A list filtering screening method based on intelligent algorithm

Abstract

The present disclosure relates to a list filtering screening method based on an intelligent algorithm, which comprises: acquiring a screening message, the screening message comprising at least a screening scenario and to-be-screened information; acquiring a target screening configuration based on the screening scenario; processing the to-be-screened information based on the target screening configuration to generate a screening request; and acquiring a screening result from a preset screening information library based on the screening request. The present disclosure sets different screening scenarios in advance for different regulatory requirements or regulatory ranges and different transaction business types, selects the corresponding target screening scenario through the information in the screening message to meet different screening requirements, and does not need to redevelop the screening system, thereby improving the efficiency and accuracy of the list filtering screening.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of computer, and particularly relates to a list filtering screening method based on intelligent algorithm. BACKGROUND

[0002] With the increasingly stringent financial transaction supervision requirements and the increasingly expanded supervision range, in order to avoid transaction risks, financial institutions need to screen the related information of the transaction object before transaction.

[0003] The screening method used by the current screening system mainly finds the content similar to the transaction object information in the existing transaction information according to a plurality of pre-set screening rules, and generates a screening result when the matching degree is greater than a matching degree threshold.

[0004] However, when the supervision requirements or the supervision range change, or the transaction business type is different, the previous screening rules often cannot meet the new screening requirements, resulting in weak screening ability of the screening system and bringing transaction risks and economic losses to the related financial institutions. SUMMARY

[0005] In order to solve the above technical problems, the present disclosure provides a list filtering screening method based on intelligent algorithm to meet different screening requirements and improve the efficiency and accuracy of list filtering screening.

[0006] In a first aspect, the present disclosure provides a list filtering screening method based on intelligent algorithm, comprising:

[0007] obtaining a screening message, wherein the screening message at least includes a screening scenario and to-be-screened information;

[0008] obtaining a target screening configuration based on the screening scenario;

[0009] processing the to-be-screened information based on the target screening configuration to generate a screening request;

[0010] obtaining a screening result from a pre-set screening information database based on the screening request.

[0011] In a second aspect, the present disclosure provides a list filtering screening device based on intelligent algorithm, comprising:

[0012] an obtaining module configured to obtain a screening message, wherein the screening message at least includes a screening scenario and to-be-screened information;

[0013] a configuration module configured to obtain a target screening configuration based on the screening scenario;

[0014] a processing module configured to process the to-be-screened information based on the target screening configuration to generate a screening request;

[0015] The screening module is configured to obtain screening results from a preset screening information library based on the screening request.

[0016] In a third aspect, the embodiments of the present disclosure provide an electronic device, comprising:

[0017] a memory;

[0018] a processor; and

[0019] a computer program;

[0020] The computer program is stored in the memory and configured to be executed by the processor to implement the method of the first aspect.

[0021] In a fourth aspect, the embodiments of the present disclosure provide a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0022] In a fifth aspect, the embodiments of the present disclosure further provide a computer program product, which comprises a computer program or instructions, and the computer program or instructions are executed by a processor to implement the list filtering and screening method based on intelligent algorithm as described above.

[0023] The list filtering and screening method based on intelligent algorithm provided by the embodiments of the present disclosure sets different screening scenarios in advance for different regulatory requirements or regulatory ranges and different transaction business types, selects the corresponding target screening scenario according to the information in the screening message, so as to meet different screening requirements, without the need to redevelop the screening system, thereby improving the efficiency and accuracy of the list filtering and screening. BRIEF DESCRIPTION OF DRAWINGS

[0024] The accompanying drawings, which are incorporated into and form part of the specification, illustrate embodiments consistent with the present disclosure and, together with the specification, serve to explain the principles of the present disclosure.

[0025] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained from these drawings without creative labor.

[0026] Figure 1 The flowchart of the list filtering and screening method based on intelligent algorithm provided by the embodiments of the present disclosure;

[0027] Figure 2 The flowchart of the list filtering and screening method based on intelligent algorithm provided by another embodiment of the present disclosure;

[0028] Figure 3 A flowchart of a list filtering screening method based on an intelligent algorithm is provided for another embodiment of the present disclosure.

[0029] Figure 4 A flowchart of a method for matching preliminary screening information with to-be-screened information and calculating a matching degree of the preliminary screening information and the to-be-screened information is provided for another embodiment of the present disclosure.

