than the preset safety limit, a reminder is sent to the user;

[0023] In response to the first target transfer limit selected by the user, the transfer limit is set to the first target transfer limit.

[0024] The embodiment of the present invention also discloses a device for setting a transfer limit, comprising:

[0025] A data acquisition unit, configured to acquire data of a plurality of preset target influencing factors from the target user's account information; the plurality of preset influencing factors at least include: consumption information, a first transfer limit, an account balance, and transfer limit adjustment information; the first transfer limit is a transfer limit actually set by the user;

[0026] A first target feature acquisition unit, configured to extract a first target feature from the data of the plurality of target influencing factors;

[0027] The transfer limit analysis unit is used to input the extracted target features into a pre-trained limit analysis model to predict the user's second transfer limit; the limit analysis model is obtained through the following training method: historical data of multiple target influencing factors are obtained from the account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output results of the limit analysis model for the training samples close to the standard transfer limit.

[0028] The transfer limit setting unit is used to update the user's transfer limit according to the relationship between the predicted second transfer limit of the user and the preset safety limit.

[0029] Optionally, also include:

[0030] The training unit of the limit analysis model includes:

[0031] A second target feature acquisition subunit, used to acquire a second target feature of historical data of multiple target influencing factors of a user account;

[0032] An input subunit, used to input the second target feature of the historical data of multiple target influencing factors of the user account as a training sample into the quota analysis model;

[0033] The training subunit is used to train the limit analysis model with the goal of making the output results of the limit analysis model for training samples close to the standard transfer limit; wherein the standard limit is the user's expected limit that matches the user's financial situation.

[0034] Optionally, the second target feature acquisition subunit is used to:

[0035] Obtaining historical data of multiple preset influencing factors from the user's account information;

[0036] Obtaining the second target feature from the historical data of each impact factor;

[0037] Determine the weight of the second target feature for each influencing factor;

[0038] According to the weight of each historical data influencing the second target characteristics of multiple target influencing factors, the second target characteristics of multiple target influencing factors are screened out from the multiple influencing factors.

[0039] Optionally, the transfer limit setting unit includes:

[0040] A first transfer limit setting subunit, configured to set the transfer limit of the user to the second transfer limit if the second transfer limit is less than a preset safety limit;

[0041] The second transfer limit setting subunit is used to set the transfer limit of the user to the preset safety transfer limit if the second transfer limit is greater than the preset safety limit.

[0042] An embodiment of the present invention discloses an electronic device, including:

[0043] Memory and processor;

[0044] The memory is used to store programs, and the processor is used to execute any one of the transfer limit setting methods described above when executing the programs stored in the memory.

[0045] The embodiment of the present invention discloses a method and device for setting a transfer limit, including: obtaining historical data of multiple target influencing factors from account information of different users as training samples, training the limit analysis model with the purpose of making the output result of the limit analysis model for the training samples close to the standard transfer limit, and analyzing the user's transfer limit according to the data of the user's current multiple target influencing factors through the pre-trained limit analysis model. Thus, the transfer limit that meets the user's actual situation can be analyzed through the pre-trained limit analysis model, and the user's transfer limit is updated according to the relationship between the predicted second transfer limit of the user and the preset safety limit, thereby further ensuring the user's fund security. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0047] Figure 1 A schematic diagram of a flow chart of a method for setting a transfer limit provided by an embodiment of the present invention is shown;

[0048] Figure 2 A schematic diagram showing a flow chart of a method for training a transfer limit analysis model provided by an embodiment of the present invention;

[0049] Figure 3 A schematic diagram showing the structure of a device for setting a transfer limit provided by an embodiment of the present invention;

[0050] Figure 4 A schematic structural diagram of an electronic device provided by an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] refer to Figure 1 , shows a flow chart of a method for setting a transfer limit provided by an embodiment of the present invention. In this embodiment, the method includes:

