CN112307087B

CN112307087B - Service data routing relation matching method and device based on decision tree

Info

Publication number: CN112307087B
Application number: CN202011204710.8A
Authority: CN
Inventors: 赖赢平
Original assignee: Ping An Technology Shenzhen Co Ltd
Current assignee: Ping An Technology Shenzhen Co Ltd
Priority date: 2020-11-02
Filing date: 2020-11-02
Publication date: 2024-03-05
Anticipated expiration: 2040-11-02
Also published as: CN112307087A

Abstract

The application relates to artificial intelligence and provides a business data routing relation matching method, device and computer equipment based on a decision tree. The method comprises the following steps: extracting user basic information corresponding to the user identifier to be ensured and the user identifier to be ensured from service data, generating a basic data set according to the user basic information, and establishing a target decision tree according to the basic data set and a preset casting relation. Traversing the decision tree according to the basic information of the target user, determining the matched casting and receiving relation, and analyzing and processing the determined casting and receiving relation. When the routing relation is determined to be the bidirectional routing relation, acquiring a target service application scene to which the user to be identified belongs, and determining a target routing relation corresponding to the target service application scene from the bidirectional routing relation. The invention also relates to a block chain technology, and service data is stored in the block chain. By adopting the method, the rapid identification of different throw-in relations can be realized when the project is changed, and the service project matching efficiency of different users is improved.

Description

Service data routing relation matching method and device based on decision tree

Technical Field

The application relates to the technical field of artificial intelligence, in particular to a business data input-output relation matching method and device based on a decision tree.

Background

With the development of artificial intelligence technology and the gradual application of internet finance in people's work and life, more users select online application. Because the insuring project involves personal privacy data, financial data and the like of the user, different insuring personnel and different relatives need to be checked in order to prevent the information leakage or malicious cheating of the user.

Traditionally, verification of insuring personnel and different throw-in relation personnel is mostly carried out by means of the throw-in relation selected by users independently, but the risk of error selection by users is still existed, and when the users select errors, the throw-in relation of the users in the business project cannot be accurately identified.

In order to reduce the recognition error caused by the error of the user's autonomous selection of the quilt relationship, a mechanism is provided for determining whether the association relationship exists by comparing the quilt relationship selected by the user with the quilt relationship stored in advance by the system after the user selects the quilt relationship. However, the judging mechanism can only realize the judgment of the association relation aiming at the user with the pre-stored quilt relation so as to prompt timely when the user selects the quilt relation to be wrong. When the business data corresponding to the policy is changed, the corresponding routing relation cannot be pre-stored, and the change condition of the routing relation of the user in the changed policy cannot be accurately determined, so that the problem of low matching efficiency of business items for different users after business change occurs is caused.

Disclosure of Invention

Based on the above, it is necessary to provide a method and a device for matching service data routing relation based on decision tree, which can improve the matching efficiency of service items for different users.

A decision tree based business data routing relationship matching method, the method comprising:

extracting corresponding insuring user identification and guaranteed user identification from service data, and extracting corresponding user basic information according to the insuring user identification and the guaranteed user identification;

generating a basic data set according to the extracted user basic information;

establishing a target decision tree according to the basic data set and a preset quilt casting relationship; the number of layers of the target decision tree is larger than the number of categories of the user basic information;

acquiring target user basic information of a user to be identified, traversing the decision tree according to the target user basic information, and determining a casting relationship matched with the target user basic information;

analyzing and processing the determined casting relationship, and determining the casting relationship as a two-way casting relationship when the user to be identified is determined to be both the insurance user and the ensured user according to the casting relationship;

And acquiring a target service application scene to which the user to be identified belongs, and determining a corresponding target routing relation from the bidirectional routing relation according to the target service application scene.

In one embodiment, the obtaining the target user basic information of the user to be identified, traversing the decision tree according to the target user basic information, and determining the routing relation matched with the target user basic information includes:

acquiring target user basic information of a user to be identified, and judging the integrity of the target user basic information; the target user basic information is stored in a blockchain;

when the completeness of the basic information of the target user is determined to meet the preset requirement, traversing each layer of the target decision tree in sequence according to the basic information of the target user; the bottom layer of the target decision tree is a quilt throwing relation;

and when each layer of the target decision tree is successfully traversed, matching the throw relation corresponding to the target user basic information from the bottom layer of the target decision tree.

In one embodiment, the obtaining the target service application scenario to which the user to be identified belongs, and determining the corresponding target routing relationship from the bidirectional routing relationship according to the target service application scenario, includes:

Acquiring a target service application scene to which a user to be identified belongs;

acquiring scene attribute information corresponding to the target service application scene; the scene attribute information comprises an application category, an application product and a product attribute;

and determining one of the two-way casting relationship according to the scene attribute information, and determining the two-way casting relationship as a target casting relationship corresponding to the user to be identified.

