Object detection method and device, storage medium and electronic equipment

Abstract

The invention discloses an object detection method and device, a storage medium and electronic equipment. Relates to the technical field of big data, and comprises the steps that a to-be-detected target object is determined, first data information of the target object is acquired, and the first data information at least comprises attribute information and transaction information of the target object; a target feature set is obtained, and the target feature set at least comprises risk feature values corresponding to risk data fields of a plurality of risk objects and weight values corresponding to the risk feature values; and performing risk detection on the target object based on a target feature set and the first data information to obtain a risk detection result. Through the method and the device, the problem that the accuracy is relatively low when the risk object is detected through a model in related technologies is solved.

Description

Technical Field

[0001] The present application relates to the field of big data technology, and in particular to a method and device for detecting an object, a storage medium, and an electronic device. Background Art

[0002] Identifying risky users in financial institutions is crucial for the development of financial business. In the existing technology, risky users are often identified through machine learning models. At present, when training machine learning models, data sets containing both positive and negative samples are used to participate in model training. However, if the proportion of target objects (i.e., risky users) is very small, it is difficult to improve the model training efficiency and target object coverage at the same time using the current machine learning method. Therefore, there is a problem of low accuracy when detecting risky objects through the model.

[0003] Regarding the problem of low accuracy when detecting risk objects through models in related technologies, no effective solution has been proposed yet. Summary of the invention

[0004] The main purpose of the present application is to provide an object detection method and device, a storage medium and an electronic device to solve the problem of low accuracy when detecting risk objects through models in related technologies.

[0005] In order to achieve the above-mentioned purpose, according to one aspect of the present application, a method for detecting an object is provided. The method comprises: determining a target object to be detected and obtaining first data information of the target object, wherein the first data information at least comprises: attribute information and transaction information of the target object; obtaining a target feature set, wherein the target feature set at least comprises: risk feature values ​​corresponding to risk data fields of multiple risk objects and weight values ​​corresponding to the risk feature values; performing risk detection on the target object based on the target feature set and the first data information to obtain a risk detection result.

[0006] Furthermore, risk detection is performed on the target object based on the target feature set and the first data information to obtain a risk detection result, including: matching the first data information and the risk feature values ​​in the target feature set to obtain matched risk feature values; calculating according to the weight values ​​of the matched risk feature values ​​to obtain the risk value of the target object; and obtaining the risk detection result based on the risk value.

[0007] Furthermore, obtaining the target feature set includes: determining the data field corresponding to the second data information of multiple risk objects and the data type corresponding to the data field; based on the data type, determining the risk field from the data field, and determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information; obtaining the target feature set based on the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value.

[0008] Further, based on the data type, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information includes: if the data type is discrete data, determining the number of first characteristic values ​​corresponding to each data field based on the second data information; calculating the proportion of the first characteristic value in the second data information to obtain the proportion value corresponding to each first characteristic value; calculating the weight value corresponding to the first characteristic value based on the proportion value corresponding to each first characteristic value and the number of the first characteristic values, or based on the proportion value corresponding to each first characteristic value to obtain the first weight value; based on the first weight value, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the first characteristic value.

[0009] Further, based on the first weight value, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the first characteristic value includes: for each data field, judging whether the standard deviation of the first weight value is greater than a first threshold value, if the standard deviation is greater than the first threshold value, determining that the data field is a risk field; for each risk field, screening the first characteristic value corresponding to the risk field based on the first weight value to obtain the risk characteristic value corresponding to the risk field; and determining the weight value corresponding to the risk characteristic value based on the first weight value.

[0010] Further, based on the data type, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information includes: if the data type is continuous data, discretizing the second data information to obtain processed second data information; determining the number of second characteristic values ​​corresponding to each data field based on the processed second data information; calculating the proportion of the second characteristic value in the processed second data information to obtain the proportion value corresponding to each second characteristic value; calculating the weight value corresponding to the second characteristic value based on the proportion value corresponding to each second characteristic value and the number of the second characteristic values ​​to obtain the second weight value; based on the second weight value, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second characteristic value.

[0011] Furthermore, according to the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value, obtaining the target characteristic set includes: filtering the risk field according to the weight value corresponding to the risk characteristic value to obtain a filtered risk field; combining the filtered risk fields to obtain a combined risk field; determining the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field according to the risk characteristic value corresponding to the filtered risk field; determining the target characteristic set according to the risk characteristic value corresponding to the risk field, the weight value corresponding to the risk characteristic value, the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field.

[0012] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a device for detecting an object is provided. The device comprises: a determination unit, used to determine a target object to be detected and obtain first data information of the target object, wherein the first data information at least comprises: attribute information and transaction information of the target object; an acquisition unit, used to obtain a target feature set, wherein the target feature set at least comprises: risk feature values ​​corresponding to risk data fields of multiple risk objects and weight values ​​corresponding to the risk feature values; a detection unit, used to perform risk detection on the target object based on the target feature set and the first data information to obtain a risk detection result.

[0013] Furthermore, the detection unit includes: a matching subunit, used to match the first data information and the risk feature value in the target feature set to obtain a matched risk feature value; a calculation subunit, used to calculate based on the weight value of the matched risk feature value to obtain the risk value of the target object; and a first determination subunit, used to obtain the risk detection result based on the risk value.