[0053] S101: Acquire data of a plurality of preset target influencing factors from the account information of a target user;

[0054] The preset multiple influencing factors include at least: consumption information, a first transfer limit, an account balance, and transfer limit adjustment information; the first transfer limit is a transfer limit actually set by the user;

[0055] Among them, multiple target impact factors are predetermined, each target impact factor is a factor that affects the transfer limit, and the target impact factor can be determined in a variety of ways, which are not limited in this embodiment. For example, it can be set by feature engineering. Preferably, it can be determined in the following way:

[0056] Obtain historical data of multiple influencing factors from the user's account information;

[0057] Acquire the characteristics of the historical data of each influencing factor from the historical data of the plurality of influencing factors;

[0058] Determine the priority weight of the feature of the historical data of each influencing factor, and according to the priority weight of the feature of the historical data of each influencing factor;

[0059] Multiple influencing factors are screened out according to the priority weight of the characteristics of the historical data of each influencing factor.

[0060] In this embodiment, when selecting a target influencing factor from multiple influencing factors, the influencing factors may be sorted according to the weight of each influencing factor, and the influencing factors ranked in the top N weights may be selected as the target influencing factors.

[0061] Or it can be understood that the weight of each influencing factor represents the priority of each influencing factor, and multiple target influencing factors are screened out from multiple influencing factors according to the priority level of each influencing factor.

[0062] Therefore, through the above introduction, it can be seen that the target influencing factors extracted by the above method can affect the user's transfer limit, wherein the extracted target influencing factors include at least: consumption information, first transfer limit, account balance, and transfer limit adjustment information.

[0063] S102: extracting target features from the data of the multiple target influencing factors;

[0064] In this embodiment, there are many ways to extract features from data, which are not limited in this embodiment.

[0065] Preferably, a feature engineering model may be used for feature extraction. The feature engineering model may include multiple types, which are not limited in this embodiment. For example, a principal component analysis model, a linear discriminant analysis model, etc. may be used.

[0066] S103: Input the extracted target features into a pre-trained limit analysis model to predict the user's second transfer limit; wherein the limit analysis model is obtained through the following training method: historical data of multiple target influencing factors are obtained from the account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output results of the limit analysis model for the training samples close to the standard transfer limit.

[0067] In this embodiment, the limit analysis model is pre-trained and has the ability to predict the user's transfer limit based on the data of the target influencing factor. The training method of the limit analysis model will be introduced below and will not be repeated in this embodiment.

[0068] In this embodiment, before the extracted target features are input into the quota analysis model, the target features may be preprocessed, such as performing data cleaning (eg, removing defective data) or normalization operations.

[0069] S104: updating the user's transfer limit according to the relationship between the predicted second transfer limit of the user and the preset safety limit.

[0070] The preset safety limit may be set by the user or by the system based on the user's situation. The specific preset safety limit may be determined as required and is not limited in this embodiment.

[0071] In this embodiment, the method for updating the user transfer limit includes the following implementation methods:

[0072] Implementation method 1:

[0073] If the second transfer limit is less than the preset safety limit, setting the transfer limit of the user to the second transfer limit;

[0074] If the second transfer limit is greater than the preset safety limit, the transfer limit of the user is set to the preset safety transfer limit.

[0075] In this embodiment, based on the user's transfer security and current financial situation, if the predicted second transfer limit of the user is less than the preset safety limit, then in order to further ensure the user's security and adapt to the user's financial situation, the user's transfer limit can be set to the second transfer limit.

[0076] Among them, if the predicted second transfer limit of the user is greater than the preset safety limit, then in order to further ensure the safety of the user, the transfer limit of the user can be set as the safety limit.

[0077] In addition, the first implementation also includes:

[0078] If the second transfer limit is greater than the preset safety limit, the user's transfer limit is set to the preset safety transfer limit, and a reminder is sent to the user.