In one embodiment, before the generating the basic data set according to the extracted user basic information, the method further comprises:

performing data preprocessing on the acquired user basic information to generate available data;

acquiring the data types of the available data and the data quantity corresponding to different data types;

determining a matched data processing mode according to different data types and corresponding data quantity;

respectively executing data processing on a plurality of available data according to different data processing modes to generate initial data corresponding to the user basic information; the initial data is used for generating a basic data set corresponding to the user basic information.

In one embodiment, the generating a basic data set according to the extracted user basic information includes:

Carrying out structuring treatment on the initial data to generate corresponding structuring data;

determining structured data of different categories according to the different categories of the initial data;

obtaining information elements corresponding to different categories of the structured data;

acquiring an abstract user information object which is created in advance;

according to the information elements, matching object information corresponding to the abstract user information object from the user basic information;

and establishing an instance set according to each piece of object information to generate a basic data set.

In one embodiment, the data types include digital, byte, and text types; the data processing mode comprises judgment processing, assignment processing and statement processing; and respectively executing data processing on a plurality of available data according to different data processing modes to generate initial data corresponding to the user basic information, wherein the initial data comprises:

judging available data of the numbers, and comparing the preset value range with the value of the available data of the numbers;

extracting available digital data which accords with the preset value range, and generating initial digital data;

Or performing assignment processing on the byte-shaped available data, and comparing the value of the byte-shaped available data with a preset value;

when the value of the byte-type available data is determined to be not in accordance with the preset value, assigning the preset value to the corresponding byte-type available data, and generating byte-type initial data according to the assigned byte-type available data;

or declaration processing is carried out on the text type available data, and the composition components of the text type available data are compared with preset composition components;

when the composition of the text-type available data is not consistent with the preset composition, declaring the text-type available data as the preset composition, and generating text-type initial data.

In one embodiment, after determining the corresponding target routing relationship from the bidirectional routing relationship according to the target service application scenario, the method further includes:

carrying out service identification according to the determined target routing relation, and determining a service item to which the target routing relation belongs;

setting corresponding policy operation authorities for users corresponding to the target routing relation aiming at different service projects; the project operation rights include project viewing, project modification, and project downloading.

A decision tree based business data routing relationship matching device, the device comprising:

the user basic information extraction module is used for extracting corresponding insurance user identification and guaranteed user identification from service data, and extracting corresponding user basic information according to the insurance user identification and the guaranteed user identification;

the basic data set generation module is used for generating a basic data set according to the extracted user basic information;

the target decision tree building module is used for building a target decision tree according to the basic data set and a preset quilt throwing relation; the number of layers of the target decision tree is larger than the classification number of the user basic information;

the traversing module is used for acquiring target user basic information of a user to be identified, traversing the decision tree according to the target user basic information and determining a casting relationship matched with the target user basic information;

the two-way quilt relation determining module is used for analyzing and processing the determined quilt relation, and determining the quilt relation as a two-way quilt relation when the user to be identified is determined to be an insurance user and a guaranteed user according to the quilt relation;

The target routing relation determining module is used for acquiring a target service application scene to which the user to be identified belongs and determining a corresponding target routing relation from the bidirectional routing relation according to the target service application scene.

A computer device comprising a memory storing a computer program and a processor which when executing the computer program performs the steps of:

generating a basic data set according to the extracted user basic information;

A computer storage medium having stored thereon a computer program which when executed by a processor performs the steps of:

generating a basic data set according to the extracted user basic information;

In the method and the device for matching the business data routing relation based on the decision tree, the corresponding user identifier is extracted from the business data, the corresponding user basic information is extracted according to the user identifier, and then the basic data set is generated according to the extracted user basic information. And establishing a target decision tree according to the basic data set and the preset quilt throwing relationship, traversing the decision tree according to the acquired target user basic information of the user to be identified, and determining the quilt throwing relationship matched with the target user basic information. Through analysis processing of the determined casting and receiving relationship, when the user to be identified is determined to be the insurance user and the guaranteed user at the same time according to the casting and receiving relationship, the casting and receiving relationship is determined to be a two-way casting and receiving relationship, and further according to the target service application scene to which the user to be identified belongs, the corresponding target casting and receiving relationship is determined from the two-way casting and receiving relationship. Because the user does not need to manually and independently select the quilt throwing relationship, the risk of wrong selection of the quilt throwing relationship by the user can be reduced, and when the business data is changed, the quick identification of the quilt throwing relationship of different users can be realized, so that the matching efficiency of business items of different users can be improved.

Drawings

FIG. 1 is an application scenario diagram of a decision tree-based business data projection relationship matching method in one embodiment;

FIG. 2 is a flow chart of a decision tree-based business data routing relationship matching method in one embodiment;

FIG. 3 is a schematic diagram of a target decision tree of a decision tree-based business data routing relationship matching method in one embodiment;

FIG. 4 is a flow chart of a decision tree-based business data routing relationship matching method in another embodiment;

FIG. 5 is a block diagram of a decision tree based business data routing relationship matching device in one embodiment;

FIG. 6 is a block diagram of a decision tree based business data routing relationship matching device in another embodiment;

fig. 7 is an internal structural diagram of a computer device in one embodiment.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the present application.