[0014] Furthermore, the acquisition unit includes: a second determination subunit, used to determine the data field corresponding to the second data information of multiple risk objects and the data type corresponding to the data field; a third determination subunit, used to determine the risk field from the data field, and determine the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information based on the data type; and a fourth determination subunit, used to obtain the target feature set based on the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value.

[0015] Furthermore, the third determination subunit includes: a first determination module, which is used to determine the number of first eigenvalues ​​corresponding to each data field based on the second data information if the data type is discrete data; a first calculation module, which is used to calculate the proportion of the first eigenvalue in the second data information to obtain the proportion value corresponding to each first eigenvalue; a second calculation module, which is used to calculate the weight value corresponding to the first eigenvalue based on the proportion value corresponding to each first eigenvalue and the number of the first eigenvalues, or based on the proportion value corresponding to each first eigenvalue, to obtain the first weight value; and a second determination module, which is used to determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the first characteristic value based on the first weight value.

[0016] Furthermore, the second determination module includes: a judgment submodule, used to judge whether the standard deviation of the first weight value is greater than a first threshold for each data field, and if the standard deviation is greater than the first threshold, determine that the data field is a risk field; a screening submodule, used to screen the first characteristic value corresponding to the risk field according to the first weight value for each risk field to obtain the risk characteristic value corresponding to the risk field; and a determination submodule, used to determine the weight value corresponding to the risk characteristic value based on the first weight value.

[0017] Furthermore, the third determination subunit includes: a processing module, which is used to discretize the second data information if the data type is continuous data to obtain processed second data information; a third determination module, which is used to determine the number of second eigenvalues ​​corresponding to each data field based on the processed second data information; a third calculation module, which is used to calculate the proportion of the second eigenvalue in the processed second data information to obtain the proportion value corresponding to each second eigenvalue; a fourth calculation module, which is used to calculate the weight value corresponding to the second eigenvalue based on the proportion value corresponding to each second eigenvalue and the number of the second eigenvalues ​​to obtain the second weight value; a fourth determination module, which is used to determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field from the second characteristic value, and the weight value corresponding to the risk characteristic value based on the second weight value.

[0018] Furthermore, the fourth determination subunit includes: a screening module, used to screen the risk field according to the weight value corresponding to the risk characteristic value to obtain the screened risk field; a combination module, used to combine the screened risk fields to obtain a combined risk field; a fifth determination module, used to determine the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field according to the risk characteristic value corresponding to the screened risk field; a sixth determination module, used to determine the target feature set according to the risk characteristic value corresponding to the risk field, the weight value corresponding to the risk characteristic value, the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field.

[0019] In order to achieve the above-mentioned purpose, according to another aspect of the present application, a computer-readable storage medium is also provided, wherein the computer-readable storage medium includes a stored executable program, wherein when the executable program is running, the device where the computer-readable storage medium is located is controlled to execute the steps of any one of the above-mentioned method embodiments.

[0020] In order to achieve the above-mentioned purpose, according to another aspect of the present application, there is further provided an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above-mentioned method embodiments.

[0021] In the embodiment of the present application, the target object to be detected is determined and the first data information of the target object is obtained, wherein the first data information at least includes: the attribute information and transaction information of the target object; the target feature set is obtained, wherein the target feature set at least includes: the risk feature values ​​corresponding to the risk data fields of multiple risk objects and the weight values ​​corresponding to the risk feature values; the target object is subjected to risk detection based on the target feature set and the first data information to obtain the risk detection result, which solves the technical problem of low accuracy when detecting risk objects through models in the related technology. In this scheme, the target feature set is determined according to the risk feature values ​​corresponding to the risk data fields of multiple risk objects and the weight values ​​corresponding to the risk feature values. When it is necessary to perform risk detection on the target object, the risk detection is performed according to the first data information of the target object and the target feature set to obtain the corresponding risk detection result. The corresponding target feature set determined by the data of multiple risk objects can effectively improve the coverage of risk object detection, and can effectively avoid the problem that the accuracy of risk detection is relatively low due to the very small proportion of risk objects in specific scenarios and the use of current machine learning methods, thereby achieving the effect of improving the accuracy of risk object detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] Figure 1 It is a hardware structure block diagram of a computer terminal for implementing an object detection method provided in an embodiment of the present application;

[0024] Figure 2 is a flow chart of a method for detecting an object provided in an embodiment of the present application;

[0025] Figure 3 is a schematic diagram of continuous data provided according to an embodiment of the present application;

[0026] Figure 4 is a schematic diagram of a detection device for an object provided in an embodiment of the present application;

[0027] Figure 5 It is a structural block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] It should be noted that the collected information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for display, data for analysis, etc.) involved in this application are information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data are in compliance with relevant laws, regulations and standards, necessary confidentiality measures are taken, and public order and good customs are not violated, and corresponding operation entrances are provided for users to choose to authorize or refuse. For example, an interface is set up between this system and relevant users or institutions to provide users with corresponding operation entrances for users to choose to agree or refuse the results of automated decision-making; if the user chooses to refuse, the expert decision-making process will be entered.

