Data processing method and device, electronic equipment and computer readable medium
Through the method of combining support vector machine and classification model, the risk level of risk merchants is calculated, which solves the problem of low accuracy in identification of risk merchants in the existing technology, and improves the accuracy of data processing and risk processing capabilities.
Patent Information
- Application Number
- CN202310589976.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-05-24
- Publication Date
- 2024-11-26
AI Technical Summary
The existing methods have low accuracy in identifying risk merchants, making it difficult to effectively identify bad merchants that disrupt shopping platform logistics and market operations.
Using support vector machines and classification models, classification scores and probability scores are determined through the decision boundary of the pending data in the decision space, and the target score is calculated based on the preset weights, thereby determining the risk level and outputting the classification of risk merchants.
It improves the accuracy of data processing, enhances the identification and processing capabilities of risk merchants, and improves the risk processing capabilities of related businesses.
Smart Images

Figure CN119027200A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of computer technology, and in particular to a data processing method, device, electronic device and computer-readable medium. Background Art
[0002] At present, there are many merchants cooperating with shopping platforms in logistics. The types of merchants and their performance characteristics are complex. Among them, there is a type of bad merchants that have long disrupted the logistics and market operations of shopping platforms. These merchants are collectively referred to as risky merchants. Existing methods have low accuracy in identifying risky merchants. Summary of the invention
[0003] In view of this, embodiments of the present application provide a data processing method, device, electronic device, and computer-readable medium, which can solve the problem of low accuracy in existing data processing.
[0004] To achieve the above objective, according to one aspect of an embodiment of the present application, a data processing method is provided, including:
[0005] In response to the data processing request, obtaining corresponding data to be processed;
[0006] Calling a support vector machine to determine, based on the data to be processed, data points corresponding to the data to be processed in a decision space corresponding to the support vector machine, determining a classification score corresponding to a target classification based on a decision boundary and data points in the decision space, and calling a classification model to determine a probability score corresponding to the target classification based on the data to be processed;
[0007] Determine the target score based on preset weights, classification scores, and probability scores;
[0008] Based on the target score, the risk level of the target classification is determined and output.
[0009] Optionally, determining a classification score corresponding to the target classification includes:
[0010] Map the data to be processed to the decision space corresponding to the classification algorithm to obtain the corresponding data points;
[0011] Calculate the distance from the data point to the decision boundary corresponding to the decision space;
[0012] Based on the distance, the classification score corresponding to the data point is determined.
[0013] Optionally, determine a target score, including:
[0014] Sort the classification scores in descending order to obtain sorted classification scores;
[0015] Sort the probability scores in descending order to obtain sorted probability scores;
[0016] Determine the sorting classification weight score according to the sorting classification score and the preset weight;
[0017] Determine the target score based on the sorting classification weight score and the sorting probability score.
[0018] Optionally, determining the sorting classification weight score according to the sorting classification score and the preset weight includes:
[0019] The product of the sorting classification score and the preset weight is calculated to obtain the sorting classification weight score.
[0020] Optionally, determining a target score according to the sorting classification weight score and the sorting probability score includes:
[0021] The sum of the sorting classification weight score and the corresponding sorting probability score is calculated, and the sum is determined as the target score.
[0022] Optionally, before calling the support vector machine, the method further includes:
[0023] Obtain the black sample set and the white sample set corresponding to the target classification, and perform a significant variance analysis based on the black sample set and the white sample set to determine the feature set;
[0024] Determine the classification score corresponding to each feature in the feature set, and then generate the corresponding classification score label;
[0025] The feature set is used as the input of the initial support vector machine, the corresponding classification score label is used as the expected output of the initial support vector machine, and the training of the initial support vector machine is performed to obtain a support vector machine.
[0026] Optionally, the data processing method further includes:
[0027] Obtain the latest operating mechanism data corresponding to the target classification;
[0028] Update the feature set based on the latest operating mechanism data.
