Security project processing method and device

Abstract

The embodiment of the invention provides a guarantee project processing method and device, and the method comprises the steps: carrying out the construction of a decision tree according to the user guarantee data of each service user of a guarantee service in a decision rule generation process of a project decision of a guarantee project, and obtaining a decision tree, and reading decision parameters and parameter thresholds contained in decision links to which the guarantee participation indexes meeting the decision type of the project decision belong from the decision tree, performing rule generation according to the decision parameters and the parameter thresholds to obtain decision rules, and generating the decision rules for performing the project decision of the guarantee service through the user guarantee data.

Description

Technical Field

[0001] This document relates to the field of data processing technology, and in particular to a method and device for processing security projects. Background Art

[0002] With the continuous development and promotion of Internet technology, the application scope of online services provided by Internet technology is becoming wider and wider, covering many service areas. In the process of service processing, the service providers of online services may use decision trees to handle classification tasks. Decision trees are a commonly used classification method. Specifically, they are a decision analysis method that judges the feasibility of a project by constructing a decision tree based on the known probabilities of various situations. Based on this, decision trees provide a feasible means for users to process online services. However, as the complexity of online services gradually increases, the requirements for the use of decision trees are also increasing, which brings certain challenges to the application of decision trees. Summary of the Invention

[0003] One or more embodiments of the present specification provide a method for processing a security project, comprising: constructing a decision tree based on the user security data of each service user of the security service to obtain a decision tree. The decision tree construction includes performing node segmentation based on the security participation data in the user security data and generating a decision tree based on the segmentation result. Determine the security participation index corresponding to the decision type for making a project decision for the security project in the decision tree. Read the decision parameters and parameter thresholds contained in the decision link to which the security participation index belongs from the decision tree, and generate rules based on the decision parameters and the parameter thresholds to obtain decision rules. The decision rules are used to process the project decision of the security project for the target user of the security service under the decision type.

[0004] One or more embodiments of the present specification provide a security project processing device, comprising: a construction module, configured to construct a decision tree based on the user security data of each service user of the security service to obtain a decision tree. The decision tree construction includes node segmentation based on the security participation data in the user security data and generating a decision tree based on the segmentation result. A determination module is configured to determine the security participation index corresponding to the decision type of the project decision for the security project in the decision tree. A generation module is configured to read the decision parameters and parameter thresholds contained in the decision link to which the security participation index belongs from the decision tree, and generate rules based on the decision parameters and the parameter thresholds to obtain decision rules. Wherein, the decision rule is used to process the project decision of the security project for the target user of the security service under the decision type.

[0005] One or more embodiments of the present specification provide a security project processing device, comprising: a processor; and a memory configured to store computer-executable instructions, wherein the computer-executable instructions, when executed, cause the processor to: construct a decision tree based on the user security data of each service user of the security service to obtain a decision tree. The decision tree construction includes node segmentation based on the security participation data in the user security data and generating a decision tree based on the segmentation result. The security participation index corresponding to the decision type of the project decision for the security project is determined in the decision tree. The decision parameters and parameter thresholds contained in the decision link to which the security participation index belongs are read from the decision tree, and a decision rule is generated based on the decision parameters and the parameter threshold to obtain a decision rule. The decision rule is used to process the project decision of the security project for the target user of the security service under the decision type.

[0006] One or more embodiments of the present specification provide a computer-readable storage medium for storing computer-executable instructions, which implement the following steps when executed: construct a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree. The decision tree construction includes node segmentation based on the protection participation data in the user protection data and generating a decision tree based on the segmentation result. Determine the protection participation index corresponding to the decision type of the project decision for the protection project in the decision tree. Read the decision parameters and parameter thresholds contained in the decision link to which the protection participation index belongs from the decision tree, and generate rules based on the decision parameters and the parameter thresholds to obtain decision rules. Wherein, the decision rule is used to process the project decision of the protection project for the target user of the protection service under the decision type. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] In order to more clearly illustrate one or more embodiments of this specification or technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments described in this specification. Those skilled in the art can derive other drawings based on these drawings without inventive effort. Figure 1 A schematic diagram of an implementation environment for a security project processing method provided in one or more embodiments of this specification; Figure 2 A processing flow chart of a method for processing a security project provided in one or more embodiments of this specification; Figure 3 A schematic diagram of a first rule generation process provided for one or more embodiments of this specification; Figure 4A schematic diagram of a second rule generation process provided for one or more embodiments of this specification; Figure 5 A flowchart of a method for processing a protection item applied to a first insurance service scenario provided in one or more embodiments of this specification; Figure 6 A flowchart of a method for processing a protection item applied to a second insurance service scenario provided in one or more embodiments of this specification; Figure 7 A schematic diagram of an embodiment of a security project processing device provided in one or more embodiments of this specification; Figure 8 A schematic diagram of the structure of a security project processing device provided in one or more embodiments of this specification. DETAILED DESCRIPTION

[0008] In order to enable those skilled in the art to better understand the technical solutions in one or more embodiments of this specification, the technical solutions in one or more embodiments of this specification will be clearly and completely described below in conjunction with the drawings in one or more embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this specification, not all of the embodiments. Based on one or more embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this document.

[0009] The method for processing security projects provided in one or more embodiments of this specification can be applied to the implementation environment of security project decision making. Figure 1 , the implementation environment includes at least: Server 101; In addition, the implementation environment may also include a server 102 for guaranteeing services; The server 101 is configured to construct a decision tree based on the user assurance data of each service user of the assurance service to obtain a decision tree, read the decision parameters and parameter thresholds of the decision link to which the assurance participation indicator belongs from the decision tree, and generate rules based on the decision parameters and parameter thresholds to obtain decision rules; the user assurance data of each service user of the assurance service can be obtained from the server 102; the server 101 and / or the server 102 can be one or more servers, a server cluster consisting of several servers, or a cloud server of a cloud computing platform; the server 101 and the server 102 can be the same server or different servers; In addition, the implementation environment may also include a user terminal 103 of the target user of the security service. The user terminal 103 can access the security projects of the security service, and the security service server 102 can perform project decision-making on the security projects accessed by the user terminal 103; the user terminal 103 can specifically be a mobile phone, a personal computer, a tablet computer, an e-book reader, a wearable device, a device for information interaction based on AR (Augmented Reality) / VR (Virtual Reality), a laptop computer, etc.

[0010] The implementation environment may also include a user terminal 104 of each service user of the security service. The user terminal 104 can access the security service, and each service user may have user security data in the security service. The user terminal 104 can specifically be a mobile phone, a personal computer, a tablet computer, an e-book reader, a wearable device, a device based on AR (Augmented Reality) / VR (Virtual Reality) for information interaction, a laptop computer, etc.

[0011] In this implementation environment, the server 101 constructs a decision tree based on the user assurance data of each service user of the assurance service to obtain a decision tree. According to the decision type of the project decision for the assurance project, the server 101 extracts the decision parameters and parameter thresholds of the assurance participation indicator matching decision type from the decision tree. Based on the decision parameters and parameter thresholds, the server 101 generates rules to obtain decision rules. In this way, the server 101 generates decision rules for the assurance project decision for the assurance service based on the user assurance data. The server 101 may obtain user protection data of each service user of the protection service from the server 102; and the decision rule may be used to perform project decision processing on the protection project for the target user of the protection service under the decision type.

[0012] One or more embodiments of a method for processing a security project provided in this specification are as follows: Reference Figure 2 The security project processing method provided in this embodiment specifically includes steps S202 to S206.

[0013] Step S202: construct a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree.