[0030] Figure 5 A flowchart of a method for calculating a matching degree of preliminary screening information and to-be-screened information when the target matching type is a second matching type is provided for an embodiment of the present disclosure.

[0031] Figure 6 A flowchart of a method for confirming preliminary screening information as a screening result when a matching degree of the preliminary screening information and the to-be-screened information meets a preset rule is provided for an embodiment of the present disclosure.

[0032] Figure 7 A structural schematic diagram of a list filtering screening device based on an intelligent algorithm is provided for an embodiment of the present disclosure.

[0033] Figure 8 A structural schematic diagram of an electronic device is provided for an embodiment of the present disclosure. DETAILED DESCRIPTION

[0034] In order to more clearly understand the above-mentioned purposes, features and advantages of the present disclosure, the schemes of the present disclosure will be further described below. It should be noted that the embodiments of the present disclosure and the features in the embodiments can be combined with each other without conflict.

[0035] In the following description, many specific details are set forth in order to provide a thorough understanding of the present disclosure, but the present disclosure can also be implemented in other ways different from those described herein; obviously, the embodiments in the description are only some of the embodiments of the present disclosure, not all the embodiments.

[0036] Name Screening is a common business in financial institutions. The business extracts various characteristic information of the transaction subject, such as name, nationality, birthday, address, etc., matches it with the sanctions list, risk list and other official institutions according to certain matching rules, screens out suspicious information, and thus achieves early warning of possible risks in the transaction process. With increasingly stringent regulatory requirements and expanding regulatory scope, more and more financial institutions need to screen their trading partners and trading business. In the prior art, the data structure based on inverted index is usually used to organize and store the lists published by various institutions, and the cosine distance, Euclidean distance and other measurement methods are used to determine whether the screening result is effective. However, since the information involved in different businesses is not the same, the existing screening rules cannot well adapt to the screening needs of various businesses, which may result in the inability of the screening system to adapt to the business screening needs, causing a large loss due to omission, or frequent early warning in the screening process, frequent manual intervention, affecting normal transactions and causing huge operating costs. At the same time, due to the randomness of the data types and input forms in the name screening, the screening result in the prior art often has a large difference from the true result, which cannot meet the business needs. In addition, in the prior art, in order to avoid the omission of the screening result as much as possible, it is often necessary to match a plurality of related matching items one by one, and the response time of a single screening is long, and the overall data throughput of the system is low. In view of the above problems, the present disclosure provides a name screening method based on intelligent algorithm, which will be introduced below in combination with specific embodiments.

[0037] Figure 1 A name screening method based on intelligent algorithm is provided for the present disclosure. The specific steps of the method are as follows:

[0038] S101, obtaining a screening message, the screening message at least comprising a screening scenario and to-be-screened information.

[0039] The screening system receives the screening message sent by the user through the business system, analyzes and obtains the screening scenario and to-be-screened information in the screening message. Specifically, by obtaining the scene ID in the screening message, the screening scenario corresponding to the scene ID is obtained from a plurality of preset screening scenarios.

[0040] S102, obtaining a target screening configuration based on the screening scenario.

[0041] Based on the screening scenario corresponding to the scene ID in the screening message, the screening system obtains the target screening configuration under the screening scenario. One target screening configuration can include one or more screening sub-configuration items.

[0042] S103, processing the to-be-screened information based on the target screening configuration, and generating a screening request.

[0043] According to the target screening configuration corresponding to the screening scenario, the screening system generates one or more screening requests corresponding thereto according to one or more screening sub-configurations in the target screening configuration.

[0044] S104, obtaining a screening result from a preset screening information library based on the screening request.

[0045] The screening information is stored in a preset screening information library in a certain format in advance, for example, in an open source distributed search analysis engine (Elastic Search, ES), and the screening system queries the ES according to the one or more screening requests generated to obtain the final screening result.

[0046] The embodiment of the present disclosure obtains a screening message, the screening message at least including a screening scenario and to-be-screened information; obtains a target screening configuration based on the screening scenario; processes the to-be-screened information based on the target screening configuration, and generates a screening request; and obtains a screening result from a preset screening information library based on the screening request. Different screening scenarios are set in advance for different regulatory requirements or regulatory ranges and different transaction business types, a corresponding target screening scenario is selected through information in the screening message to meet different screening requirements, and the screening system does not need to be redeveloped, thereby improving the efficiency and accuracy of the list filtering screening.