[0029] In addition, the present application also provides a data processing device, including:
[0030] an acquisition unit, configured to acquire corresponding data to be processed in response to a data processing request;
[0031] a score determination unit configured to call a support vector machine to determine, based on the data to be processed, data points corresponding to the data to be processed in a decision space corresponding to the support vector machine, determine a classification score corresponding to the target classification based on a decision boundary and data points in the decision space, and call a classification model to determine a probability score corresponding to the target classification based on the data to be processed;
[0032] a target score determination unit configured to determine a target score based on a preset weight, a classification score, and a probability score;
[0033] The risk level determination unit is configured to determine and output the risk level of the target classification based on the target score.
[0034] Optionally, the score determination unit is further configured to:
[0035] Map the data to be processed to the decision space corresponding to the classification algorithm to obtain the corresponding data points;
[0036] Calculate the distance from the data point to the decision boundary corresponding to the decision space;
[0037] Based on the distance, the classification score corresponding to the data point is determined.
[0038] Optionally, the target score determination unit is further configured to:
[0039] Sort the classification scores in descending order to obtain sorted classification scores;
[0040] Sort the probability scores in descending order to obtain sorted probability scores;
[0041] Determine the sorting classification weight score according to the sorting classification score and the preset weight;
[0042] Determine the target score based on the sorting classification weight score and the sorting probability score.
[0043] Optionally, the target score determination unit is further configured to:
[0044] The product of the sorting classification score and the preset weight is calculated to obtain the sorting classification weight score.
[0045] Optionally, the target score determination unit is further configured to:
[0046] The sum of the sorting classification weight score and the corresponding sorting probability score is calculated, and the sum is determined as the target score.
[0047] Optionally, the data processing device further includes a training unit configured to:
[0048] Obtain the black sample set and the white sample set corresponding to the target classification, and perform a significant variance analysis based on the black sample set and the white sample set to determine the feature set;
[0049] Determine the classification score corresponding to each feature in the feature set, and then generate the corresponding classification score label;
[0050] The feature set is used as the input of the initial support vector machine, the corresponding classification score label is used as the expected output of the initial support vector machine, and the training of the initial support vector machine is performed to obtain a support vector machine.
[0051] Optionally, the data processing device further includes an updating unit configured to:
[0052] Obtain the latest operating mechanism data corresponding to the target classification;
[0053] Update the feature set based on the latest operating mechanism data.
[0054] In addition, the present application also provides a data processing electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by one or more processors, the one or more processors implement the data processing method as described above.
[0055] In addition, the present application also provides a computer-readable medium on which a computer program is stored, and when the program is executed by a processor, the data processing method as described above is implemented.
[0056] One embodiment of the above invention has the following advantages or beneficial effects: the application obtains the corresponding data to be processed by responding to the data processing request; calls the support vector machine to determine the data points corresponding to the data to be processed in the decision space corresponding to the support vector machine based on the data to be processed, determines the classification score corresponding to the target classification based on the decision boundary and data points in the decision space, calls the classification model to determine the probability score corresponding to the target classification based on the data to be processed; determines the target score based on the preset weight, classification score and probability score; determines the risk level of the target classification based on the target score and outputs it. Thus, the accuracy of data processing can be improved to improve the risk handling capability of related businesses.
[0057] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] The accompanying drawings are used to better understand the present application and do not constitute an improper limitation on the present application.
[0059] Figure 1 It is a schematic diagram of the main process of a data processing method provided according to an embodiment of the present application;
[0060] Figure 2 It is a schematic diagram of the main process of a data processing method provided according to an embodiment of the present application;
[0061] Figure 3Schematic diagram of intelligent risk control early warning mechanism for risky merchants according to a data processing method provided in one embodiment of the present application;
[0062] Figure 4 is a logical diagram of risk score calculation of risky merchants according to a data processing method provided in one embodiment of the present application;
[0063] Figure 5 is a schematic diagram of main units of a data processing device according to an embodiment of the present application;
[0064] Figure 6 is an exemplary system architecture diagram to which the embodiments of the present application can be applied;
[0065] Figure 7 It is a structural diagram of a computer system of a terminal device or server suitable for implementing an embodiment of the present application. DETAILED DESCRIPTION
[0066] The following is an explanation of the exemplary embodiments of the present application in conjunction with the accompanying drawings, including various details of the embodiments of the present application to facilitate understanding, which should be considered as merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present application. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description. It should be noted that in the technical solution of the present disclosure, the collection, collection, update, analysis, processing, use, transmission, storage and other aspects of user personal information involved are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Take necessary measures for user personal information to prevent illegal access to user personal information data and maintain user personal information security, network security and national security.