[0014] The protection service described in this embodiment refers to a service that provides protection to users; the protection service may be an insurance service; the protection service may specifically be a protection service that provides service users with protection items of one or more protection categories, such as an accident protection item that provides accident protection to service users, a health protection item that provides health protection, a disease protection item that provides disease protection, and / or a travel protection item that provides travel protection, for example, an accident protection item is accident insurance, a health protection item is health insurance, a disease protection item is disease insurance, and a travel protection item is travel insurance; in addition, the protection item may also be other types of protection items; optionally, the protection service includes a protection subroutine within an application; specifically, the protection subroutine may be a protection applet, and the application may be a payment application or a third-party application; In addition to the fact that the protection service may include a protection sub-program within the application, the protection service may also be a protection channel within the protection sub-program. Optionally, the protection service includes a protection channel of any protection category within the protection sub-program; the protection category may include an accident protection category, a disease protection category, a health protection category and / or a travel protection category, and the protection category may also be other protection categories; the protection channel may include a protection module or protection unit of any protection category, and the protection channel of any protection category may provide corresponding protection of any protection category to the service user; in this regard, the protection service may include an accident protection service that provides accident protection to the service user, a health protection service that provides health protection, a disease protection service that provides disease protection and / or a travel protection service that provides travel protection. In addition, it may also be other protection services that provide other protections. The protection service may include an accident protection service, a health protection service, a disease protection service and / or a travel protection service within the protection sub-program.

[0015] The service user may be a protected user or an insured user of the protection service, specifically an insured user who participates in, purchases or applies for a protection project of the protection service. The service user may include users who have made claims and / or users who have not made claims for the protection service; the user protection data of the service user may include user attribute data, user behavior data and / or protection participation data; user attribute data may be data related to the user attributes of the service user, such as user attribute data including birth time, salary, asset amount and / or geographical area, in addition, user attribute data may also be other data; user behavior data may include transaction behavior data of the service user in the application and / or protection service, the application may be a payment application, and transaction behavior data may include transaction amount, number of transaction orders and / or transaction frequency; protection participation data may be protection project data of the service user's participation in the protection project, protection participation data may include protection participation resource amount or protection participation amount, and specific protection participation data may include protection issuance resource amount and / or protection expenditure resource amount, the protection issuance resource amount may be the protection issuance amount or the claim amount, and the protection expenditure resource amount may be the protection expenditure amount or the premium; A service user's insurance participation data can be for a single insurance program or for all insurance programs the service user participated in within a preset time period, such as all insurance programs the service user participated in over x years. The insurance programs a service user participated in within the preset time period can be of the same or different insurance categories, including accident insurance, health insurance, disease insurance, and / or travel insurance. A decision tree is a tree structure that can include a root node, internal nodes, and leaf nodes, each of which can represent a class label.

[0016] During specific implementation, user protection data of each service user of the protection service can be obtained, and a decision tree can be constructed based on the user protection data to obtain a decision tree. Specifically, user protection data of each service user of the protection service can be obtained after detecting that a preset time period has expired, and a decision tree can be constructed based on the user protection data to obtain a decision tree. The decision tree obtained here can be one or more; optionally, the decision tree construction includes node segmentation according to the protection participation data in the user protection data and generating a decision tree based on the segmentation result.

[0017] In practical applications, the decision effect of a single decision tree may be limited. Therefore, in order to improve the richness and decision effect of decision rules subsequently generated by the decision tree, a random forest method can be used to construct each decision tree. Specifically, row sampling and / or column sampling can be performed with replacement in the user assurance data of each service user of the assurance service, and each decision tree is constructed based on the row sampling results and / or column sampling results. Rule generation is performed through multiple decision trees to improve the comprehensiveness of the decision rules. In an optional implementation manner provided by this embodiment, in the process of constructing a decision tree based on the user assurance data of each service user of the assurance service to obtain a decision tree, user sampling is performed from each service user to obtain each sampled user set, and each decision tree is constructed based on the user assurance data of the sampled users included in each sampled user set, or each decision tree is constructed based on the user assurance data of the sampled users included in each sampled user set under each sampling category. Specifically, the following operations can be performed: Sampling users from each service user according to the number of decision tree constructions to obtain a sampled user set; For each sampling user set, data sampling is performed from the data categories corresponding to the user assurance data to obtain each sampling category, and each decision tree is constructed based on the user assurance data of the sampling users included in each sampling user set under each sampling category.

[0018] Among them, the sampling user set refers to a set of users obtained by user selection from each service user. The sampling user set can be a set consisting of one or more sampling users; the number of sets of each sampling user set can be the number of constructions for decision tree construction, each sampling user set can correspond one-to-one to each sampling category, and each sampling category can be each sampling data category; the sampling category corresponding to each sampling user set can be one or more, and the sampling categories corresponding to each sampling user set can be the same or different; for example, if the number of constructions for decision tree construction is n, then the number of each sampling user set is also n, and the number of each sampling category is also n. Each sampling user set corresponds to its own sampling category. The sampling categories corresponding to sampling user set a are birth date, salary, and geographical area, and the sampling categories corresponding to sampling user set b are geographical area and marital status.

[0019] Specifically, user sampling can be performed with replacement from each service user according to the number of constructions for decision tree construction to obtain each sampled user set. For each sampled user set, data sampling is performed from the data category corresponding to the user protection data to obtain the sampling category corresponding to each sampled user set. Based on the user protection data of the sampled users included in each sampled user set under the sampling category, each decision tree is constructed.

[0020] For example Figure 3As shown, the number of constructions for decision tree construction is n, and row and column sampling is performed according to the construction number n, that is, user sampling is performed with replacement from each service user to obtain n sampling user sets, and data sampling is performed for each sampling user set from the data category corresponding to the user protection data to obtain the sampling category corresponding to each sampling user set, and n decision trees are constructed based on the user protection data of the sampling users contained in each sampling user set in the n sampling user sets under their respective corresponding sampling categories.

[0021] Specifically, during the decision tree construction process, node segmentation may be performed based on the guarantee participation data in the user guarantee data of each service user of the guarantee service, and a decision tree may be generated based on the segmentation result. During the specific execution process, the guarantee participation data may be introduced and node segmentation may be performed based on the guarantee participation data. In an optional implementation provided by this embodiment, during the node segmentation based on the guarantee participation data in the user guarantee data, a target segmentation condition is determined in the segmentation condition based on the guarantee participation data of the service users corresponding to each sub-node of the current node under the segmentation condition, and the node segmentation is performed based on the target segmentation condition. Specifically, the following operations may be performed: Determine the target splitting condition in the splitting condition according to the guarantee participation data of the service users corresponding to each child node of the current node under the splitting condition; Perform node splitting on the current node based on the target splitting condition.

[0022] Optionally, the service user's guarantee participation data includes the guarantee issuance resource amount and the guarantee expenditure resource amount; node splitting can be node splitting, node splitting refers to the process of splitting a node into multiple nodes, and the splitting condition can be a splitting condition; each child node of the current node under the splitting condition can be at least two, and the current node can have at least two child nodes under the splitting condition.

[0023] Among them, the current node can be a node that needs to be split in the current decision tree, the current node can be the root node in the current decision tree, or it can be an internal node in the current decision tree, and the current node can be one or more; the splitting condition can be a condition for node splitting or node splitting of the current node; optionally, the splitting condition is generated based on the user attribute data and / or user behavior data contained in the user protection data of the service user corresponding to the current node, for example, the service users of the protection service include service user 1, service user 2...service user n, the service users corresponding to the current node include service user 2, service user 5 and service user 7, and the birth time of service user 2, service user 5 and service user 7 is The birth time and order numbers are 20 and 300 for service user 2, 25 and 240 for service user 5, and 30 and 500 for service user 7. The splitting conditions generated according to the birth time and order number of the service user corresponding to the current node include birth time ≤ 20 and birth time > 20, birth time ≤ 25 and birth time > 25, birth time ≤ 30 and birth time > 30, number of orders ≤ 300 and number of orders > 300, number of orders ≤ 240 and number of orders > 240, number of orders ≤ 500 and number of orders > 500; here, birth time ≤ 20 and birth time > 20 can be a splitting condition, and the others are similar. The splitting condition can also be birth time < 20 and birth time ≥ 20, and the others are similar.