The business data routing relation matching method based on the decision tree can be applied to an application environment shown in fig. 1. Wherein the terminal 102 communicates with the server 104 via a network. When the relationship between the service data of the user service item needs to be identified, the server 104 extracts the corresponding user identifier from the service data, and extracts the corresponding user basic information according to the user identifier. The user basic information may be obtained from a local storage of the terminal 102 or from a cloud storage of the server 104. And generating a basic data set according to the extracted user basic information, and establishing a target decision tree according to the basic data set and a preset routing relation. The method comprises the steps of obtaining target user basic information of a user to be identified, traversing a decision tree according to the target user basic information, determining a casting relationship matched with the target user basic information, and analyzing and processing the determined casting relationship. When the user to be identified is determined to be the insurance user and the guaranteed user at the same time according to the casting relationship, the casting relationship is determined to be the bidirectional casting relationship, the target service application scene of the user to be identified is obtained, and the corresponding target casting relationship is determined from the bidirectional casting relationship according to the target service application scene. The terminal 102 may be, but not limited to, various personal computers, notebook computers, smartphones, tablet computers, and portable wearable devices, and the server 104 may be implemented by a stand-alone server or a server cluster composed of a plurality of servers.

In one embodiment, as shown in fig. 2, a decision tree-based service data routing relationship matching method is provided, and the method is applied to the server in fig. 1 for illustration, and includes the following steps:

step S202, extracting corresponding insuring user identification and guaranteed user identification from service data, and extracting corresponding user basic information according to the insuring user identification and the guaranteed user identification.

Specifically, when the service data of the user service project is detected to be subjected to the casting relation recognition, the casting user identification and the guaranteed user identification corresponding to each service data are obtained, and user basic information corresponding to the casting user identification and user basic information corresponding to the guaranteed user identification are extracted from the local storage or the cloud storage. The user basic information comprises the name, sex, birthday, certificate type and certificate number of the user. Step S204, a basic data set is generated according to the extracted user basic information.

Specifically, by carrying out structuring processing on initial data corresponding to user basic information, corresponding structured data is generated, different categories corresponding to the initial data are obtained, and structured data corresponding to the different categories are determined. Information elements corresponding to different types of structured data are obtained, an abstract user information object which is created in advance is obtained, and then object information corresponding to the abstract user information object is matched from user basic information according to the information elements, so that an instance set is built according to each object information, and a basic data set is generated.

Wherein the information elements also include name, gender, birth date, certificate type, and certificate number. When the user's throw-quilt relation needs to be identified, all the user's insurance users and the user who is being thrown under the insurance policy that the user belongs to need to be identified first, and an instance set is established by the abstract user information objects corresponding to all the user's insurance users and the user who is being thrown.

Further, the process of establishing the instance set represents a data modeling process, and because the data information can be changed, the data modeling needs to be performed again for each identification, and after the modeling, the data is still, and when the modeling is performed, the static characteristics are considered, namely the static characteristics such as name, gender, birthday, certificate type, certificate number and the like are considered. The initial data can be structured to determine one piece of data in the basic data set corresponding to each piece of user basic information, or the data can be understood as the object information corresponding to the abstract user information object can be matched from the user basic information according to the information elements, so that the basic data set can be integrated.

Step S206, a target decision tree is established according to the basic data set and the preset routing relation.

Specifically, a target decision tree is established according to a basic data set and a preset routing relationship, wherein the classification of user base information included in the basic data set includes five categories including name, gender, birthday, certificate type and certificate number, the number of layers of the target decision tree is larger than the category number of the basic information of the user, and the target decision tree further includes a root node of a top layer and a routing relationship of the bottom layer.

As shown in fig. 3, a schematic structural diagram of a target decision tree with matched business data routing relationship is provided, and referring to fig. 3, it can be seen that a top layer of the target decision tree is a root node, a first layer is a name in user basic information, a second layer is a gender in the user basic information, a third layer is a birthday in the user basic information, a fourth layer is a certificate type in the user basic information, a fifth layer is a certificate number corresponding to the certificate type, and a bottom layer is a routing relationship. In other embodiments, the order of the layers may be changed during the process of creating the target decision tree, which is not limited to the order shown in fig. 3.

Step S208, obtaining target user basic information of the user to be identified, traversing the decision tree according to the target user basic information, and determining the casting relationship matched with the target user basic information.

Specifically, the target user basic information of the user to be identified is obtained, and the integrity of the target user basic information is judged, namely whether the target user basic information completely comprises a name, a gender, a birthday, a certificate type and a certificate number is judged. When the completeness of the basic information of the target user meets the preset requirement, traversing each layer of the target decision tree in sequence according to the basic information of the target user; and when each layer of the target decision tree is successfully traversed, matching the routing relation corresponding to the basic information of the target user from the bottom layer of the target decision tree. The user to be identified can be a business project change application user, and when the application user changes, the application relationship needs to be determined again.

