Dual recording address determination method, device, equipment and storage medium

Abstract

The present application relates to the fields of artificial intelligence and positioning identification, and specifically discloses a method, apparatus, device and storage medium for determining a dual-recording address. The method includes: obtaining dual-recording record data reported by multiple terminal devices; taking each of the dual-recording record data as a sample, performing feature extraction on each of the samples, and constructing a sample data set based on the extracted features and feature values; performing node division on the sample data set based on the Gini index as the basis for selecting division nodes to construct a binary tree model; using the binary tree model, determining a decision rule set, wherein the decision rule set is used to judge the authenticity of the dual-recording address of the dual-recording record data; obtaining target dual-recording record data and target dual-recording address reported by the terminal device to be verified; and using the decision rule set, determining whether the target dual-recording address is correct based on the target dual-recording record data.

Description

Technical Field

[0001] The present application relates to the field of positioning and identification, and in particular to a method, device, equipment and storage medium for determining a dual-recording address. Background Art

[0002] Currently, insurance agencies conduct insurance sales through agents. During dual recording, they obtain GPS information and dual recording data from user devices, then parse this GPS information to obtain the dual recording address. However, commercially available GPS external hardware devices can perform GPS relocation, allowing agents to falsely record dual recording locations. Inaccurate dual recording address information can complicate the subsequent retrieval of important information and troubleshooting. It can also lead to malicious misleading of policyholders, increasing the risk of policy cancellations and complaints. This can result in significant losses for insurance companies. Therefore, determining the accuracy of dual recording addresses has become a pressing issue. Summary of the Invention

[0003] The present application provides a dual-recording address determination method, apparatus, device and storage medium for detecting dual-recording addresses and ensuring the accuracy of dual-recording addresses.

[0004] In a first aspect, the present application provides a method for determining a dual recording address, the method comprising:

[0005] Obtain dual recording data reported by multiple terminal devices;

[0006] Taking each of the dual-recorded data as a sample, performing feature extraction on each of the samples, and constructing a sample data set based on the extracted features and feature values;

[0007] Based on the Gini index as a basis for selecting partition nodes, the sample data set is partitioned into nodes to construct a binary tree model;

[0008] Determining a decision rule set using the binary tree model, wherein the decision rule set is used to determine the authenticity of a dual-recorded address of dual-recorded data;

[0009] Obtain the target dual recording record data and target dual recording address reported by the terminal device to be verified;

[0010] Using the decision rule set, it is determined whether the target dual recording address is correct based on the target dual recording data.

[0011] In a second aspect, the present application further provides a dual recording address determination device, the dual recording address determination device comprising:

[0012] A data acquisition module is used to obtain dual recording data reported by multiple terminal devices;

[0013] A feature processing module, configured to take each of the dual-record data as a sample, extract features from each of the samples, and construct a sample data set based on the extracted features and feature values;

[0014] A model building module, configured to divide the sample data set into nodes based on the Gini index as a basis for selecting division nodes to build a binary tree model;

[0015] a rule generation module, configured to determine a decision rule set using the binary tree model, wherein the decision rule set is used to determine the authenticity of a dual-record address of dual-record data;

[0016] A data receiving module is used to obtain the target dual recording data and target dual recording address reported by the terminal device to be verified;

[0017] The comparison and judgment module is used to use the decision rule set to determine whether the target dual recording address is correct according to the target dual recording record data.

[0018] In a third aspect, the present application also provides a computer device, comprising a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program and implement any one of the dual recording address determination methods provided in the embodiments of the present application when executing the computer program.

[0019] In a fourth aspect, the present application further provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements any dual-recording address determination method provided in the embodiments of the present application.

[0020] The present application discloses a method, apparatus, device and storage medium for determining a double-recorded address. The method utilizes multi-dimensional geographic location tag information, constructs a binary tree model by using the Gini index, and determines a decision rule set based on the lifting index to determine whether the double-recorded address is forged. This method can reduce the situation where a single address indicator is tampered with to cause a double-recorded address misjudgment, and improve the recognition rate of double-recorded false positioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 This is a block diagram of an application scenario of a dual recording address determination method provided by an embodiment of the present application;

[0023] Figure 2 This is a schematic flow chart of a dual recording address determination method provided in an embodiment of the present application;

[0024] Figure 3 This is a schematic block diagram of a binary tree model provided in an embodiment of the present application;

[0025] Figure 4 This is a schematic block diagram of a dual recording address determination device provided in an embodiment of the present application;

[0026] Figure 5 This is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0028] The flowcharts shown in the accompanying drawings are for illustrative purposes only and do not necessarily include all contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may be decomposed, combined, or partially merged, so the actual execution order may vary depending on the actual situation.

