Decision tree configuration method, device, computer equipment and storage medium

Abstract

The present application relates to a decision tree configuration method, apparatus, computer device, and storage medium. The method comprises: moving multiple business nodes to a main page; for each business node, in response to a configuration operation on the current business node, displaying the business node configuration page on the upper layer of the main page; if the current business node is an execution node, configuring the node type and decision strategy of the execution node on the configuration page; if the current business node is a data node, configuring the data node based on variables obtained on the configuration page; if the current business node is an end node, configuring the end node based on decision conditions obtained on the configuration page; generating a decision tree based on each business node, and making risk decisions for user behavior based on the decision tree. This method enables risk decisions to be made for complex businesses.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a decision tree configuration method, apparatus, computer equipment, and storage medium. Background Art

[0002] With the development of information technology, methods for leveraging data structures for decision analysis have emerged. The decision tree is a machine learning method based on a tree structure. Decision trees offer good interpretability and can effectively assist decision makers in decision analysis, making them widely used in bank credit modeling. Modelers can manually configure the tree structure and subordinate relationships to create a decision tree. Traditional decision trees primarily assess risk based on probability. However, when complex business decisions require a range of variables, converting these variables into probability distributions for constructing a decision tree becomes difficult. Summary of the Invention

[0003] Based on this, it is necessary to provide a decision tree configuration method, device, computer equipment and storage medium that can configure complex rules to address the above technical problems.

[0004] A decision tree configuration method, the method comprising:

[0005] Move multiple business nodes to the main page;

[0006] For each of the service nodes, in response to a configuration operation on the current service node, displaying a configuration page of the service node on an upper layer of the main page;

[0007] If the current service node is an execution node, configure the node type and decision strategy of the execution node on the configuration page;

[0008] If the current service node is a data node, configure the data node based on the variables obtained on the configuration page;

[0009] If the current service node is an end node, configure the end node based on the decision condition obtained on the configuration page;

[0010] A decision tree is generated based on each of the service nodes to make risk decisions on user behaviors based on the decision tree.

[0011] In one embodiment, the variables include defined variables; configuring the data node based on the variables obtained on the configuration page includes: reading an attribute list based on the defined variables about the data node obtained on the configuration page; when querying the attribute corresponding to the defined variable in the attribute list, saving the definition information corresponding to the defined variable, and saving the defined variable in a data variable platform; in response to a publishing operation, publishing the defined variables saved in the data variable platform, thereby completing the configuration of the data node.

[0012] In one embodiment, making risk decisions on user behavior based on the decision tree includes: calling a policy package based on an execution node in the decision tree; executing the decision policies in the policy package in parallel or sequentially to make risk decisions on user behavior based on the executed decision policies.

[0013] In one embodiment, it also includes: obtaining the parameters to be output in the policy parameter configuration page; querying the corresponding template based on the obtained parameters; displaying the template on the policy parameter configuration page; and in response to the template screening operation triggered on the policy parameter configuration page, configuring the output parameters of the decision strategy based on the template remaining after screening.

[0014] In one embodiment, the risk decision-making for user behavior based on the decision tree includes: obtaining material information corresponding to the user behavior; taking the root node of the decision tree as the starting node, and performing branch judgment on the material information based on the nodes passed through in the decision tree in sequence to determine the next level node to flow to until reaching the leaf node; and making a risk decision for the user behavior based on the result information stored in the leaf node.

[0015] In one embodiment, the method further includes: recording a decision path of the decision tree during the process of making risk decisions; the decision path is a path composed of nodes passed through in the decision tree.

[0016] A decision tree configuration device, comprising:

[0017] Mobile module, used to move multiple business nodes to the main page;

[0018] A display module, configured to display, for each of the service nodes, a configuration page of the service node on an upper layer of the main page in response to a configuration operation on the current service node;

[0019] An execution node configuration module, configured to configure the node type and decision-making strategy of the execution node on the configuration page if the current business node is an execution node;

[0020] A data node configuration module, configured to configure the data node based on the variables obtained on the configuration page if the current service node is a data node;

[0021] an end node configuration module, configured to configure the end node based on the decision conditions obtained on the configuration page if the current service node is an end node;

[0022] A generation module is used to generate a decision tree based on each of the business nodes, so as to make risk decisions on user behaviors based on the decision tree.

