Resource transfer data monitoring method and device, computer device and storage medium

Abstract

The application relates to a resource transfer data monitoring method and device, computer equipment and a storage medium, which can be used in the financial field or other fields. The method comprises the following steps: performing vectorization processing on resource transfer data of a target user to obtain a target vector corresponding to the resource transfer data; determining the offset degree of the target vector and the center points of each sample vector group in a preset vector library according to the target vector and the vector library; each sample vector group in the vector library is determined according to the vectors corresponding to the multiple sample resource transfer data of the target user in a target time period; determining a monitoring result according to the offset degrees of the target vector and the center points of each sample vector group; and the monitoring result is used to represent whether the resource transfer data is abnormal. The method can improve the monitoring accuracy of the resource transfer data.

Description

Technical Field

[0001] This application relates to the financial sector, and in particular to a method, apparatus, computer equipment, and storage medium for monitoring resource transfer data. Background Technology

[0002] Currently, when a user's account experiences abnormal resource transfers, it can result in resource loss for the user. Therefore, it is necessary to monitor for abnormal resource transfers in a timely manner to prevent such losses.

[0003] In traditional techniques, the characteristics of abnormal resource transfers are obtained by analyzing the recent abnormal resource transfer data of user accounts, and then the user account is analyzed to determine whether an abnormal resource transfer has occurred.

[0004] However, traditional technologies suffer from low accuracy in monitoring abnormal resource transfers. Summary of the Invention

[0005] Therefore, it is necessary to provide a method, apparatus, computer equipment, and storage medium for monitoring resource transfer data that can improve the monitoring accuracy of resource transfer data, addressing the aforementioned technical problems.

[0006] Firstly, this application provides a method for monitoring resource transfer data. The method includes:

[0007] The resource transfer data of the target user is vectorized to obtain the target vector corresponding to the resource transfer data;

[0008] Determine the offset between the target vector and the center point of each sample vector group in the preset vector library; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period;

[0009] The monitoring result is determined based on the offset between the target vector and the center point of each of the sample vector groups; the monitoring result is used to characterize whether the resource transfer data is abnormal.

[0010] In one embodiment, determining the monitoring result based on the offset between the target vector and the center point of each of the sample vector groups includes:

[0011] Based on the offset between the target vector and the center point of each of the sample vector groups, determine the sum of the offsets between the target vector and the center point of each of the sample vector groups;

[0012] The monitoring result is determined based on the sum of the offsets and the preset offset threshold.

[0013] In one embodiment, determining the monitoring result based on the sum of the offsets and a preset offset threshold includes:

[0014] If the sum of the offsets is greater than the offset threshold, then the resource transfer data is determined to be abnormal.

[0015] If the sum of the offsets is less than or equal to the offset threshold, then the resource transfer data is determined to be normal.

[0016] In one embodiment, determining the sum of the offsets between the target vector and the center points of each of the sample vector groups based on the offsets between the target vector and the center points of each of the sample vector groups includes:

[0017] Obtain the importance weight of each sample vector group; the importance weight of each sample vector group is used to characterize the proximity between the time corresponding to each sample vector group and the time corresponding to the resource transfer data;

[0018] Based on the offsets and the importance weights of each sample vector group, the sum of the offsets between the target vector and the center points of each sample vector group is determined.

[0019] In one embodiment, each of the sample vector groups includes multiple sample vectors, and the method further includes:

[0020] For each sample vector group, the center point with the smallest sum of distances to the center points of other sample vectors in the sample vector group is determined as the center point of the sample vector group.

[0021] In one embodiment, the method further includes:

[0022] The target user's multiple sample resource transfer data within a target time period are vectorized to obtain a sample vector corresponding to each sample resource transfer data; the target time period is earlier than the time corresponding to the resource transfer data.

[0023] According to the preset time unit, each sample vector is divided to obtain multiple sample vector groups;

[0024] The vector library is generated based on the multiple sample vector groups.

[0025] In one embodiment, the step of vectorizing the resource transfer data of the target user to obtain the target vector corresponding to the resource transfer data includes:

[0026] The resource transfer data of the target user is vectorized according to the preset vectorization model to obtain the target vector corresponding to the resource transfer data.

[0027] Secondly, this application also provides a monitoring device for resource transfer data. The device includes:

[0028] The acquisition module is used to perform vectorization processing on the resource transfer data of the target user and obtain the target vector corresponding to the resource transfer data.

[0029] The first determining module is used to determine the offset between the target vector and the center point of each sample vector group in the preset vector library; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0030] The second determining module is used to determine the monitoring result based on the offset between the target vector and the center point of each of the sample vector groups; the monitoring result is used to characterize whether the resource transfer data is abnormal.

[0031] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0032] The resource transfer data of the target user is vectorized to obtain the target vector corresponding to the resource transfer data;

[0033] Based on the target vector and a preset vector library, the offset between the target vector and the center point of each sample vector group in the vector library is determined; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0034] The monitoring result is determined based on the offset between the target vector and the center point of each of the sample vector groups; the monitoring result is used to characterize whether the resource transfer data is abnormal.