[0031] Example 1

[0032] According to an embodiment of the present application, a method embodiment for detecting an object is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0033] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1FIG. 1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing an object detection method. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more (102a, 102b, ..., 102n are used to illustrate) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0034] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0035] The memory 104 can be used to store software programs and modules of application software, such as program instructions / data storage devices corresponding to the object detection method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, realizing the above-mentioned object detection method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0036] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0037] The display may be a touch screen type liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0038] Under the above operating environment, this application provides Figure 2 The object detection method shown. Figure 2 It is a flow chart of the object detection method according to the first embodiment of the present application.

[0039] Step S201, determining a target object to be detected and acquiring first data information of the target object, wherein the first data information at least includes: attribute information and transaction information of the target object.

[0040] Optionally, a target object that needs to be subjected to risk detection is determined, and first data information of the target object is obtained from the database of the financial institution. It should be noted that the first data information may include attribute information and transaction information of the target object, for example, the target object's gender, occupation, account type, transaction frequency, transaction time and other data.

[0041] Step S202: obtaining a target feature set, wherein the target feature set at least includes: risk feature values ​​corresponding to risk data fields of multiple risk objects and weight values ​​corresponding to the risk feature values.

[0042] Optionally, the risk data field is determined based on the data of the user who has been marked as a risk object, as well as the risk characteristic value corresponding to the risk data field and the weight value corresponding to the risk characteristic value, and the above-mentioned target feature set is determined based on the risk characteristic value corresponding to the risk data field and the weight value corresponding to the risk characteristic value. It should be noted that a data field usually refers to a column in a table, which contains data of the same type. For example, a user table may contain fields such as "user name", "email", "registration date", etc. In this solution, the data field can be gender, occupation, account type, transaction frequency, transaction time and other fields. The risk characteristic value corresponding to the risk data field is the value corresponding to the risk object. For example, the risk characteristic value corresponding to the transaction frequency data field of the risk object is 20.

[0043] Step S203: Perform risk detection on the target object based on the target feature set and the first data information to obtain a risk detection result.

[0044] Optionally, risk detection is performed on the target object according to the target feature set and the first data information to obtain a risk detection result corresponding to the target object.

[0045] To summarize, the target feature set is determined based on the risk feature values ​​corresponding to the risk data fields of multiple risk objects and the weight values ​​corresponding to the risk feature values. When risk detection is required for the target object, risk detection is performed based on the first data information of the target object and the target feature set to obtain the corresponding risk detection result. Determining the corresponding target feature set through the data of multiple risk objects can effectively improve the coverage of risk object detection, and can effectively avoid the problem of low accuracy of risk detection due to the small proportion of risk objects in specific scenarios using current machine learning methods, thereby achieving the effect of improving the accuracy of risk object detection.

[0046] Optionally, in the object detection method provided in the embodiment of the present application, risk detection is performed on the target object based on the target feature set and the first data information, and the risk detection result is obtained, including: matching the risk feature values ​​in the first data information and the target feature set to obtain matched risk feature values; calculating according to the weight values ​​of the matched risk feature values ​​to obtain the risk value of the target object; and obtaining the risk detection result based on the risk value.

[0047] In an optional embodiment, performing risk detection on a target object includes the following steps: matching the first data information of the target object with the risk feature value in the target feature set to obtain a matched risk feature value, then summing and calculating the risk value of the target object according to the weight value of the matched risk feature value, and finally obtaining a risk detection result according to the risk value. For example, if the risk value is greater than a threshold value, the target object is determined to be a risk object.

[0048] By extracting effective feature values ​​from risk objects, and judging whether the object to be predicted is a risk object based on these features, the accuracy of risk judgment is improved.

[0049] Optionally, in the object detection method provided in the embodiment of the present application, obtaining the target feature set includes: determining the data field corresponding to the second data information of multiple risk objects and the data type corresponding to the data field; based on the data type, determining the risk field from the data field, and determining the risk feature value corresponding to the risk field and the weight value corresponding to the risk feature value from the second data information; obtaining the target feature set based on the risk feature value corresponding to the risk field and the weight value corresponding to the risk feature value.

[0050] In an optional embodiment, the following steps are used to obtain the above-mentioned target feature set: obtain second data information of multiple risk objects, and determine the data fields in the second data information and the data type corresponding to the data fields, and then determine the risk fields from the data fields according to the data type, and determine the risk feature values ​​corresponding to the risk fields and the weight values ​​corresponding to the risk feature values ​​from the second data information, and then obtain the target feature set according to the risk feature values ​​corresponding to the risk fields and the weight values ​​corresponding to the risk feature values.

[0051] By distinguishing the types of data fields and determining risk fields according to the data types, the accuracy of determining the target feature set is improved.

[0052] Optionally, in the object detection method provided in the embodiment of the present application, based on the data type, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information includes: if the data type is discrete data, then based on the second data information, determining the number of first characteristic values ​​corresponding to each data field; calculating the proportion of the first characteristic value in the second data information to obtain the proportion value corresponding to each first characteristic value; calculating the weight value corresponding to the first characteristic value based on the proportion value corresponding to each first characteristic value and the number of first characteristic values, or based on the proportion value corresponding to each first characteristic value, to obtain the first weight value; based on the first weight value, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the first characteristic value.

