CN117033715A

CN117033715A - Query message processing method, device, equipment and storage medium

Info

Publication number: CN117033715A
Application number: CN202310953079.9A
Authority: CN
Inventors: 侍桃丽; 韦东俊; 钟宇航; 黄佳佳
Original assignee: Industrial and Commercial Bank of China Ltd ICBC
Current assignee: Industrial and Commercial Bank of China Ltd ICBC
Priority date: 2023-07-31
Filing date: 2023-07-31
Publication date: 2023-11-10

Abstract

The disclosure provides a query message processing method, a query message processing device, query message processing equipment and a query message storage medium, which can be applied to the technical fields of artificial intelligence and financial science and technology. The method comprises the following steps: receiving a query message sent by a first business entity; generating an assembled query message based on the query message, the first preset matching rule and the first preset assembling rule; sending the assembled query message to a second peer organization; receiving an associated message sent by a second peer entity in response to the assembly query message; generating an assembly association message based on the association message, a second preset matching rule and a second preset assembly rule; and sending the assembly association message to a first business organization.

Description

Query message processing method, device, equipment and storage medium

Technical Field

The present disclosure relates to the field of artificial intelligence and financial technology, and in particular, to a query message processing method, apparatus, device, medium, and program product.

Background

The inquiry check-up service among different financial institutions is an important guarantee for ensuring the safe and efficient operation of the payment system. In the related technology, especially for the processing of international remittance and remittance business, for the compliance message, the query or check-up message needs to be forwarded as a proxy financial institution, and the process has high requirements on personnel due to frequent query and large data volume, and the accuracy and confidentiality of the data also become the difficult problems faced by the financial institution, so that a great deal of manpower and time are required, and meanwhile, certain risks exist, such as the condition of omission or mistakes during manual operation.

Disclosure of Invention

In view of the foregoing, the present disclosure provides a query message processing method, apparatus, device, medium, and program product.

According to a first aspect of the present disclosure, there is provided a query message processing method, including: receiving a query message sent by a first business entity;

generating an assembled query message based on the query message, a first preset matching rule and a first preset assembling rule;

sending the assembled query message to a second peer organization;

receiving an associated message sent by the second peer entity in response to the assembly query message;

generating an assembly association message based on the association message, a second preset matching rule and a second preset assembly rule;

and sending the assembly association message to the first business mechanism.

According to an embodiment of the disclosure, after the sending the assembly association message to the first business entity, the method further includes: and recording the query message processing flow and related index parameters in real time by using a real-time recording platform.

According to an embodiment of the disclosure, the generating an assembled query message based on the query message, a first preset matching rule and a first preset assembling rule includes:

Inputting the query message into a target query message matching model, and outputting a compliance query message matched with the first preset matching rule; and

and assembling the compliance query message based on the compliance query message and a first preset assembly rule to generate an assembly query message.

According to an embodiment of the present disclosure, the target query message matching model is obtained by training in the following manner:

based on the query message service rule, the first preset matching rule and the sample query message data set, extracting the characteristics of the sample query message data set to obtain a sample query characteristic matrix;

determining an initial query message matching model based on the sample query message data set and the sample query feature matrix; the sample query message data set comprises a plurality of sample query message data with the same attribute, and the sample query feature matrix comprises a plurality of feature vectors which are in one-to-one correspondence with the plurality of sample query message data;

training the initial query message matching model by using the sample query feature matrix;

and under the condition that the matching accuracy of the initial query message matching model is larger than or equal to a preset threshold value, obtaining the target query message matching model.

According to an embodiment of the present disclosure, the query message processing method further includes: under the condition that the target query message matching model can not output a compliance query message matched with the first preset matching rule, modifying the query message to obtain a modified query message meeting the first preset matching rule; and

and inputting the modified query message into the target query message matching model again, and outputting a compliance query message matched with the first preset matching rule.

According to an embodiment of the disclosure, the generating an assembly association message based on the association message, a second preset matching rule and a second preset assembly rule includes:

inputting the associated message into a target associated message matching model, and outputting a compliance associated message matched with the two preset matching rules; and

and assembling the compliance associated message based on the compliance associated message and a second preset assembly rule to generate an assembly associated message.