[0023] In one embodiment, the variables include definition variables; the device also includes: a definition module, used to read an attribute list based on the definition variables about the data node obtained on the configuration page; when querying the attribute corresponding to the definition variable in the attribute list, saving the definition information corresponding to the definition variable, and saving the definition variable in the data variable platform; in response to the publishing operation, publishing the definition variable saved in the data variable platform, thereby completing the configuration of the data node.

[0024] In one embodiment, the device further includes: a calling module for calling a policy package based on an execution node in the decision tree; executing the decision policies in the policy package in parallel or sequentially to make risk decisions on user behaviors based on the executed decision policies.

[0025] In one embodiment, the device also includes: a policy parameter configuration module, which is used to obtain the parameters to be output in the policy parameter configuration page; query the corresponding template based on the obtained parameters; display the template on the policy parameter configuration page; and in response to the template screening operation triggered on the policy parameter configuration page, configure the output parameters of the decision strategy based on the template remaining after screening.

[0026] In one embodiment, the device also includes: a decision module for obtaining material information corresponding to user behavior; taking the root node of the decision tree as the starting node, performing branch judgment on the material information based on the nodes passed through in the decision tree in sequence to determine the next level node to flow to until reaching a leaf node; and making a risk decision on the user behavior based on the result information stored in the leaf node.

[0027] In one embodiment, the decision module is further configured to record a decision path of the decision tree during the process of making risk decisions; the decision path is a path consisting of nodes passed through in the decision tree.

[0028] A computer device includes a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the above-mentioned decision tree configuration method.

[0029] A computer-readable storage medium stores a computer program, which, when executed by a processor, causes the processor to perform the steps of the above-mentioned decision tree configuration method.

[0030] The above-mentioned decision tree configuration method, device, computer equipment and storage medium move multiple business nodes to the main page; for each business node, in response to the configuration operation of the current business node, the configuration page of the business node is displayed on the upper layer of the main page; if the current business node is an execution node, the node type and decision strategy of the execution node are configured on the configuration page; if the current business node is a data node, the data node is configured based on the variables obtained on the configuration page; if the current business node is an end node, the end node is configured based on the decision conditions obtained on the configuration page; a decision tree is generated based on each business node, and risk decisions are made on user behaviors based on the decision tree. By configuring multiple business nodes on the configuration page, complex rules can be flexibly divided into levels and complex businesses can be converted into executable decision trees, which can make risk decisions on various user behaviors. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 A diagram illustrating an application environment of a decision tree configuration method according to an embodiment;

[0032] Figure 2 A flowchart of a decision tree configuration method according to an embodiment;

[0033] Figure 3a is a schematic diagram of the structure of a decision tree in one embodiment;

[0034] Figure 3b A schematic diagram of a data structure for storing a decision tree in one embodiment;

[0035] Figure 4 A schematic diagram of a configuration page of an execution node in one embodiment;

[0036] Figure 5 Schematic diagram of class relationship in one embodiment;

[0037] Figure 6 A schematic diagram of a configuration page for a policy output template in one embodiment;

[0038] Figure 7 A schematic diagram of a configuration page of a data node in one embodiment;

[0039] Figure 8A schematic diagram of defining variables in one embodiment;

[0040] Figure 9 A schematic diagram of a configuration page for an end node in one embodiment;

[0041] Figure 10 A schematic diagram of a policy package call in one embodiment;

[0042] Figure 11 is a schematic diagram of a decision tree in one embodiment;

[0043] Figure 12 1 is a flow chart of a decision-making method in one embodiment;

[0044] Figure 13 is a schematic diagram of a decision tree in one embodiment;

[0045] Figure 14 A schematic diagram of a decision tree execution in one embodiment;

[0046] Figure 15 A schematic diagram of a decision tree usage scenario in one embodiment;

[0047] Figure 16 A structural block diagram of a decision tree configuration device in one embodiment;

[0048] Figure 17 A structural block diagram of a decision tree configuration device in another embodiment;

[0049] Figure 18 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0051] The decision tree configuration method provided in this application can be applied to Figure 1 In the application environment shown, the application environment includes a terminal 102 and a server 104.