[0029] It should be understood that the terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the present application. As used in this specification and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms unless the context clearly indicates otherwise.

[0030] It will also be understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0031] In order to reduce the situation where a single address indicator is tampered with to cause a double-recorded address misjudgment during insurance business development and to improve the false positioning recognition rate, the present application provides a double-recorded address determination method, device, equipment and storage medium.

[0032] The following embodiments of the present application are described in detail in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0033] The specific application scenarios of the dual recording address determination method are as follows: Figure 1 As shown, the determination method can be applied to a server, specifically to a server of an insurance application, which runs in the server and is used to obtain dual recording data uploaded by the insurance agent through the client of the insurance application, and the client runs in the terminal device used by the insurance agent.

[0034] When installing the insurance application on a terminal device, the terminal device must authorize the corresponding permissions, such as the permission to obtain GPS information, IP address, Wi-Fi physical address, base station location information, and cell identification code information.

[0035] It should be noted that embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Artificial Intelligence (AI) refers to the theories, methods, technologies, and application systems that use digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to achieve optimal results.

[0036] Fundamental AI technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, big data processing, operating / interaction systems, and mechatronics. AI software technologies primarily encompass computer vision, robotics, biometrics, speech processing, natural language processing, and machine learning / deep learning.

[0037] See also Figure 2 , see Figure 2 , Figure 2 This is a schematic flow chart of a dual-recorded address determination method provided by an embodiment of the present application. This dual-recorded address determination method utilizes multi-dimensional geographic location tag information to determine whether a dual-recorded address is fraudulent. This method can reduce the possibility of dual-recorded address misjudgments caused by tampering with a single address indicator, and improve the recognition rate of dual-recorded false location.

[0038] like Figure 2 As shown, the dual recording address determination method specifically includes: steps S101 to S106.

[0039] S101: Obtain dual recording data reported by multiple terminal devices.

[0040] In an embodiment of the present application, the terminal device may include a smart phone, tablet computer, laptop computer or desktop computer used by the insurance agent. An insurance application is installed in the terminal device of the insurance agent. The format of the insurance application may be an App, and the insurance order is signed through the insurance application. At a certain stage of the contract signing, the agent needs to be required to record audio and video of the key stages, that is, to obtain the corresponding audio and video recordings. At the same time, the system information of the terminal device, GPS longitude and latitude, GPS longitude and latitude accuracy, IP address information, Wi-Fi physical address, currently detected base station location information, ultra-wideband (UWB) signal, and currently detected cell identification code information, client policy information, contact address and other information are obtained through the authorization of the terminal device. This information and the audio and video recordings are packaged into dual-recording data and reported to the server.

[0041] It should be noted that the positioning technology and positioning information acquisition method provided in the embodiments of the present application are only used as detailed descriptions and analyses of specific embodiments, and are not intended to limit the present application. According to actual application scenarios, the positioning technology of the present application also includes: ultrasonic indoor positioning technology, radio frequency identification (RFID) indoor positioning technology, infrared positioning technology, iBeacon Bluetooth indoor positioning technology, Wi-Fi indoor positioning technology, ultra-wideband indoor positioning technology, ZigBee indoor positioning technology and Beidou navigation positioning technology; the positioning technology of the present application can also be any combination of one or more positioning technologies and all possible combinations.

[0042] In some embodiments, the dual recording data reported by each terminal device includes not only audio and video recordings, but also location information, network information, and insurance policy information related to the audio and video recordings.

[0043] The location information includes at least: GPS longitude and latitude, the accuracy of GPS longitude and latitude, and terminal location information based on base station positioning.

[0044] The network information includes at least: system information of the terminal device, IP address information, Wi-Fi physical address, currently detected base station location information and currently detected cell identification code information.

[0045] The policy information at least includes: client policy information and contact address.