[0035] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0036] The resource transfer data of the target user is vectorized to obtain the target vector corresponding to the resource transfer data;

[0037] Based on the target vector and a preset vector library, the offset between the target vector and the center point of each sample vector group in the vector library is determined; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0038] The monitoring result is determined based on the offset between the target vector and the center point of each of the sample vector groups; the monitoring result is used to characterize whether the resource transfer data is abnormal.

[0039] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0040] The resource transfer data of the target user is vectorized to obtain the target vector corresponding to the resource transfer data;

[0041] Based on the target vector and a preset vector library, the offset between the target vector and the center point of each sample vector group in the vector library is determined; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0042] The monitoring result is determined based on the offset between the target vector and the center point of each of the sample vector groups; the monitoring result is used to characterize whether the resource transfer data is abnormal.

[0043] The aforementioned method, apparatus, computer equipment, and storage medium for monitoring resource transfer data obtain multiple sample vector groups based on the vectors corresponding to multiple sample resource transfer data of a target user within a target time period, thus generating a preset vector library. By vectorizing the resource transfer data of the target user, the target vector corresponding to the resource transfer data can be obtained. Therefore, based on the target vector and the preset database, the offset between the target vector and the center point of each sample vector group in the vector library can be determined. Furthermore, the monitoring result can be determined based on the offset between the target vector and the center point of each sample vector group. Since each sample vector group in the preset vector library represents the vectors corresponding to all sample resource transfer data within the target time period, the preset... The feature information included in each sample vector group in the vector library is relatively comprehensive. Therefore, the richness of the offset between the target vector and the center point of each sample vector group in the vector library is also high. Thus, the monitoring result of whether the acquired resource transfer data is abnormal can be accurately determined based on the offset between the target vector and the center point of each sample vector group. This avoids the problem of low monitoring accuracy of resource transfer data due to the large number of abnormal types of resource transfer data and the inaccurate acquisition of abnormal resource transfer features. In addition, the process of determining the monitoring result by the offset between the target vector and the center point of each sample vector group does not require comparison with a large amount of data, making the determination process simpler and less prone to errors. Attached Figure Description

[0044] Figure 1 This is an application environment diagram of a resource transfer data monitoring method in one embodiment;

[0045] Figure 2 This is a flowchart illustrating a method for monitoring resource transfer data in one embodiment;

[0046] Figure 3 This is a flowchart illustrating a method for monitoring resource transfer data in another embodiment;

[0047] Figure 4 This is a flowchart illustrating a method for monitoring resource transfer data in another embodiment;

[0048] Figure 5 This is a flowchart illustrating a method for monitoring resource transfer data in another embodiment;

[0049] Figure 6 This is a flowchart illustrating a method for monitoring resource transfer data in another embodiment;

[0050] Figure 7 This is a structural block diagram of a resource transfer data monitoring device in one embodiment;

[0051] Figure 8This is a structural block diagram of a resource transfer data monitoring device in another embodiment;

[0052] Figure 9 This is a structural block diagram of a resource transfer data monitoring device in another embodiment;

[0053] Figure 10 This is a structural block diagram of a resource transfer data monitoring device in another embodiment;

[0054] Figure 11 This is a structural block diagram of a resource transfer data monitoring device in another embodiment. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0056] It should be noted that the resource transfer data monitoring method, device, computer equipment, and storage medium of the present invention can be used in the financial field, or in any technical field other than the financial field. The present invention does not limit the application field of the resource transfer data monitoring method, device, computer equipment, and storage medium.

[0057] The resource transfer data monitoring method provided in this application embodiment can be applied to, for example... Figure 1 The application environment shown. The computer device can be a terminal, and its internal structure diagram can be as follows. Figure 1 As shown, the computer device includes a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, NFC (Near Field Communication), or other technologies. When executed by the processor, the computer program implements a method for monitoring resource transfer data. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad mounted on the computer device casing, or an external keyboard, touchpad, or mouse.

[0058] In one embodiment, such as Figure 2As shown, a method for monitoring resource transfer data is provided, which can be applied to... Figure 1 Taking the terminal in the example, the explanation includes the following steps:

[0059] S201, Perform vectorization processing on the resource transfer data of the target user to obtain the target vector corresponding to the resource transfer data.

[0060] The resource transfer data includes data such as resource transfer time, resource transfer type, and resource transfer value. In this embodiment, the resource transfer data is the data generated when the target user performs a resource transfer action, and there is a one-to-one correspondence between the target user's resource transfer action and the target user's resource transfer data.

[0061] Optionally, in this embodiment, by vectorizing the resource transfer data of the target user, the text-based resource transfer data can be converted into a digital vector.