[0052] The terminal 102 moves multiple business nodes to the main page; for each business node, in response to the configuration operation of the current business node, the terminal 102 displays the configuration page of the business node on the upper layer of the main page; if the current business node is an execution node, the terminal 102 configures the node type and decision strategy of the execution node on the configuration page; if the current business node is a data node, the terminal 102 configures the data node based on the variables obtained on the configuration page; if the current business node is an end node, the terminal 102 configures the end node based on the decision conditions obtained on the configuration page; the terminal 102 generates a decision tree based on each business node to make risk decisions on user behavior based on the decision tree.

[0053] The terminal 102 may be a smart phone, a tablet computer, a laptop computer, a desktop computer, a smart speaker, a smart watch, etc., but is not limited thereto.

[0054] The server 104 may be an independent physical server or a service node in a blockchain system. The service nodes in the blockchain system form a peer-to-peer (P2P) network. The P2P protocol is an application layer protocol running on top of the Transmission Control Protocol (TCP).

[0055] In addition, server 104 can also be a server cluster composed of multiple physical servers, and can be a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms.

[0056] The terminal 102 and the server 104 may be connected via Bluetooth, USB (Universal Serial Bus), or a network, and this application does not impose any limitation thereto.

[0057] In one embodiment, Figure 2 As shown, a decision tree configuration method is provided, which is applied to Figure 1 The following steps are used as an example to illustrate the terminal in the figure:

[0058] S202, moving multiple business nodes to the main page.

[0059] Business nodes refer to all nodes in a decision tree, including start nodes, execution nodes, data nodes, and end nodes. A decision tree is a tree-structured prediction model. An execution node represents a judgment on an attribute, each branch represents the output of a judgment, and each end node represents a classification result. A decision tree treats the different rule judgments or variable value judgment logic in a risk identification strategy as sequential business nodes. By executing these business nodes, project risks can be assessed, providing a decision analysis method for determining project feasibility.

[0060] In one embodiment, the decision tree can be configured by flexibly dragging business nodes based on the topology front-end framework. Topology is a visual online drawing engine. Business node controls can be configured based on the topology front-end framework. Business personnel can drag multiple business nodes. In response to the drag operation triggered by the business personnel, the terminal will move the corresponding business node to the main page. For example, at the left end of the main page window, there are multiple business node controls, including: start node control, execution node control, data node control, end node control and edge control. In response to the mouse drag operation triggered by the business personnel, the terminal can move the start node, execution node, data node and end node to the main page. After that, the terminal can move multiple edges to connect multiple business nodes to each other.

[0061] In one embodiment, the decision tree configuration data includes nodes and edges, and the terminal stores the decision tree in a data structure where nodes contain edges and edges contain tail nodes. Figure 3a As shown in the figure, the structure of the current decision tree is shown, where node A is connected to two edges, L1 and L2, L1 is connected to node B, and L2 is connected to node C. The data structure stored in the current decision tree is as follows Figure 3b As shown, node A stores the identifier of node A and the two edges L1 and L2 connected to it. Edge L1 stores the identifier of edge L1 and the connected tail node B. Edge L2 stores the identifier of edge L2 and the connected tail node C.

[0062] S204 : For each service node, in response to a configuration operation on the current service node, a configuration page of the service node is displayed on an upper layer of the main page.

[0063] In one embodiment, the configuration operation for the current service node can be a click on the service node control. In response to the click on the current service node, the terminal displays the configuration page for the service node on the upper layer of the main page. For example, after a service operator drags an execution node control to the main page, and then double-clicks the execution node control on the main page, the terminal displays the configuration page for the execution node on the upper layer of the main page in response to the double-click on the current execution node.

[0064] S206: If the current service node is an execution node, configure the node type and decision strategy of the execution node on the configuration page.

[0065] Execution nodes are business nodes that make decisions. Execution nodes can configure branching rules by selecting node types such as variables, policies, policy packages, condition groups, decision tables, and scorecards. Furthermore, policies utilize multiple variables for decision making. During decision tree execution, variables are derived from input material or from the variable platform. During decision tree configuration, variables can be created on data nodes or on the data variable platform.

[0066] In one embodiment, after detecting an input execution node configuration operation, the terminal can select the node type and bucketing method on the execution node configuration page. The node type refers to the type of the execution node's next layer, and the bucketing method refers to the branching rules of the current execution node. On the configuration page, you can select an existing bucketing method or configure a new one. Furthermore, the terminal will display different configuration pages depending on the selected node type.