According to an embodiment of the present disclosure, the above-mentioned target association message matching model is obtained by training in the following manner:

based on the associated message service rule, the second preset matching rule and the sample associated message data set, extracting the characteristics of the sample associated message data set to obtain a sample associated characteristic matrix;

Determining an initial association message matching model based on the sample association message data set and the sample association feature matrix; the sample association message data set comprises a plurality of sample association message data with the same attribute, and the sample association feature matrix comprises a plurality of feature vectors which are in one-to-one correspondence with the plurality of sample association message data;

training the initial association message matching model by using the sample association characteristic matrix; and

and under the condition that the matching accuracy of the initial association message matching model is larger than or equal to a preset threshold value, obtaining the target association message matching model.

According to an embodiment of the present disclosure, the query message processing method further includes:

modifying the associated message under the condition that the target associated message matching model can not output the compliant associated message matched with the second preset matching rule, so as to obtain a modified associated message meeting the second preset matching rule; and

and inputting the modified association message into the target association message matching model again, and outputting a compliance association message matched with the second preset matching rule.

According to an embodiment of the present disclosure, after the real-time recording of the query message processing flow and the related index parameters by using the real-time recording platform, the method further includes:

Responding to the query message processing flow, starting a query message analysis task, and obtaining a query message analysis result; and

and generating a summary text of the query message analysis result based on the query message analysis result.

According to an embodiment of the present disclosure, the above-mentioned related index parameter includes at least one of: the system comprises a mechanism parameter, a time parameter, a state parameter, a quantity parameter, an early warning parameter and a non-compliance parameter.

According to a second aspect of the present disclosure, there is provided a query message processing apparatus, including:

the first receiving module is used for receiving a query message sent by the first business mechanism;

the first generation module is used for generating an assembled query message based on the query message, a first preset matching rule and a first preset assembling rule;

the first sending module is used for sending the assembled query message to a second peer organization;

the second receiving module is used for receiving the associated message sent by the second peer organization in response to the query message;

the second generation module is used for generating an assembly association message based on the association message, a second preset matching rule and a second preset assembly rule; and

and the second sending module is used for sending the assembly association message to the first business mechanism.

According to an embodiment of the present disclosure, the above apparatus further includes:

and the recording module is used for recording the query message processing flow and related index parameters in real time by utilizing the real-time recording platform after the assembly related message is sent to the first business mechanism.

According to an embodiment of the present disclosure, the first generating module includes a first output sub-module and a first assembling sub-module.

The output sub-module is used for inputting the query message into a target query message matching model and outputting a compliance query message matched with the first preset matching rule; and

and the assembly submodule is used for assembling the compliance query message based on the compliance query message and a first preset assembly rule and generating an assembly query message.

According to an embodiment of the present disclosure, the training method of the target query message matching model further includes:

under the condition that the target query message matching model can not output a compliance query message matched with the first preset matching rule, modifying the query message to obtain a modified query message meeting the first preset matching rule; and

According to an embodiment of the present disclosure, the second generating module includes: a second output sub-module and a second assembly sub-module.

The second output sub-module is used for inputting the association message into a target association message matching model and outputting a compliance association message matched with the two preset matching rules; and

and the second assembly submodule is used for assembling the compliance association message based on the compliance association message and a second preset assembly rule and generating an assembly association message.

According to an embodiment of the present disclosure, the training method for the target association message matching model further includes:

the starting module is used for responding to the query message processing flow after the query message processing flow and the related index parameters are recorded in real time by the real-time recording platform, starting a query message analysis task and obtaining a query message analysis result; and

the generation module is used for generating a summary text of the query message analysis result based on the query message analysis result after the query message processing flow and the related index parameters are recorded in real time by using the real-time recording platform.

A third aspect of the present disclosure provides an electronic device, comprising: one or more processors; and a memory for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method.

A fourth aspect of the present disclosure also provides a computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the above-described method.

A fifth aspect of the present disclosure also provides a computer program product comprising a computer program which, when executed by a processor, implements the above method.

According to the query message processing method, the device, the equipment, the storage medium and the program product provided by the disclosure, a query message sent by a first business organization is received; generating an assembled query message based on the query message, the first preset matching rule and the first preset assembling rule; sending the assembled query message to a second peer organization; receiving an associated message sent by a second peer entity in response to the assembly query message; generating an assembly association message based on the association message, a second preset matching rule and a second preset assembly rule; and sending the assembly association message to a first business organization. Because the assembly inquiry message and the assembly association message are generated according to the preset matching rule and the preset assembly rule, and the assembly message is sent to the corresponding peer organization, the automatic processing of compliance inquiry and check and reply is realized, the manual intervention is reduced to a great extent, and the accuracy and confidentiality of message processing are improved.