[0024] Specifically, a splitting condition can be generated based on the user attribute data and / or user behavior data contained in the user protection data of the service user corresponding to the current node in the current decision tree, and the target splitting condition can be determined in the splitting condition according to the protection participation data of the service users corresponding to each child node of the current node under the splitting condition, and the current node can be split based on the target splitting condition; in the process of performing node splitting on the current node based on the target splitting condition, the service user corresponding to the current node can be divided or split based on the target splitting condition to obtain the service users corresponding to each child node of the current node.

[0025] Continuing with the above example, the splitting conditions generated based on the birth time and number of orders of the service user corresponding to the current node in the current decision tree include birth time ≤ 20 and birth time > 20, birth time ≤ 25 and birth time > 25, birth time ≤ 30 and birth time > 30, number of orders ≤ 300 and number of orders > 300, number of orders ≤ 240 and number of orders > 240, number of orders ≤ 500 and number of orders > 500. The service users corresponding to the two child nodes of the current node under birth time ≤ 20 and birth time > 20 are "service user 2" and "service user 5 and service user 7" respectively. The service users corresponding to the two child nodes of the current node under other splitting conditions are similar. According to the security participation data of the service users corresponding to each child node of the current node under the splitting condition, the target splitting condition is determined in the splitting condition, and the current node is split based on the target splitting condition.

[0026] On this basis, in order to identify users with a high guarantee issuance rate through a decision tree and improve the accuracy and effectiveness of subsequent project decisions for guarantee projects based on the decision rules generated by the decision tree; in an optional implementation provided by this embodiment, in the process of determining the target splitting condition in the splitting condition based on the guarantee participation data of the service users corresponding to each sub-node of the current node under the splitting condition, the guarantee participation index corresponding to each sub-node is calculated based on the guarantee participation data, and the target splitting condition is determined in the splitting condition based on the guarantee participation index. Specifically, the following operations can be performed: Calculate the guarantee payment rate corresponding to each sub-node based on the guarantee payment resource amount and the guarantee expenditure resource amount; The guaranteed payment rate difference corresponding to the segmentation condition is calculated based on the guaranteed payment rate, and the target segmentation condition is determined in the segmentation condition according to the guaranteed payment rate difference.

[0027] Among them, the guarantee issuance resource amount and the guarantee expenditure fund amount can be the total guarantee issuance resource amount and the total guarantee expenditure resource amount of the service users corresponding to each sub-node of the current node under the segmentation conditions. The guarantee issuance resource amount may include the claim amount, specifically including the claim amount within a preset time period. The guarantee expenditure resource amount may include the premium, specifically including the premium within a preset time period. The guarantee issuance rate may include the claims rate or the claim rate, specifically the claims ratio or the claim ratio. The guarantee issuance rate difference may include the claims ratio difference or the claim ratio difference.

[0028] Furthermore, in order to further differentiate users with high guarantee payment rates from users with low guarantee payment rates through the decision tree, these two types of users are distinguished as much as possible, so that subsequent project decisions for guarantee projects can be made more conveniently; in an optional implementation provided by this embodiment, in the process of determining the target segmentation condition among the segmentation conditions based on the guarantee payment rate difference, the segmentation condition with the difference in guarantee participation index or the index difference ranking first among the segmentation conditions is determined as the target segmentation condition. Specifically, the following operations can be performed: Sort each segmentation condition according to the difference in guarantee payment rate corresponding to each segmentation condition; In the sorting results, a segmentation condition whose sorting position is before the preset position is determined as a target segmentation condition.

[0029] The segmentation condition whose ranking is before the preset ranking may be the segmentation condition whose ranking is first.

[0030] Specifically, the guaranteed payment rate corresponding to each child node can be calculated based on the guaranteed payment resource amount and guaranteed expenditure resource amount of the service users corresponding to each child node of the current node under the splitting conditions, and the guaranteed payment rate difference corresponding to the splitting conditions can be calculated based on the guaranteed payment rate corresponding to each child node. The splitting conditions are sorted in descending order according to the guaranteed payment rate difference corresponding to each splitting condition, and the splitting condition with the first ranking in the sorting result is determined as the target splitting condition; in the process of calculating the guaranteed payment rate corresponding to each child node based on the guaranteed payment resource amount and guaranteed expenditure resource amount of the service users corresponding to each child node of the current node under the splitting conditions, the ratio of the guaranteed payment resource amount to the guaranteed expenditure resource amount can be calculated as the guaranteed payment rate.

[0031] For example, the splitting conditions include birth time ≤ 20 and birth time > 20, birth time ≤ 25 and birth time > 25, birth time ≤ 30 and birth time > 30, number of orders ≤ 300 and order number > 300, number of orders ≤ 240 and order number > 240, number of orders ≤ 500 and order number > 500. The two child nodes of the current node under birth time ≤ 20 and birth time > 20 correspond to the service users "Service User 2" and "Service User 5 and Service User 7" respectively. The guaranteed resource amount and guaranteed expenditure are issued according to service user 2. The guaranteed payment rate m1 of service user 2 is calculated based on the resource amount. The guaranteed payment rate m2 is calculated based on the total guaranteed payment resource amount and the total guaranteed expenditure resource amount of service users 5 and service users 7. The positive number of (m1-m2) is calculated as the guaranteed payment rate difference corresponding to the splitting conditions "birth time ≤ 20 and birth time > 20". The calculation method of the guaranteed payment rate difference corresponding to other splitting conditions is similar. The splitting conditions are sorted from large to small according to the guaranteed payment rate difference, and the splitting condition with the first ranking in the sorting result is determined as the target splitting condition.

[0032] During specific implementation, in order to improve the effect of decision tree construction and to avoid excessively long construction time of the decision tree, in the process of generating the decision tree based on the segmentation result, if the segmentation result satisfies the termination condition, the current decision tree may be used as the decision tree. The segmentation result may include the number of service users corresponding to the sub-nodes obtained by node segmentation based on the current decision tree and / or the number of segmentation times (cumulative number of segmentation times). Specifically, if the number of service users corresponding to the sub-nodes obtained by node segmentation based on the current decision tree is less than a number threshold, or if the number of segmentation times is greater than a number threshold, the current decision tree may be used as the decision tree. If the number of users is greater than or equal to the number threshold or the number of segmentation times is less than or equal to the number threshold, the sub-nodes may be segmented based on user protection data of the service users corresponding to the sub-nodes or the protection participation data in the user protection data until the number of service users corresponding to the sub-nodes after the node segmentation is less than the number threshold or the number of segmentation times is greater than the number threshold, thereby obtaining a decision tree. Specifically, in an optional implementation manner provided by this embodiment, in the process of generating the decision tree based on the segmentation result, the following operations are performed: Detecting whether the number of service users corresponding to the child nodes obtained by node splitting based on the current decision tree is less than a number threshold, or updating the number of splits based on the node splitting of the current decision tree and detecting whether the number of splits is greater than a number threshold; If not, the sub-node is segmented based on the protection participation data in the user protection data of the service user corresponding to the sub-node; if so, the current decision tree is used as the decision tree.

[0033] The number of splits may be accumulated each time a node split is performed, and the number of splits may be a cumulative number of splits.

[0034] Specifically, in the process of constructing a decision tree, the service user corresponding to the root node may be the user protection data of each service user of the protection service. The splitting condition of the root node can be generated based on the user attribute data and / or user behavior data contained in the user protection data of each service user corresponding to the root node. The target splitting condition is determined in the splitting condition based on the protection participation data of the service users corresponding to each child node of the root node under the splitting condition. The root node is split based on the target splitting condition to obtain each child node of the root node. The splitting condition of each child node is generated based on the user attribute data and / or user behavior data of the service user corresponding to each child node of the root node. The target splitting condition is determined in the splitting condition based on the protection participation data of the service users corresponding to each child node under the splitting condition. The node splitting is performed on each child node based on the target splitting condition to obtain each child node of each child node. It is iterated according to the node splitting method provided above until the number of users of the service users corresponding to the child node after the node split is less than the number threshold or the number of splits is greater than the number threshold, thereby obtaining a decision tree.