[0053] In an optional embodiment, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value according to the data type includes the following steps: if the data type is discrete data, that is, enumerated data, first determine the number of first characteristic values ​​corresponding to each data field. For example, for gender, the corresponding first characteristic value is two for male and female.

[0054] Then, the proportion of the first characteristic value in the second data information is calculated to obtain the proportion value corresponding to the first characteristic value. For example, for account type A, the number of account types of account type A in multiple risk objects is calculated, and then the proportion value corresponding to account type A is calculated. If the number of first characteristic values ​​is greater than a preset value (for example, 8), the weight value corresponding to the first characteristic value is calculated according to the proportion value corresponding to each first characteristic value and the number of first characteristic values ​​to obtain a first weight value. For example, the first weight value = log n (m*n). Where n is the number of first eigenvalues, and m is the proportion of the first eigenvalues. If the number of first eigenvalues ​​is less than the preset value, the first weight value is directly obtained based on the proportion of each first eigenvalue, that is, m is used as the first weight value.

[0055] Algorithm analysis of the weight of data fields: Assume that in the sample, data field A has 4 features, data field B has 10 features, and data field C has 100 features. In the positive sample, feature a of field A, feature b of field B, and feature c of field C all account for 50%. Since field C has a high degree of discreteness and field A has a low degree of discreteness, when the feature proportions are the same, the concentration of feature c is higher than that of feature a, and the influence of this feature on the field features is also higher. Referring to Table 1, if the above feature weight algorithm is used, it can be obtained that the feature weight of feature a on field A is 0.5 < feature weight of feature b on field B is 0.7 < feature weight of feature c on field C is 0.85, and the calculation result can objectively reflect the actual situation.

[0056] Table 1

[0057]

[0058] Finally, according to the first weight value, the risk field is determined from the data field, and the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value are determined from the first characteristic value.

[0059] By calculating the proportion of eigenvalues, we can more accurately evaluate the impact of different eigenvalues ​​on risk detection and improve the accuracy of determining the target feature set.

[0060] Optionally, in the object detection method provided in the embodiment of the present application, determining the risk field from the data field based on the first weight value, determining the risk characteristic value corresponding to the risk field from the first characteristic value, and the weight value corresponding to the risk characteristic value include: for each data field, judging whether the standard deviation of the first weight value is greater than the first threshold value, if the standard deviation is greater than the first threshold value, determining that the data field is a risk field; for each risk field, screening the first characteristic value corresponding to the risk field based on the first weight value to obtain the risk characteristic value corresponding to the risk field; and determining the weight value corresponding to the risk characteristic value based on the first weight value.

[0061] In an optional embodiment, the standard deviation of the first weight value corresponding to each data field is calculated, and then it is determined whether the standard deviation of the first weight value is greater than the first threshold. If the standard deviation is greater than the first threshold, the data field can be determined to be a risk field. If the standard deviation of the first weight value is less than or equal to the first threshold, it means that the field under the data field has no obvious characteristics and needs to be discarded. It should be noted that the first threshold can be dynamically adjusted according to the accuracy of subsequent risk judgments.

[0062] For each risk field, the first feature value corresponding to the risk field can be screened according to the first weight value to obtain the risk feature value corresponding to the risk field, for example, one or more features with the highest feature weight are extracted as the risk feature value of the risk field. Finally, the weight value corresponding to the risk feature value is determined according to the first weight value.

[0063] The standard deviation of the weight value can be used to evaluate whether the data field has obvious characteristic values, improve the accuracy of determining the risk field, and screen the first characteristic value corresponding to the risk field according to the weight value, so as to more accurately grasp the risk characteristic value corresponding to the risk field.

[0064] Optionally, in the object detection method provided in the embodiment of the present application, based on the data type, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information includes: if the data type is continuous data, discretizing the second data information to obtain processed second data information; determining the number of second characteristic values ​​corresponding to each data field based on the processed second data information; calculating the proportion of the second characteristic values ​​in the processed second data information to obtain the proportion value corresponding to each second characteristic value; calculating the weight value corresponding to the second characteristic value based on the proportion value corresponding to each second characteristic value and the number of second characteristic values ​​to obtain the second weight value; based on the second weight value, determining the risk field from the data field, determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second characteristic value.

[0065] In an optional embodiment, if the data type is continuous data, the second data information needs to be discretized, and then the number of second eigenvalues ​​corresponding to each data field is determined for the processed second data information, and then the proportion of the second eigenvalues ​​in the processed second data information is calculated to obtain the proportion value corresponding to each second eigenvalue, and according to the proportion value corresponding to each second eigenvalue and the number of second eigenvalues, the weight value corresponding to the second eigenvalue is calculated to obtain the second weight value, and finally, according to the second weight value, the risk field is determined from the data field, the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value are determined from the second characteristic value.

[0066] It should be noted that, for continuous second data information, the second eigenvalue corresponding to each data field can be a eigenvalue range, that is, the second data information can be discretized by dividing the second data information into multiple data segments, and the data range corresponding to each data segment is used as the second eigenvalue corresponding to this data field.