[0047] Figure 2 A list filtering screening method flowchart based on an intelligent algorithm is provided for another embodiment of the present disclosure. As shown in Figure 2 The method includes the following steps:

[0048] S201, obtaining a screening message, the screening message at least including a screening scenario and to-be-screened information.

[0049] S202, obtaining a target screening configuration corresponding to the screening scenario based on a pre-established corresponding relationship between the screening scenario and the screening configuration.

[0050] The user sets one or more screening scenarios in the screening system in advance, and each scenario can include one or more screening sub-configuration items such as entity screening, transaction counterparty screening, high-risk country screening, and transaction account screening.

[0051] The entity screening sub-configuration item can include: a total minimum matching degree of the to-be-screened information and corresponding information in the preset screening information library; a screening list for selecting some specific list in the preset screening information library for screening, such as a certain country sanction list; a screening object type, such as selecting personal information, institution information or all information in the preset screening information library; whether to preferentially match a name and an ID number; an information type involved in the to-be-screened information and a screening weight of each information type, the information can include one or more of a name, an ID number, a nationality, a gender, a birthday and an address; a matching degree algorithm of the to-be-screened information and corresponding information in the preset screening information library, and the like. The counterparty screening sub-configuration item can include: a screening list, a screening object type, whether to screen a bank identification code (BIC) of a counterparty, a minimum matching degree of a counterparty name and a corresponding name in the preset screening information library and a matching degree algorithm thereof, and the like. The high-risk country screening sub-configuration item can include a high-risk country type, such as a high-risk transaction due to economic reasons of a certain country or a high-risk transaction due to a business type, and the like. The transaction account screening sub-configuration item can include an account type, such as whether there is a certain type of illegal transaction in historical transaction records of the transaction account, and the like. It can be understood that the user can reasonably select or set one or more of the above screening sub-configuration items according to actual conditions, and can add other screening sub-configuration items according to actual conditions.

[0052] If the target screening configuration corresponding to the screening scenario is not found, the screening is ended, and the related information of this screening is sent back to the business system.

[0053] After obtaining the target screening configuration, the screening system traverses the to-be-screened information, and generates one or more screening requests based on at least one screening sub-configuration item in the target screening configuration according to the following steps.

[0054] S203, it is judged whether there is an entity screening sub-configuration item. If yes, S204 is executed; if no, S205 is executed.

[0055] S204, an entity screening request is generated.

[0056] If the target screening configuration is set with an entity screening sub-configuration item, an entity screening request is generated according to the screening list, the screening object type and the like in the entity screening sub-configuration item, and the related information in the to-be-screened information in the screening message.

[0057] S205, it is judged whether there is a counterparty screening sub-configuration item. If yes, S206 is executed; if no, S207 is executed.

[0058] S206, a counterparty screening request is generated.

[0059] If the transaction counterparty screening sub-configuration item is set in the target screening configuration, a transaction counterparty screening request is generated according to the screening list, screening object type, whether to screen the transaction counterparty BIC code and other configurations in the transaction counterparty screening sub-configuration item, and the transaction counterparty name, BIC code and other information in the to-be-screened information.

[0060] S207, it is judged whether there is a high-risk country screening sub-configuration item. If yes, S208 is executed, and if no, S209 is executed.

[0061] S208, a high-risk country screening request is generated.

[0062] If the high-risk country screening sub-configuration item is set in the target screening configuration, a high-risk country screening request is generated according to the high-risk country type in the high-risk country screening sub-configuration item and the country code in the to-be-screened information.

[0063] S209, it is judged whether there is a transaction account screening sub-configuration item. If yes, S210 is executed.

[0064] S210, a transaction account screening request is generated.

[0065] If the transaction account screening sub-configuration item is set in the target screening configuration, a transaction account screening request is generated according to the account type in the transaction account screening sub-configuration item and the transaction account information in the to-be-screened information.

[0066] S211, it is judged whether one or more screening requests are generated. If yes, S210 is executed; and if no, S213 is executed.

[0067] S212, based on the one or more screening requests, screening results are obtained from the preset screening information library.