Drawings

The foregoing and other objects, features and advantages of the disclosure will be more apparent from the following description of embodiments of the disclosure with reference to the accompanying drawings, in which:

FIG. 1 schematically illustrates an application scenario diagram of a query message processing method, apparatus, device, storage medium and program product according to an embodiment of the present disclosure;

FIG. 2 schematically illustrates a flow chart of a query message processing method according to an embodiment of the disclosure;

FIG. 3 schematically illustrates a flow chart of another message processing method according to an embodiment of the disclosure;

FIG. 4 schematically illustrates a flow chart of yet another message processing method according to an embodiment of the disclosure;

FIG. 5 schematically illustrates a system architecture diagram of a message processing method according to an embodiment of the present disclosure;

FIG. 6 schematically illustrates a block diagram of a query message processing apparatus according to an embodiment of the disclosure; and

fig. 7 schematically illustrates a block diagram of an electronic device adapted to implement a query message processing method according to an embodiment of the disclosure.

Detailed Description

Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It should be understood that the description is only exemplary and is not intended to limit the scope of the present disclosure. In the following detailed description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. It may be evident, however, that one or more embodiments may be practiced without these specific details. In addition, in the following description, descriptions of well-known structures and techniques are omitted so as not to unnecessarily obscure the concepts of the present disclosure.

The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. The terms "comprises," "comprising," and/or the like, as used herein, specify the presence of stated features, steps, operations, and/or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

All terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art unless otherwise defined. It should be noted that the terms used herein should be construed to have meanings consistent with the context of the present specification and should not be construed in an idealized or overly formal manner.

Where expressions like at least one of "A, B and C, etc. are used, the expressions should generally be interpreted in accordance with the meaning as commonly understood by those skilled in the art (e.g.," a system having at least one of A, B and C "shall include, but not be limited to, a system having a alone, B alone, C alone, a and B together, a and C together, B and C together, and/or A, B, C together, etc.).

In the technical solution of the present disclosure, the related user information (including, but not limited to, user personal information, user image information, user equipment information, such as location information, etc.) and data (including, but not limited to, data for analysis, stored data, displayed data, etc.) are information and data authorized by the user or sufficiently authorized by each party, and the related data is collected, stored, used, processed, transmitted, provided, disclosed, applied, etc. and processed, all in compliance with the related laws and regulations and standards of the related country and region, necessary security measures are taken, no prejudice to the public order, and corresponding operation entries are provided for the user to select authorization or rejection.

In the related technology, in the process of inquiring and replying messages, because of frequent inquiry and large data volume, the requirements on personnel are very high, the accuracy and confidentiality of data become difficult problems faced by financial institutions, a great deal of manpower and time are required, and a certain risk exists. In view of this, the disclosure provides a query message processing method, which can implement automated processing of compliance query and query by intelligently matching query and query messages and assembling and transmitting the matched compliance query and query messages to corresponding peer institutions, thereby reducing manual intervention to a greater extent and improving accuracy and confidentiality of message processing.

Embodiments of the present disclosure provide a query message processing method, apparatus, device, storage medium, and program product, where the method includes: by receiving a query message sent by a first authority; generating an assembled query message based on the query message, the first preset matching rule and the first preset assembling rule; sending the assembled query message to a second peer organization; receiving an associated message sent by a second peer entity in response to the assembly query message; generating an assembly association message based on the association message, a second preset matching rule and a second preset assembly rule; and sending the assembly association message to a first business organization.

Fig. 1 schematically illustrates an application scenario diagram of a query message processing method according to an embodiment of the present disclosure.

As shown in fig. 1, an application scenario 100 according to this embodiment may include a server 101, a server 102, and a server 103, with a network 104 being used as a medium to provide a communication link between the server 101, the server 102, and the server 103. The server 101 in the embodiment of the present disclosure may be a server provided in an agency, the server 102 may be a server provided in a money transfer organization, and the server 103 may be a server provided in a collection organization. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

It should be noted that, the query message processing method provided in the embodiments of the present disclosure may be generally executed by the server 101. Accordingly, the query message processing apparatus provided in the embodiments of the present disclosure may be generally disposed in the server 101. The query message processing method provided by the embodiments of the present disclosure may also be performed by a server or a server cluster that is different from the server 101 and is capable of communicating with the server 102 and the server 103 and/or the server 105. Accordingly, the query message processing apparatus provided by the embodiments of the present disclosure may also be disposed in a server or a server cluster different from the server 105 and capable of communicating with the server 102 and the server 103 and/or the server 105.