[0067] It should be noted that continuous data can be divided into first-class continuous data (distribution is continuous, such as age) and second-class continuous data (distribution is non-continuous and has a large span, such as amount). For first-class continuous data, the first-class continuous data is converted into discrete data, and then the feature analysis method of discrete data fields is used for feature analysis. For second-class continuous data, it is first converted into first-class continuous data by power reduction and rounding, and then the feature analysis method of first-class continuous data is used for feature analysis.

[0068] The first method of converting continuous data into discrete data is: for each value X of the continuous data field n Each corresponds to a data volume Y n , assuming the value of X a The corresponding maximum data volume is Y a , value X b The corresponding minimum data volume is Y b When Y m <Y m-1 And Y m <Y m+1 When Y m Recorded as the minimum point; Y n >Y n-1 And Y n >Y n+1 When Y n is recorded as the maximum point. m -Y n |≥α|Y a -Y b| When (to prevent frequent segmentation, a threshold α ∈ (0, 1) is set, and when the difference between the maximum and minimum values is very small, no segmentation processing is performed), record the starting point of segmentation as X m ; If another point X is found l and there exists Y l < Y l-1 and Y l < Y l+1 (where m < n < l), when |Y l - Y n | ≥ α|Y a - Y b |, record the ending point of segmentation as X l . At this time, record the segmentation interval as (X m , X l ), and so on, find multiple segmentation intervals, and set the found multiple intervals as different feature values.

[0069] For example, for the curve shown as Figure 3 in the figure, n is the maximum point and 1 is the minimum point, then the corresponding (m, n) and (n, 1) can be used as a segmentation interval.

[0070] By discretizing the continuous second data information and then calculating the weights, the accuracy of determining the risk feature values corresponding to the risk fields in the continuous data and the weight values corresponding to the risk feature values is improved.

[0071] Optionally, in the object detection method provided in the embodiments of the present application, according to the risk feature values corresponding to the risk fields and the weight values corresponding to the risk feature values, the obtained target feature set includes: screening the risk fields according to the weight values corresponding to the risk feature values to obtain the screened risk fields; combining the screened risk fields to obtain the combined risk fields; determining the risk feature values corresponding to the combined risk fields and the weight values of the risk feature values corresponding to the combined risk fields according to the risk feature values corresponding to the screened risk fields; determining the target feature set according to the risk feature values corresponding to the risk fields, the weight values corresponding to the risk feature values, the risk feature values corresponding to the combined risk fields, and the weight values of the risk feature values corresponding to the combined risk fields.

[0072] In an optional embodiment, in order to further improve the accuracy of subsequent matching, the following steps may also be included: the risk field is screened according to the weight value corresponding to the risk feature value to obtain the screened risk field. For example, the risk field corresponding to the feature value ranked in the top k of the feature weight is selected as the candidate combination field (i.e., the risk field after the screening). Then, the risk fields after the screening are combined in pairs to obtain the combined risk field. Then, according to the risk feature value corresponding to the risk field after the screening, the risk feature value corresponding to the combined risk field and the weight value of the risk feature value corresponding to the combined risk field are determined. For example, the risk field after the screening is field A+field B, feature a corresponding to field A, and feature b corresponding to field B, then the feature value corresponding to field A+field B is feature a+feature b. Then, according to the proportion of feature a+feature b in the second data information, the weight value of the risk feature value corresponding to the combined risk field is obtained. As shown in Table 2. Feature a+feature b corresponding to field A+field B, feature b+feature c corresponding to field B+field C, and feature c+feature a corresponding to field C+field A.

[0073] Table 2

[0074]

[0075]

[0076] Finally, the target feature set is determined according to the risk feature value corresponding to the risk field, the weight value corresponding to the risk feature value, the risk feature value corresponding to the combined risk field and the weight value of the risk feature value corresponding to the combined risk field.

[0077] In an optional embodiment, in order to facilitate subsequent risk calculation, the weight values ​​corresponding to the risk feature values ​​are normalized: single field feature weight normalization: normalized weight of feature a = feature a weight / (feature a weight + feature b weight + feature c weight) = 0.5 / (0.5 + 0.7 + 0.85) = 0.244, similarly, the normalized weights of feature b and feature c are calculated respectively, and the combined field feature weights are normalized: normalized weight of {feature a + feature b} = {feature a + feature b} weight / ({feature a + feature b} weight + {feature b + feature c} weight + {feature c + feature a} weight), similarly, the normalized weights of {feature b + feature c} and {feature c + feature a} are calculated respectively, as shown in Table 3.

[0078] Table 3

[0079]

[0080] The following steps can be used to achieve the joint normalization of single field features and combined field feature weights. The single field feature weights and combined field feature weights are recalculated according to the p:q principle. If the p:q=8:2 principle is followed, the single feature normalization weight '=single feature normalization weight*80%, the combined field feature weight '=combined field feature weight*20%. The calculated results are shown in Table 4.