[0068] If one or more screening requests of any type are generated in the above process, the screening system performs screening in the preset screening information library according to the generated screening requests to obtain screening results. If no screening request of any type is generated in the above process, the screening is ended, and the information related to the screening is returned to the business system.

[0069] S213, the process is ended.

[0070] The embodiments of the present disclosure set different screening scenes and corresponding screening configurations for different screening requirements, and set multiple types of screening sub-configuration items, so that the list filtering screening method based on intelligent algorithm provided by the embodiments of the present disclosure can be well applied to various screening scenes, and the screening accuracy is improved, and the flexibility and accuracy of the list filtering screening are further improved.

[0071] Figure 3 A smart algorithm-based list filtering screening method flowchart is provided for another embodiment of the present disclosure. As shown in Figure 3 , the method comprises the following steps:

[0072] S301, a screening message is obtained, the screening message comprising at least a screening scenario and to-be-screened information.

[0073] S302, based on the screening scenario, a target screening configuration is obtained.

[0074] S303, based on the target screening configuration, the to-be-screened information is processed to generate a screening request.

[0075] S304, based on the screening request, preliminary screening information is obtained from a preset screening information library.

[0076] The screening system performs screening in the preset screening information library according to the generated screening request to obtain preliminary screening information.

[0077] S305, the preliminary screening information is matched with the to-be-screened information, and the matching degree of the preliminary screening information and the to-be-screened information is calculated.

[0078] Specifically, S305 can be implemented by the method as shown in Figure 4 . As shown in Figure 4 , S305 can be implemented by the following steps:

[0079] S401, based on the target screening configuration, one or more first fields are extracted from the preliminary screening information, and one or more second fields are extracted from the to-be-screened information.

[0080] According to the information types involved in the to-be-screened information set in the target screening configuration, one or more first fields are extracted from the preliminary screening information, and one or more second fields are extracted from the to-be-screened information. For example, the nationality in the preliminary screening information is extracted as a first field, and the address in the preliminary screening information is extracted as another first field; the nationality in the to-be-screened information is extracted as a second field, and the address in the to-be-screened information is extracted as another second field. When any information in the preliminary screening information or the to-be-screened information is missing, it is considered that the matching degree of the corresponding first field and second field is a second preset value, for example, the to-be-screened information has a second field related to nationality, and the preliminary screening information does not have a first field related to nationality, then it is considered that the matching degree of the first field and the second field related to nationality is 0.

[0081] S402, based on the screening scenario, a target matching type is obtained.

[0082] When there is no information missing in the preliminary screening information and the information to be screened, a target matching type of each field is obtained according to a screening scenario.

[0083] S403, if the target matching type is the first matching type, a matching degree of the preliminary screening information and the information to be screened is calculated according to data types of the first field and the second field.

[0084] Specifically, if the first field or the second field is set type data, and there is an intersection between the first field and the second field, the matching degree of the first field and the second field is a first preset value; if the first field or the second field is set type data, and there is no intersection between the first field and the second field, the matching degree of the first field and the second field is a second preset value; if the first field and the second field are non-set type data, and the first field and the second field are completely identical, the matching degree of the first field and the second field is the first preset value; if the first field and the second field are non-set type data, and the first field and the second field are not completely identical, the matching degree of the first field and the second field is the second preset value.

[0085] If it is determined that the target matching type is the first matching type, when the first field or the second field is set type data, if there is an intersection between the two sets, it is considered that the matching degree of the field is the first preset value, and if there is no intersection between the two sets, it is considered that the matching degree of the field is the second preset value. For example, if the set type data corresponding to the first field and the second field both contain the element "Z country", it is considered that the matching degree of the first field and the second field is 1; if the set type data corresponding to the first field and the second field do not have the same element, it is considered that the matching degree of the first field and the second field is 0.

[0086] When the first field and the second field are not set type data, if the first field and the second field are completely identical, it is considered that the matching degree is the first threshold value; if the first field and the second field are not completely identical, it is considered that the matching degree is the second threshold value. For example, the first field and the second field are two lists, and only when the information in the two lists is completely identical, the matching degree of the first field and the second field is 1, otherwise the matching degree is 0.