Further, since the information input by the user in real time cannot determine whether the information is correct or not, the data recorded by the system is required to be used as a correct template, and then the user basic information to be identified is matched, so that the accuracy and the integrity of the user basic information are maintained. The method for identifying the basic information of the target user is to traverse the target decision tree according to the structure of the target decision tree shown in fig. 3, namely according to the sequence of the name, the gender, the birth date, the certificate type and the certificate number, and all the basic information of the five users need to be successfully matched.

In one embodiment, the traversal is first performed at a first level of the target decision tree by name, and when successfully matched to a name in the target user base information, the traversal is performed at a second level of the target decision tree according to gender. And traversing the third layer of the target decision tree according to the birthday when the matching is successful in the second layer. And when the matching is successful in the third layer, traversing in the fourth layer of the target decision tree according to the certificate type. And when the matching is successful in the fourth layer, matching is performed in the fifth layer of the target decision tree according to the document number, and when the matching is also successful in the fifth layer, namely, all the five pieces of user basic information are successfully matched, determining a casting relationship matched with the target user basic information from the sixth layer of the target decision tree.

And step S210, analyzing and processing the determined casting and receiving relationship, and determining the casting and receiving relationship as a two-way casting and receiving relationship when the user to be identified is determined to be the insurance user and the ensured user at the same time according to the casting and receiving relationship.

Specifically, by analyzing and processing the determined quilt relation, whether special conditions exist or not is determined, namely whether the user to be identified is both the insurance user and the guaranteed user or not can be determined according to the quilt relation. When traversing the decision tree, and obtaining that the user to be identified is the user to be identified, namely the user to be identified is the user to be protected, in the sixth layer, determining the user to be identified as the two-way user to be identified, and further selecting one of the user to be identified as one of the user to be identified and the user to be protected according to the target service application scene to which the user to be identified belongs.

In one embodiment, two special cases are included, firstly, whether the identified user is the guaranteeing user or the guaranteed user at the same time, and the identification result in the current case includes two user attributes, namely, the guaranteeing user and the guaranteed user are returned as the identification results, and the relationship operation of the guaranteeing user or the guaranteed user is determined according to the actual application scene. Secondly, if the five items of information of the users to be identified are the same, adding the apoptosis date as a judging condition, judging whether the users are the same user according to the apoptosis date, and if the users are the same user, reserving any user basic information.

Step S212, obtaining a target service application scene to which the user to be identified belongs, and determining a corresponding target routing relation from the two-way routing relation according to the target service application scene.

Specifically, a target service application scene to which a user to be identified belongs is obtained, and scene attribute information corresponding to the target service application scene is obtained. Wherein the scene attribute information includes an application category, an application product, and a product attribute. And one of the two-way casting and receiving relations can be determined according to the scene attribute information, and the target casting and receiving relation corresponding to the user to be identified is determined.

Further, taking the case that the scene attribute information comprises the insurance product and the product attribute as an example, determining whether the current user to be identified is an insurance user or an ensured user according to the actual insurance product and the corresponding product attribute by acquiring the actual insurance product and the corresponding product attribute. And determining one of the two-way quilt throwing relations according to the identification result, and determining the two-way quilt throwing relation as a target quilt throwing relation corresponding to the user to be identified.

In one embodiment, after determining the corresponding target routing relationship from the bidirectional routing relationship according to the target business application scenario, the method further includes:

Carrying out service identification according to the determined target routing relation, and determining a service item to which the target routing relation belongs; aiming at different service items, setting corresponding item operation authorities for users corresponding to target casting relations; the project operational rights include project viewing, project modification, and project downloading.

Specifically, service identification is performed on the determined target throw-in relation, whether the target throw-in relation belongs to the insurance service or the protected service is determined, and then project operation authority which the user corresponding to the target throw-in relation should have is determined. The operation rights of the user to the business project are set to be different, for example, the user can view or modify the project, and the user can only provide viewing rights.

It should be emphasized that, to further ensure the privacy and security of the service data, the user base information, and the target user base information, the service data, the user base information, and the target user base information may also be stored in a node of a blockchain.

In the decision tree-based business data routing relation matching method, the corresponding insurance user identification is extracted from the business data, the corresponding user basic information is extracted according to the insurance user identification, and then the basic data set is generated according to the extracted user basic information. And establishing a target decision tree according to the basic data set and the preset quilt throwing relationship, traversing the decision tree according to the acquired target user basic information of the user to be identified, and determining the quilt throwing relationship matched with the target user basic information. Through analysis processing of the determined casting and receiving relationship, when the user to be identified is determined to be the insurance user and the guaranteed user at the same time according to the casting and receiving relationship, the casting and receiving relationship is determined to be a two-way casting and receiving relationship, and further according to the target service application scene to which the user to be identified belongs, the corresponding target casting and receiving relationship is determined from the two-way casting and receiving relationship. Because the user does not need to manually and independently select the quilt throwing relationship, the risk of wrong selection of the quilt throwing relationship by the user can be reduced, and when the business data is changed, the quick identification of the quilt throwing relationship of different users can be realized, so that the matching efficiency of business items of different users can be improved.