[0081] Table 4

[0082]

[0083]

[0084] The object detection method provided by the embodiment of the present application determines the target object to be detected and obtains the first data information of the target object, wherein the first data information at least includes: the attribute information and transaction information of the target object; obtains the target feature set, wherein the target feature set at least includes: the risk feature values ​​corresponding to the risk data fields of multiple risk objects and the weight values ​​corresponding to the risk feature values; based on the target feature set and the first data information, the target object is subjected to risk detection to obtain the risk detection result, thereby solving the technical problem that the accuracy of risk object detection by the model is relatively low. In this scheme, the target feature set is determined according to the risk feature values ​​corresponding to the risk data fields of multiple risk objects and the weight values ​​corresponding to the risk feature values. When the target object needs to be subjected to risk detection, the risk detection is performed according to the first data information of the target object and the target feature set to obtain the corresponding risk detection result. The corresponding target feature set determined by the data of multiple risk objects can effectively improve the coverage of risk object detection, and can effectively avoid the problem that the accuracy of risk detection is relatively low due to the very small proportion of risk objects in specific scenarios and the use of current machine learning methods, thereby achieving the effect of improving the accuracy of risk object detection.

[0085] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0086] Example 2

[0087] The present application also provides an object detection device. It should be noted that the object detection device of the present application can be used to execute the object detection method provided by the present application. The object detection device provided by the present application is introduced below.

[0088] According to an embodiment of the present application, a device for implementing the above-mentioned object detection method is also provided, such as Figure 4 As shown, the device includes: a determination unit 401, an acquisition unit 402 and a detection unit 403.

[0089] The determination unit 401 is used to determine the target object to be detected and obtain first data information of the target object, wherein the first data information at least includes: attribute information and transaction information of the target object;

[0090] An acquisition unit 402 is used to acquire a target feature set, wherein the target feature set at least includes: risk feature values ​​corresponding to risk data fields of multiple risk objects and weight values ​​corresponding to the risk feature values;

[0091] The detection unit 403 is used to perform risk detection on the target object based on the target feature set and the first data information to obtain a risk detection result.

[0092] The object detection device provided in the embodiment of the present application determines the target object to be detected and obtains the first data information of the target object through the determination unit 401, wherein the first data information at least includes: the attribute information and transaction information of the target object; the acquisition unit 402 obtains the target feature set, wherein the target feature set at least includes: the risk feature values ​​corresponding to the risk data fields of multiple risk objects and the weight values ​​corresponding to the risk feature values; the detection unit 403 performs risk detection on the target object based on the target feature set and the first data information to obtain the risk detection result, thereby solving the technical problem that the accuracy of risk object detection by the model is relatively low. In this scheme, the target feature set is determined according to the risk feature values ​​corresponding to the risk data fields of multiple risk objects and the weight values ​​corresponding to the risk feature values. When the target object needs to be detected, the risk detection is performed according to the first data information of the target object and the target feature set to obtain the corresponding risk detection result. The corresponding target feature set determined by the data of multiple risk objects can effectively improve the coverage of risk object detection, and can effectively avoid the problem that the accuracy of risk detection is relatively low due to the very small proportion of risk objects in specific scenarios and the use of current machine learning methods, thereby achieving the effect of improving the accuracy of risk object detection.

[0093] Optionally, in the object detection device provided in the embodiment of the present application, a matching subunit is used to match the first data information and the risk feature value in the target feature set to obtain a matched risk feature value; a calculation subunit is used to calculate based on the weight value of the matched risk feature value to obtain the risk value of the target object; and a first determination subunit is used to obtain a risk detection result based on the risk value.

[0094] Optionally, in the object detection device provided in the embodiment of the present application, the acquisition unit includes: a second determination subunit, used to determine the data field corresponding to the second data information of multiple risk objects and the data type corresponding to the data field; a third determination subunit, used to determine the risk field from the data field, and determine the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information based on the data type; and a fourth determination subunit, used to obtain a target feature set based on the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value.

[0095] Optionally, in the object detection device provided in the embodiment of the present application, the third determination subunit includes: a first determination module, which is used to determine the number of first eigenvalues ​​corresponding to each data field based on the second data information if the data type is discrete data; a first calculation module, which is used to calculate the proportion of the first eigenvalue in the second data information to obtain the proportion value corresponding to each first eigenvalue; a second calculation module, which is used to calculate the weight value corresponding to the first eigenvalue based on the proportion value corresponding to each first eigenvalue and the number of first eigenvalues, or based on the proportion value corresponding to each first eigenvalue, to obtain the first weight value; and a second determination module, which is used to determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field from the first characteristic value, and the weight value corresponding to the risk characteristic value based on the first weight value.

[0096] Optionally, in the object detection device provided in the embodiment of the present application, the second determination module includes: a judgment submodule, used to judge whether the standard deviation of the first weight value is greater than the first threshold for each data field, and if the standard deviation is greater than the first threshold, the data field is determined to be a risk field; a screening submodule, used to screen the first characteristic value corresponding to the risk field according to the first weight value for each risk field to obtain the risk characteristic value corresponding to the risk field; and a determination submodule, used to determine the weight value corresponding to the risk characteristic value based on the first weight value.

[0097] Optionally, in the object detection device provided in the embodiment of the present application, the third determination subunit includes: a processing module, which is used to discretize the second data information if the data type is continuous data, so as to obtain processed second data information; a third determination module, which is used to determine the number of second eigenvalues ​​corresponding to each data field based on the processed second data information; a third calculation module, which is used to calculate the proportion of the second eigenvalue in the processed second data information, and obtain the proportion value corresponding to each second eigenvalue; a fourth calculation module, which is used to calculate the weight value corresponding to the second eigenvalue based on the proportion value corresponding to each second eigenvalue and the number of second eigenvalues, and obtain the second weight value; a fourth determination module, which is used to determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field from the second characteristic value, and the weight value corresponding to the risk characteristic value based on the second weight value.