[0087] S404, if the target matching type is the second matching type, and the matching accuracy of the first matching type is higher than the matching accuracy of the second matching type, each of the first field and each of the second field is converted according to a pre-set field conversion rule, and a matching degree of the preliminary screening information and the information to be screened is calculated based on the matching degree of the converted first field and the converted second field.

[0088] Specifically, S404 can be implemented by the method as shown in Figure 5 Figure 5 As shown in

[0089] S501, acquire the language types of the first field and the second field.

[0090] S502, determine whether the language types of the first field and the second field are the same. If yes, execute S503.

[0091] S503, convert the first field and each of the second fields according to the pre-set field conversion rule.

[0092] The user pre-sets the field conversion rule in the screening system, which can include one or more of the following: whether to convert full-width characters into half-width characters; whether to ignore word order; whether to ignore numbers in words; whether to ignore case; whether to convert traditional Chinese characters into simplified Chinese characters; whether to support homophonic characters; whether to support polyphonic characters; whether to recognize four-corner code; whether to ignore special characters; whether to support conversion between abbreviations and full names; supported stop word types, etc.

[0093] If it is determined that the target matching type is the second matching type, first determine the language types of the first field and the second field. If the language types are different, it is considered that they are not matched, i.e., the matching degree is 0. If the language types are the same, pre-process the first field and the second field according to the pre-set field conversion rule. For example, if the field conversion rule is configured to convert traditional Chinese characters into simplified Chinese characters, convert the traditional Chinese characters in the first field and the second field into corresponding simplified Chinese characters.

[0094] S504, perform word segmentation processing on the converted first field and each of the converted second fields to obtain one or more first word groups and one or more second word groups.

[0095] If the segmented word belongs to a stop word and the stop word type belongs to the supported stop word types in the pre-set field conversion rule, the word is removed from the word group and no longer participates in subsequent processing. If the segmented word belongs to an abbreviation in the pre-set field conversion rule, the word is removed from the word group, and the corresponding full name word group is added to the word group to continue participating in subsequent processing. If the segmented word group is Chinese, and the pre-set field conversion rule is set to support homophonic characters or support polyphonic characters, the Chinese characters are converted into pinyin to continue participating in subsequent processing.

[0096] S505, match the one or more first word groups and the one or more second word groups based on the minimum edit distance to obtain a plurality of matching groups, the minimum edit distance of each matching group, and the number of unmatched word groups. ​

[0097] After the word segmentation processing, the screening system obtains one or more first word groups and one or more second word groups. The one or more first word groups are matched with the one or more second word groups based on the minimum edit distance, and the specific process is as follows:

[0098] The number of the first word groups is compared with the number of the second word groups, and the word group with the smaller number is matched with the word group with the larger number. For example, the number of the first word groups is less than the number of the second word groups, and then the first word groups are matched with the second word groups. For each first word group, a second word group with the minimum edit distance is found, and a matching group is formed. The first word group and the second word group included in the matching group no longer participate in subsequent matching. After multiple matching, each first word group is matched with a second word group with the minimum edit distance, and the same number of matching groups as the number of the first word groups is obtained, the minimum edit distance of the first word group and the second word group in each matching group, and the number of unmatched word groups. The number of unmatched word groups is equal to the difference between the number of the first word groups and the number of the second word groups.

[0099] S506, according to the sum of the minimum edit distance of each matching group and the sum of the lengths of the words in the unmatched word groups, the total number of characters of the first word groups, and the total number of characters of the second word groups, calculating the matching degree of the first field and the second field.

[0100] First, the minimum edit distance of the first field and the second field is calculated, which is the sum of the minimum edit distance of all matching groups and the total length of characters of the unmatched word groups.

[0101] Further calculate the matching degree of the first field and the second field, the formula is as follows:

[0102]

[0103] Wherein, θ is the matching degree of the first field and the second field, D is the minimum edit distance of the first field and the second field, L a is the total number of characters of the first word groups, L b is the total number of characters of the second word groups.

[0104] S306, if the matching degree of the preliminary screening information and the information to be screened meets the preset rule, confirming the preliminary screening information as the screening result.

[0105] Specifically, S306 can be realized by the method as shown in Figure 6 The following will be specifically introduced to S306 by the method as shown in Figure 6

[0106] ​After calculating the matching degrees of all the first fields and the second fields, first, the type of the screening request is judged, and the embodiments of the present disclosure take the entity screening request, the counterparty screening request, the high-risk country screening request and the transaction account screening request as examples.