It should be understood that the number of networks and servers in fig. 1 is merely illustrative. There may be any number of networks and servers, as desired for implementation.

Fig. 2 schematically illustrates a flow chart of a query message processing method according to an embodiment of the disclosure.

As shown in fig. 2, the query message processing method of this embodiment includes operations S210 to S260.

In operation S210, a query message transmitted by a first authority is received.

According to embodiments of the present disclosure, the first business entity may be a collection entity in a cross-border money transfer service, or may be a collection entity in a money transfer service between different financial institutions within the environment, such as a collection entity a bank in a cross-border money transfer service. The query message may be a message sent by a collection facility to an intermediary agency, either overseas or in-house, such as a query message sent by a collection facility a bank to an intermediary agency B bank in a cross-border money transfer service.

In operation S220, an assembled query message is generated based on the query message, the first preset matching rule and the first preset assembling rule.

According to an embodiment of the present disclosure, the first preset matching rule may be set according to a structural element rule of the query message, for example, a rule for matching according to a message element, an attribute, a type, and the like included in the query message structure. The first preset assembling rule may be to assemble according to a service type, a message element, etc., so as to generate an assembling query message, where the message element includes but is not limited to: query type, batch package to be queried/service to be queried, detail service to be queried, currency symbol of service to be queried, amount, bill number, payment name, query content, etc.

In operation S230, the assembled query message is transmitted to the second peer organization.

According to embodiments of the present disclosure, the second peer entity may be a money transfer entity in a cross-border money transfer service, or may be a money transfer entity in a money transfer service between different financial entities within the environment, such as a money transfer entity K bank in a cross-border money transfer service.

In operation S240, an association message transmitted by the second peer authority in response to the assembly query message is received.

According to an embodiment of the disclosure, the association message may be a reply message after the second peer organization performs a response process on the assembled query message.

In operation S250, an assembly association message is generated based on the association message, the second preset matching rule and the second preset assembly rule.

According to an embodiment of the present disclosure, the second preset matching rule may be set according to a structural element rule of the associated message (i.e., the reply message), for example, a rule for matching according to a message element, an attribute, a type, and the like included in the associated message structure. The second preset assembly rule may be to assemble according to a service type, a message element, etc., so as to generate an assembly-related message, where the message element includes but is not limited to: original inquiry application, inquiry type, batch package to be inquired/service to be inquired, detail service to be inquired, currency symbol of service to be inquired, amount, check content and the like.

In operation S260, the assembly association message is transmitted to the first authority.

According to embodiments of the present disclosure, the specific content of the query message sent by the overseas a bank may include, for example, the payment mechanism/person's title, the payment mechanism/person's detailed address, the nature of the business, the type of product and service, the purpose of payment, the purpose of cargo, and channel records, among others.

Taking table 1 as an example, describing the generation of an assembled query message based on the query message, the first preset matching rule and the first preset assembling rule, table 1 is an assembled query message schematic according to an embodiment of the disclosure:

TABLE 1

The assembled inquiry message is sent to an internal H bank, and an associated message (reply message) sent by the H bank in response to the assembled inquiry message is received, wherein the content of the associated message comprises the full name of a payment mechanism/person, the detailed address of the payment mechanism/person, the nature of an enterprise, the types of products and services, the purpose of payment, the purpose of goods, channel records and the like.

Taking table 2 as an example, describing the generation of an assembly association message based on the association message, the second preset matching rule and the second preset assembly rule, table 2 is an illustration of the assembly association message according to an embodiment of the disclosure:

TABLE 2

According to an embodiment of the present disclosure, a query message sent by a first authority is received; generating an assembled query message based on the query message, the first preset matching rule and the first preset assembling rule; sending the assembled query message to a second peer organization; receiving an associated message sent by a second peer entity in response to the assembly query message; generating an assembly association message based on the association message, a second preset matching rule and a second preset assembly rule; and sending the assembly association message to a first business organization. Because the assembly inquiry message and the assembly association message are generated according to the preset matching rule and the preset assembly rule, and the assembly message is sent to the corresponding peer organization, the automatic processing of compliance inquiry and check and reply is realized, the manual intervention is reduced to a great extent, and the accuracy and confidentiality of message processing are improved.