[0062] Optionally, in this embodiment, the resource transfer data can be vectorized according to a preset correspondence. For example, the preset correspondence includes the correspondence between resource transfer time and a first value, the correspondence between resource transfer type and a second value, and the correspondence between resource transfer value and a third value. The first value, the second value, and the third value corresponding to the resource data can be determined according to the above correspondence, and then the target vector corresponding to the resource transfer data can be formed according to the first value, the second value, and the third value.

[0063] S202, determine the offset between the target vector and the center point of each sample vector group in the preset vector library; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0064] In this embodiment, the offset is a numerical value. The center point of each sample vector is a point in the vector space, and the center point of the target vector is also a point in the vector space. In this embodiment, the offset can be used to characterize the distance between the center point of the target vector and the center point of each sample vector group.

[0065] In this embodiment, the vector library includes multiple sample vector groups. The vectors in each sample vector group are obtained based on the transfer data of multiple sample resources. In this embodiment, the offset between the target vector and the center point of each sample vector group in the vector library can be determined based on the center point of the target vector and the center point of each sample vector group in the vector library.

[0066] Optionally, the target time period may include multiple time periods. For example, the target time period may include year A and year B. Optionally, multiple sample resource transfer data corresponding to year A and multiple sample resource transfer data corresponding to year B can be obtained, and the multiple sample resource transfer data corresponding to year A and multiple sample resource transfer data corresponding to year B can be vectorized to obtain sample vector groups corresponding to year A and year B. Alternatively, the vectors corresponding to multiple sample resource transfer data in the target time period can be obtained, and the vectors corresponding to multiple sample resource transfer data in the target time period can be divided according to year A and year B to obtain sample vector groups corresponding to year A and year B.

[0067] S203, determine the monitoring results based on the offset between the target vector and the center point of each sample vector group; the monitoring results are used to characterize whether the resource transfer data is abnormal.

[0068] Optionally, the judgment result corresponding to each sample vector group can be determined based on the offset between the target vector and the center point of each sample vector group. The judgment result can include normal and abnormal. When the number of judgment results corresponding to each sample vector group that are abnormal is greater than a preset number, the monitoring result is determined to be abnormal. For example, the vector library includes sample vector group 1, sample vector group 2, sample vector group 3, sample vector group 4, and sample vector group 5, with a preset number of 2. When the judgment results corresponding to sample vector group 1, sample vector group 2, and sample vector group 3 are all abnormal, the number of judgment results corresponding to the sample vector group that are abnormal is 2. Therefore, the monitoring result corresponding to the resource transfer data of the target user is abnormal.

[0069] In the aforementioned method for monitoring resource transfer data, multiple sample vector groups are obtained based on the vectors corresponding to multiple sample resource transfer data of the target user within a target time period, thus creating a pre-defined vector library. By vectorizing the resource transfer data of the target user, the target vector corresponding to the resource transfer data can be obtained. Therefore, based on the target vector and the pre-defined database, the offset between the target vector and the center point of each sample vector group in the vector library can be determined. Furthermore, the monitoring result can be determined based on the offset between the target vector and the center point of each sample vector group. Since each sample vector group in the pre-defined vector library represents the vectors corresponding to all sample resource transfer data within the target time period, the pre-defined vector library contains... The vector group contains comprehensive feature information. Therefore, based on the target vector and the preset vector library, the richness of the offset between the target vector and the center point of each sample vector group in the vector library is also high. Thus, the monitoring result representing whether the acquired resource transfer data is abnormal can be accurately determined based on the offset between the target vector and the center point of each sample vector group. This avoids the problem of low monitoring accuracy of resource transfer data due to the large number of abnormal types of resource transfer data and the inaccurate acquisition of abnormal resource transfer features. In addition, the process of determining the monitoring result by the offset between the target vector and the center point of each sample vector group does not require comparison with a large amount of data, making the determination process simpler and less prone to errors.

[0070] The following describes the specific process of determining the monitoring results based on the offset between the target vector and the center points of each sample vector group. In one embodiment, such as... Figure 3 As shown, the above S203 includes:

[0071] S301, determine the sum of the offsets between the target vector and the center points of each sample vector group based on the offsets between the target vector and the center points of each sample vector group.

[0072] Optionally, the sum of the offsets between the target vector and the center points of each sample vector group can be the sum of the offsets between the target vector and the center points of each sample vector group. For example, if there are sample vector groups 1, 2, and 3, and the offset between the target vector and the center point of sample vector group 1 is 2, the offset between the target vector and the center point of sample vector group 2 is 1, and the offset between the target vector and the center point of sample vector group 3 is 3, then the sum of the offsets between the target vector and the center points of each sample vector group is 6.

[0073] Optionally, the sum of the offsets between the target vector and the center point of each sample vector group can be the sum of the squares of the offsets between the target vector and the center point of each sample vector group. For example, if there are sample vector groups 1, 2, and 3, and the offset between the target vector and the center point of sample vector group 1 is 2, the offset between the target vector and the center point of sample vector group 2 is 1, and the offset between the target vector and the center point of sample vector group 3 is 3, then the sum of the offsets between the target vector and the center point of each sample vector group is 14.