[0046] S102: taking each of the dual-record data as a sample, performing feature extraction on each of the samples, and constructing a sample data set according to the extracted features and feature values.

[0047] Specifically, feature extraction is the process of extracting the characteristic values ​​of a sample. Each sample refers to a piece of dual-entry data. For example, each sample dataset can be divided according to the insurance policy number. The sample features and characteristic values ​​are determined based on multiple pieces of information in the dual-entry data. After feature extraction is complete, the sample dataset is constructed based on the extracted features and characteristic values.

[0048] Exemplarily, multiple pieces of information in the dual-recording data include the system information of the terminal device, GPS longitude and latitude, the accuracy of GPS longitude and latitude, IP address information, Wi-Fi physical address, currently detected base station location information, and currently detected cell identification code information, client policy information, contact address and other information, each corresponding to its own label. The features of the sample may include GPS longitude and latitude and IP address information, or GPS longitude and latitude and Wi-Fi physical address. In this way, more types of features can be extracted, and the corresponding feature value extraction methods may also include multiple methods, such as using a comparison method between the two. For example, whether the GPS longitude and latitude and the IP address information are consistent, the feature values ​​include "yes" and "no", which can be represented by 1 and 0. There are many ways to extract feature values, and the above are only examples and are not specifically limited.

[0049] In some embodiments, before extracting features from each sample, each dual-recorded data set can be cleaned to remove any unqualified dual-recorded data. This improves the accuracy of extracted features and feature values, and enhances the reference value of the sample dataset.

[0050] For example, dual recording data without audio or video recording is cleared, or the system information of the terminal device, GPS longitude and latitude, the accuracy of GPS longitude and latitude, IP address information, Wi-Fi physical address, currently detected base station location information and currently detected cell identification code information, client insurance policy information, and user dual recording information in which one or more of the contact address is empty is cleared.

[0051] Exemplarily, corresponding dual-recording record data can also be deleted according to the null value rate, such as deleting dual-recording record data with a null value rate greater than a preset threshold. For example, if 5 of the 9 items of information in the dual-recording record data 1, including the system information of the terminal device, GPS latitude and longitude, the accuracy of GPS latitude and longitude, IP address information, Wi-Fi physical address, currently detected base station location information, and currently detected cell identification code information, client insurance policy information, and contact address, are null values, that is, the null value rate is 5 / 9, which is approximately 55.56%. The preset threshold is 50, and the dual-recording record data 1 is deleted. The preset threshold can be set according to actual conditions, such as 50% or 60%.

[0052] S013. Based on the Gini index as a basis for selecting partition nodes, perform node partitioning on the sample data set to construct a binary tree model.

[0053] It should be noted that a binary tree refers to an ordered tree in which the degree of the nodes in the tree is no more than 2. It is the simplest and most important tree. The recursive definition of a binary tree is: a binary tree is an empty tree, or a non-empty tree consisting of a root node and two non-intersecting left and right subtrees of the root; the left and right subtrees are also binary trees. Traversal is the most basic operation on a tree. Traversing a binary tree means walking through all the nodes of the binary tree according to certain rules and order, so that each node is visited once and only once. Since a binary tree is a nonlinear structure, traversing the tree is essentially converting the nodes of the binary tree into a linear sequence to represent it.

[0054] Specifically, the root node is determined based on the Gini index of the sample dataset for each feature, with the feature corresponding to the minimum Gini index serving as the root node. The sample dataset is then divided into a left-node dataset and a right-node dataset based on the features and their corresponding eigenvalues. The root nodes of the left-node dataset and the right-node dataset are then determined until all features have been traversed, resulting in a binary tree model. The Gini index represents the impurity of a feature; a smaller Gini index indicates lower impurity and a better feature.

[0055] For example, the root node is first determined based on the Gini index of the sample dataset under each feature. Specifically, the feature corresponding to the minimum Gini index is used as the root node. Feature A with the minimum Gini index and its corresponding eigenvalue a are then selected. Based on this optimal feature A and eigenvalue a, the sample dataset D is divided into two parts, D1 and D2. At the same time, left and right child nodes of the current node are established, with the left node's dataset being D1 and the right node's dataset being D2. The same recursive partitioning is performed on the left and right child node datasets until all features have been traversed, ultimately generating a binary tree model.