[0067] Figure 1 is a schematic diagram of the main flow of a data processing method provided according to an embodiment of the present application, such as Figure 1 As shown, the data processing method includes:
[0068] Step S101, in response to a data processing request, obtaining corresponding data to be processed.
[0069] In this embodiment, the execution subject of the data processing method (for example, it can be a server) can receive the data processing request through a wired connection or a wireless connection. The data processing request can, for example, be a request to analyze the data to determine whether it corresponds to a risky merchant. After receiving the data processing request, the execution subject can obtain the corresponding data to be processed. Specifically, the data to be processed can be the merchant operation data on the shopping platform or can be logistics transportation data. The embodiment of the present application does not specifically limit the data to be processed.
[0070] The risky merchants in the embodiments of the present application may be merchants that have disrupted the logistics processing and market operations of the logistics platform for a long time in the logistics processing scenario. The embodiments of the present application do not specifically limit the types of risky merchants.
[0071] Step S102, calling the support vector machine to determine the data points corresponding to the data to be processed in the decision space corresponding to the support vector machine based on the data to be processed, determining the classification score corresponding to the target classification based on the decision boundary and the data points in the decision space, and calling the classification model to determine the probability score corresponding to the target classification based on the data to be processed.
[0072] Specifically, the data to be processed can be mapped to data points in the decision space corresponding to the support vector machine by mapping. The decision boundary in the decision space can be the maximum margin hyperplane for solving the input data (that is, the data to be processed). The classification score of the target classification corresponding to the data to be processed is determined by the distance between the data point corresponding to the data to be processed in the decision space and the decision boundary.
[0073] The support vector machine is used to predict whether the data to be processed corresponds to the target classification. For example, the target classification may be risky merchants. Specifically, the classification score of the data to be processed corresponding to the target classification output by the support vector machine can be used to determine whether the data to be processed corresponds to the target classification. The classification model is used to predict the probability score of the data to be processed corresponding to the target classification.
[0074] Specifically, before calling the support vector machine, the data processing method also includes: obtaining a black sample set and a white sample set corresponding to the target classification, performing a significance variance analysis based on the black sample set and the white sample set to determine a feature set; determining the classification score corresponding to each feature in the feature set, and then generating a corresponding classification score label; using the feature set as the input of the initial support vector machine, using the corresponding classification score label as the expected output of the initial support vector machine, and performing training on the initial support vector machine to obtain a support vector machine.
[0075] For example, the premise of selecting the risk merchant feature set is to determine the sample set, which includes historical risk merchants (i.e., black sample set) and white sample set. Because only the data of historical risk merchants when they are in normal operation is meaningful, through data mining and analysis, the time node when the merchant's weekly shipping volume decreased by 80% compared with the previous week is determined, and the values of each indicator are calculated two weeks ago as the indicator data of the risk merchant when it is in normal operation; at the same time, non-risk merchants with the same number of black samples are selected as white samples. After determining the black and white samples and the time range of the operating indicators, it is necessary to perform a significant variance analysis on the indicators of the two types of data in the black and white sample sets. For example, in a certain analysis process, the following four indicators are found to have significant differences: the number of ordering accounts, the number of categories, the number of shipping addresses, and the discount rate. Finally, the feature set X selected by the support vector machine is determined as: the number of ordering accounts, the number of categories, the number of shipping addresses, and the discount rate. The feature set X is not static. The operating mechanism of risky merchants is changing, and the data characteristics of the performance will also change. Therefore, the feature set also needs to be continuously iterated and updated. The feature set is used as the input of the initial support vector machine, the corresponding classification score label is used as the expected output of the initial support vector machine, and the initial support vector machine is trained to obtain the support vector machine. The support vector machine is called to determine the data points corresponding to the data to be processed in the decision space corresponding to the support vector machine based on the data to be processed, and the classification score corresponding to the target classification is determined based on the decision boundary and the data points in the decision space.