[0098] Optionally, in the detection device of the object provided in the embodiment of the present application, the fourth determination subunit includes: a screening module, which is used to screen the risk field according to the weight value corresponding to the risk characteristic value to obtain the screened risk field; a combination module, which is used to combine the screened risk fields to obtain the combined risk field; a fifth determination module, which is used to determine the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field according to the risk characteristic value corresponding to the screened risk field; and a sixth determination module, which is used to determine the target feature set based on the risk characteristic value corresponding to the risk field, the weight value corresponding to the risk characteristic value, the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field.

[0099] It should be noted that the above-mentioned determination unit 401, acquisition unit 402 and detection unit 403 correspond to steps S201 to S203 in the first embodiment, and the three units and the corresponding steps implement the same examples and application scenarios, but are not limited to the contents disclosed in the first embodiment. It should be noted that the above-mentioned modules or units can be hardware components or software components stored in a memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n), and the above-mentioned modules can also be part of the device and can be run in the computer terminal 10 provided in the first embodiment.

[0100] Example 3

[0101] An embodiment of the present application may provide an electronic device, Figure 5 is a structural block diagram of an electronic device according to an embodiment of the present application. Figure 5 As shown, the electronic device may include: one or more ( Figure 5(only one is shown) processor 502, memory 504, storage controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.

[0102] Among them, the memory can be used to store software programs and modules, such as program instructions / modules corresponding to the methods and devices in the embodiments of the present application, and the processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0103] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: determine the target object to be detected and obtain the first data information of the target object, wherein the first data information at least includes: attribute information and transaction information of the target object; obtain a target feature set, wherein the target feature set at least includes: risk feature values ​​corresponding to risk data fields of multiple risk objects and weight values ​​corresponding to the risk feature values; perform risk detection on the target object based on the target feature set and the first data information to obtain a risk detection result.

[0104] The processor can call the information and application stored in the memory through the transmission device to execute the following steps: perform risk detection on the target object based on the target feature set and the first data information, and obtain the risk detection result including: matching the risk feature values ​​in the first data information and the target feature set to obtain matching risk feature values; calculating based on the weight values ​​of the matching risk feature values ​​to obtain the risk value of the target object; and obtaining the risk detection result based on the risk value.

[0105] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: Obtaining the target feature set includes: determining the data field corresponding to the second data information of multiple risk objects and the data type corresponding to the data field; based on the data type, determining the risk field from the data field, and determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information; obtaining the target feature set based on the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value.

[0106] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: based on the data type, determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field from the second data information, and the weight value corresponding to the risk characteristic value, including: if the data type is discrete data, then based on the second data information, determine the number of first characteristic values ​​corresponding to each data field; calculate the proportion of the first characteristic value in the second data information to obtain the proportion value corresponding to each first characteristic value; based on the proportion value corresponding to each first characteristic value and the number of first characteristic values, or based on the proportion value corresponding to each first characteristic value, calculate the weight value corresponding to the first characteristic value to obtain the first weight value; based on the first weight value, determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field from the first characteristic value, and the weight value corresponding to the risk characteristic value.

[0107] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: based on the first weight value, determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field from the first characteristic value, and the weight value corresponding to the risk characteristic value, including: for each data field, determine whether the standard deviation of the first weight value is greater than the first threshold value, if the standard deviation is greater than the first threshold value, determine that the data field is a risk field; for each risk field, screen the first characteristic value corresponding to the risk field based on the first weight value to obtain the risk characteristic value corresponding to the risk field; based on the first weight value, determine the weight value corresponding to the risk characteristic value.

[0108] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: based on the data type, determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field from the second data information, and the weight value corresponding to the risk characteristic value, including: if the data type is continuous data, discretize the second data information to obtain the processed second data information; based on the processed second data information, determine the number of second characteristic values ​​corresponding to each data field; calculate the proportion of the second characteristic values ​​in the processed second data information to obtain the proportion value corresponding to each second characteristic value; calculate the weight value corresponding to the second characteristic value based on the proportion value corresponding to each second characteristic value and the number of second characteristic values ​​to obtain the second weight value; based on the second weight value, determine the risk field from the data field, determine the risk characteristic value corresponding to the risk field from the second characteristic value, and the weight value corresponding to the risk characteristic value.

[0109] The processor can call the information and application stored in the memory through the transmission device to perform the following steps: based on the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value, obtain the target feature set including: screening the risk field according to the weight value corresponding to the risk characteristic value to obtain the screened risk field; combining the screened risk fields to obtain a combined risk field; based on the risk characteristic value corresponding to the screened risk field, determine the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field; based on the risk characteristic value corresponding to the risk field, the weight value corresponding to the risk characteristic value, the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field, determine the target feature set.