[0067] For example, the configuration page of the execution node is as follows Figure 4 As shown, the configuration page includes: a drop-down box for selecting the node type, a search box for the bucketing method, a button for adding a new bucketing method, a list of bucketing methods, and details of the bucketing method. The details of the bucketing method include: the bucket number and bucket details of the selected bucketing method. The bucket details are a detailed description of the specific branching rules of the selected bucketing method. Specifically, the drop-down box for selecting the node type includes variables, policies, policy packages, condition groups, decision tables, scorecards, etc. When it is necessary to judge the risk by age, select a variable in the drop-down box for selecting the node type. In response to the variable selection operation triggered on the current configuration page, the terminal will refresh the configuration page. The business personnel select the age variable on the updated configuration page and select the branch rule that those over 20 years old are low risk and those under 20 years old are high risk in the bucketing method. The terminal will configure the execution node according to the above configuration.

[0068] In one embodiment, Figure 5As shown, the policy content includes the policy code, policy identifier, decision tree version, and policy status. The policy code is business-defined, and the policy identifier is a unique identifier generated based on the policy code and the current decision tree version. Nodes store the policy identifier, node identifier, and node type. Edges store the policy identifier, edge identifier, head node, tail node, and branching rules. Start nodes store the starting node and policy identifier. Policy input parameters store the policy identifier and variable code.

[0069] In one embodiment, before configuring the decision tree, the terminal obtains the parameters to be output on the policy parameter configuration page; based on the obtained parameters, it queries the corresponding template; the template is displayed on the policy parameter configuration page; and in response to a template filtering operation triggered on the policy parameter configuration page, the output parameters of the decision policy are configured based on the remaining templates after filtering. In addition, the policy parameter configuration page can also configure input parameters, selecting the variables to be used as input parameters, and the terminal will verify the input parameters.

[0070] For example, the terminal will provide an output parameter template configuration page, where business personnel can configure the output parameters of the policy. The output template configuration page includes an output field search and an output template configuration jump button. The terminal can select the output template of the policy, or configure the output template by itself through the output template configuration jump button. Figure 6 As shown, the output template configuration page allows you to enter output fields, select the output template type, and click the output template configuration jump button. By clicking the query button, the terminal will provide corresponding template search results based on the entered output fields and output template type. Template search results include: output field, output template type, creation time, updater, and update time. By checking multiple output fields in the output template, you can filter them out. The remaining output fields in the output template after filtering are the output fields of the end node.

[0071] S208: If the current service node is a data node, configure the data node based on the variables obtained on the configuration page.

[0072] Among them, the data node refers to the business node used to define temporary variables or perform calculations. The data node has no branches and is directly connected to the only next connection node.

[0073] In one embodiment, after detecting the input data node configuration operation, the terminal can select the variable encoding, variable name, variable data type and variable assignment in the data node configuration page, wherein the variable encoding and variable name can be configured in a customized manner, the variable encoding can be numbers, English, characters, special characters and any combination of the above types, and the variable name can also be numbers, English, characters, special characters and any combination of the above types. In addition, the variable assignment can be performed in a direct assignment manner or a combined calculation manner. The direct assignment manner means that a number can be used to directly assign a value to the variable, and the combined calculation manner means that the current variable is assigned a value through a combined calculation of multiple other variables. Depending on the selected assignment method, the terminal will display different configuration pages.

[0074] For example, the configuration page of a data node is as follows Figure 7 As shown, the configuration page includes: a text input box for variable code, a text input box for variable name, a drop-down box for data type, a check box for assignment method, etc., wherein the drop-down box for data type can include numbers, strings, Boolean values, and null, etc. When the direct assignment method is selected, the configuration page of the data node includes a text input box and a drop-down box for assignment. There are multiple numerical values ​​in the drop-down box, which can be directly selected. Specifically, when you need to define an age variable, you can enter 01 in the text input box for code, enter age in the text input box for name, and select the number type in the drop-down box for data type. Check the check box for direct assignment. In response to the check operation triggered on the current configuration page, the terminal will refresh the configuration page. The updated configuration page includes: a text input box and a drop-down box for assignment. Enter 20 in the text input box, and the terminal will assign the value 20 to the age variable.