In one embodiment, as shown in fig. 4, another method for matching business data routing relationship based on decision tree is provided, which specifically includes the following steps:

step S402, data preprocessing is carried out on the acquired user basic information, and usable data is generated.

Specifically, the obtained user basic information is subjected to data preprocessing, invalid data and repeated data in the user basic information are deleted, and missing data in the user basic information is supplemented or deleted to generate available data corresponding to the user basic information.

Step S404, data types of available data and data amounts corresponding to different data types are obtained.

Specifically, the data types of the available data include a digital type, a byte type, and a text type, wherein different data types correspond to the same or different data amounts, i.e., data pieces.

Step S406, according to different data types and corresponding data quantity, a matched data processing mode is determined.

Specifically, the processing modes include judgment processing, assignment processing and declaration processing, and according to different data types and corresponding data amounts, the data processing mode for determining matching includes judgment processing corresponding to available data of digital type, assignment processing corresponding to available data of byte type and declaration processing corresponding to available data of text type.

Step S408, respectively executing data processing on a plurality of available data according to different data processing modes to generate initial data corresponding to the user basic information, wherein the initial data is used for generating a basic data set corresponding to the user basic information.

Specifically, the data types of the available data include a digital type, a byte type and a text type, and the available data of the digital type is judged, the values of the available data of the digital type and the preset value range are compared, and the available data of the digital type conforming to the preset value range is extracted to generate the initial data of the digital type.

And carrying out assignment processing on the available data of the byte type, and comparing the value of the available data of the byte type with a preset value. When the value of the available data of the byte type is determined to be not in accordance with the preset value, the preset value is assigned to the available data of the corresponding byte type, and the initial data of the byte type is generated according to the assigned available data of the byte type.

And carrying out declaration processing on the text-type available data, comparing the composition of the text-type available data with the preset composition, and when the composition of the text-type available data is not consistent with the preset composition, declaring the text-type available data as the preset composition to generate the text-type initial data.

In this embodiment, the user basic information includes a name, a gender, a birthday, a certificate type, and a certificate number of the user, wherein the birthday of the user belongs to available data of a digital type, and the name, the gender, and the certificate of the user are similar to available data of a text type, and the certificate number of the user belongs to available data of a byte type.

In the service data routing relation matching method based on the decision tree, the available data is generated by carrying out data preprocessing on the acquired user basic information, the data types of the available data and the data quantity corresponding to different data types are acquired, and then the matched data processing mode is determined according to the different data types and the corresponding data quantity. And respectively executing data processing on the plurality of available data according to different data processing modes to generate initial data corresponding to the user basic information. The method realizes the data processing of the available data according to different data processing modes, and obtains the initial data for generating the basic data set corresponding to the basic information of the user. Because the basic information of the user is processed in advance, the problem that repeated matching is needed due to matching failure caused by invalid data or missing data and the like when matching of the passive relation is performed later is avoided, and the operation efficiency of matching of the passive relation of the policy is further improved.

It should be understood that, although the steps in the flowcharts of fig. 2 and 4 are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in fig. 2 and 4 may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor does the order in which the sub-steps or stages are performed necessarily occur in sequence, but may be performed alternately or alternately with at least a portion of the other steps or sub-steps of other steps.

In one embodiment, as shown in fig. 5, there is provided a decision tree-based service data routing relationship matching apparatus, including: a user basic information extraction module 502, a basic data set generation module 504, a target decision tree establishment module 506, a traversal module 508, a bi-directional routing relationship determination module 510, and a target routing relationship determination module 512, wherein:

The user basic information extraction module 502 is configured to extract a corresponding user identifier for application and a corresponding user identifier for being ensured from service data, and extract corresponding user basic information according to the user identifier for application and the user identifier for being ensured.

A basic data set generating module 504 is configured to generate a basic data set according to the extracted user basic information.

The target decision tree establishment module 506 is configured to establish a target decision tree according to the basic data set and a preset routing relationship.

And the traversing module 508 is used for acquiring the target user basic information of the user to be identified, traversing the decision tree according to the target user basic information, and determining the casting relationship matched with the target user basic information.

The bi-directional routing relation determining module 510 is configured to analyze and process the determined routing relation, and determine the routing relation as a bi-directional routing relation when the user to be identified is determined to be both the guaranteeing user and the guaranteed user according to the routing relation.

The target routing relationship determining module 512 is configured to obtain a target service application scenario to which the user to be identified belongs, and determine a corresponding target routing relationship from the bidirectional routing relationship according to the target service application scenario.