[0079] That is, if the predicted second transfer limit is greater than the preset safety limit, then it can be considered that the predicted second transfer limit may be risky. In this case, a reminder can be sent to the user, and the user's transfer limit can be set to a safety limit while ensuring the safety of the user's funds.

[0080] Implementation method 2:

[0081] If the second transfer limit is less than the preset safety limit, setting the transfer limit of the user to the second transfer limit;

[0082] If the predicted third transfer limit is greater than the preset safety limit, sending a first reminder message to the user;

[0083] In response to the first target transfer limit selected by the user, the transfer limit is set to the first target transfer limit.

[0084] Among them, under the condition of ensuring the security of the user's account and ensuring that the current transfer limit can meet the user's current financial situation, if the predicted second transfer limit is less than the preset safety limit, then it can be considered that the predicted second transfer limit is more in line with the user's current actual situation, and therefore, the predicted second transfer limit is set as the user's transfer limit. However, if the predicted second transfer limit is greater than the preset safety limit, then it can be considered that the predicted second transfer limit may be risky. In this case, a reminder can be sent to the user, and the transfer limit can be set to the first target transfer limit selected by the user according to the user's setting requirements.

[0085] Implementation method three:

[0086] If the predicted second transfer limit is less than the preset safety limit, sending a second reminder message to the user;

[0087] In response to a second target transfer limit selected by the user, setting the transfer limit to the second target transfer limit;

[0088] If the predicted second transfer limit is greater than the preset safety limit, a third reminder message is sent to the user;

[0089] In response to the third target transfer limit selected by the user, the transfer limit is set to the third target transfer limit.

[0090] The second target transfer limit is any one of the second transfer limit and the safety limit.

[0091] The third target transfer limit is any one of the second transfer limit and the safety limit.

[0092] It can be seen that in this embodiment, no matter what the relationship between the predicted transfer limit and the safety limit is, a reminder is sent to the user, and the transfer limit is set based on the information replied by the user.

[0093] In this embodiment, historical data of multiple target influencing factors are obtained from account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output result of the limit analysis model for the training samples close to the standard transfer limit, and the user's transfer limit is analyzed according to the data of the user's current multiple target influencing factors through the pre-trained limit analysis model. Thus, the transfer limit that meets the user's actual situation can be analyzed through the pre-trained limit analysis model, and the user's transfer limit is updated according to the relationship between the predicted second transfer limit of the user and the preset safety limit, further ensuring the user's fund security.

[0094] refer to Figure 2 , shows a flow chart of a method for training a transfer limit analysis model provided by an embodiment of the present invention. In this embodiment, the method includes:

[0095] S201: Acquire a second target feature of historical data of multiple target influencing factors of a user account;

[0096] In this embodiment, the target impact factor is a factor that affects the user's transfer limit. The target impact factor can be determined in a variety of ways, which are not limited in this embodiment. Preferably, it can be determined by the following method:

[0097] Obtaining historical data of multiple preset influencing factors from the user's account information;

[0098] Obtaining the second target feature from the historical data of each impact factor;

[0099] Determine the weight of the second target feature for each influencing factor;

[0100] According to the weight of each historical data influencing the second target characteristics of multiple target influencing factors, the second target characteristics of multiple target influencing factors are screened out from the multiple influencing factors.

[0101] In this embodiment, when selecting a target influencing factor from multiple influencing factors, the influencing factors may be sorted according to the weight of each influencing factor, and the influencing factors ranked in the top N weights may be selected as the target influencing factors.

[0102] Or it can be understood that the weight of each influencing factor represents the priority of each influencing factor, and multiple target influencing factors are screened out from multiple influencing factors according to the priority level of each influencing factor.

[0103] S202: inputting the second target feature of the historical data of multiple target influencing factors of the user account into the quota analysis model as a training sample;

[0104] In this embodiment, before the extracted target feature is input into the quota analysis model, the second target feature may be preprocessed, such as performing data cleaning (eg, removing defective data) or normalization operations.