[0035] After the decision tree is constructed based on the user assurance data of each service user of the assurance service to obtain the decision tree, pruning processing can be performed on the decision tree, specifically post-pruning processing can be performed.

[0036] It should be noted that the above-mentioned operation of constructing a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree can be replaced by constructing a decision tree based on the user data of each service user of the protection service to obtain a decision tree, or can be replaced by constructing a decision tree based on the user data of the service users of the protection service to obtain a decision tree, or can be replaced by constructing a structure tree based on the user data of the service users of the protection service to obtain a structure tree. The structure tree may include a decision tree or other types of structure trees; and it constitutes a new implementation method together with the other processing steps provided in this embodiment.

[0037] Step S204: determining the guarantee participation index corresponding to the decision type of the project decision for the guarantee project in the decision tree.

[0038] The above-mentioned decision tree is constructed based on the user guarantee data of each service user of the guarantee service to obtain a decision tree. In this step, the guarantee participation index corresponding to the decision type of the project decision of the guarantee project is determined in the decision tree, so as to improve the convenience of subsequently generating decision rules under the decision type.

[0039] The project decision described in this embodiment may include underwriting decision, claims settlement decision and / or insured amount change decision for the protection item, and the insured amount change decision may include insured amount reduction decision and / or insured amount increase decision; the decision type may include underwriting type, claims settlement type and / or insured amount change type, and the insured amount change type may include insured amount reduction type and / or insured amount increase type. Underwriting refers to verifying the user's insurance of the protection item, and the underwriting decision refers to deciding whether to insure the user for the protection item. Claim settlement refers to verifying the claim for the user for the protection item, and the claims settlement decision refers to deciding whether to make a claim for the user for the protection item. The insured amount change decision refers to deciding whether to change the insured amount of the protection item for the user.

[0040] The guarantee participation index can be a guarantee issuance index, or a guarantee participation index within a preset time period, specifically a guarantee issuance rate, a claim settlement rate or a payment rate; the guarantee issuance rate, claim settlement rate or payment rate in this embodiment can be replaced by a guarantee issuance index or a guarantee participation index.

[0041] During specific implementation, a preset indicator threshold can be determined according to the decision type of the project decision for the security project, and the security participation indicator that meets the preset indicator threshold can be determined in the decision tree; specifically, the security participation indicator that meets the preset indicator threshold can be determined among the security participation indicators corresponding to the leaf nodes of the decision tree, or the indicator determination conditions can be determined according to the decision type, and the security participation indicator can be determined in the decision tree according to the indicator determination conditions. The indicator determination conditions may include determining the security participation indicator with the first indicator size or determining the security participation indicator with the last indicator size. Here, the first security participation indicator and / or the last security participation indicator can be the security participation indicator with the first and / or last ranking in the indicator size, and the ranking can be from large to small.

[0042] In actual applications, different types of project decisions for guarantee projects require different guarantee participation indicators. In order to improve the flexibility and pertinence of subsequent rule generation, in the process of determining the guarantee participation indicator corresponding to the decision type of the project decision for the guarantee project in the decision tree, the indicator determination condition can be determined according to the decision type of the project decision for the guarantee project, and the corresponding guarantee participation indicator can be determined in the decision tree according to the indicator determination condition. The indicator determination condition may include a first determination condition for determining a guarantee participation indicator greater than a preset indicator threshold and / or a second determination condition for determining a guarantee participation indicator less than or equal to the preset indicator threshold; Specifically, in the first optional implementation provided by this embodiment, in the process of determining the guarantee participation indicator corresponding to the decision type of the project decision for the guarantee project in the decision tree, the following operations are performed: If the decision type is underwriting type, claim settlement type or sum assured reduction type, a protection participation index greater than a preset index threshold is determined in the decision tree.

[0043] Among them, the preset indicator threshold can be a pre-set indicator threshold, and the preset indicator threshold can be an arbitrary value; the leaf node in the decision tree can represent a class label, and the class label can be the protection participation index corresponding to the leaf node. Each leaf node corresponds to its own protection participation index, and the protection participation index can be a protection issuance index, a protection issuance rate, a claim rate or a payment rate. The protection participation index of the leaf node can be calculated based on the protection participation data of the service user corresponding to the leaf node. Specifically, it can be the ratio of the protection issuance resource amount to the protection expenditure resource amount of the service user corresponding to the leaf node. When there are multiple service users, the protection issuance resource amount can be the total protection issuance resource amount, and the protection expenditure resource amount can be the total protection expenditure resource amount.

[0044] Specifically, if the decision type is an underwriting type, a claims settlement type, or a sum insured reduction type, a protection participation index greater than a preset index threshold may be determined among the protection participation indexes corresponding to the leaf nodes of the decision tree.

[0045] In a second optional implementation provided by this embodiment, in the process of determining the guarantee participation indicator corresponding to the decision type of the project decision for the guarantee project in the decision tree, the following operations are performed: If the decision type is an increase in the insured amount, determine the protection participation index that is less than or equal to the preset index threshold in the decision tree.

[0046] It should be noted that the preset indicator threshold in the above-mentioned "greater than the preset indicator threshold" and the preset indicator threshold in this "less than or equal to the preset indicator threshold" may be the same as or different from each other.

[0047] In the process of determining the protection participation index corresponding to the decision type of the project decision for the protection project in the decision tree, when the decision type is an underwriting type, a claims settlement type or a sum insured reduction type, the protection participation index with the largest index size in the decision tree can be determined; if the decision type is a sum insured increase type, the protection participation index with the smallest index size in the decision tree can be determined.

[0048] Step S206: Read the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs from the decision tree, and generate rules based on the decision parameters and parameter thresholds to obtain decision rules.

[0049] The above-mentioned guarantee participation index corresponding to the decision type of the project decision for the guarantee project is determined in the decision tree. In this step, the decision parameters and parameter thresholds contained in the decision link to which the guarantee participation index belongs are read from the decision tree, and the decision rules are generated according to the decision parameters and parameter thresholds to obtain the decision rules.

[0050] The decision link described in this embodiment can be a decision branch or decision path to which the participation indicator belongs, and can be a decision link, decision branch or decision path to which the leaf node corresponding to the participation indicator belongs; the decision parameter can correspond to the root node and / or internal node in the decision link, and the parameter threshold can include the parameter upper limit threshold and / or the parameter lower limit threshold.

[0051] During specific implementation, the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs can be read from the decision tree, and rules are generated based on the decision parameters and parameter thresholds to obtain decision rules; for example, the decision type is the underwriting type, and the preset indicator threshold corresponding to the underwriting type is determined to be 90%. In the decision tree, the guarantee participation indicators 95%, 92% and 94% that are greater than the preset indicator threshold 90% are determined, and the decision parameters and parameter thresholds included in the decision links to which the guarantee participation indicators 95%, 92% and 94% belong are read from the decision tree. Taking the guarantee participation indicator 95% as an example, the decision link to which the guarantee participation indicator 95% belongs is birth length greater than 35, salary less than 3000, and number of orders less than 200. The decision parameters included in the decision link to which the guarantee participation indicator 95% belongs are birth length, salary and number of orders, and the parameter thresholds are greater than 35, less than 3000 and less than 200, respectively. The decision rules are generated based on the decision parameters and parameter thresholds to obtain decision rules.

[0052] In actual applications, candidate decision rules generated based on decision parameters and parameter thresholds may not meet the project decision requirements of the guarantee service. In order to improve the adaptability of decision rules to the project decision scenarios of the guarantee service and improve the effectiveness of decision rules, in a first optional implementation manner provided by this embodiment, in the process of generating decision rules based on decision parameters and parameter thresholds, the decision parameters and the upper or lower thresholds of the parameters are combined to obtain candidate decision rules. The decision rules are obtained by removing candidate decision rules whose decision parameters do not meet the monotonic property or removing candidate decision rules whose decision parameters of the same parameter category do not meet the quantity threshold. Specifically, the following operations can be performed: Merging the decision parameters and the upper or lower thresholds of the parameters to obtain candidate decision rules; Detecting whether the decision parameters in each candidate decision rule are monotonic attributes, or detecting whether the number of decision parameters of the same parameter category in each candidate decision rule is less than a quantity threshold; If not, the detected candidate decision rule is eliminated from the candidate decision rules to obtain a decision rule; the quantity threshold may be 2.