[0056] See also Figure 3 , Figure 3A four-level binary tree model for determining dual-recorded addresses is presented. This binary tree contains seven features, which are compared against each other: H: whether the dual-recorded address and GPS latitude and longitude are within a preset range; I: whether the IP address information and Wi-Fi physical address are within a preset range; J: whether the GPS latitude and longitude accuracy is greater than 97%; K: whether the IP address information and the client's insurance policy information are within a preset range; L: whether the Wi-Fi physical address and base station location are within a preset range; M: whether the IP address information and the currently detected cell identification code are within a preset range; and N: whether the client's insurance policy information and contact address are within a preset range. Feature values ​​include "yes" and "no," represented by "1" and "0." Based on this binary tree model, a condition that all feature values ​​are "1" indicates that the dual-recorded address is not suspected of being fraudulent. A sample dataset is considered to contain a sample dataset with all feature values ​​of "1" if and only if all feature values ​​in this binary tree model are "1."

[0057] In some embodiments, for a given sample dataset D, assuming there are k categories and the number of the kth category is , then the Gini index expression of the sample dataset D is:

[0058]

[0059] In some embodiments, for a sample dataset D, if a certain feature value a of feature A is used to divide D into two parts, namely, two sub-sample datasets D1 and D2, then under the condition of feature A, the Gini index expression of the sample dataset D is:

[0060]

[0061] Gini(D, A) represents the Gini index of the sample data set D under the condition of feature A. From this, the Gini index of the sample data set D under each feature in the sample data set can be calculated.

[0062] S104: Determine a decision rule set using the binary tree model, wherein the decision rule set is used to determine the authenticity of the dual-recorded address of the dual-recorded data.

[0063] Specifically, according to the binary tree model corresponding to the sample data set, the lifting index corresponding to each node in the binary tree model is calculated; the target node layer number of the binary tree model is determined according to the lifting index of the node, and the decision rule set is determined according to the nodes involved in the target node layer number.

[0064] It should be noted that the lift index is a metric used to evaluate the effectiveness of a prediction model. It measures how much better a model or rule's predictive ability is than random selection. A larger lift index indicates a better performance. Specifically, in this embodiment, the lift index calculates the ratio of bad samples (forged addresses) captured using the rule to the total number of samples captured without using the rule.

[0065] For example, if the number of target node layers is determined to be 5, then the rules corresponding to the nodes involved in these 5 layers and the rule chain composed of the node corresponding rules constitute a rule set for determining whether the user's double-recorded address is forged, which is the decision rule set.

[0066] In some embodiments, the target node layer number can be determined based on the changing trend of the node's lifting index in the binary tree model. For example, if the node's lifting index changes from large to small starting from the root node, the layer number corresponding to the node before the change is determined to be the target node layer number. For example, if the lifting index of the 5th layer node starts to decrease, the 5th layer node is determined to be the target node layer number.

[0067] In other embodiments, the target node layer can also be determined based on whether the lifting index of the node in the binary tree model is less than or equal to a preset index threshold. If the lifting index of the node in a certain layer is less than the preset index threshold, then the layer is determined to be the target node layer. The preset index threshold can be set according to actual conditions. For example, if the lifting index of the node in the 5th layer is less than or equal to the preset index threshold, then the node in the 5th layer is determined to be the target node layer.

[0068] S105: Obtain target dual recording data and target dual recording address reported by the terminal device to be verified.

[0069] It should be noted that when an insurance agent signs an insurance order through a terminal device, the terminal device used by the insurance agent to sign the insurance order is the terminal device to be verified.

[0070] Obtain the target dual-recording record data and target dual-recording address reported by the terminal device to be verified. For example, the target dual-recording record data and target dual-recording address are determined by: institution name, agent, and region. The target dual-recording record data includes the terminal device's system information (specifically, device fingerprint information collected by the SDK), GPS longitude and latitude, GPS longitude and latitude accuracy, IP address information, Wi-Fi physical address, currently detected base station location information and currently detected cell identification code information, client policy information, contact address, and other information. The target dual-recording address is specifically the address reported by the insurance agent for signing the insurance order.