[0107] For screening according to the entity screening request, first, it is judged whether the priority matching of the name and the certificate number is set in the entity screening sub-configuration item. If the priority matching of the name and the certificate number is set, it is judged whether the matching degrees of the first field and the second field related to the name and the certificate number are both the first preset value. As shown in the formula (1), the first preset value can be 1. If yes, it is considered that the matching degree of the preliminary screening information and the information to be screened conforms to the preset rule, the screening hits, and the corresponding preliminary screening information is the screening result. If the matching degrees of the first field and the second field related to the name and the certificate number are not both the first preset value, the matching degree of the preliminary screening information and the information to be screened is calculated, and the formula is as follows: Figure 6

[0108]

[0109] Wherein, δ is the matching degree of the preliminary screening information and the information to be screened, P is the matching degree of a certain first field and a certain second field, and W is the matching degree calculation weight of the first field and the second field. If the matching degree of the preliminary screening information and the information to be screened is greater than or equal to the minimum matching degree set in the entity screening sub-configuration item, it is considered that the screening hits, and the corresponding preliminary screening information is the screening result. If the matching degree of the preliminary screening information and the information to be screened is less than the minimum matching degree set in the entity screening sub-configuration item, it is considered that the screening does not hit, and the corresponding preliminary screening information cannot be used as the screening result.

[0110] For screening according to the counterparty screening request, first, it is judged whether the BIC code of the screening counterparty is set in the counterparty screening sub-configuration item. If yes, it is judged whether the matching degrees of the first field and the second field related to the BIC code are the first preset value. If yes, it is considered that the matching degree of the preliminary screening information and the information to be screened conforms to the preset rule, the screening hits, and the corresponding preliminary screening information is the screening result. If the matching degrees of the first field and the second field related to the BIC code are not the first preset value, the matching degrees of the first field and the second field related to the counterparty name are further calculated. If the matching degrees of the first field and the second field related to the counterparty name are greater than or equal to the minimum matching degree in the counterparty screening sub-configuration item, it is considered that the screening hits, and the corresponding preliminary screening information is the screening result. If the matching degrees of the first field and the second field related to the counterparty name are less than the minimum matching degree in the counterparty screening sub-configuration item, it is considered that the screening does not hit, and the corresponding preliminary screening information cannot be used as the screening result.

[0111] ​For screening according to the high-risk country screening request and the transaction account screening request, if the preliminary screening information is not empty, it is considered that the screening hits, and the preliminary screening information is the screening result.

[0112] The different data processing and matching methods are implemented according to different screening scenes, the preset field conversion rule can support a relatively complex matching algorithm, the list filtering screening demand can be better adapted, and the flexibility and accuracy of the list filtering screening are improved.

[0113] Meanwhile, since the one or more first word groups and the one or more second word groups are matched based on the minimum edit distance, a smaller number of word groups are matched with a larger number of word groups, compared with the plurality of times of matching the same to-be-matched item in the prior art, the calculation complexity is greatly reduced under the premise of ensuring the accuracy of the calculation result, the system operation resource burden is reduced, the time required for the list filtering screening is reduced, and the efficiency of the list filtering screening is improved.

[0114] Figure 7 A structure diagram of the list filtering screening device based on the intelligent algorithm is provided for the embodiments of the present disclosure. The list filtering screening device based on the intelligent algorithm provided by the embodiments of the present disclosure can execute the processing flow provided by the list filtering screening method based on the intelligent algorithm, as shown in Figure 7 The list filtering screening device based on the intelligent algorithm 700 includes an acquisition module 710, a configuration module 720, a processing module 730, and a screening module 740. The acquisition module 710 is configured to acquire a screening message, and the screening message includes at least a screening scene and to-be-screened information. The configuration module 720 is configured to acquire a target screening configuration based on the screening scene. The processing module 730 is configured to process the to-be-screened information based on the target screening configuration to generate a screening request. The screening module 740 is configured to acquire a screening result from a preset screening information database based on the screening request.

[0115] Optionally, the configuration module 720 is further configured to acquire the target screening configuration corresponding to the screening scene based on a preset corresponding relationship between the screening scenes and the screening configurations.