[0105] The process of preprocessing the second target feature is consistent with the process of preprocessing the first target, and will not be described in detail in this embodiment.

[0106] S203: training the limit analysis model with the goal of making the output of the limit analysis model for the training samples close to the standard transfer limit;

[0107] Among them, the standard limit is the user's expected limit that matches the user's financial situation.

[0108] In this embodiment, the limit analysis model can be any machine learning model, or a model formed by combining multiple machine learning models, which is not limited in this embodiment.

[0109] In this embodiment, the limit analysis model is pre-trained and has the ability to predict the user's transfer limit based on the target influencing factor data, that is, the characteristics of the user's target influencing factor are input into the limit prediction model, and the user's transfer limit can be predicted.

[0110] In this embodiment, historical data of multiple target influencing factors are obtained from account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output result of the limit analysis model for the training samples close to the standard transfer limit, and the user's transfer limit is analyzed based on the user's current data of multiple target influencing factors through the pre-trained limit analysis model. Thus, the transfer limit that meets the user's actual situation can be analyzed through the pre-trained limit analysis model.

[0111] refer to Figure 3 , showing a schematic diagram of the structure of a device for setting a transfer limit provided by an embodiment of the present invention, comprising:

[0112] The data acquisition unit 301 is used to acquire data of a plurality of preset target influencing factors from the account information of the target user; the plurality of preset influencing factors at least include: consumption information, a first transfer limit, an account balance, and transfer limit adjustment information; the first transfer limit is a transfer limit actually set by the user;

[0113] A first target feature acquisition unit 302 is used to extract a first target feature from the data of the multiple target influencing factors;

[0114] The transfer limit analysis unit 303 is used to input the extracted target features into a pre-trained limit analysis model to predict the user's second transfer limit; the limit analysis model is obtained through the following training method: historical data of multiple target influencing factors are obtained from the account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output results of the limit analysis model for the training samples close to the standard transfer limit.

[0115] The transfer limit setting unit 304 is used to update the user's transfer limit according to the relationship between the predicted second transfer limit of the user and the preset safety limit.

[0116] Optionally, also include:

[0117] The training unit of the limit analysis model includes:

[0118] A second target feature acquisition subunit, used to acquire a second target feature of historical data of multiple target influencing factors of a user account;

[0119] An input subunit, used to input the second target feature of the historical data of multiple target influencing factors of the user account as a training sample into the quota analysis model;

[0120] The training subunit is used to train the limit analysis model with the goal of making the output results of the limit analysis model for training samples close to the standard transfer limit; wherein the standard limit is the user's expected limit that matches the user's financial situation.

[0121] Optionally, the second target feature acquisition subunit is used to:

[0122] Obtaining historical data of multiple preset influencing factors from the user's account information;

[0123] Obtaining the second target feature from the historical data of each impact factor;

[0124] Determine the weight of the second target feature for each influencing factor;

[0125] According to the weight of each historical data influencing the second target characteristics of multiple target influencing factors, the second target characteristics of multiple target influencing factors are screened out from the multiple influencing factors.

[0126] Optionally, the transfer limit setting unit includes:

[0127] A first transfer limit setting subunit, configured to set the transfer limit of the user to the second transfer limit if the second transfer limit is less than a preset safety limit;

[0128] The second transfer limit setting subunit is used to set the transfer limit of the user to the preset safety transfer limit if the second transfer limit is greater than the preset safety limit.

[0129] Optionally, the transfer limit setting unit includes:

[0130] a reminder unit, configured to send a first reminder message to the user if the second transfer limit is greater than a preset safety limit;

[0131] The transfer limit setting subunit is used to set the transfer limit as the first target transfer limit in response to the first target transfer limit selected by the user.