[0071] According to the method steps provided in the above embodiment, each acquired target dual recording data and target dual recording address is converted into a corresponding binary tree model, and the preset judgment condition of each node in the binary tree model is obtained, and the judgment condition is encapsulated to generate a decision rule set.

[0072] S106: Using the decision rule set, determine whether the target dual recording address is correct according to the target dual recording data.

[0073] Since the decision rule set has been determined in the above process, which includes some optimal nodes, the decision rule set can be used in combination with the double-recording record data when the insurance agent signs the insurance order to determine the authenticity of the double-recording address reported by the insurance agent, and then determine whether the double-recording address reported by the insurance agent is forged.

[0074] For example, combined with big data detection technology based on artificial intelligence, the target double-record record data and target double-record address stored in the server are obtained, a binary tree model and decision rules are generated, and all sample data sets suspected of fraud are extracted. Furthermore, the scope of fraud in double-record addresses can be judged based on the name of the institution and the region, or personal fraud can be investigated based on the agent, so as to further specify the responsibility for the problem.

[0075] The dual-recorded address determination method provided in the above embodiment utilizes multi-dimensional geographic location tag information, constructs a binary tree model by using the Gini index, and determines a decision rule set based on the lifting index to determine whether the dual-recorded address is forged. This can reduce the situation where a single address indicator is tampered with to cause a dual-recorded address misjudgment, and improve the recognition rate of dual-recorded false positioning.

[0076] See also Figure 4 , Figure 4 The embodiment of the present application further provides a schematic block diagram of a dual recording address determination device, wherein the dual recording address determination device 300 is used to execute the aforementioned dual recording address determination method. The dual recording address determination device can be configured in a server or a terminal.

[0077] The server can be a standalone server or a server cluster, or 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 (CDNs), and big data and artificial intelligence platforms. The terminal can be an electronic device such as a mobile phone, tablet computer, laptop computer, desktop computer, personal digital assistant, or wearable device.

[0078] like Figure 4As shown, the dual-recorded address determination device 300 includes: a data acquisition module 301, a feature processing module 302, a model construction module 303, a rule generation module 304, a data receiving module 305, and a comparison and judgment module 306.

[0079] The data acquisition module 301 is used to acquire dual recording data reported by multiple terminal devices.

[0080] The feature processing module 302 is configured to treat each of the dual-record data as a sample, extract features from each of the samples, and construct a sample data set based on the extracted features and feature values.

[0081] In some embodiments, before the feature processing module 302 is used to treat each of the dual-record data as a sample, extract features from each of the samples, and construct a sample data set based on the extracted features and feature values, it is further specifically used to:

[0082] The dual recording data is cleaned, and the data cleaning is used to clean up the dual recording data that does not meet the requirements.

[0083] The model building module 303 is configured to perform node partitioning on the sample data set based on the Gini index as a basis for selecting partition nodes to construct a binary tree model.

[0084] The model building module 303 is specifically used to determine the root node according to the Gini index of the sample data set under each feature, wherein the feature corresponding to the minimum Gini index is used as the root node; the sample data set is divided into a left node data set and a right node data set according to the feature and the feature value corresponding to the feature, and the root nodes of the left node data set and the right node data set are determined until all features are traversed to obtain a binary tree model.

[0085] The rule generation module 304 is configured to determine a decision rule set using the binary tree model, wherein the decision rule set is used to determine the authenticity of the dual-recorded address of the dual-recorded data.

[0086] The rule generation module 304 is specifically used to calculate the lifting index corresponding to each node in the binary tree model according to the binary tree model corresponding to the sample data set; determine the target node layer number of the binary tree model according to the lifting index of the node, and determine the decision rule set according to the nodes involved in the target node layer number.

[0087] In some embodiments, the rule generation module 304 is also specifically used to determine the target node layer number based on the changing trend of the lifting index of the node in the binary tree model; wherein, determining the target node layer number based on the changing trend of the lifting index of the node in the binary tree model includes: starting from the root node in the binary tree model, determining the changing trend of the review index, and if the lifting index of the node changes from large to small, then determining the layer number corresponding to the node before the change as the target node layer number.

[0088] In some embodiments, the rule generation module 304 is also specifically used to determine the target node layer number based on whether the promotion index of the node in the binary tree model is less than or equal to the preset index threshold; if the promotion index of the node in a certain layer is less than or equal to the preset index threshold, then the layer is determined to be the target node layer number.