[0076] Call the classification model to input the data to be processed into the classification model and output the probability score corresponding to the target classification.
[0077] Step S103, determining a target score based on preset weights, classification scores and probability scores.
[0078] The preset weight may be a weight coefficient corresponding to the classification score and a weight coefficient corresponding to the probability score set based on the accuracy and hit rate. For example, the weight coefficient corresponding to the classification score is 6, and the weight coefficient corresponding to the probability score is 1. For example, the target score score may be calculated according to the following formula: score = score (support vector machine) * 6 + score (neural network).
[0079] Specifically, determining the target score includes: sorting the classification scores in descending order to obtain the sorted classification scores, for example, sorting the classification scores corresponding to the data to be processed in descending order to obtain 7, 5, 3, and 1; sorting the probability scores in descending order to obtain the sorted probability scores, for example, 0.9, 0.6, 0.4, and 0.2; determining the sorted classification weight scores according to the sorted classification scores and preset weights, for example, 7*6=42, 5*6=30, 3*6=18, and 1*6=6; determining the target scores 42+0.9=42.9, 30+0.6=30.6, 18+0.4=18.4, and 6+0.2=6.2 according to the sorted classification weight scores 42, 30, 18, and 6 and the sorted probability scores 0.9, 0.6, 0.4, and 0.2. These four target scores are the target scores corresponding to the four data to be processed, and each data to be processed corresponds to a target score.
[0080] Specifically, determining the sorting classification weight score according to the sorting classification score and the preset weight includes: calculating the product of the sorting classification score and the preset weight to obtain the sorting classification weight score. For example, 7*6=42, 5*6=30, 3*6=18, 1*6=6.
[0081] Specifically, the target score is determined according to the sorting classification weight score and the sorting probability score, including: calculating the sum of the sorting classification weight score (e.g., 42, 30, 18, 6) and the corresponding sorting probability score (e.g., 0.9, 0.6, 0.4, 0.2), and determining the sum as the target score. For example, 42+0.9=42.9, 30+0.6=30.6, 18+0.4=18.4, 6+0.2=6.2.
[0082] Step S104: Based on the target score, determine the risk level of the target classification and output it.
[0083] For example, the risk control level parameter description is as follows: high-risk merchants: target score 6-20; medium-high risk merchants: target score 20-50; medium-risk merchants: target score 50-100; general risk merchants: target score above 100.
[0084] By determining the risk control level score range in which the target score is located, such as 6-20, 20-50, 50-100, and above 100, the corresponding risk level is determined, such as high-risk risk merchants, medium-high risk risk merchants, medium-risk risk merchants, and general risk risk merchants.
[0085] This embodiment obtains the corresponding data to be processed by responding to the data processing request; calls the support vector machine to determine the data points corresponding to the data to be processed in the decision space corresponding to the support vector machine based on the data to be processed, determines the classification score corresponding to the target classification based on the decision boundary and data points in the decision space, calls the classification model to determine the probability score corresponding to the target classification based on the data to be processed; determines the target score based on the preset weight, classification score and probability score; determines the risk level of the target classification based on the target score and outputs it. This can improve the accuracy of data processing and improve the risk handling capability of related businesses.
[0086] Figure 2 is a schematic diagram of the main flow of a data processing method provided according to an embodiment of the present application, such as Figure 2 As shown, the data processing method includes:
[0087] Step S201, in response to a data processing request, obtaining corresponding data to be processed.
[0088] Step S202 , calling a support vector machine to map the data to be processed to a decision space corresponding to the classification algorithm based on the data to be processed, so as to obtain corresponding data points.
[0089] The decision space may be a multi-dimensional space. The execution subject may call a support vector machine to convert the data to be processed into data points in the decision space based on a mapping algorithm.
[0090] Step S203, calculating the distance from the data point to the decision boundary corresponding to the decision space.
[0091] Create a separation surface of the decision boundary in the decision space to divide the decision space into two regions. Calculate the distance from the data point corresponding to the data to be processed to the decision boundary.