[0075] In one embodiment, Figure 8 As shown, the terminal reads the attribute list based on the definition variables about the data node obtained on the configuration page; when the attribute corresponding to the definition variable is queried in the attribute list, the definition information corresponding to the definition variable is saved, and the definition variable is saved in the data variable platform; in response to the publishing operation, the definition variable saved in the data variable platform is published, thereby completing the configuration of the data node.

[0076] S210: If the current service node is an end node, configure the end node based on the decision condition obtained on the configuration page.

[0077] The end node can also be called a leaf node. The end node has no child nodes and edges and is used to end the traversal of the current decision tree and output the final decision result.

[0078] In one embodiment, the terminal can search for the corresponding risk decision in the output parameter template of the end node based on the policy. The end node can output a variable or constant, select the data format and assign a value to this variable or constant, and add output to the end node. A risk decision refers to the decision tree's assessment of a user's behavior or operation, and whether to approve or reject it.

[0079] For example, the configuration page of the end node is as follows Figure 9 As shown, the configuration page includes: a text box for risk decision, a drop-down box for data type, a text input box for assignment operation, and an add button for additional output. Among them, in the drop-down box for data type, you can select numbers, strings, Boolean values, and null, etc., the text input box for assignment operation can input variables or constants, and the additional output can output labels or actions, including: blacklisting, control, and rejection codes. Specifically, when the output decision result is pass and the credit limit is 50,000, select the string type in the drop-down box for data type, and enter the characters of pass and credit limit 50,000 in the text input box for assignment operation; when the output decision result is variable a, select the variable type in the drop-down box for data type, and enter a in the text input box for assignment operation. The terminal will configure the end node according to the configuration operation.

[0080] S212: Generate a decision tree based on each business node to make a risk decision on the user behavior based on the decision tree.

[0081] In one embodiment, the terminal calls a policy package based on an execution node in a decision tree; executes the decision policies in the policy package in parallel or sequentially to make risk decisions on user behavior based on the executed decision policies, wherein the execution node can call policies, policy packages, and other decision trees. For example, Figure 10 As shown, policy A can be a Vincio policy; policy B can be a qlExpress policy; policy C can be an RST policy tree; when the execution node calls policy D, policies A and B will be executed sequentially, and when the execution node calls policy E, policies A and B will be executed concurrently.

[0082] In one embodiment, the decision tree is as follows Figure 11 As shown, the terminal traverses the decision tree, entering from the start node and determining which branch of the first execution node the input parameters satisfy. If the left branch is satisfied, the terminal enters the data node. After executing the data node, the terminal enters the first end node, ends the traversal, and outputs the first result. If the right branch is satisfied, the terminal enters the second execution node and determines which branch of the second execution node the input parameters satisfy. If the left branch is satisfied, the terminal enters the first end node, ends the traversal, and outputs the first result. If the right branch is satisfied, the terminal enters the second end node, ends the traversal, and outputs the second result.

[0083] In the above-mentioned decision tree configuration method, multiple business nodes are moved to the main page; for each business node, in response to the configuration operation of the current business node, the configuration page of the business node is displayed on the upper layer of the main page; if the current business node is an execution node, the node type and decision strategy of the execution node are configured on the configuration page; if the current business node is a data node, the data node is configured based on the variables obtained on the configuration page; if the current business node is an end node, the end node is configured based on the decision conditions obtained on the configuration page; a decision tree is generated based on each business node, and risk decisions are made for user behaviors based on the decision tree. By configuring multiple business nodes on the configuration page, complex rules can be flexibly divided into levels and complex businesses can be converted into executable decision trees, which can make risk decisions for various user behaviors.

[0084] In one embodiment, Figure 12 As shown, S212 includes:

[0085] S1202, obtaining material information corresponding to the user behavior.

[0086] Among them, material information can be used as input parameters, and the terminal can judge the branches of the execution node based on the input parameters, and can also calculate the variables in the data node. Figure 13 As shown, enter from the start node, query the variables in the input parameters, execute the nodes according to the query results, and reach the end node.

[0087] S1204 , starting with the root node of the decision tree, and sequentially performing branch judgment on the material information based on the nodes passed through in the decision tree to determine the next level node to flow to, until a leaf node is reached.

[0088] Among them, the leaf node refers to the end node in the decision tree, such as Figure 14 As shown, after the terminal executes the current node, it performs branch judgment on the material information. When there is a satisfied branch, it executes the next level node corresponding to the satisfied branch until it reaches the end node, and outputs the result information stored in the end node; when there is no satisfied branch, it exits abnormally and outputs an abnormal result.