In the decision tree-based service data routing relation matching device, the corresponding user identifier is extracted from service data, the corresponding user basic information is extracted according to the user identifier, and then the basic data set is generated according to the extracted user basic information. And establishing a target decision tree according to the basic data set and the preset quilt throwing relationship, traversing the decision tree according to the acquired target user basic information of the user to be identified, and determining the quilt throwing relationship matched with the target user basic information. Through analysis processing of the determined casting and receiving relationship, when the user to be identified is determined to be the insurance user and the guaranteed user at the same time according to the casting and receiving relationship, the casting and receiving relationship is determined to be a two-way casting and receiving relationship, and further according to the target service application scene to which the user to be identified belongs, the corresponding target casting and receiving relationship is determined from the two-way casting and receiving relationship. Because the user does not need to manually and independently select the quilt throwing relationship, the risk of wrong selection of the quilt throwing relationship by the user can be reduced, and when the business data is changed, the quick identification of the quilt throwing relationship of different users can be realized, so that the business project matching efficiency of different users can be improved.

In one embodiment, as shown in fig. 6, another service data routing relation matching device based on a decision tree is provided, including: the available data generation module 602, the data type acquisition module 604, the data processing manner matching module 606, and the initial data generation module 608, wherein:

the available data generating module 602 is configured to perform data preprocessing on the obtained user basic information to generate available data.

The data type obtaining module 604 is configured to obtain a data type of the available data and a data amount corresponding to the different data types.

The data processing mode matching module 606 is configured to determine a matched data processing mode according to different data types and corresponding data amounts.

The initial data generating module 608 is configured to perform data processing on a plurality of available data according to different data processing manners, and generate initial data corresponding to user basic information, where the initial data is used to generate a basic data set corresponding to the user basic information.

In the decision tree-based business data routing relation matching device, the available data is generated by carrying out data preprocessing on the acquired user basic information, the data types of the available data and the data quantity corresponding to different data types are acquired, and then the matched data processing mode is determined according to the different data types and the corresponding data quantity. And respectively executing data processing on the plurality of available data according to different data processing modes to generate initial data corresponding to the user basic information. The method realizes the data processing of the available data according to different data processing modes, and obtains the initial data for generating the basic data set corresponding to the basic information of the user. Because the basic information of the user is processed in advance, the problem that repeated matching is needed due to matching failure caused by invalid data or missing data and the like when matching of the passive relation is performed later is avoided, and the operation efficiency of matching of the passive relation of the policy is further improved.

In one embodiment, the traversal module is further to:

acquiring target user basic information of a user to be identified, and judging the integrity of the target user basic information; when the completeness of the basic information of the target user meets the preset requirement, traversing each layer of the target decision tree in sequence according to the basic information of the target user; the bottom layer of the target decision tree is a quilt throwing relation; and when each layer of the target decision tree is successfully traversed, matching the routing relation corresponding to the basic information of the target user from the bottom layer of the target decision tree.

In one embodiment, the target throw relationship determination module is further to:

acquiring a target service application scene to which a user to be identified belongs; acquiring scene attribute information corresponding to a target service application scene; the scene attribute information comprises an application category, an application product and a product attribute; and determining one of the two-way casting and receiving relations from the two-way casting and receiving relations according to the scene attribute information, and determining the two-way casting and receiving relation as a target casting and receiving relation corresponding to the user to be identified.

In one embodiment, the base data set generation module is further to:

carrying out structuring treatment on the initial data to generate corresponding structured data; according to different categories of the initial data, determining structured data of different categories; acquiring information elements corresponding to different types of structured data; acquiring an abstract user information object which is created in advance; according to the information elements, matching object information corresponding to the abstract user information object from the user basic information; and establishing an instance set according to the object information to generate a basic data set.

In one embodiment, a policy-based policy-cast-quilt relationship matching device is provided, and the policy-based policy-cast-quilt relationship matching device further comprises a policy operation authority setting module for

In one embodiment, the initial data generation module is further to:

judging available data of the numbers, and comparing the preset value range with the value of the available data of the numbers; extracting available digital data which accords with a preset value range, and generating initial digital data;

or performing assignment processing on the byte-shaped available data, and comparing the value of the byte-shaped available data with a preset value; when the value of the available data of the byte type is determined to be not in accordance with the preset value, the preset value is assigned to the available data of the corresponding byte type, and the initial data of the byte type is generated according to the assigned available data of the byte type;

or declaration processing is carried out on the text-type available data, and the composition components of the text-type available data are compared with preset composition components; when it is determined that the composition of the available data of the text type is inconsistent with the preset composition, declaring the available data of the text type as the preset composition, and generating initial data of the text type.

For specific limitation of the decision tree-based service data routing relationship matching device, reference may be made to the limitation of the decision tree-based service data routing relationship matching method hereinabove, and the description thereof will not be repeated here. All or part of each module in the decision tree-based business data routing relation matching device can be realized by software, hardware and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.