[0053] Specifically, if the test result is yes, no processing is required; in the process of detecting whether the decision parameters in each candidate decision rule are monotonic attributes, each candidate decision rule can be detected separately. Specifically, whether the decision parameters in each candidate decision rule have parameter thresholds in opposite directions can be detected. If there are parameter thresholds in opposite directions, the decision parameter is determined to be a monotonic attribute. If not, the decision parameter is determined to be not a monotonic attribute. For example, in the candidate decision rule, the birth time is greater than 35 and the birth time is less than or equal to 40, the decision parameter "birth time" has a parameter threshold in the opposite direction and does not have a monotonic attribute, and the number of parameters of the decision parameter "birth time" in the same parameter category is greater than or equal to the quantity threshold 2. In the candidate decision rule, the birth time is greater than 35, the decision parameter "birth time" has a monotonic attribute, and the number of parameters of the decision parameter "birth time" in the same parameter category is less than 2.

[0054] For example, the decision parameters of the decision link to which 95% of the participation index is guaranteed are read from the decision tree, namely, birth time, salary, and birth time, and the parameter thresholds are greater than 35, less than 3000, and less than 40, respectively. The decision parameter "birth time" is merged with the parameter lower limit threshold "greater than 35", the decision parameter "salary" is merged with the parameter upper limit threshold "less than 3000", and the decision parameter "birth time" is merged with the parameter upper limit threshold "less than 40". The candidate decision rule obtained is "birth time greater than 35, salary less than 300, and birth time less than 40". The birth time in this candidate decision rule is not a monotonic attribute, and the number of birth times is greater than or equal to 2. Therefore, the candidate decision rule "birth time greater than 35, salary less than 300, and birth time less than 40" is eliminated from the candidate decision rules to obtain the decision rule.

[0055] For example Figure 3 As shown, the decision parameters and parameter thresholds contained in the decision link to which the guarantee participation indicator belongs are read from the decision tree, and the decision parameters and the upper and lower thresholds of the parameters are merged to obtain candidate decision rules, and the candidate decision rules are screened to obtain decision rules.

[0056] In addition, in the second optional implementation provided by this embodiment, in the process of generating a decision rule according to the decision parameter and the parameter threshold to obtain the decision rule, the following operations are performed: Merging the decision parameters and the upper or lower thresholds of the parameters to obtain candidate decision rules; If the proportion of service users corresponding to the candidate decision rule in the user base of each service user is greater than the proportion threshold, the candidate decision rule is used as the decision rule.

[0057] Among them, the service users corresponding to the candidate decision rule may be the service users corresponding to the leaf nodes of the decision link to which the candidate decision rule belongs, and these service users may be all service users corresponding to the candidate decision rule; the user ratio of service users in each service user refers to the proportion of service users in each service user, specifically refers to the proportion or ratio of the number of users of service users corresponding to the candidate decision rule in the number of users of each service user.

[0058] On this basis, in order to further improve the comprehensiveness and richness of the decision rules, in an optional implementation manner provided in this embodiment, after executing the candidate decision rules obtained by merging the decision parameters and the upper or lower threshold values ​​of the parameters, when the user proportion is less than or equal to the proportion threshold, the service users corresponding to the candidate decision rules can be eliminated from each service user to obtain updated service users, and a decision tree is constructed based on the user protection data of the updated service users to obtain the next decision tree, and the candidate decision rules and the decision rules corresponding to the first or last protection participation indicators extracted from the next decision tree are used as decision rules. This can be specifically achieved in the following manner: If the user ratio is less than or equal to the ratio threshold, the service user corresponding to the candidate decision rule is eliminated from each service user to obtain the updated service user; A decision tree is constructed based on the user assurance data of the updated service user to obtain the next decision tree, the next decision tree is parsed, and the parsing result and the candidate decision rules are used as decision rules.

[0059] Specifically, the process of constructing a decision tree based on the user protection data of the updated service user is similar to the process of constructing a decision tree based on the user protection data of each service user of the protection service as mentioned above, and will not be repeated here; in the process of parsing the next decision tree and using the parsing results and candidate decision rules as decision rules, the protection participation index with the first or last index size can be determined in the next decision tree, and the corresponding decision rule is generated based on the decision parameters and parameter thresholds contained in the decision link to which the protection participation index belongs in the decision tree. If the service users corresponding to the corresponding decision rule and the candidate decision rule have a user ratio greater than the proportion threshold among all service users, the corresponding decision rule and the candidate decision rule will be used as the decision rule. If it is less than or equal to the proportion threshold, the service users corresponding to the two can continue to be eliminated from all service users, and the next decision tree can be constructed until the service users corresponding to the decision rule have a user ratio greater than the proportion threshold among all service users.

[0060] For example Figure 4 As shown, a decision tree is constructed based on the user assurance data of each service user of the assurance service to obtain a decision tree, the decision type for the project decision of the assurance project is the underwriting type, the indicator determination condition corresponding to the underwriting type is to determine the assurance participation indicator with the largest indicator size, the decision parameters and parameter thresholds contained in the decision link to which the largest assurance participation indicator belongs are read from the decision tree, and rules are generated based on the decision parameters and parameter thresholds to obtain candidate decision rules, if the proportion of service users corresponding to the candidate decision rule in the user base of each service user is greater than the proportion threshold, the candidate decision rule is used as the decision rule, if the user proportion is less than or equal to the proportion threshold, the service user corresponding to the candidate decision rule is eliminated from each service user to obtain an updated service user, and a decision tree is constructed based on the user assurance data of the updated service user to obtain the next decision tree, and the decision parameters and parameter thresholds contained in the decision link to which the largest indicator size belongs are read from the next decision tree and rules are generated to obtain the next decision rule, until the proportion of service users corresponding to the candidate decision rule and the next decision rule in the user base of each service user is greater than the proportion threshold.

[0061] In specific implementation, the decision rule can be used to perform project decision processing of the protection project for the target user of the protection service. Optionally, the decision rule is used to perform project decision processing of the protection project for the target user of the protection service under the decision type. Based on the above-mentioned determination of the protection participation index greater than the preset index threshold in the decision tree, the first optional implementation mode provided by this embodiment is that in the process of performing project decision processing of the protection project for the target user of the protection service under the decision type, if the user attribute data and / or user behavior data of the target user meets the decision rules under the underwriting type, the claims settlement type or the insurance amount reduction type, the target user is insured for the protection project, the protection resources are issued or the insurance amount is reduced. Specifically, this can be achieved in the following manner: Detect whether the target user's user attribute data and / or user behavior data triggers decision rules for underwriting type, claim settlement type, or insured amount reduction type; If triggered, the target user's insurance processing for the protection project or the issuance of protection resources will be intercepted, or the insurance amount of the target user's protection project will be reduced.

[0062] Among them, the decision rules for any one or two of the underwriting type, claim settlement type and protection reduction type can be the same, and the decision rules for the three can also be the same or different.

[0063] Specifically, if the target user belongs to the underwriting type, the insurance processing of the target user for the protection item can be intercepted when the target user's user attribute data and / or user behavior data triggers the decision rule; if the target user belongs to the claims settlement type, the issuance of protection resources for the protection item to the target user can be intercepted when the target user's user attribute data and / or user behavior data triggers the decision rule; if the target user belongs to the insurance amount reduction type, the insurance amount of the protection item of the target user can be reduced when the target user's user attribute data and / or user behavior data triggers the decision rule; if the target user does not trigger the decision rule, no processing can be done or the target user can be insured for the protection item or protection resources can be issued.