[0089] S1206: Make risk decisions on user behavior based on the result information stored in the leaf node.

[0090] In one embodiment, the terminal records the decision path of the decision tree during the process of making risk decisions; the decision path is a path consisting of nodes passed through in the decision tree.

[0091] In this embodiment, by obtaining the material information corresponding to the user behavior, branch judgments are made on the material information based on the nodes passed in the decision tree, risk decisions are made on the user behavior, and the decision path is recorded. It is possible to make risk decisions on complex businesses, and after outputting the results, the decision path can be viewed to optimize the decision tree.

[0092] This application also provides an application scenario, which applies the above-mentioned decision tree configuration method. Specifically, the application of the decision tree configuration method in this application scenario is as follows:

[0093] like Figure 15 As shown, after the decision tree is generated, the terminal executes from the start node; enters the execution node of age judgment, and queries whether it is in the preset age group based on the age variable in the material information; if the age variable does not meet the age group of 18-60 years old, enters the end node and outputs the result of rejection; if the age variable meets the age group of 18-60 years old, enters the execution node of income level judgment; queries multiple preset income levels based on the income variable in the material information, if the income variable only meets the lowest preset level C, enters the end node and outputs the result of rejection; if the income variable meets the middle preset level B, enters the end node and outputs the result of passed, with an amount of 10,000; if the income variable meets the highest preset level A, enters the end node and outputs the result of passed, with an amount of 50,000.

[0094] It should be understood that although Figure 2 、 12 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figure 2 、 12 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0095] In one embodiment, Figure 16 As shown, a decision tree configuration device is provided. The device can be a software module or a hardware module, or a combination of the two to form a part of a computer device. The device specifically includes: a moving module 1602, a display module 1604, an execution node configuration module 1606, a data node configuration module 1608, an end node configuration module 1610 and a generation module 1612, wherein:

[0096] The moving module 1602 is used to move multiple service nodes to the main page.

[0097] The display module 1604 is configured to display a configuration page of each service node on the upper layer of the main page in response to a configuration operation on the current service node.

[0098] The execution node configuration module 1606 is used to configure the node type and decision strategy of the execution node on the configuration page if the current business node is an execution node.

[0099] The data node configuration module 1608 is used to configure the data node based on the variables obtained on the configuration page if the current service node is a data node.

[0100] The end node configuration module 1610 is configured to configure the end node based on the decision conditions obtained on the configuration page if the current service node is an end node.

[0101] The generating module 1612 is configured to generate a decision tree based on each service node, so as to make risk decisions on user behaviors based on the decision tree.

[0102] In one embodiment, the variables include defined variables; Figure 17 The device also includes: a definition module 1614, which is used to read the attribute list based on the definition variables about the data node obtained on the configuration page; when the attribute corresponding to the definition variable is queried in the attribute list, save the definition information corresponding to the definition variable, and save the definition variable in the data variable platform; in response to the publishing operation, publish the definition variable saved in the data variable platform, thereby completing the configuration of the data node.

[0103] In one embodiment, the device further includes: a calling module 1616 for calling a policy package based on an execution node in a decision tree; executing the decision policies in the policy package in parallel or sequentially to make risk decisions on user behaviors based on the executed decision policies.

[0104] In one embodiment, the device also includes: a policy parameter configuration module 1618, which is used to obtain the parameters to be output in the policy parameter configuration page; query the corresponding template based on the obtained parameters; display the template on the policy parameter configuration page; and in response to the template screening operation triggered on the policy parameter configuration page, configure the output parameters of the decision strategy based on the template remaining after screening.

[0105] In one embodiment, the device also includes: a decision module 1620, which is used to obtain material information corresponding to user behavior; starting with the root node of the decision tree, branching and judging the material information based on the nodes passed through in the decision tree to determine the next level node to flow to until reaching the leaf node; and making risk decisions on user behavior based on the result information stored in the leaf node.

[0106] In one embodiment, the decision module 1620 is further configured to record a decision path of a decision tree during the process of making risk decisions; a decision path is a path consisting of nodes passed through in the decision tree.

[0107] The specific definition of the decision tree configuration device can be found in the definition of the decision tree configuration method above and will not be repeated here. Each module in the above-mentioned decision tree configuration device can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the corresponding operations of each of the above modules.