[0092] Step S204: determining the classification score corresponding to the data point according to the distance.
[0093] The greater the distance between the data point corresponding to the data to be processed and the decision boundary, the higher the risk of the risky merchant, and the higher the risk, the lower the corresponding classification score. Specifically, the classification score corresponding to the data point corresponding to the distance can be determined based on the corresponding relationship between the distance and the classification score.
[0094] Step S205 , calling the classification model to determine the probability score corresponding to the target classification based on the data to be processed.
[0095] The data to be processed is input into the classification model to output the probability score corresponding to the target classification.
[0096] Step S206, determining a target score based on the preset weight, classification score and probability score.
[0097] The product of the preset weight and the classification score is calculated, and then the product is added to the probability score to obtain the target score.
[0098] Step S207: Based on the target score, determine the risk level of the target classification and output it.
[0099] According to the correspondence between the preset target score and the risk level, the risk level corresponding to the target score corresponding to the data processing request is determined. When the risk level is high risk, early warning information can be generated and output.
[0100] Specifically, the data processing method also includes: obtaining the latest operation mechanism data corresponding to the target classification; and updating the feature set based on the latest operation mechanism data.
[0101] As the overall environment changes, the operating mechanisms of risk merchants are also changing, and the data characteristics of the performance will also change, so the feature set also needs to be continuously iterated and updated.
[0102] Figure 3 Schematic diagram of intelligent risk control warning mechanism for risky merchants according to a data processing method provided by an embodiment of the present application. Figure 3 As shown in Figure 1, the intelligent risk control early warning mechanism for risky merchants is divided into three stages, namely, the stage of selecting the risky merchant feature set, the stage of determining the risky merchant, and the stage of outputting the risk level of the risky merchant. Figure 3 As shown, when the intelligent risk control early warning mechanism for risky merchants is turned on, data mining is performed to obtain indicators 1, indicator 2, indicator 3, ..., etc. for analysis, and then feature set selection is performed through significant variance analysis (that is, by testing whether the overall means are equal to determine whether the categorical independent variables have a significant impact on the numerical dependent variables) to obtain a feature set consisting of feature 1, feature 2, feature 3, etc., and then machine learning is performed on the obtained feature set. When performing machine learning, the data set is first preprocessed, and the model is trained and tested with the feature set after data preprocessing. Finally, the trained model is used to label the risky merchants, and the risk score (that is, the target score) of the risky merchants is calculated, and then the corresponding risk level (for example, high risk, medium-high risk, medium risk, general risk) is determined.
[0103] Figure 4 FIG. 1 is a logic diagram of calculating the risk score of a risk merchant according to a data processing method provided in one embodiment of the present application. Figure 4As shown, the support vector machine calculates the distance from the data point corresponding to the data to be processed in the decision space to the decision boundary, where the larger the distance, the higher the risk of the risky merchant, and the higher the risk, the lower the score. Calculate the probability of being determined as a risky merchant, where the higher the probability, the higher the risk of being determined as a risky merchant, and the higher the risk, the lower the score. The results of the two algorithms are sorted and scored respectively. Because when testing the model, it is found that the accuracy and hit rate of the support vector machine are higher than those of the neural network, the support vector machine is more trusted, so the score weight assigned to the output result of the support vector machine is higher. The comprehensive score of the example is given by the formula: score = score (support vector machine) * 6 + score (neural network), where 6 is the corresponding weight of the support vector machine, and finally outputs the comprehensive score of each risky merchant, and then obtains the corresponding risk level of each risky merchant according to the comprehensive score, so as to achieve faster and more accurate judgment of risky merchants.
[0104] Figure 5 Schematic diagram of the main units of the data processing device according to an embodiment of the present application. Figure 5 As shown, the data processing device 500 includes an acquisition unit 501 , a score determination unit 502 , a target score determination unit 503 and a risk level determination unit 504 .