[0064] Based on the above determination of the guarantee participation indicator being less than or equal to the preset indicator threshold in the decision tree, in a second optional implementation provided by this embodiment, during the process of making a project decision for a target user of the guarantee service under the decision type for the guarantee project, the following operations are performed: If the target user's user attribute data and / or user behavior data triggers the decision rule under the insurance coverage increase type, the insurance coverage of the target user's protection item will be increased.

[0065] Specifically, if the decision rules under the insurance amount increase type are not met, no action may be taken.

[0066] It should be noted that the above steps S204 to S206 can be replaced by reading the decision parameters and parameter thresholds contained in the decision link to which the guarantee participation indicator corresponds to the decision type of the project decision for the guarantee project from the decision tree, and generating rules based on the decision parameters and parameter thresholds to obtain decision rules; or can be replaced by parsing the decision tree based on the decision type of the project decision for the guarantee project to obtain decision rules; or can be replaced by reading the decision parameters and parameter thresholds contained in the decision link to which the guarantee participation indicator meets the decision type from the decision tree, and generating rules based on the decision parameters and parameter thresholds to obtain decision rules.

[0067] It should also be noted that, considering that the user protection data, user attribute data, user behavior data, protection participation data and other related data involved in this specification may belong to the user's privacy to a certain extent, therefore, if you want to collect user protection data and other related data, you can obtain the user's authorization before collecting the data, so that the operation of collecting data complies with relevant data management regulations. For example, data authorization can be performed during the access to the protection service, or during the first access to the protection service. In addition, other methods can also be used for data authorization; the specific method of data authorization can be to send a user data authorization reminder to the user, and the user can obtain data collection authorization after confirming the reminder through an instruction, or the method of data authorization can also be to obtain data collection authorization by signing a data authorization agreement; this embodiment will not be repeated here.

[0068] It should be added that, each optional implementation method and each feasible execution method in steps S202 to S206 provided in this embodiment can be executed independently as needed, or can be combined and referenced with each other. At the same time, each specific execution step in each optional implementation method or each feasible execution method can also be executed independently or combined as needed. The execution conditions of "if" or "under what circumstances" involved in each step or operation can be directly deleted, and the subsequent operations of the post-execution conditions are not specifically limited in this embodiment.

[0069] To sum up, the one or more protection project processing methods provided in this embodiment construct a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree. In one case, if the decision type is an underwriting type, a claims settlement type or a reduction in the insured amount type, a protection participation index greater than a preset index threshold is determined in the decision tree. In another case, if the decision type is an increase in the insured amount type, a protection participation index less than or equal to the preset index threshold is determined in the decision tree; the decision parameters and parameter thresholds contained in the decision link to which the protection participation index belongs are read from the decision tree, and decision rules are generated based on the decision parameters and parameter thresholds to obtain decision rules, so as to generate corresponding decision rules for different decision types, thereby improving the effectiveness and pertinence of the decision rules.

[0070] The following uses the application of a protection item processing method provided by this embodiment in the first insurance service scenario as an example to further illustrate the protection item processing method provided by this embodiment. Figure 5 The protection project processing method applied to the first insurance service scenario specifically includes the following steps.

[0071] Step S502 : sampling users from the service users of the insurance service according to the number of decision tree constructions to obtain a sampled user set.

[0072] Step S504 : For each sampled user set, data sampling is performed from the data categories corresponding to the user insurance data to obtain each sampling category.

[0073] Step S506 , constructing decision trees based on the user insurance data of the sampled users in each sampling category included in each sampled user set to obtain each decision tree.

[0074] Optionally, the decision tree construction includes performing node segmentation according to the insurance participation data in the user insurance data and generating a decision tree based on the segmentation results.

[0075] Step S508: Determine in each decision tree the insurance claim rate that is greater than a preset threshold.

[0076] It is also possible to determine an insurance claim rate that is less than or equal to a preset threshold in each decision tree, or to determine an insurance claim rate that is greater than a preset threshold among the insurance claim rates corresponding to the leaf nodes of each decision tree.

[0077] Step S510 , reading the decision parameters and parameter thresholds included in the decision link to which the insurance claim rate belongs from each decision tree, and merging the decision parameters and parameter thresholds to obtain candidate decision rules.

[0078] Step S512 : determining, from the candidate decision rules, those candidate decision rules whose decision parameters do not have the monotonic property and eliminating them to obtain a decision rule.

[0079] Optionally, the decision rule is used to perform project decision processing on insurance projects for target users of insurance services.

[0080] It should be noted that any one of steps S502 to S512 or any combination of multiple steps can be replaced by the corresponding technical means provided by the above steps S202 to S206 according to the needs of implementation and deployment, and any one of steps S502 to S512 or any combination of multiple steps can be combined into a new implementation method according to the needs of implementation and deployment; and any one of steps S502 to S512 or any combination of multiple steps can also form a new implementation method with one or more steps provided by the above steps S202 to S206 according to the actual deployment needs, or form a new implementation method with one or more optional implementation methods provided by steps S202 to S206, which will not be repeated here.

[0081] The following uses the application of a protection item processing method provided by this embodiment in the second insurance service scenario as an example to further illustrate the protection item processing method provided by this embodiment. Figure 6 The protection project processing method applied to the second insurance service scenario specifically includes the following steps.

[0082] Step S602: construct a decision tree based on the user insurance data of each service user of the insurance service to obtain a decision tree.

[0083] Optionally, the decision tree construction includes performing node segmentation according to the insurance participation data in the user insurance data and generating a decision tree based on the segmentation results.

[0084] Step S604: determine the insurance claim rate that ranks first in the decision tree, and read the decision parameters and parameter thresholds included in the decision link to which the insurance claim rate belongs from the decision tree.

[0085] The insurance claim rate with the lowest claim rate may also be determined in the decision tree, and the decision parameters and parameter thresholds included in the decision link to which the insurance claim rate belongs may be read from the decision tree.

[0086] Step S606: merging the decision parameters and the parameter thresholds to obtain candidate decision rules.

[0087] Step S608: If the proportion of service users corresponding to the candidate decision rule among all service users is less than or equal to the proportion threshold, the service users corresponding to the candidate decision rule are removed from all service users to obtain updated service users.

[0088] Step S610: construct a decision tree based on the user insurance data of the updated service user to obtain the next decision tree.

[0089] Step S612: extracting the decision parameters and parameter thresholds included in the decision link to which the insurance claim ratio with the highest claim ratio belongs from the next decision tree.

[0090] The decision parameters and parameter thresholds included in the decision link to which the insurance claim ratio with the lowest claim ratio belongs can also be extracted from the next decision tree.

[0091] Step S614: construct the next decision rule according to the decision parameter and the parameter threshold. If the user proportions corresponding to the next decision rule and the candidate decision rule are greater than the proportion threshold, the candidate decision rule and the next decision rule are used as the decision rule.

[0092] Optionally, the decision rule is used to perform project decision processing on insurance projects for target users of insurance services.

[0093] Steps S608 to S614 may be replaced by: if the proportion of service users corresponding to the candidate decision rule among all service users is greater than a proportion threshold, the candidate decision rule may be used as the decision rule.

[0094] It should be noted that any one of steps S602 to S614 or any combination of multiple steps can be replaced by the corresponding technical means provided by the above steps S202 to S206 according to the needs of implementation and deployment, and any one of steps S602 to S614 or any combination of multiple steps can be combined into a new implementation method according to the needs of implementation and deployment; and any one of steps S602 to S614 or any combination of multiple steps can also form a new implementation method with one or more steps provided by the above steps S202 to S206 according to the actual deployment needs, or form a new implementation method with one or more optional implementation methods provided by steps S202 to S206, which will not be repeated here.

[0095] An embodiment of a security project processing device provided in this specification is as follows: In the above embodiment, a security item processing method is provided, and correspondingly, a security item processing device is also provided, which will be described below with reference to the accompanying drawings.