In one embodiment, a computer device is provided, which may be a server, the internal structure of which may be as shown in fig. 7. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store user base information. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program, when executed by the processor, implements a decision tree based business data throw-by relationship matching method.

It will be appreciated by those skilled in the art that the structure shown in fig. 7 is merely a block diagram of some of the structures associated with the present application and is not limiting of the computer device to which the present application may be applied, and that a particular computer device may include more or fewer components than shown, or may combine certain components, or have a different arrangement of components.

In one embodiment, a computer device is provided comprising a memory storing a computer program and a processor that when executing the computer program performs the steps of:

generating a basic data set according to the extracted user basic information;

establishing a target decision tree according to the basic data set and a preset quilt throwing relation; the number of layers of the target decision tree is greater than the number of categories of the basic information of the user;

acquiring target user basic information of a user to be identified, traversing a decision tree according to the target user basic information, and determining a casting relationship matched with the target user basic information;

Analyzing and processing the determined casting and receiving relationship, and determining the casting and receiving relationship as a two-way casting and receiving relationship when the user to be identified is determined to be the insurance user and the guaranteed user at the same time according to the casting and receiving relationship;

In one embodiment, the processor when executing the computer program further performs the steps of:

acquiring target user basic information of a user to be identified, and judging the integrity of the target user basic information; target user basic information is stored in a blockchain;

when the completeness of the basic information of the target user meets the preset requirement, traversing each layer of the target decision tree in sequence according to the basic information of the target user; the bottom layer of the target decision tree is a quilt throwing relation;

and when each layer of the target decision tree is successfully traversed, matching the routing relation corresponding to the basic information of the target user from the bottom layer of the target decision tree.

Acquiring scene attribute information corresponding to a target service application scene; the scene attribute information comprises an application category, an application product and a product attribute;

and determining one of the two-way casting and receiving relations from the two-way casting and receiving relations according to the scene attribute information, and determining the two-way casting and receiving relation as a target casting and receiving relation corresponding to the user to be identified.

performing data preprocessing on the acquired user basic information to generate available data; acquiring data types of available data and data quantity corresponding to different data types;

respectively executing data processing on a plurality of available data according to different data processing modes to generate initial data corresponding to user basic information; the initial data is used to generate a set of base data corresponding to the user base information.

carrying out structuring treatment on the initial data to generate corresponding structured data; according to different categories of the initial data, determining structured data of different categories;

Acquiring information elements corresponding to different types of structured data; acquiring an abstract user information object which is created in advance;

according to the information elements, matching object information corresponding to the abstract user information object from the user basic information; and establishing an instance set according to the object information to generate a basic data set.

extracting available digital data which accords with a preset value range, and generating initial digital data;

when the value of the available data of the byte type is determined to be not in accordance with the preset value, the preset value is assigned to the available data of the corresponding byte type, and the initial data of the byte type is generated according to the assigned available data of the byte type;

or declaration processing is carried out on the text-type available data, and the composition components of the text-type available data are compared with preset composition components;

When it is determined that the composition of the available data of the text type is inconsistent with the preset composition, declaring the available data of the text type as the preset composition, and generating initial data of the text type.

In one embodiment, a computer storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:

generating a basic data set according to the extracted user basic information;

In one embodiment, the computer program when executed by the processor further performs the steps of:

Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the various embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.

The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, consensus mechanism, encryption algorithm and the like. The Blockchain (Blockchain), which is essentially a decentralised database, is a string of data blocks that are generated by cryptographic means in association, each data block containing a batch of information of network transactions for verifying the validity of the information (anti-counterfeiting) and generating the next block. The blockchain may include a blockchain underlying platform, a platform product services layer, an application services layer, and the like.

The technical features of the above embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.

The above examples merely represent a few embodiments of the present application, which are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it would be apparent to those skilled in the art that various modifications and improvements could be made without departing from the spirit of the present application, which would be within the scope of the present application. Accordingly, the scope of protection of the present application is to be determined by the claims appended hereto.

Claims

1. A decision tree based business data routing relationship matching method, the method comprising:

performing data preprocessing on the acquired user basic information to generate available data, and acquiring the data types of the available data and the data quantity corresponding to different data types;

determining matched data processing modes according to different data types and corresponding data amounts, and respectively executing data processing on a plurality of available data according to different data processing modes to generate initial data corresponding to the user basic information;

carrying out structuring treatment on the initial data to generate corresponding structured data, and determining the structured data of different categories according to the different categories of the initial data;

information elements corresponding to different categories of the structured data are obtained, and an abstract user information object which is created in advance is obtained, so that object information corresponding to the abstract user information object is matched from the user basic information according to the information elements;