[0089] The data receiving module 305 is configured to obtain the target dual recording record data and the target dual recording address reported by the terminal device to be verified.

[0090] The comparison and judgment module 306 is configured to use the decision rule set to determine whether the target dual recording address is correct according to the target dual recording data.

[0091] It should be noted that, those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the model training device and each module described above can refer to the corresponding processes in the aforementioned dual-recording address determination method embodiment, and will not be repeated here.

[0092] The above-mentioned dual recording address determination device can be implemented in the form of a computer program. The computer program can be used in Figure 5 Runs on the computer device shown.

[0093] See also Figure 5 , Figure 5 This is a schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server or a terminal.

[0094] See Figure 5 The computer device includes a processor, a memory, and a network interface connected through a system bus, wherein the memory may include a non-volatile storage medium and an internal memory.

[0095] The non-volatile storage medium can store an operating system and a computer program. The computer program includes program instructions, which, when executed, can cause the processor to execute any of the dual recording address determination methods provided in the embodiments of the present application.

[0096] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0097] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor, the processor can execute any one of the dual recording address determination methods provided in the embodiments of the present application.

[0098] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will understand that Figure 5 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.

[0099] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc.

[0100] Exemplarily, in one embodiment, the processor is configured to run a computer program stored in the memory to implement the following steps:

[0101] Obtain dual recording data reported by multiple terminal devices;

[0102] Taking each of the dual-recorded data as a sample, performing feature extraction on each of the samples, and constructing a sample data set based on the extracted features and feature values;

[0103] Based on the Gini index as a basis for selecting partition nodes, the sample data set is partitioned into nodes to construct a binary tree model;

[0104] Determining a decision rule set using the binary tree model, wherein the decision rule set is used to determine the authenticity of a dual-recorded address of dual-recorded data;

[0105] Obtain the target dual recording record data and target dual recording address reported by the terminal device to be verified;

[0106] Using the decision rule set, it is determined whether the target dual recording address is correct based on the target dual recording data.

[0107] In some embodiments, before the processor is used to treat each of the dual-record data as a sample, extract features from each of the samples, and construct a sample data set based on the extracted features and feature values, it is further specifically used to implement:

[0108] The dual recording data is cleaned, and the data cleaning is used to clean up the dual recording data that does not meet the requirements.

[0109] When the processor performs node partitioning on the sample data set to construct a binary tree model based on the Gini index as a basis for selecting partition nodes, the processor is further configured to implement:

[0110] The root node is determined according to the Gini index of the sample data set under each feature, wherein the feature corresponding to the minimum Gini index is used as the root node; the sample data set is divided into a left node data set and a right node data set according to the feature and the eigenvalue corresponding to the feature, and the root nodes of the left node data set and the right node data set are determined until all features are traversed to obtain a binary tree model.

[0111] When the processor is used to determine the decision rule set using the constructed binary tree model, it is also specifically used to calculate the lifting index corresponding to each node in the binary tree model based on the binary tree model corresponding to the sample data set; determine the target node layer number of the binary tree model based on the lifting index of the node, and determine the decision rule set based on the nodes involved in the target node layer number.

[0112] In some embodiments, when determining the target number of node layers of the binary tree model according to the lifting index of the node, the processor is further configured to implement:

[0113] The target node layer number is determined according to the changing trend of the lifting index of the node in the binary tree model; wherein, the method of determining the target node layer number according to the changing trend of the lifting index of the node in the binary tree model includes: determining the changing trend of the review index starting from the root node in the binary tree model, and if the lifting index of the node changes from large to small, then determining the layer number corresponding to the node before the change is the target node layer number.

[0114] In some embodiments, when determining the target number of node layers of the binary tree model according to the lifting index of the node, the processor is further configured to implement:

[0115] The target node layer number is determined based on whether the lifting index of the node in the binary tree model is less than or equal to a preset index threshold; if the lifting index of the node in a certain layer is less than or equal to the preset index threshold, the layer is determined to be the target node layer number.

[0116] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and the processor executes the program instructions to implement any of the dual recording address determination methods provided in the embodiments of the present application.