[0096] Reference Figure 7 , which shows a schematic diagram of an embodiment of a security project processing device provided by this embodiment.

[0097] Since the device embodiment corresponds to the method embodiment, the description is relatively simple. For the relevant parts, please refer to the corresponding description of the method embodiment provided above. The device embodiment described below is only illustrative.

[0098] This embodiment provides a security item processing device, including: A construction module 702 is configured to construct a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree; the decision tree construction includes segmenting nodes based on the protection participation data in the user protection data and generating a decision tree based on the segmentation results; A determination module 704 is configured to determine, in the decision tree, a guarantee participation indicator corresponding to a decision type for making a project decision for a guarantee project; A generating module 706 is configured to read the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs from the decision tree, and generate a decision rule based on the decision parameters and the parameter thresholds to obtain a decision rule; The decision rule is used to perform project decision processing of the guarantee project for the target user of the guarantee service under the decision type.

[0099] An embodiment of a security project processing device provided in this specification is as follows: Corresponding to the above-described method for processing security items, based on the same technical concept, one or more embodiments of this specification further provide a security item processing device, which is used to execute the above-described method for processing security items. Figure 8 A schematic diagram of the structure of a security project processing device provided in one or more embodiments of this specification.

[0100] This embodiment provides a security project processing device, including: like Figure 8 As shown, the security project processing device can vary significantly due to different configurations and performance. It may include one or more processors 801 and memory 802. Memory 802 may store one or more applications or data. Memory 802 may be either ephemeral or persistent. The applications stored in memory 802 may include one or more modules (not shown), each of which may comprise a series of computer-executable instructions within the security project processing device. Furthermore, processor 801 may be configured to communicate with memory 802 to execute the series of computer-executable instructions within memory 802 on the security project processing device. The security project processing device may also include one or more power supplies 803, one or more wired or wireless network interfaces 804, one or more input / output interfaces 805, one or more keyboards 806, and the like.

[0101] In a specific embodiment, a security project processing device includes a memory and one or more programs, wherein the one or more programs are stored in the memory, and the one or more programs may include one or more modules, and each module may include a series of computer-executable instructions for the security project processing device, and the one or more programs are configured to be executed by one or more processors, including computer-executable instructions for performing the following: Constructing a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree; said decision tree construction includes segmenting nodes based on the protection participation data in the user protection data and generating a decision tree based on the segmentation results; Determining, in the decision tree, a guarantee participation indicator corresponding to a decision type for a project decision to be made for the guarantee project; Reading the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs from the decision tree, and generating rules according to the decision parameters and the parameter thresholds to obtain decision rules; The decision rule is used to perform project decision processing of the guarantee project for the target user of the guarantee service under the decision type.

[0102] An embodiment of a computer-readable storage medium provided in this specification is as follows: Corresponding to the above-described method for processing security projects, based on the same technical concept, one or more embodiments of this specification further provide a computer-readable storage medium.

[0103] The computer-readable storage medium provided in this embodiment is used to store computer-executable instructions, which, when executed, implement the following steps: Constructing a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree; said decision tree construction includes segmenting nodes based on the protection participation data in the user protection data and generating a decision tree based on the segmentation results; Determining, in the decision tree, a guarantee participation indicator corresponding to a decision type for a project decision to be made for the guarantee project; Reading the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs from the decision tree, and generating rules according to the decision parameters and the parameter thresholds to obtain decision rules; The decision rule is used to perform project decision processing of the guarantee project for the target user of the guarantee service under the decision type.

[0104] It should be noted that the embodiment of a computer-readable storage medium in this specification and the embodiment of a security project processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned corresponding method, and the repeated parts will not be repeated.

[0105] An embodiment of a computer program product provided in this specification is as follows: Corresponding to the above-described method for processing security projects, based on the same technical concept, one or more embodiments of this specification also provide a computer program product.

[0106] A computer program product comprising a computer program / instructions, which, when executed by a processor, implements the following steps: Constructing a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree; said decision tree construction includes segmenting nodes based on the protection participation data in the user protection data and generating a decision tree based on the segmentation results; Determining, in the decision tree, a guarantee participation indicator corresponding to a decision type for a project decision to be made for the guarantee project; Reading the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs from the decision tree, and generating rules according to the decision parameters and the parameter thresholds to obtain decision rules; The decision rule is used to perform project decision processing of the guarantee project for the target user of the guarantee service under the decision type.

[0107] It should be noted that the embodiment of a computer program product in this specification and the embodiment of a security project processing method in this specification are based on the same inventive concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the aforementioned corresponding method, and the repeated parts will not be repeated.

[0108] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on the differences from other embodiments. For example, the device embodiment, equipment embodiment and computer-readable storage medium embodiment are similar to the method embodiment, so the description is relatively simple. For relevant content in the device embodiment, equipment embodiment and computer-readable storage medium embodiment, please refer to the partial description of the method embodiment.

[0109] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] In the 1930s, technological improvements could be clearly distinguished as either hardware improvements (for example, improvements to circuit structures like diodes, transistors, and switches) or software improvements (improvements to process flows). However, with the advancement of technology, many process flow improvements today can be considered direct improvements to hardware circuit structures. Designers almost always create the corresponding hardware circuit structure by programming the improved process flow into the hardware circuit. Therefore, it cannot be said that a process flow improvement cannot be implemented using physical hardware modules. For example, a programmable logic device (PLD), such as a field programmable gate array (FPGA), is an integrated circuit whose logical function is determined by user programming. Designers can "integrate" a digital system on a PLD by programming it themselves, without having to hire a chip manufacturer to design and manufacture a dedicated integrated circuit chip. Moreover, nowadays, instead of manually fabricating integrated circuit chips, this programming is mostly performed using software called a "logic compiler." This is similar to the software compilers used during program development. Before compilation, the original code must be written in a specific programming language, called a Hardware Description Language (HDL). There are many types of HDL, including ABEL (Advanced Boolean Expression Language), AHDL (Altera Hardware Description Language), Confluence, CUPL (Cornell University Programming Language), HDCal, JHDL (Java Hardware Description Language), Lava, Lola, MyHDL, PALASM, and RHDL (Ruby Hardware Description Language). Currently, the most commonly used are VHDL (Very-High-Speed ​​Integrated Circuit Hardware Description Language) and Verilog. Those skilled in the art will also understand that simply by programming a method flow in one of these hardware description languages ​​and then programming it into an integrated circuit, a hardware circuit that implements the logic method flow can be easily obtained.

[0111] The controller can be implemented in any suitable manner. For example, the controller can take the form of a microprocessor or processor and a computer-readable medium storing computer-readable program code (e.g., software or firmware) executable by the (micro)processor, logic gates, switches, an application-specific integrated circuit (ASIC), a programmable logic controller, and an embedded microcontroller. Examples of controllers include, but are not limited to, the following microcontrollers: ARC 625D, Atmel AT91SAM, Microchip PIC18F26K20, and Silicone Labs C8051F320. The memory controller can also be implemented as part of the memory control logic. Those skilled in the art will also appreciate that, in addition to implementing the controller purely in computer-readable program code, the controller can also be implemented in the form of logic gates, switches, an application-specific integrated circuit, a programmable logic controller, an embedded microcontroller, etc. by logically programming the method steps. Therefore, such a controller can be considered a hardware component, and the means for implementing the various functions included therein can also be considered as structures within the hardware component. Alternatively, the means for implementing the various functions can be considered both a software module implementing the method and a structure within the hardware component.

[0112] The systems, devices, modules, or units described in the above embodiments may be implemented by computer chips or entities, or by products having certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.