Establishing an instance set according to each piece of object information to generate a basic data set;

establishing a target decision tree according to the basic data set and a preset quilt casting relationship; the number of layers of the target decision tree is larger than the number of categories of the user basic information; the top layer of the target decision tree is a root node, the first layer is a name in the user basic information, the second layer is a gender in the user basic information, the third layer is a birthday in the user basic information, the fourth layer is a certificate type in the user basic information, the fifth layer is a certificate number corresponding to the certificate type, and the bottom layer is a throw-quilt relation;

acquiring target user basic information of a user to be identified, judging the integrity of the target user basic information, and traversing each layer of the target decision tree in sequence according to the target user basic information when the integrity of the target user basic information meets the preset requirement; the target user basic information is stored in a blockchain; the bottom layer of the target decision tree is a quilt throwing relation;

when each layer of the target decision tree is successfully traversed, matching a casting relation corresponding to the target user basic information from the bottom layer of the target decision tree;

2. The method of claim 1, wherein the obtaining the target service application scenario to which the user to be identified belongs, and determining the corresponding target routing relationship from the bidirectional routing relationship according to the target service application scenario, comprises:

3. The method of claim 1, wherein the data types include a digital type, a byte type, and a text type; the data processing mode comprises judgment processing, assignment processing and statement processing; and respectively executing data processing on a plurality of available data according to different data processing modes to generate initial data corresponding to the user basic information, wherein the initial data comprises:

4. The method of claim 1, further comprising, after determining a corresponding target routing relationship from the bi-directional routing relationships according to the target business application scenario:

aiming at different business projects, setting corresponding project operation authorities for users corresponding to the target casting relation; the project operation rights include project viewing, project modification, and project downloading.

5. A decision tree-based business data routing relationship matching device, the device comprising:

the available data generation module is used for carrying out data preprocessing on the acquired user basic information to generate available data;

the data type acquisition module is used for acquiring the data types of the available data and the data quantity corresponding to different data types;

the data processing mode matching module is used for determining a matched data processing mode according to different data types and corresponding data quantity;

the initial data generation module is used for respectively executing data processing on a plurality of available data according to different data processing modes to generate initial data corresponding to the user basic information;

The basic data set generation module is used for: carrying out structuring treatment on the initial data to generate corresponding structured data, and determining the structured data of different categories according to the different categories of the initial data; information elements corresponding to different categories of the structured data are obtained, and an abstract user information object which is created in advance is obtained, so that object information corresponding to the abstract user information object is matched from the user basic information according to the information elements; establishing an instance set according to each piece of object information to generate a basic data set;

the target decision tree building module is used for building a target decision tree according to the basic data set and a preset quilt throwing relation; the number of layers of the target decision tree is larger than the number of categories of the user basic information; the top layer of the target decision tree is a root node, the first layer is a name in the user basic information, the second layer is a gender in the user basic information, the third layer is a birthday in the user basic information, the fourth layer is a certificate type in the user basic information, the fifth layer is a certificate number corresponding to the certificate type, and the bottom layer is a throw-quilt relation;

the traversing module is used for acquiring target user basic information of a user to be identified, judging the integrity of the target user basic information, and traversing each layer of the target decision tree in sequence according to the target user basic information when the integrity of the target user basic information is determined to meet the preset requirement; the target user basic information is stored in a blockchain; the bottom layer of the target decision tree is a quilt throwing relation; when each layer of the target decision tree is successfully traversed, matching a casting relation corresponding to the target user basic information from the bottom layer of the target decision tree; the two-way quilt relation determining module is used for analyzing and processing the determined quilt relation, and determining the quilt relation as a two-way quilt relation when the user to be identified is determined to be an insurance user and a guaranteed user according to the quilt relation;

6. The apparatus of claim 5, wherein the target throw relationship determination module is further configured to:

acquiring a target service application scene to which a user to be identified belongs; acquiring scene attribute information corresponding to the target service application scene; the scene attribute information comprises an application category, an application product and a product attribute; and determining one of the two-way casting relationship according to the scene attribute information, and determining the two-way casting relationship as a target casting relationship corresponding to the user to be identified.

7. The apparatus of claim 5, wherein the initial data generation module is further configured to:

judging available data of the numbers, and comparing the preset value range with the value of the available data of the numbers; extracting available digital data which accords with the preset value range, and generating initial digital data; or performing assignment processing on the byte-shaped available data, and comparing the value of the byte-shaped available data with a preset value; when the value of the byte-type available data is determined to be not in accordance with the preset value, assigning the preset value to the corresponding byte-type available data, and generating byte-type initial data according to the assigned byte-type available data; or declaration processing is carried out on the text type available data, and the composition components of the text type available data are compared with preset composition components; when the composition of the text-type available data is not consistent with the preset composition, declaring the text-type available data as the preset composition, and generating text-type initial data.

8. The apparatus of claim 5, further comprising a policy operation authority setting module configured to:

carrying out service identification according to the determined target routing relation, and determining a service item to which the target routing relation belongs; aiming at different business projects, setting corresponding project operation authorities for users corresponding to the target casting relation; the project operation rights include project viewing, project modification, and project downloading.

9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 4 when the computer program is executed.

10. A computer storage medium having stored thereon a computer program, which when executed by a processor realizes the steps of the method according to any of claims 1 to 4.