According to an embodiment of the present disclosure, after sending the assembly association message to the first business entity, the method further includes: and recording the query message processing flow and related index parameters in real time by using a real-time recording platform.

According to an embodiment of the present disclosure, the real-time recording platform may be a platform for monitoring and recording the processing flow of the query message and the related index parameters in real time. The processing flow of the query message comprises the processing flow of the compliant query message and the non-compliant query message and the processing flow of the associated message. Wherein the relevant index parameters include, but are not limited to: the system comprises a mechanism parameter, a time parameter, a state parameter, a quantity parameter, an early warning parameter and a non-compliance parameter.

In one possible embodiment, a variety of intelligent recording and monitoring conditions may be provided in the real-time recording platform, wherein the recording and monitoring conditions include, but are not limited to, flow delays, repetitive processing, and the like. For example, the query time and flow of a certain query message are too long, or the same query message is forwarded for multiple times, or the traffic volume of the query message is suddenly increased or suddenly reduced at a certain moment, the recording platform records and monitors the abnormal situation, and processes or alarms correspondingly according to the abnormal situation.

According to the embodiment of the disclosure, the real-time recording platform is utilized to monitor and record the processing flow of the query message and the related index parameters in real time, so that the processing process and the result of each query or related message (query message) can be recorded, and the related data can be counted, thereby better grasping the progress and the state of the processing flow of the query message, realizing the whole-process monitoring and improving the processing accuracy of the query message.

According to an embodiment of the present disclosure, generating an assembled query message based on the query message, a first preset matching rule, and a first preset assembly rule includes: inputting the query message into a target query message matching model, and outputting a compliance query message matched with a first preset matching rule; and based on the compliance query message and the first preset assembly rule, assembling the compliance query message to generate an assembly query message.

According to embodiments of the present disclosure, the target query message matching model may be a neural network model employing a deep learning algorithm, such as: BP neural network model, convolutional neural network model (CNN), and recurrent neural network model (RNN).

According to the embodiment of the disclosure, the query message is identified and matched through the target query message matching model, so that the query message matching and identifying efficiency can be improved, and finally the query message processing efficiency is improved.

Fig. 3 schematically illustrates a flow chart of another message processing method according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, the target query message matching model is trained in the following manner, and specifically as shown in fig. 3, the query message processing method of this embodiment includes operations S310 to S340.

In operation S310, feature extraction is performed on the sample query message data set based on the query message service rule, the first preset matching rule and the sample query message data set, so as to obtain a sample query feature matrix.

According to an embodiment of the present disclosure, the business rule may be a processing rule of a query message structure, where the query message structure includes a message element, an attribute, a type, a signed element, and the like. For example, the attribute filling rule in the message structure of the query message is [0..1] or [1..1], and when the attribute filling rule does not meet the filling requirement, the system cannot perform identification processing. The sample query message data set may be a data set composed of historical compliance query message data in a specific past time period, which may be set according to practical situations, and is not limited herein. For example, compliance query message data is collected over the past two years, forming a sample query message dataset. Then, extracting key feature data and labeling data in a sample service data set to obtain a sample query feature matrix, wherein the key feature data can comprise query type (query type) data, detail service data to be queried (origin transaction), currency symbol/Amount data (amont) and the like in a message element; the labeling data may be position labeling information corresponding to key feature data, for example, the sequence number of the position labeling information of query type (query type) data in the sample query message in the query message structure is 4, the number of the line is 5, and the number of the column is 3.

Then, an initial association message matching model can be determined through the acquired sample query message dataset and the sample query feature matrix.

In operation S320, an initial query message matching model is determined based on the sample query message dataset and the sample query feature matrix.

According to an embodiment of the present disclosure, a sample query message data set includes a plurality of sample query message data of the same attribute, and a sample query feature matrix includes a plurality of feature vectors in one-to-one correspondence with the plurality of sample query message data. Wherein, the same attribute can be the same message element in the sample query message data.

In operation S330, an initial query message matching model is trained using the sample query feature matrix.

In operation S340, under the condition that it is determined that the matching accuracy of the initial query message matching model is greater than or equal to the preset threshold, the target query message matching model is obtained.