[0074] S302, determine the monitoring result based on the total offset and the preset offset threshold.

[0075] Optionally, the monitoring results may include resource transfer data normal, resource transfer data status pending determination, resource transfer data abnormal, and resource transfer data error. The offset threshold may include multiple offset ranges. For example, if the total offset is in the offset range (-∞, 0), the monitoring result is resource transfer data error; if the total offset is in the offset range [0, 10), the monitoring result is resource transfer data normal; if the total offset is in the offset range [10, 20), the monitoring result is resource transfer data status pending determination and requires further confirmation by staff; and if the total offset is in the offset range [20, ∞), the monitoring result is resource transfer data abnormal.

[0076] In this embodiment, using offset can avoid the situation where the monitoring results are incorrect due to calculation errors when using the offset between a target vector and the center point of a sample vector group. At the same time, combining offset threshold makes the monitoring results more accurate and the judgment logic simple and clear.

[0077] The following describes the specific judgment process for determining the monitoring result based on the sum of the offsets and a preset offset threshold. In one embodiment, such as... Figure 4 As shown, the above S302 includes:

[0078] S401, if the total offset is greater than the offset threshold, then the resource transfer data is determined to be abnormal.

[0079] In this embodiment, when the total offset is greater than the offset threshold, it indicates a significant difference between the resource transfer data and the sample resource transfer data, signifying that the resource transfer data is abnormal. For example, if the total offset is 25 and the offset threshold is 10, the total offset is greater than the offset threshold, and the resource transfer data corresponding to this total offset is abnormal.

[0080] S402, if the total offset is less than or equal to the offset threshold, then the resource transfer data is determined to be normal.

[0081] In this embodiment, when the total offset is less than or equal to the offset threshold, it indicates that the difference between the resource transfer data and the sample resource transfer data is small or non-existent, indicating that the resource transfer data is abnormal. For example, if the total offset is 10 and the offset threshold is 10, the total offset equals the offset threshold, and the resource transfer data corresponding to this total offset is normal.

[0082] In this embodiment, the monitoring results are divided into abnormal resource transfer data and normal resource transfer data, so that users can more accurately obtain whether the current resource transfer behavior is abnormal without the need for secondary judgment.

[0083] In the scenario described above, where the sum of the offsets between the target vector and the center points of each sample vector group is determined based on the offsets between the target vector and the center points of each sample vector group, the sum of the offsets between the target vector and the center points of each sample vector group can be determined based on the importance weights of each sample vector group and each offset. In one embodiment, such as Figure 5 As shown, the above S301 includes:

[0084] S501, obtain the importance weight of each sample vector group; the importance weight of each sample vector group is used to characterize the closeness between the time corresponding to each sample vector group and the time corresponding to the resource transfer data.

[0085] In this embodiment, the importance weights of each sample vector group are different. The closer the time corresponding to a sample vector group is to the time corresponding to the resource transfer data, the higher the importance weight of that sample vector group. For example, if there are sample vector groups 1, 2, and 3, where sample vector group 1 corresponds to year A, sample vector group 2 corresponds to year B, sample vector group 3 corresponds to year C, and the time corresponding to the resource transfer data is year D, and the time order of the years is year B, year C, year A, year D, the importance weight of sample vector group 1 is 0.5, the importance weight of sample vector group 3 is 0.3, and the importance weight of sample vector group 2 is 0.2.

[0086] S502, based on the importance weights of each offset and each sample vector group, determine the sum of the offsets between the target vector and the center points of each sample vector group.

[0087] In this embodiment, the offsets are weighted and summed according to their respective offsets and the importance weights of each sample vector group to obtain the total offset between the target vector and the center point of each sample vector group. For example, if there are sample vector group 1, sample vector group 2, and sample vector group 3, with an importance weight of 0.5 for sample vector group 1, 0.2 for sample vector group 2, and 0.3 for sample vector group 3, and the offset between the target vector and the center point of sample vector group 1 is 2, the offset between the target vector and the center point of sample vector group 2 is 1, and the offset between the target vector and the center point of sample vector group 3 is 3, then the total offset between the target vector and the center point of each sample vector group is 2 × 0.5 + 1 × 0.2 + 3 × 0.3 = 2.1.

[0088] In this embodiment, the importance weight of each sample vector group is determined by the proximity between the time corresponding to each sample vector group and the time corresponding to the resource transfer data. Compared with using the same weight for each sample vector group, the sum of the offsets is more accurate by the method in this embodiment, thereby improving the accuracy of monitoring resource transfer.

[0089] The process of determining the center point of a sample vector group will be described below. In one embodiment, each sample vector group includes multiple sample vectors. The method further includes, for each sample vector group, determining the center point of the sample vector group as the center point of the sample vector group whose sum of distances to the center points of other sample vectors in the sample vector group is the smallest.