[0116] Optionally, the processing module 730 is further configured to traverse the to-be-screened information, and generate one or more screening requests based on at least one screening sub-configuration item in the target screening configuration.

[0117] Optionally, the screening module 740 is further configured to acquire preliminary screening information from a preset screening information library based on the screening request; match the preliminary screening information with the to-be-screened information, and calculate a matching degree of the preliminary screening information and the to-be-screened information; and if the matching degree of the preliminary screening information and the to-be-screened information meets a preset rule, confirm the preliminary screening information as a screening result.

[0118] Optionally, the screening module 740 is further configured to extract one or more first fields from the preliminary screening information and one or more second fields from the to-be-screened information based on the target screening configuration; acquire a target matching type based on the screening scene; if the target matching type is a first matching type, calculate the matching degree of the preliminary screening information and the to-be-screened information according to data types of the first fields and the second fields; and if the target matching type is a second matching type and a matching accuracy of the first matching type is higher than a matching accuracy of the second matching type, convert the first fields and each of the second fields according to a preset field conversion rule, and calculate the matching degree of the preliminary screening information and the to-be-screened information based on a matching degree of the converted first fields and the converted second fields.

[0119] Optionally, the screening module 740 is further configured to if the first fields or the second fields are set type data and there is an intersection between the first fields and the second fields, the matching degree of the first fields and the second fields is a first preset value; if the first fields or the second fields are set type data and there is no intersection between the first fields and the second fields, the matching degree of the first fields and the second fields is a second preset value; if the first fields and the second fields are non-set type data and the first fields and the second fields are completely same, the matching degree of the first fields and the second fields is the first preset value; if the first fields and the second fields are non-set type data and the first fields and the second fields are not completely same, the matching degree of the first fields and the second fields is the second preset value; and calculate the matching degree of the preliminary screening information and the to-be-screened information based on the matching degree of the first fields and the second fields.

[0120] Optionally, the screening module 740 is further configured to perform word segmentation processing on the converted first fields and each of the converted second fields to obtain one or more first word groups and one or more second word groups; match the one or more first word groups and the one or more second word groups based on a minimum edit distance to obtain a plurality of matching groups, a minimum edit distance of each matching group, and a number of unmatched word groups; and calculate the matching degree of the first fields and the second fields according to a sum of the minimum edit distances of each matching group, a sum of lengths of the unmatched word groups, a total number of characters of the first word groups, and a total number of characters of the second word groups.

[0121] Figure 7 The list filtering screening device based on the intelligent algorithm of the illustrated embodiment can be used to execute the technical solutions of the method embodiment described above, and the implementation principle and technical effects are similar, which will not be described here.

[0122] Figure 8 The structure schematic diagram of the electronic device provided by the embodiment of the present disclosure. The electronic device provided by the embodiment of the present disclosure can execute the processing flow provided by the list filtering screening method based on the intelligent algorithm, as shown in Figure 8 As shown, the electronic device 80 includes a memory 81, a processor 82, a computer program and a communication interface 83; wherein the computer program is stored in the memory 81 and is configured to be executed by the processor 82 to execute the list filtering screening method based on the intelligent algorithm as described above.

[0123] In addition, the embodiment of the present disclosure also provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the list filtering screening method based on the intelligent algorithm described in the above embodiment.

[0124] In addition, the embodiment of the present disclosure also provides a computer program product, which includes a computer program or instructions, and the computer program or instructions are executed by a processor to implement the method as described above.