According to the embodiment of the disclosure, the accuracy of the initial query message matching model may be an evaluation result obtained by performing accuracy evaluation on the initial query message matching model. The accuracy evaluation method may be a cross-checking method, such as k-fold cross-checking, thorough cross-checking (Exhaustive Cross Validation), and the like. When the matching accuracy of the initial query message matching model is greater than a preset threshold (for example, 90%), a target query message matching model can be obtained and applied to matching identification of actual query messages, wherein the preset threshold can be set according to service characteristics and actual conditions, and the specific threshold is not limited.

According to the embodiment of the disclosure, the characteristics of the received query message are extracted, the historical query message data is utilized to train the query message matching model, the target query message matching model is generated, and the processing speed and accuracy of the query message are improved by carrying out intelligent recognition and matching on the query message.

According to an embodiment of the disclosure, the query message processing method further includes modifying the query message to obtain a modified query message meeting a first preset matching rule when the target query message matching model cannot output a compliance query message matching the first preset matching rule; and inputting the modified query message into the target query message matching model again, and outputting a compliance query message matched with the first preset matching rule.

According to the embodiment of the disclosure, under the condition that the query message cannot be normally output by the target query message matching model, namely, the query message is correspondingly subjected to floor modification, when the modified query message meets the first preset matching rule, the modified query message is input to the target query message matching model again, and the compliance query message meeting the first preset matching rule is output. For example, when a message element in a query message lacks a bill number (BillNumber), the query message cannot be normally output by the target query message matching model, after the bill number of the missing item is complemented and verified through the floor processing, the target query message matching model is input again, and a compliance query message matched with a first preset matching rule is output.

According to an embodiment of the present disclosure, generating an assembly association message based on the association message, a second preset matching rule, and a second preset assembly rule includes: inputting the associated message into a target associated message matching model, and outputting a compliance associated message matched with two preset matching rules; and assembling the compliance associated message based on the compliance associated message and a second preset assembly rule, and generating an assembly associated message.

According to an embodiment of the present disclosure, the target-associated message matching model may be a neural network model employing a deep learning algorithm, such as: BP neural network model, convolutional neural network model (CNN), and recurrent neural network model (RNN).

According to the embodiment of the disclosure, the target associated message matching model is used for identifying and matching the associated message, so that the associated message matching identification efficiency can be improved, and finally the associated message processing efficiency is improved.

Fig. 4 schematically illustrates a flow chart of yet another message processing method according to an embodiment of the disclosure.

According to an embodiment of the present disclosure, the target associated message matching model is trained in the following manner, and specifically as shown in fig. 4, the associated message processing method of this embodiment includes operations S410 to S440.

In operation S410, feature extraction is performed on the sample association message data set based on the association message service rule, the second preset matching rule and the sample association message data set, so as to obtain a sample association feature matrix.

According to an embodiment of the present disclosure, the association message (i.e., check and reply message) service rule may be a processing rule of an association message structure, where the association message structure includes a message element, an attribute, a type, a signed element, and the like. For example, the attribute filling rule in the message structure of the associated message is [0..1] or [1..1], and when the attribute filling rule does not meet the filling requirement, the system cannot perform identification processing. The sample associated message data set may be a data set composed of historical compliance associated message data in a specific time period in the past, where the specific time period may be set according to practical situations, and is not limited herein. For example, compliance associated message data is collected over the past two years to form a sample associated message dataset. Then, extracting key feature data and labeling data in a sample associated service data set to obtain a sample associated feature matrix, wherein the key feature data can comprise query type (query type) data, detail service data to be queried (origin transaction), currency symbol/Amount data (account) and the like in a message element; the labeling data may be position labeling information corresponding to key feature data, for example, the sequence number of the position labeling information of query type (query type) data in the sample association message in the query message structure is 5, the number of the rows is 6, and the number of the columns is 3.

Then, an initial association message matching model can be determined through the acquired sample association message data set and the sample association feature matrix.

In operation S420, an initial association message matching model is determined based on the sample association message dataset and the sample association feature matrix.

According to an embodiment of the present disclosure, a sample association packet data set includes a plurality of sample association packet data of the same attribute, and a sample association feature matrix includes a plurality of feature vectors in one-to-one correspondence with the plurality of sample association packet data. The attribute is the same as the message element in the sample associated message data.

In operation S430, an initial association message matching model is trained using the sample association feature matrix.

In operation S440, if it is determined that the matching accuracy of the initial association message matching model is greater than or equal to the preset threshold, the target association message matching model is obtained.