[0090] In this embodiment, the sample vector group includes multiple sample vectors. First, the center point of each sample vector is determined. Then, the distance between each sample vector is determined based on its center point. Further, the sum of the distances between the center point of each sample vector and the center points of other vectors in the sample vector group is obtained. By comparing the sums of these distances, the center point with the smallest sum of distances to the center points of other sample vectors in the sample vector group is determined as the center point of the sample vector group. Optionally, the distances between the center points of each sample vector can be obtained using a preset distance calculation formula, thereby determining the center point of the sample vector group based on the distances between the center points of each sample vector; alternatively, the sample vectors in each sample vector group can be input into a preset center point determination model based on a pre-trained model to obtain the center point of each sample vector group.

[0091] In this embodiment, the center point of each sample vector in the sample vector group that is equidistant from the center points of other sample vectors is determined as the center point of the sample vector group. This ensures that the determined center point can characterize the common features of each sample vector group, thereby improving the monitoring accuracy of resource transfer data.

[0092] The process of generating the preset vector library will be described below. In one embodiment, such as... Figure 6 As shown, the above method also includes:

[0093] S601, vectorize multiple sample resource transfer data of the target user within the target time period to obtain the sample vector corresponding to each sample resource transfer data; the target time period is earlier than the time corresponding to the resource transfer data.

[0094] In this embodiment, multiple sample resource transfer data of the target user within a target time period are obtained, and the multiple sample resource transfer data of the target user within the target time period are vectorized to obtain the vectors corresponding to the multiple sample resource transfer data of the target user within the target time period. It should be noted that the method used to vectorize the sample resource transfer data is the same as the method used to vectorize the resource transfer data.

[0095] For example, the time corresponding to the resource transfer data is in time period F. The time periods earlier than the time corresponding to the resource transfer data include time periods A, B, C, D, and E in sequence. Among them, time period A is the earliest. Historical resource transfer data in time period E can be selected as sample resource transfer data. Vectorization processing is performed on each sample resource transfer data to obtain the sample vector corresponding to each sample resource transfer data.

[0096] S602, according to the preset time unit, divide each sample vector into multiple sample vector groups.

[0097] Optionally, the preset time unit can be 1 year; or, the preset time unit can be 1 quarter; or, the preset time unit can be 1 month. For example, when the preset time unit is 1 year and the length of the time period corresponding to each sample vector is 5 years, the sample vectors can be divided into 5 sample vector groups.

[0098] S603 generates a vector library based on multiple sample vector groups.

[0099] In this embodiment, multiple sample vector groups are combined into a vector library. Optionally, one user can correspond to one vector library, or all sample vector groups corresponding to all users can be stored in one vector library. When monitoring resource transfer data of a target user, the corresponding sample vector group is selected from the vector library for processing.

[0100] In this embodiment, each sample vector is divided according to a preset time unit, so that the features of each sample vector in each sample vector group are more similar, making it easier to perform further processing when it is necessary to use each sample vector group in the vector library.

[0101] In the scenario described above, where resource transfer data of a target user is vectorized to obtain the target vector corresponding to the resource transfer data, a vectorization model is used to vectorize the resource transfer data of the target user to obtain the target vector corresponding to the resource transfer data. In one embodiment, S201 includes: vectorizing the resource transfer data of the target user according to a preset vectorization model to obtain the target vector corresponding to the resource transfer data.

[0102] In this embodiment, the vectorization model is pre-trained and stored in the terminal. The target user's resource transfer data is used as input to the vectorization model, which then performs vectorization processing on the target user's resource transfer data to obtain the target vector corresponding to the resource transfer data. Optionally, the vectorization model can be any one of the following vectorization models: One-Hot Model, Bag-of-Words Model (BOW), Word2vec, Document2vec, etc.

[0103] In this embodiment, a vectorization model is used to vectorize the resource transfer data of the target user, resulting in a more accurate target vector with a smaller error, thereby improving the monitoring accuracy of the resource transfer data.

[0104] The following describes an embodiment of this disclosure using a specific scenario of monitoring resource transfer data. The method includes the following steps:

[0105] S1, based on the preset vectorization model, the resource transfer data of the target user is vectorized to obtain the target vector corresponding to the resource transfer data.

[0106] S2, vectorize multiple sample resource transfer data of the target user within the target time period to obtain sample vectors corresponding to each sample resource transfer data; the target time period is earlier than the time corresponding to the resource transfer data; divide each sample vector according to the preset time unit to obtain multiple sample vector groups; generate a vector library based on multiple sample vector groups.

[0107] S3. For each sample vector group, the center point with the smallest sum of distances to the center points of other sample vectors in the sample vector group is determined as the center point of the sample vector group.