[0125] It should be noted that, in this paper, relationship terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the terms "include", "contain" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or device. Without more limitations, the element defined by the statement "including a…" does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0126] The above is only a specific embodiment of the present disclosure, which enables those skilled in the art to understand or implement the present disclosure. Various modifications of these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present disclosure. Therefore, the present disclosure will not be limited to these embodiments described herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A smart algorithm based list filtering screening method characterized in that, The method comprises: obtaining a screening message, the screening message comprising at least a screening scenario and to-be-screened information; based on the screening scenario, obtaining a target screening configuration, each screening scenario comprising one or more screening sub-configuration items of the following types: entity screening, transaction counterparty screening, high-risk country screening, and transaction account screening; based on the target screening configuration, processing the to-be-screened information to generate a screening request; based on the screening request, obtaining preliminary screening information from a preset screening information library; matching the preliminary screening information with the to-be-screened information to calculate the matching degree of the preliminary screening information and the to-be-screened information; if the matching degree of the preliminary screening information and the to-be-screened information meets a preset rule, confirming the preliminary screening information as a screening result; wherein the matching of the preliminary screening information with the to-be-screened information to calculate the matching degree of the preliminary screening information and the to-be-screened information comprises: based on the target screening configuration, extracting one or more first fields from the preliminary screening information and one or more second fields from the to-be-screened information; based on the screening scenario, obtaining a target matching type; if the target matching type is a first matching type, calculating the matching degree of the preliminary screening information and the to-be-screened information according to the data types of the first fields and the second fields; if the target matching type is a second matching type and the matching accuracy of the first matching type is higher than that of the second matching type, converting the first fields and each of the second fields according to a pre-set field conversion rule, and calculating the matching degree of the preliminary screening information and the to-be-screened information based on the matching degree of the converted first fields and second fields.

2. The method of claim 1, wherein, The obtaining of the target screening configuration based on the screening scenario comprises: based on the correspondence between the pre-established screening scenarios and screening configurations, obtaining the target screening configuration corresponding to the screening scenario.

3. The method of claim 1, wherein, The processing of the to-be-screened information based on the target screening configuration to generate a screening request comprises: traversing the to-be-screened information and generating one or more screening requests based on at least one screening sub-configuration item in the target screening configuration.

4. The method of claim 1, wherein, The calculation of the matching degree of the preliminary screening information and the to-be-screened information according to the data types of the first fields and the second fields comprises: if the first field or the second field is a set type data and there is an intersection between the first field and the second field, the matching degree of the first field and the second field is a first preset value; if the first field or the second field is a set type data and there is no intersection between the first field and the second field, the matching degree of the first field and the second field is a second preset value; if the first field and the second field are non-set type data and the first field and the second field are exactly the same, the matching degree of the first field and the second field is a first preset value; if the first field and the second field are non-set type data and the first field and the second field are not exactly the same, the matching degree of the first field and the second field is a second preset value; calculate a matching degree between the preliminary screening information and the information to be screened based on the matching degree between the first field and the second field.

5. The method of claim 1, wherein, The calculating the matching degree between the preliminary screening information and the information to be screened based on the matching degree between the converted first field and the converted second field comprises: performing word segmentation on the converted first field and each converted second field to obtain one or more first word groups and one or more second word groups; matching the one or more first word groups and the one or more second word groups based on a minimum edit distance to obtain a plurality of matching groups, a minimum edit distance of each matching group, and a number of unmatched word groups; calculating the matching degree between the first field and the second field according to a sum of the minimum edit distances of each matching group, a sum of lengths of words in the unmatched word groups, a total number of characters in the first word groups, and a total number of characters in the second word groups.

6. An intelligent algorithm-based list filtering and screening device, characterized in that, an acquisition module configured to acquire a screening message, the screening message comprising at least a screening scenario and information to be screened; a configuration module configured to acquire a target screening configuration based on the screening scenario; a processing module configured to process the information to be screened based on the target screening configuration to generate a screening request; a screening module configured to acquire preliminary screening information from a preset screening information library; match the preliminary screening information with the information to be screened to calculate a matching degree between the preliminary screening information and the information to be screened; if the matching degree between the preliminary screening information and the information to be screened meets a preset rule, confirm the preliminary screening information as a screening result; the screening module is further configured to extract one or more first fields from the preliminary screening information and one or more second fields from the information to be screened based on the target screening configuration; acquire a target matching type based on the screening scenario; if the target matching type is a first matching type, calculate the matching degree between the preliminary screening information and the information to be screened according to data types of the first field and the second field; if the target matching type is a second matching type and a matching accuracy of the first matching type is higher than a matching accuracy of the second matching type, convert the first field and each second field according to a preset field conversion rule, and calculate the matching degree between the preliminary screening information and the information to be screened based on a matching degree between the converted first field and the converted second field.

7. An electronic device, comprising: comprise: a memory; a processor; and a computer program; wherein the computer program is stored in the memory and configured to be executed by the processor to implement the method of any one of claims 1-5.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the method of any one of claims 1-5. The computer program is executed by the processor to implement the method of any one of claims 1-5.

Images