[0117] The computer-readable storage medium may be an internal storage unit of the computer device described in the aforementioned embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a SmartMedia Card (SMC), a Secure Digital (SD) card, a flash memory card, etc. equipped on the computer device.

[0118] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present application, and such modifications or substitutions should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for determining a dual recording address, characterized in that: The method comprises: Obtain dual recording data reported by multiple terminal devices; Taking each of the dual-recorded data as a sample, performing feature extraction on each of the samples, and constructing a sample data set based on the extracted features and feature values; Determine a root node according to the Gini index of the sample data set under each feature, wherein the feature corresponding to the minimum Gini index is used as the root node; divide the sample data set into a left node data set and a right node data set according to the feature and the feature value corresponding to the feature, and determine the root nodes of the left node data set and the right node data set until all features are traversed to obtain a binary tree model; Calculating a lifting index corresponding to each node in the binary tree model according to the binary tree model corresponding to the sample data set; determining a target node layer number of the binary tree model according to the lifting index of the node, and determining a decision rule set according to the nodes involved in the target node layer number, wherein the decision rule set is used to determine the authenticity of the dual-recorded address of the dual-recorded data; Obtain the target dual recording record data and target dual recording address reported by the terminal device to be verified; Using the decision rule set, it is determined whether the target dual recording address is correct based on the target dual recording data.

2. The method according to claim 1, characterized in that The dual recording data includes the audio and video recordings and the location information, network information and insurance policy information related to the recording of the audio and video recordings; The location information includes at least: GPS longitude and latitude, GPS longitude and latitude accuracy, and terminal location information based on base station positioning; The network information includes at least: system information of the terminal device, IP address information, Wi-Fi physical address, currently detected base station location information and currently detected cell identification code information; The policy information at least includes: client policy information and contact address.

3. The method according to claim 1, characterized in that The determining of the target number of node layers of the binary tree model according to the lifting index of the node includes: Determine the target node layer number according to the change trend of the lifting index of the node in the binary tree model; Among them, determining the target node layer number based on the changing trend of the lifting index of the node in the binary tree model includes: determining the changing trend of the lifting index starting from the root node in the binary tree model, and if the lifting index of the node changes from large to small, then determining the layer number corresponding to the node before the change as the target node layer number.

4. The method according to claim 1, wherein The determining of the target number of node layers of the binary tree model according to the lifting index of the node includes: Determining the target node layer number according to whether the lifting index of the node in the binary tree model is less than or equal to a preset index threshold; If the promotion index of the nodes of a certain layer is less than or equal to the preset index threshold, the layer is determined to be the target node layer number.

5. The method according to claim 1, wherein Before taking each of the dual-recorded data as a sample and performing feature extraction on each sample, the method further includes: The dual recording data is cleaned, and the data cleaning is used to clean up the dual recording data that does not meet the requirements.

6. A dual recording address determination device, characterized in that: include: A data acquisition module is used to acquire dual recording data reported by multiple terminal devices, wherein each dual recording data includes the audio and video recording and the location information, network information and insurance policy information related to the recording of the audio and video recording; A feature processing module, configured to take each of the dual-record data as a sample, extract features from each of the samples, and construct a sample data set based on the extracted features and feature values; A model construction module is used to determine a root node based on the Gini index of the sample data set under each feature, wherein the feature corresponding to the minimum Gini index is used as the root node; divide the sample data set into a left node data set and a right node data set based on the feature and the feature value corresponding to the feature, and determine the root nodes of the left node data set and the right node data set until all features are traversed to obtain a binary tree model; A rule generation module is configured to calculate a lifting index corresponding to each node in the binary tree model according to the binary tree model corresponding to the sample data set; determine a target node layer number of the binary tree model according to the lifting index of the node, and determine a decision rule set according to the nodes involved in the target node layer number, wherein the decision rule set is used to determine the authenticity of the dual-record address of the dual-record data; A data receiving module is used to obtain the target dual recording data and target dual recording address reported by the terminal device to be verified; The comparison and judgment module is used to use the decision rule set to determine whether the target dual recording address is correct according to the target dual recording record data.

7. A computer device, characterized in that: The computer device includes a memory and a processor; The memory is used to store computer programs; The processor is configured to execute the computer program and implement the dual recording address determination method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements the dual recording address determination method according to any one of claims 1 to 5.

Images