[0108] S4. Based on the target vector and the preset vector library, determine the offset between the target vector and the center point of each sample vector group in the vector library.

[0109] S5, obtain the importance weight of each sample vector group; the importance weight of each sample vector group is used to characterize the closeness between the time corresponding to each sample vector group and the time corresponding to the resource transfer data; based on each offset and the importance weight of each sample vector group, determine the sum of the offsets between the target vector and the center point of each sample vector group.

[0110] S6. If the total offset is greater than the offset threshold, the resource transfer data is determined to be abnormal; if the total offset is less than or equal to the offset threshold, the resource transfer data is determined to be normal.

[0111] In the aforementioned method for monitoring resource transfer data, multiple sample vector groups are obtained based on the vectors corresponding to multiple sample resource transfer data of the target user within a target time period, thus creating a pre-defined vector library. By vectorizing the resource transfer data of the target user, the target vector corresponding to the resource transfer data can be obtained. Therefore, based on the target vector and the pre-defined database, the offset between the target vector and the center point of each sample vector group in the vector library can be determined. Furthermore, the monitoring result can be determined based on the offset between the target vector and the center point of each sample vector group. Since each sample vector group in the pre-defined vector library represents the vectors corresponding to all sample resource transfer data within the target time period, the pre-defined vector library contains... The vector group contains comprehensive feature information. Therefore, based on the target vector and the preset vector library, the richness of the offset between the target vector and the center point of each sample vector group in the vector library is also high. Thus, the monitoring result representing whether the acquired resource transfer data is abnormal can be accurately determined based on the offset between the target vector and the center point of each sample vector group. This avoids the problem of low monitoring accuracy of resource transfer data due to the large number of abnormal types of resource transfer data and the inaccurate acquisition of abnormal resource transfer features. In addition, the process of determining the monitoring result by the offset between the target vector and the center point of each sample vector group does not require comparison with a large amount of data, making the determination process simpler and less prone to errors.

[0112] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0113] Based on the same inventive concept, this application also provides a resource transfer data monitoring device for implementing the resource transfer data monitoring method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more resource transfer data monitoring device embodiments provided below can be found in the limitations of the resource transfer data monitoring method described above, and will not be repeated here.

[0114] In one embodiment, such as Figure 7 As shown, a monitoring device for resource transfer data is provided, comprising: an acquisition module 10, a first determination module 11, and a second determination module 12, wherein:

[0115] The acquisition module 10 is used to perform vectorization processing on the resource transfer data of the target user and obtain the target vector corresponding to the resource transfer data.

[0116] The first determining module 11 is used to determine the offset between the target vector and the center point of each sample vector group in the preset vector library; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0117] The second determining module 12 is used to determine the monitoring results based on the offset between the target vector and the center point of each sample vector group; the monitoring results are used to characterize whether the resource transfer data is abnormal.

[0118] The resource transfer data monitoring device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0119] In one embodiment, such as Figure 8 As shown, the second determining module 12 includes: a first determining unit 121 and a second determining unit 122, wherein:

[0120] The first determining unit 121 is used to determine the total offset between the target vector and the center point of each sample vector group based on the offset between the target vector and the center point of each sample vector group.

[0121] The second determining unit 122 is used to determine the monitoring result based on the total offset and the preset offset threshold.

[0122] The resource transfer data monitoring device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0123] In one embodiment, the second determining unit 122 is used to determine that the resource transfer data is abnormal if the total offset is greater than the offset threshold, and to determine that the resource transfer data is normal if the total offset is less than or equal to the offset threshold.

[0124] The resource transfer data monitoring device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0125] In one embodiment, the first determining unit 121 is used to obtain the importance weight of each sample vector group; the importance weight of each sample vector group is used to characterize the closeness between the time corresponding to each sample vector group and the time corresponding to the resource transfer data; and the total offset between the target vector and the center point of each sample vector group is determined according to each offset and the importance weight of each sample vector group.

[0126] The resource transfer data monitoring device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0127] In one embodiment, each sample vector group includes multiple sample vectors, such as... Figure 9 As shown, the above-mentioned device further includes: a third determining module 13, wherein:

[0128] The third determining module 13 is used to determine the center point of the sample vector group as the center point of the sample vector group for each sample vector group, which has the smallest sum of distances to the center points of other sample vectors in the sample vector group.

[0129] The resource transfer data monitoring device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0130] In one embodiment, such as Figure 10 As shown, the above-mentioned device further includes: a processing module 14, a dividing module 15, and a generating module 16, wherein:

[0131] Processing module 14 is used to vectorize multiple sample resource transfer data of the target user within a target time period to obtain the sample vector corresponding to each sample resource transfer data; the target time period is earlier than the time corresponding to the resource transfer data.

[0132] The partitioning module 15 is used to partition each sample vector according to a preset time unit to obtain multiple sample vector groups.

[0133] The generation module 16 is used to generate a vector library based on multiple sample vector groups.