According to the embodiment of the disclosure, the accuracy of the initial association message matching model may be an evaluation result obtained by performing accuracy evaluation on the initial association message matching model. The accuracy evaluation method may be a cross-checking method, such as k-fold cross-checking, thorough cross-checking (Exhaustive Cross Validation), and the like. When the matching accuracy of the initial association message matching model is greater than a preset threshold (for example, 90%), a target association message matching model can be obtained and applied to matching identification of an actual association (check-repeat) message, wherein the preset threshold can be set according to service characteristics and actual conditions, and the specific threshold is not limited.

According to the embodiment of the disclosure, the characteristics of the received associated message are extracted, the associated message matching model is trained by utilizing the historical associated message data, the target associated message matching model is generated, and the associated message processing speed and accuracy are improved by carrying out intelligent identification matching on the associated message.

According to an embodiment of the disclosure, the query message processing method further includes modifying the association message to obtain a modified association message meeting a second preset matching rule when the target association message matching model cannot output a compliant association message matching the second preset matching rule; and inputting the modified association message into the target association message matching model again, and outputting the compliance association message matched with the second preset matching rule.

According to the embodiment of the disclosure, under the condition that the associated message cannot be normally output by the target associated message matching model, namely, the associated message is correspondingly subjected to floor modification, when the modified associated message meets a second preset matching rule, the modified associated message is input to the target associated message matching model again, and the compliance associated message meeting the second preset matching rule is output. For example, when a message element in a certain associated message lacks Content (Content), the message element cannot be normally output by the target query message matching model, after the Content of the missing item is complemented and verified through the floor processing, the target query message matching model is input again, and a compliance associated message matched with a second preset matching rule is output.

According to an embodiment of the present disclosure, after recording the query message processing flow and the related index parameters in real time by using the real-time recording platform, the method further includes: responding to the query message processing flow, starting a query message analysis task, and obtaining a query message analysis result; and generating a summary text of the query message analysis result based on the query message analysis result.

According to the embodiment of the disclosure, the analysis result of the query message can be obtained by analyzing the rule related to the compliance message, the non-compliance message and the abnormal condition in the query service processing flow by utilizing the big data analysis technology, and the analysis result of the query message is presented in the form of summarized text. The main content of the analysis includes, but is not limited to: inquiring message processing time analysis, throughput analysis, efficiency analysis, anomaly monitoring and analysis, for example, the message processing time analysis can be performed by counting, analyzing and visualizing the processing time, and determining the average duration, the maximum time, the minimum time and the like of the message processing so as to optimize the message processing efficiency; the processing amount analysis can be to analyze the flow, peak value and the like of message processing, and can be combined with historical data to carry out comparison and trend analysis, so as to adjust the business flow and optimize the resource allocation; the efficiency analysis can be to determine processing bottleneck and limiting factors by analyzing the processing flow of the compliance query reply message and propose an optimization scheme; the anomaly monitoring and analysis may be monitoring and statistics of anomalies and presented via a visualization tool. The analysis result comprises the state and the quality of the query message. Representations of summary text include, but are not limited to, excel forms and Word documents.

According to the embodiment of the disclosure, the query message processing flow is analyzed, the processing result is summarized and presented in the text, high-quality data support is provided for security decision, financial institution managers and system developers can know the system performance more clearly and improve the performance of the system, the compliance operation level of the financial institution can be effectively improved, and financial risks are reduced.

According to an embodiment of the present disclosure, the relevant index parameters include at least one of: the system comprises a mechanism parameter, a time parameter, a state parameter, a quantity parameter, an early warning parameter and a non-compliance parameter.

In one possible embodiment, the mechanism parameter may be a processing mechanism for the query message and/or the association message; the time parameter may be processing time of the query message and/or the associated message; the status parameter may be a processing status of the query message and/or the associated message, such as unprocessed, in-process, or completed, etc.; the quantity parameter may be a processing quantity of the query message and/or the associated message; the early warning parameters can be early warning parameters such as early warning threshold value, early warning times, early warning frequency and the like which are carried out when the abnormal condition of the query message and/or the associated message is abnormal; the non-compliance parameter may be a parameter of performing a corresponding floor processing on the query message and/or the associated message, for example, a parameter such as a processing amount and/or a processing time of the floor processing.

Fig. 5 schematically illustrates a system architecture diagram of a message processing method according to an embodiment of the disclosure.