[0105] The acquisition unit 501 is configured to acquire corresponding data to be processed in response to a data processing request;
[0106] The score determination unit 502 is configured to call the support vector machine to determine the data points corresponding to the data to be processed in the decision space corresponding to the support vector machine based on the data to be processed, determine the classification score corresponding to the target classification based on the decision boundary and the data points in the decision space, and call the classification model to determine the probability score corresponding to the target classification based on the data to be processed;
[0107] A target score determination unit 503 is configured to determine a target score based on a preset weight, a classification score and a probability score;
[0108] The risk level determination unit 504 is configured to determine and output the risk level of the target classification based on the target score.
[0109] In some embodiments, the score determination unit 502 is further configured to: map the data to be processed to the decision space corresponding to the classification algorithm to obtain the corresponding data point; calculate the distance from the data point to the decision boundary corresponding to the decision space; and determine the classification score corresponding to the data point based on the distance.
[0110] In some embodiments, the target score determination unit 503 is further configured to: sort the classification scores in descending order to obtain a sorted classification score; sort the probability scores in descending order to obtain a sorted probability score; determine the sorted classification weight score based on the sorted classification score and the preset weight; determine the target score based on the sorted classification weight score and the sorted probability score.
[0111] In some embodiments, the target score determination unit 503 is further configured to: calculate the product of the sorting classification score and the preset weight to obtain the sorting classification weight score.
[0112] In some embodiments, the target score determination unit 503 is further configured to: calculate the sum of the sorting classification weight score and the corresponding sorting probability score, and determine the sum as the target score.
[0113] In some embodiments, the data processing device further includes Figure 5 The training unit not shown in the figure is configured to: obtain a black sample set and a white sample set corresponding to the target classification, perform a significant variance analysis based on the black sample set and the white sample set to determine a feature set; determine the classification score corresponding to each feature in the feature set, and then generate a corresponding classification score label; use the feature set as the input of the initial support vector machine, use the corresponding classification score label as the expected output of the initial support vector machine, and perform training on the initial support vector machine to obtain a support vector machine.
[0114] In some embodiments, the data processing device further includes Figure 5 The updating unit not shown in the figure is configured to: obtain the latest operation mechanism data corresponding to the target classification; and update the feature set based on the latest operation mechanism data.
[0115] It should be noted that the data processing method and the data processing device of the present application have a corresponding relationship in terms of specific implementation contents, so the repeated contents will not be described again.
[0116] Figure 6 An exemplary system architecture 600 to which the data processing method or data processing device according to the embodiment of the present application can be applied is shown.
[0117] like Figure 6 As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.
[0118] Users can use terminal devices 601, 602, and 603 to interact with server 605 through network 604 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 601, 602, and 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only examples).
[0119] The terminal devices 601 , 602 , and 603 may be various electronic devices having a data processing screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, desktop computers, and the like.
[0120] Server 605 may be a server that provides various services, such as a background management server that provides support for data processing requests submitted by users using terminal devices 601, 602, and 603 (only as an example). The background management server may respond to the data processing request and obtain the corresponding data to be processed; call the support vector machine to determine the data points corresponding to the data to be processed in the decision space corresponding to the support vector machine based on the data to be processed, determine the classification score corresponding to the target classification based on the decision boundary and data points in the decision space, call the classification model to determine the probability score corresponding to the target classification based on the data to be processed; determine the target score based on the preset weight, classification score, and probability score; determine the risk level of the target classification based on the target score and output it. This can improve the accuracy of data processing to improve the risk handling capability of related businesses.
[0121] It should be noted that the data processing method provided in the embodiment of the present application is generally executed by the server 605 , and accordingly, the data processing device is generally set in the server 605 .
[0122] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.
[0123] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present application. Figure 7 The terminal device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.
[0124] like Figure 7As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the computer system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.
[0125] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.
[0126] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present application are executed.
[0127] It should be noted that the computer-readable medium shown in the present application may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Computer-readable storage media may include, for example, but are not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.
[0128] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.
[0129] The units involved in the embodiments described in the present application may be implemented by software or hardware. The units described may also be set in a processor, for example, it may be described as: a processor includes an acquisition unit, a score determination unit, a target score determination unit, and a risk level determination unit. The names of these units do not, in some cases, constitute limitations on the units themselves.