[0113] For the convenience of description, the above devices are described as being divided into various units according to their functions. Of course, when implementing the embodiments of this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0114] Those skilled in the art will appreciate that one or more embodiments of this specification may be provided as a method, system, or computer program product. Thus, one or more embodiments of this specification may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, this specification may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0115] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable test processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable test processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0116] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable test processing equipment to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device that implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0117] These computer program instructions may also be loaded onto a computer or other programmable test processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable device provide for implementing the process described in the flow. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0118] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0119] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0120] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can be implemented using any method or technology for information storage. Information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase-change RAM (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory computer-readable media such as modulated data signals and carrier waves.

[0121] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a list of features includes not only those features but also other features not explicitly listed, or features inherent to such process, method, commodity, or apparatus. In the absence of further limitations, features defined by the phrase "comprising a..." do not preclude the presence of other identical features in the process, method, commodity, or apparatus that includes the features.

[0122] One or more embodiments of this specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, and the like that perform specific tasks or implement specific abstract data types. One or more embodiments of this specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communications network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.

[0123] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0124] The foregoing description is merely an example of the present invention and is not intended to limit the present invention. Persons skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be included within the scope of the claims herein.

Claims

1. A method for processing a security project, comprising: A decision tree is constructed based on user assurance data of each service user of the assurance service to obtain a decision tree; The decision tree construction includes performing node segmentation according to the protection participation data in the user protection data and generating a decision tree based on the segmentation result; Determining, in the decision tree, a guarantee participation indicator corresponding to a decision type for a project decision to be made for the guarantee project; Reading the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs from the decision tree, and generating rules according to the decision parameters and the parameter thresholds to obtain decision rules; The decision rule is used to perform project decision processing of the guarantee project for the target user of the guarantee service under the decision type.

2. The method for processing security items according to claim 1, wherein the node segmentation based on the security participation data in the user security data comprises: Determining a target splitting condition in the splitting condition according to the guarantee participation data of service users corresponding to each child node of the current node under the splitting condition; Performing node segmentation on the current node based on the target segmentation condition; The security participation data of the service user includes the security issuance resource amount and the security expenditure resource amount.

3. The security item processing method according to claim 2, wherein the segmentation condition is generated based on user attribute data and / or user behavior data included in the user security data of the service user corresponding to the current node.

4. The guarantee project processing method according to claim 2, wherein determining the target splitting condition in the splitting condition based on the guarantee participation data of the service users corresponding to each sub-node of the current node under the splitting condition comprises: Calculate the guaranteed payment rate corresponding to each subnode according to the guaranteed payment resource amount and the guaranteed expenditure resource amount; The guaranteed payment rate difference corresponding to the segmentation condition is calculated based on the guaranteed payment rate, and the target segmentation condition is determined among the segmentation conditions according to the guaranteed payment rate difference.

5. The method for processing security projects according to claim 1, wherein generating a decision rule based on the decision parameter and the parameter threshold comprises: Combining the decision parameter and the parameter upper threshold or the parameter lower threshold to obtain a candidate decision rule; Detecting whether a decision parameter in each candidate decision rule is a monotonic attribute, or detecting whether the number of decision parameters of the same parameter category in each candidate decision rule is less than a quantity threshold; If not, the detected candidate decision rule is eliminated from the candidate decision rules to obtain the decision rule.

6. The method for processing security projects according to claim 1, wherein generating a decision rule based on the decision parameter and the parameter threshold comprises: Combining the decision parameter and the parameter upper threshold or the parameter lower threshold to obtain a candidate decision rule; If the proportion of service users corresponding to the candidate decision rule among the service users is greater than a proportion threshold, the candidate decision rule is used as the decision rule.

7. The method for processing security items according to claim 6, further comprising: after the step of combining the decision parameter and the upper or lower threshold of the parameter to obtain a candidate decision rule, performing the following steps: If the user proportion is less than or equal to the proportion threshold, the service user corresponding to the candidate decision rule is eliminated from the service users to obtain an updated service user; A decision tree is constructed based on the user security data of the update service user to obtain a next decision tree, the next decision tree is parsed, and the parsing result and the candidate decision rule are used as the decision rule.

8. The method for processing a security project according to claim 1, wherein determining the security participation index corresponding to the decision type of the project decision for the security project in the decision tree comprises: If the decision type is an underwriting type, a claims settlement type, or a sum assured reduction type, a protection participation index greater than a preset index threshold is determined in the decision tree.

9. The method for processing a guarantee project according to claim 8, wherein the step of performing a decision process on a target user of the guarantee service under the decision type for the guarantee project comprises: Detecting whether the user attribute data and / or user behavior data of the target user triggers a decision rule under the underwriting type, the claim settlement type, or the insured amount reduction type; If triggered, the insurance application process or the issuance of insurance resources for the target user's insurance item will be intercepted, or the insurance amount of the target user's insurance item will be reduced.

10. The method for processing a security project according to claim 1, wherein determining the security participation index corresponding to the decision type of the project decision for the security project in the decision tree comprises: If the decision type is an increase in the insured amount, determining a protection participation index that is less than or equal to a preset index threshold in the decision tree; Accordingly, the project decision processing of the guarantee project for the target user of the guarantee service under the decision type includes: If the user attribute data and / or user behavior data of the target user triggers the decision rule under the insurance amount increase type, the insurance amount of the protection item of the target user is increased.

11. The guarantee project processing method according to claim 1, wherein the guarantee service includes a guarantee subroutine within an application program or a guarantee channel under any guarantee category within the guarantee subroutine.

12. The method for processing security projects according to claim 2, wherein generating a decision tree based on the segmentation results comprises: Detecting whether the number of service users corresponding to the child nodes obtained by node segmentation based on the current decision tree is less than a number threshold, or updating the number of segmentations based on the node segmentation of the current decision tree and detecting whether the number of segmentations is greater than a number threshold; If not, the sub-node is segmented based on the protection participation data in the user protection data of the service user corresponding to the sub-node; if so, the current decision tree is used as the decision tree.

13. The method for processing insurance items according to claim 4, wherein determining the target segmentation condition from the segmentation conditions based on the difference in insurance payment rates comprises: Sorting the various segmentation conditions according to the difference in guarantee payment rates corresponding to the various segmentation conditions; In the sorting results, a segmentation condition whose sorting position is before the preset position is determined as the target segmentation condition.

14. The method for processing security items according to claim 1, wherein the step of constructing a decision tree based on the security data of each service user of the security service to obtain the decision tree comprises: Sampling users from the service users according to the number of decision tree constructions to obtain a sampled user set; For each sampling user set, data sampling is performed from the data category corresponding to the user assurance data to obtain each sampling category, and each decision tree is constructed based on the user assurance data of the sampling users included in each sampling user set under each sampling category.

15. A security project processing device, comprising: A construction module is configured to construct a decision tree according to user assurance data of each service user of the assurance service to obtain a decision tree; The decision tree construction includes performing node segmentation according to the protection participation data in the user protection data and generating a decision tree based on the segmentation result; A determination module configured to determine, in the decision tree, a guarantee participation indicator corresponding to a decision type for making a project decision for a guarantee project; a generating module configured to read the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs from the decision tree, and generate a decision rule based on the decision parameters and the parameter thresholds to obtain a decision rule; The decision rule is used to perform project decision processing of the guarantee project for the target user of the guarantee service under the decision type.

16. A security project processing device comprising: processor; and a memory configured to store computer-executable instructions that, when executed, cause the processor to: Constructing a decision tree based on the user protection data of each service user of the protection service to obtain a decision tree; said decision tree construction includes segmenting nodes based on the protection participation data in the user protection data and generating a decision tree based on the segmentation results; Determining, in the decision tree, a guarantee participation indicator corresponding to a decision type for a project decision to be made for the guarantee project; Reading the decision parameters and parameter thresholds included in the decision link to which the guarantee participation indicator belongs from the decision tree, and generating rules according to the decision parameters and the parameter thresholds to obtain decision rules; The decision rule is used to perform project decision processing of the guarantee project for the target user of the guarantee service under the decision type.

17. A computer-readable storage medium for storing computer-executable instructions, wherein the computer-executable instructions implement the steps of the method of claim 1 when executed.

Images