[0134] The resource transfer data monitoring device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0135] In one embodiment, such as Figure 11 As shown, the above-mentioned acquisition module 10 includes: an acquisition unit 101, wherein:

[0136] The acquisition unit 101 is used to perform vectorization processing on the resource transfer data of the target user according to the preset vectorization model, and obtain the target vector corresponding to the resource transfer data.

[0137] The resource transfer data monitoring device provided in this embodiment can execute the above method embodiment, and its implementation principle and technical effect are similar, so it will not be described again here.

[0138] Each module in the aforementioned resource transfer data monitoring device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0139] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0140] The resource transfer data of the target user is vectorized to obtain the target vector corresponding to the resource transfer data;

[0141] Determine the offset between the target vector and the center point of each sample vector group in the preset vector library; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0142] The monitoring results are determined based on the offset between the target vector and the center point of each sample vector group; the monitoring results are used to characterize whether the resource transfer data is abnormal.

[0143] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0144] Determine the sum of the offsets between the target vector and the center points of each sample vector group based on the offsets between the target vector and the center points of each sample vector group.

[0145] The monitoring results are determined based on the total offset and the preset offset threshold.

[0146] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0147] If the total offset exceeds the offset threshold, the resource transfer data is determined to be abnormal.

[0148] If the total offset is less than or equal to the offset threshold, then the resource transfer data is considered normal.

[0149] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0150] Obtain the importance weight of each sample vector group; the importance weight of each sample vector group is used to characterize the degree of proximity between the time corresponding to each sample vector group and the time corresponding to the resource transfer data;

[0151] Based on the importance weights of each offset and each sample vector group, the total offset between the target vector and the center point of each sample vector group is determined.

[0152] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0153] For each sample vector group, the center point of the sample vector group is determined as the center point of the sample vector group whose sum of distances to the center points of other sample vectors in the sample vector group is the center point of the sample vector group.

[0154] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0155] Vectorize multiple sample resource transfer data of the target user within the target time period to obtain the sample vector corresponding to each sample resource transfer data; the target time period is earlier than the time corresponding to the resource transfer data.

[0156] According to the preset time unit, each sample vector is divided into multiple sample vector groups;

[0157] A vector library is generated based on multiple sample vector groups.

[0158] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0159] The target user's resource transfer data is vectorized according to the preset vectorization model to obtain the target vector corresponding to the resource transfer data.

[0160] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0161] The resource transfer data of the target user is vectorized to obtain the target vector corresponding to the resource transfer data;

[0162] Determine the offset between the target vector and the center point of each sample vector group in the preset vector library; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0163] The monitoring results are determined based on the offset between the target vector and the center point of each sample vector group; the monitoring results are used to characterize whether the resource transfer data is abnormal.

[0164] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0165] Determine the sum of the offsets between the target vector and the center points of each sample vector group based on the offsets between the target vector and the center points of each sample vector group.

[0166] The monitoring results are determined based on the total offset and the preset offset threshold.

[0167] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0168] If the total offset exceeds the offset threshold, the resource transfer data is determined to be abnormal.

[0169] If the total offset is less than or equal to the offset threshold, then the resource transfer data is considered normal.

[0170] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0171] Obtain the importance weight of each sample vector group; the importance weight of each sample vector group is used to characterize the degree of proximity between the time corresponding to each sample vector group and the time corresponding to the resource transfer data;

[0172] Based on the importance weights of each offset and each sample vector group, the total offset between the target vector and the center point of each sample vector group is determined.

[0173] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0174] For each sample vector group, the center point of the sample vector group is determined as the center point of the sample vector group whose sum of distances to the center points of other sample vectors in the sample vector group is the center point of the sample vector group.

[0175] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0176] Vectorize multiple sample resource transfer data of the target user within the target time period to obtain the sample vector corresponding to each sample resource transfer data; the target time period is earlier than the time corresponding to the resource transfer data.

[0177] According to the preset time unit, each sample vector is divided into multiple sample vector groups;

[0178] A vector library is generated based on multiple sample vector groups.

[0179] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0180] The target user's resource transfer data is vectorized according to the preset vectorization model to obtain the target vector corresponding to the resource transfer data.

[0181] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0182] The resource transfer data of the target user is vectorized to obtain the target vector corresponding to the resource transfer data;

[0183] Determine the offset between the target vector and the center point of each sample vector group in the preset vector library; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period.

[0184] The monitoring results are determined based on the offset between the target vector and the center point of each sample vector group; the monitoring results are used to characterize whether the resource transfer data is abnormal.

[0185] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0186] Determine the sum of the offsets between the target vector and the center points of each sample vector group based on the offsets between the target vector and the center points of each sample vector group.

[0187] The monitoring results are determined based on the total offset and the preset offset threshold.

[0188] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0189] If the total offset exceeds the offset threshold, the resource transfer data is determined to be abnormal.

[0190] If the total offset is less than or equal to the offset threshold, then the resource transfer data is considered normal.