[0132] The device of this embodiment obtains historical data of multiple target influencing factors from account information of different users as training samples, trains the limit analysis model with the purpose of making the output result of the limit analysis model for the training samples close to the standard transfer limit, and analyzes the user's transfer limit based on the data of the user's current multiple target influencing factors through the pre-trained limit analysis model. Thus, the transfer limit that meets the user's actual situation can be analyzed through the pre-trained limit analysis model, and the user's transfer limit is updated based on the predicted relationship between the user's second transfer limit and the preset safety limit, further ensuring the user's fund security.

[0133] refer to Figure 4 , shows a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. In this embodiment, the electronic device includes:

[0134] Memory 401 and processor 402;

[0135] The memory 401 is used to store programs, and the processor 402 is used to execute the following method for setting a transfer limit when executing the program stored in the memory 401:

[0136] Acquire data of a plurality of preset target influencing factors from the target user's account information; the plurality of preset influencing factors at least include: consumption information, a first transfer limit, an account balance, and transfer limit adjustment information; the first transfer limit is a transfer limit actually set by the user;

[0137] Extracting a first target feature from the data of the plurality of target impact factors;

[0138] The extracted target features are input into a pre-trained limit analysis model to predict the user's second transfer limit; the limit analysis model is obtained through the following training method: historical data of multiple target influencing factors are obtained from the account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output results of the limit analysis model for the training samples close to the standard transfer limit.

[0139] The user's transfer limit is updated based on the relationship between the predicted second transfer limit of the user and the preset safety limit.

[0140] Optionally, the training process of the quota analysis model includes:

[0141] Obtaining a second target feature of historical data of multiple target influencing factors of the user account;

[0142] Inputting the second target feature of the historical data of multiple target influencing factors of the user account into the quota analysis model as a training sample;

[0143] The limit analysis model is trained with the goal of making the output results of the limit analysis model for training samples close to the standard transfer limit; wherein the standard limit is the user's expected limit that matches the user's financial situation.

[0144] Optionally, the step of obtaining the second target feature of the historical data of multiple target influencing factors of the user account includes:

[0145] Obtaining historical data of multiple preset influencing factors from the user's account information;

[0146] Obtaining the second target feature from the historical data of each impact factor;

[0147] Determine the weight of the second target feature for each influencing factor;

[0148] According to the weight of each historical data influencing the second target characteristics of multiple target influencing factors, the second target characteristics of multiple target influencing factors are screened out from the multiple influencing factors.

[0149] Optionally, updating the user's transfer limit according to the predicted relationship between the user's second transfer limit and a preset safety limit includes:

[0150] If the second transfer limit is less than the preset safety limit, setting the transfer limit of the user to the second transfer limit;

[0151] If the second transfer limit is greater than the preset safety limit, the transfer limit of the user is set to the preset safety transfer limit.

[0152] Optionally, updating the user's transfer limit according to the relationship between the preset second transfer limit of the user and the preset safety limit includes:

[0153] If the second transfer limit is greater than the preset safety limit, a reminder is sent to the user;

[0154] In response to the first target transfer limit selected by the user, the transfer limit is set to the first target transfer limit.

[0155] It should be noted that the various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0156] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for setting a transfer limit, characterized in that: include: Obtaining data of a plurality of preset target influencing factors from the target user's account information; The preset multiple influencing factors include at least: consumption information, a first transfer limit, an account balance, and transfer limit adjustment information; the first transfer limit is a transfer limit actually set by the user; Extracting a first target feature from the data of the plurality of target impact factors; The extracted target features are input into a pre-trained limit analysis model to predict the second transfer limit of the user; the limit analysis model is obtained by the following training method: historical data of multiple target influencing factors are obtained from account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output results of the limit analysis model for the training samples close to the standard transfer limit; updating the user's transfer limit according to the relationship between the predicted second transfer limit of the user and a preset safety limit, wherein the preset safety limit is set by the user or by the system based on the user's situation; Wherein, updating the user's transfer limit according to the predicted relationship between the user's second transfer limit and the preset safety limit includes: If the second transfer limit is less than the preset safety limit, setting the transfer limit of the user to the second transfer limit; If the second transfer limit is greater than the preset safety limit, the transfer limit of the user is set to the preset safety transfer limit; or, if the second transfer limit is greater than the preset safety limit, a first reminder message is sent to the user; in response to the first target transfer limit selected by the user, the transfer limit is set to the first target transfer limit.