[0110] It can be understood by those skilled in the art that Figure 5 The structure shown is for illustration only, and the electronic device may also be a smart phone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (Mobile Internet Devices, MID), a PAD, or other terminal devices. Figure 5 The structure of the electronic device is not limited. Figure 5 More or fewer components (such as network interfaces, display devices, etc.) shown in, or having Figure 5 Different configurations shown.

[0111] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0112] Example 4

[0113] The embodiment of the present application further provides a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the object detection method provided in the first embodiment.

[0114] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0115] The present application also provides a computer program product, which, when executed on a data processing device, is suitable for executing the program steps of the object detection method.

[0116] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0117] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0118] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0119] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0120] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0121] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0122] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for detecting an object, characterized in that: include: Determine a target object to be detected and obtain first data information of the target object, wherein the first data information at least includes: attribute information and transaction information of the target object; Acquire a target feature set, wherein the target feature set at least includes: risk feature values ​​corresponding to risk data fields of multiple risk objects and weight values ​​corresponding to the risk feature values; Based on the target feature set and the first data information, risk detection is performed on the target object to obtain a risk detection result.

2. The method according to claim 1, characterized in that Performing risk detection on the target object based on the target feature set and the first data information, obtaining a risk detection result includes: Matching the first data information with the risk feature value in the target feature set to obtain a matched risk feature value; Calculate the risk value of the target object based on the weight value of the matched risk feature value; The risk detection result is obtained according to the risk value.

3. The method according to claim 1, characterized in that Obtaining the target feature set includes: Determine data fields corresponding to the second data information of multiple risk objects and data types corresponding to the data fields; According to the data type, determine a risk field from the data field, and determine a risk characteristic value corresponding to the risk field and a weight value corresponding to the risk characteristic value from the second data information; The target feature set is obtained according to the risk feature value corresponding to the risk field and the weight value corresponding to the risk feature value.

4. The method according to claim 3, characterized in that According to the data type, determining the risk field from the data field, and determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information includes: If the data type is discrete data, determining the number of first characteristic values ​​corresponding to each data field according to the second data information; Calculate the proportion of the first characteristic value in the second data information to obtain a proportion value corresponding to each first characteristic value; Calculating a weight value corresponding to each first eigenvalue according to a proportion value corresponding to each first eigenvalue and the number of the first eigenvalues, or according to a proportion value corresponding to each first eigenvalue, to obtain a first weight value; According to the first weight value, a risk field is determined from the data field, and a risk characteristic value corresponding to the risk field and a weight value corresponding to the risk characteristic value are determined from the first characteristic value.

5. The method according to claim 4, characterized in that Determining the risk field from the data field according to the first weight value, and determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the first characteristic value includes: For each data field, determining whether the standard deviation of the first weight value is greater than a first threshold, and if the standard deviation is greater than the first threshold, determining that the data field is a risk field; For each risk field, screening the first characteristic value corresponding to the risk field according to the first weight value to obtain the risk characteristic value corresponding to the risk field; A weight value corresponding to the risk characteristic value is determined based on the first weight value.

6. The method according to claim 3, characterized in that: According to the data type, determining the risk field from the data field, and determining the risk characteristic value corresponding to the risk field and the weight value corresponding to the risk characteristic value from the second data information includes: If the data type is continuous data, discretizing the second data information to obtain processed second data information; Determining the number of second characteristic values ​​corresponding to each data field according to the processed second data information; Calculating the proportion of the second characteristic value in the processed second data information to obtain a proportion value corresponding to each second characteristic value; Calculate the weight value corresponding to the second eigenvalue according to the proportion value corresponding to each second eigenvalue and the number of the second eigenvalues ​​to obtain a second weight value; According to the second weight value, a risk field is determined from the data field, and a risk characteristic value corresponding to the risk field and a weight value corresponding to the risk characteristic value are determined from the second characteristic value.

7. The method according to claim 3, characterized in that According to the risk feature value corresponding to the risk field and the weight value corresponding to the risk feature value, the target feature set is obtained, including: The risk field is screened according to the weight value corresponding to the risk characteristic value to obtain a screened risk field; Combining the screened risk fields to obtain a combined risk field; Determine the risk characteristic value corresponding to the combined risk field and the weight value of the risk characteristic value corresponding to the combined risk field according to the risk characteristic value corresponding to the screened risk field; The target feature set is determined according to the risk feature value corresponding to the risk field, the weight value corresponding to the risk feature value, the risk feature value corresponding to the combined risk field and the weight value of the risk feature value corresponding to the combined risk field.

8. A device for detecting an object, characterized in that: include: A determination unit, configured to determine a target object to be detected and obtain first data information of the target object, wherein the first data information at least includes: attribute information and transaction information of the target object; An acquisition unit, configured to acquire a target feature set, wherein the target feature set at least includes: risk feature values ​​corresponding to risk data fields of a plurality of risk objects and weight values ​​corresponding to the risk feature values; A detection unit is used to perform risk detection on the target object based on the target feature set and the first data information to obtain a risk detection result.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored executable program, wherein when the executable program is executed, the device where the computer-readable storage medium is located is controlled to execute the object detection method according to any one of claims 1 to 7.

10. An electronic device, characterized in that: include: A memory storing an executable program; A processor, configured to run the program, wherein the program, when running, executes the object detection method according to any one of claims 1 to 7.

Images