[0108] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 18 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a decision tree configuration method is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0109] Those skilled in the art will understand that Figure 18 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0110] In one embodiment, a computer device is further provided, including a memory and a processor. The memory stores a computer program, and the processor implements the steps in the above method embodiments when executing the computer program.

[0111] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above-mentioned method embodiments when executed by a processor.

[0112] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the steps of each of the above-described method embodiments.

[0113] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0114] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0115] The above embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A decision tree configuration method, characterized in that: The method comprises: Move multiple business nodes to the main page; For each of the service nodes, in response to a configuration operation on the current service node, displaying a configuration page of the service node on an upper layer of the main page; If the current business node is an execution node, the configuration page includes a drop-down box for selecting a node type and a bucketing method list for selecting a bucketing method. The node type and bucketing method are configured through the drop-down box and bucketing method list on the configuration page. If the node type is a decision strategy, the decision strategy is Vincio strategy, qlExpress strategy, or RST strategy tree. The execution node is a business node that performs decision judgment. If the current business node is a data node, the data node is configured based on the variables obtained on the configuration page; the data node is directly connected to the only next business node to define temporary variables or perform calculations; If the current service node is an end node, configure the end node based on the decision condition obtained on the configuration page; A decision tree is generated based on each of the service nodes to make risk decisions on user behaviors based on the decision tree.

2. The method according to claim 1, characterized in that The variables include defined variables; and configuring the data node based on the variables obtained on the configuration page includes: Reading a property list based on the defined variables about the data node obtained on the configuration page; When the attribute corresponding to the defined variable is queried in the attribute list, definition information corresponding to the defined variable is saved, and the defined variable is saved in the data variable platform; In response to the publishing operation, the defined variables stored in the data variable platform are published, thereby completing the configuration of the data node.

3. The method according to claim 1, characterized in that The risk decision-making for user behavior based on the decision tree includes: Invoking a policy package based on an execution node in the decision tree; The decision strategies in the strategy package are executed in parallel or sequentially to make risk decisions on user behaviors based on the executed decision strategies.

4. The method according to claim 3, characterized in that Also includes: Get the parameters to be output in the strategy parameter configuration page; Querying a corresponding template based on the obtained parameters; Displaying the template on the policy parameter configuration page; In response to a template screening operation triggered on the policy parameter configuration page, the output parameters of the decision policy are configured based on the templates remaining after screening.

5. The method according to claim 1, wherein The risk decision-making for user behavior based on the decision tree includes: Obtain material information corresponding to user behavior; Starting from the root node of the decision tree, the material information is subjected to branch judgment based on the nodes passed through in the decision tree in order to determine the next level node to flow to, until a leaf node is reached; Based on the result information stored in the leaf node, a risk decision is made on the user behavior.

6. The method according to claim 5, characterized in that Also includes: Recording the decision path of the decision tree during the process of risk decision-making; The decision path is a path consisting of nodes passed through in the decision tree.

7. A decision tree configuration device, characterized in that: The device comprises: Mobile module, used to move multiple business nodes to the main page; A display module, configured to display, for each of the service nodes, a configuration page of the service node on an upper layer of the main page in response to a configuration operation on the current service node; An execution node configuration module is configured to configure the node type and bucketing method using the drop-down box and bucketing method list on the configuration page if the current business node is an execution node; if the node type is a decision strategy, the decision strategy is a Vincio strategy, a qlExpress strategy, or an RST strategy tree; and the execution node is a business node that performs decision-making. A data node configuration module, configured to configure the data node based on the variables obtained on the configuration page if the current business node is a data node; the data node is directly connected to the only next business node to define temporary variables or perform calculations; an end node configuration module, configured to configure the end node based on the decision conditions obtained on the configuration page if the current service node is an end node; A generation module is used to generate a decision tree based on each of the business nodes, so as to make risk decisions on user behaviors based on the decision tree.

8. The device according to claim 7, characterized in that The device further comprises: A definition module is used to read an attribute list based on the definition variables about the data node obtained on the configuration page; when querying the attribute corresponding to the definition variable in the attribute list, save the definition information corresponding to the definition variable, and save the definition variable in the data variable platform; in response to the publishing operation, publish the definition variables saved in the data variable platform, thereby completing the configuration of the data node.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images