2. The method according to claim 1, characterized in that The training process of the quota analysis model includes: Obtaining a second target feature of historical data of multiple target influencing factors of the user account; Inputting the second target feature of the historical data of multiple target influencing factors of the user account into the quota analysis model as a training sample; The limit analysis model is trained with the goal of making the output results of the limit analysis model for training samples close to the standard transfer limit; wherein the standard limit is the user's expected limit that matches the user's financial situation.

3. The method according to claim 2, characterized in that The second target feature of obtaining the historical data of multiple target influencing factors of the user account includes: Obtaining historical data of multiple preset influencing factors from the user's account information; Obtaining the second target feature from the historical data of each impact factor; Determine the weight of the second target feature for each influencing factor; According to the weight of each historical data influencing the second target characteristics of multiple target influencing factors, the second target characteristics of multiple target influencing factors are screened out from the multiple influencing factors.

4. A device for setting a transfer limit, characterized in that: include: A data acquisition unit, used to acquire data of a plurality of preset target influencing factors from the account information of the target user; The preset multiple influencing factors include at least: consumption information, a first transfer limit, an account balance, and transfer limit adjustment information; the first transfer limit is a transfer limit actually set by the user; A first target feature acquisition unit, configured to extract a first target feature from the data of the plurality of target influencing factors; A transfer limit analysis unit is used to input the extracted target features into a pre-trained limit analysis model to predict the second transfer limit of the user; the limit analysis model is obtained by the following training method: historical data of multiple target influencing factors are obtained from account information of different users as training samples, and the limit analysis model is trained with the purpose of making the output results of the limit analysis model for the training samples close to the standard transfer limit; A transfer limit setting unit, configured to update the user's transfer limit according to the relationship between the predicted second transfer limit of the user and a preset safety limit, wherein the preset safety limit is set by the user or by the system based on the user's situation; Wherein, the transfer limit setting unit includes: A first transfer limit setting subunit, configured to set the transfer limit of the user to the second transfer limit if the second transfer limit is less than a preset safety limit; The second transfer limit setting subunit is used to set the user's transfer limit to a preset safety transfer limit if the second transfer limit is greater than the preset safety limit; or to send a first reminder message to the user if the second transfer limit is greater than the preset safety limit; in response to a first target transfer limit selected by the user, set the transfer limit to the first target transfer limit.

5. The device according to claim 4, characterized in that Also includes: The training unit of the limit analysis model includes: A second target feature acquisition subunit, used to acquire a second target feature of historical data of multiple target influencing factors of a user account; An input subunit, used to input the second target feature of the historical data of multiple target influencing factors of the user account as a training sample into the quota analysis model; The training subunit is used to train the limit analysis model with the goal of making the output results of the limit analysis model for training samples close to the standard transfer limit; wherein the standard limit is the user's expected limit that matches the user's financial situation.

6. The device according to claim 5, characterized in that The second target feature acquisition subunit is used to: Obtaining historical data of multiple preset influencing factors from the user's account information; Obtaining the second target feature from the historical data of each impact factor; Determine the weight of the second target feature for each influencing factor; According to the weight of each historical data influencing the second target characteristics of multiple target influencing factors, the second target characteristics of multiple target influencing factors are screened out from the multiple influencing factors.

7. An electronic device, characterized in that: include: Memory and processor; The memory is used to store programs, and the processor is used to execute a method for setting a transfer limit as described in any one of claims 1 to 3 when executing the program stored in the memory.

Images