[0191] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0192] Obtain the importance weight of each sample vector group; the importance weight of each sample vector group is used to characterize the degree of proximity between the time corresponding to each sample vector group and the time corresponding to the resource transfer data;

[0193] Based on the importance weights of each offset and each sample vector group, the total offset between the target vector and the center point of each sample vector group is determined.

[0194] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0195] For each sample vector group, the center point of the sample vector group is determined as the center point of the sample vector group whose sum of distances to the center points of other sample vectors in the sample vector group is the center point of the sample vector group.

[0196] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0197] Vectorize multiple sample resource transfer data of the target user within the target time period to obtain the sample vector corresponding to each sample resource transfer data; the target time period is earlier than the time corresponding to the resource transfer data.

[0198] According to the preset time unit, each sample vector is divided into multiple sample vector groups;

[0199] A vector library is generated based on multiple sample vector groups.

[0200] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0201] The target user's resource transfer data is vectorized according to the preset vectorization model to obtain the target vector corresponding to the resource transfer data.

[0202] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0203] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0204] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0205] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for monitoring resource transfer data, characterized in that, The method includes: The resource transfer data of the target user is vectorized according to a preset correspondence to determine the first value, second value and third value corresponding to the resource transfer data, and a target vector corresponding to the resource transfer data is formed based on the first value, second value and third value; the resource transfer data includes resource transfer time, resource transfer type and resource transfer value; The offset between the target vector and the center point of each sample vector group in the preset vector library is determined; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period; the offset represents the distance between the center point of the target vector and the center point of each sample vector group, and each sample vector group is obtained by dividing each sample vector according to a preset time unit; Based on the importance weight of the target vector and the offset of the center point of each sample vector group, the total offset of the target vector and the center point of each sample vector group is determined. The importance weight is used to characterize the closeness between the time corresponding to each sample vector group and the time corresponding to the resource transfer data. The monitoring result is determined based on the sum of the offsets and the preset offset threshold; the monitoring result is used to characterize whether the resource transfer data is abnormal.

2. The method according to claim 1, characterized in that, Determining the monitoring result based on the sum of the offsets and a preset offset threshold includes: If the sum of the offsets is greater than the offset threshold, then the resource transfer data is determined to be abnormal. If the sum of the offsets is less than or equal to the offset threshold, then the resource transfer data is determined to be normal.

3. The method according to claim 1 or 2, characterized in that, The step of determining the sum of the offsets between the target vector and the center points of each sample vector group based on the importance weight of the target vector and the offset of the center point of each sample vector group includes: Obtain the importance weights of each of the aforementioned sample vector groups; Based on the offsets and the importance weights of each sample vector group, the total offset between the target vector and the center point of each sample vector group is determined.

4. The method according to claim 1, characterized in that, Each of the aforementioned sample vector groups includes multiple sample vectors, and the method further includes: For each sample vector group, the center point with the smallest sum of distances to the center points of other sample vectors in the sample vector group is determined as the center point of the sample vector group.

5. The method according to claim 1 or 2, characterized in that, The method further includes: The vector library is generated based on each of the aforementioned sample vector groups; Each of the aforementioned sample vectors is obtained by vectorizing multiple sample resource transfer data of the target user within a target time period, resulting in a sample vector corresponding to each of the sample resource transfer data; the target time period is earlier than the time corresponding to the resource transfer data.

6. The method according to claim 1, characterized in that, The step of vectorizing the resource transfer data of the target user according to a preset correspondence, determining the first value, second value, and third value corresponding to the resource transfer data, and forming the target vector corresponding to the resource transfer data based on the first value, second value, and third value includes: The resource transfer data of the target user is vectorized according to the preset vectorization model to obtain the target vector corresponding to the resource transfer data.

7. A monitoring device for resource transfer data, characterized in that, The device includes: The acquisition module is used to vectorize the resource transfer data of the target user according to a preset correspondence, determine the first value, second value and third value corresponding to the resource transfer data, and form the target vector corresponding to the resource transfer data based on the first value, second value and third value; the resource transfer data includes resource transfer time, resource transfer type and resource transfer value; The first determining module is used to determine the offset between the target vector and the center point of each sample vector group in the preset vector library; each sample vector group in the vector library is determined based on the vectors corresponding to multiple sample resource transfer data of the target user within the target time period; the offset represents the distance between the center point of the target vector and the center point of each sample vector group, and each sample vector group is obtained by dividing each sample vector according to a preset time unit; The second determining module is used to determine the sum of the offsets between the target vector and the center points of each sample vector group based on the importance weight of the target vector and the offset of the center point of each sample vector group. The importance weight is used to characterize the closeness between the time corresponding to each sample vector group and the time corresponding to the resource transfer data. The monitoring result is determined based on the sum of the offsets and a preset offset threshold. The monitoring result is used to characterize whether the resource transfer data is abnormal.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images