[0130] As another aspect, the present application also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device responds to a data processing request and obtains the corresponding data to be processed; calls a support vector machine to determine the data points corresponding to the data to be processed in the decision space corresponding to the support vector machine based on the data to be processed, determines the classification score corresponding to the target classification based on the decision boundary and data points in the decision space, calls a classification model to determine the probability score corresponding to the target classification based on the data to be processed; determines the target score based on the preset weight, classification score and probability score; determines the risk level of the target classification based on the target score and outputs it.
[0131] According to the technical solution of the embodiment of the present application, the accuracy of data processing can be improved to improve the risk handling capability of related businesses.
[0132] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.
Claims
1. A data processing method, characterized in that: include: In response to the data processing request, obtaining corresponding data to be processed; Calling a support vector machine to determine, based on the data to be processed, data points corresponding to the data to be processed in a decision space corresponding to the support vector machine, determining a classification score corresponding to a target classification based on a decision boundary in the decision space and the data points, and calling a classification model to determine a probability score corresponding to the target classification based on the data to be processed; Determining a target score based on a preset weight, the classification score, and the probability score; Based on the target score, the risk level of the target classification is determined and output.
2. The method according to claim 1, characterized in that The determining of the classification score corresponding to the target classification includes: Mapping the data to be processed to a decision space corresponding to the classification algorithm to obtain corresponding data points; Calculating the distance from the data point to the decision boundary corresponding to the decision space; According to the distance, a classification score corresponding to the data point is determined.
3. The method according to claim 1, characterized in that Determining the target score includes: Sorting the classification scores in descending order to obtain sorted classification scores; Sorting the probability scores in descending order to obtain sorted probability scores; Determining a sorting classification weight score according to the sorting classification score and the preset weight; A target score is determined based on the sorting classification weight score and the sorting probability score.
4. The method according to claim 3, characterized in that The step of determining the sorting classification weight score according to the sorting classification score and the preset weight includes: The product of the sorting classification score and the preset weight is calculated to obtain a sorting classification weight score.
5. The method according to claim 3, characterized in that: The determining of the target score according to the sorting classification weight score and the sorting probability score comprises: The sum of the sorting classification weight score and the corresponding sorting probability score is calculated, and the sum is determined as the target score.
6. The method according to claim 1, characterized in that Before calling the support vector machine, the method further includes: Obtaining a black sample set and a white sample set corresponding to the target classification, and performing a significant variance analysis based on the black sample set and the white sample set to determine a feature set; Determine the classification score corresponding to each feature in the feature set, and then generate a corresponding classification score label; The feature set is used as an input of an initial support vector machine, the corresponding classification score label is used as an expected output of the initial support vector machine, and training of the initial support vector machine is performed to obtain a support vector machine.
7. The method according to claim 6, characterized in that The method further comprises: Obtain the latest operation mechanism data corresponding to the target classification; Based on the latest operation mechanism data, the feature set is updated.
8. A data processing device, characterized in that: include: an acquisition unit, configured to acquire corresponding data to be processed in response to a data processing request; a score determination unit configured to call a support vector machine to determine, based on the data to be processed, a data point corresponding to the data to be processed in a decision space corresponding to the support vector machine, determine a classification score corresponding to a target classification based on a decision boundary in the decision space and the data point, and call a classification model to determine a probability score corresponding to the target classification based on the data to be processed; a target score determination unit configured to determine a target score based on a preset weight, the classification score and the probability score; The risk level determination unit is configured to determine and output the risk level of the target classification based on the target score.
9. The device according to claim 8, characterized in that The score determination unit is further configured to: Mapping the data to be processed to a decision space corresponding to the classification algorithm to obtain corresponding data points; Calculating the distance from the data point to the decision boundary corresponding to the decision space; According to the distance, a classification score corresponding to the data point is determined.
10. The device according to claim 8, characterized in that The target score determination unit is further configured to: Sorting the classification scores in descending order to obtain sorted classification scores; Sorting the probability scores in descending order to obtain sorted probability scores; Determining a sorting classification weight score according to the sorting classification score and the preset weight; A target score is determined based on the sorting classification weight score and the sorting probability score.
11. A data processing electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.
12. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.