According to an embodiment of the disclosure, as shown in fig. 5, in a cross-border or in-border money transfer service, a money transfer mechanism sends a money transfer message of a certain money transfer service to an agency, the agency sends the received and checked money transfer message to a collection mechanism, the collection mechanism generates a query message according to a service processing rule, the query message is sent to the agency, the agency matches and assembles according to a correlation rule, generates an assembled query message conforming to the matching rule and sends the assembled query message to the money transfer mechanism, the money transfer mechanism forms a correlation message (i.e. a check-up message) based on the received query message and carries out response processing, and sends the correlation message to the agency, and the agency matches and assembles according to the correlation rule, generates an assembled correlation message conforming to the matching rule and sends the assembled correlation message to the collection mechanism, and finally completes processing of the query-up message.

Based on the query message processing method, the disclosure also provides a query message processing device. The device will be described in detail below in connection with fig. 6.

Fig. 6 schematically shows a block diagram of a query message processing apparatus according to an embodiment of the disclosure.

As shown in fig. 6, the query message processing apparatus 600 of this embodiment includes a first receiving module 610, a first generating module 620, a first transmitting module 630, a second receiving module 640, a second generating module 650, and a second transmitting module 660.

The first receiving module 610 is configured to receive a query message sent by a first authority. In an embodiment, the first receiving module 610 may be configured to perform the operation S210 described above, which is not described herein.

The first generating module 620 is configured to generate an assembled query message based on the query message, the first preset matching rule, and the first preset assembling rule. In an embodiment, the first generating module 620 may be used to perform the operation S220 described above, which is not described herein.

The first sending module 630 is configured to send the assembled query packet to a second peer organization. In an embodiment, the first sending module 630 may be used to perform the operation S230 described above, which is not described herein.

The second receiving module 640 is configured to receive an association message sent by the second peer entity in response to the query packet. In an embodiment, the second receiving module 640 may be configured to perform the operation S240 described above, which is not described herein.

The second generating module 650 is configured to generate an assembled association message based on the association message, a second preset matching rule, and a second preset assembling rule. In an embodiment, the second generating module 650 may be configured to perform the operation S250 described above, which is not described herein.

The second sending module 660 is configured to send the assembly association message to the first business entity. In an embodiment, the second sending module 660 may be configured to perform the operation S260 described above, which is not described herein.

According to an embodiment of the present disclosure, the query message processing apparatus 600 further includes a recording module, configured to record the query message processing flow and the related index parameters in real time by using the real-time recording platform after the assembly association message is sent to the first business organization.

According to an embodiment of the present disclosure, a first generation module includes a first output sub-module and a first assembly sub-module.

The first output sub-module is used for inputting the query message into the target query message matching model and outputting the compliance query message matched with the first preset matching rule.

The first assembly submodule is used for assembling the compliance query message based on the compliance query message and a first preset assembly rule to generate an assembly query message.

According to the embodiment of the disclosure, the target query message matching model is obtained through training in the following manner: based on the query message business rule, the first preset matching rule and the sample query message data set, extracting features of the sample query message data set to obtain a sample query feature matrix; determining an initial query message matching model based on the sample query message dataset and the sample query feature matrix; the sample query message data set comprises a plurality of sample query message data with the same attribute, and the sample query feature matrix comprises a plurality of feature vectors which are in one-to-one correspondence with the plurality of sample query message data; training an initial query message matching model by utilizing a sample query feature matrix; and under the condition that the matching accuracy of the initial query message matching model is larger than or equal to a preset threshold value, obtaining a target query message matching model.

According to an embodiment of the present disclosure, the training method of the target query message matching model further includes: under the condition that the target query message matching model can not output the compliance query message matched with the first preset matching rule, modifying the query message to obtain a modified query message meeting the first preset matching rule; and inputting the modified query message into the target query message matching model again, and outputting a compliance query message matched with the first preset matching rule.

And the second output sub-module is used for inputting the associated message into the target associated message matching model and outputting the compliance associated message matched with the two preset matching rules.

According to the embodiment of the disclosure, the target association message matching model is obtained through training in the following manner: based on the associated message service rule, the second preset matching rule and the sample associated message data set, extracting features of the sample associated message data set to obtain a sample associated feature matrix; determining an initial association message matching model based on the sample association message data set and the sample association feature matrix; the sample association message data set comprises a plurality of sample association message data with the same attribute, and the sample association feature matrix comprises a plurality of feature vectors which are in one-to-one correspondence with the plurality of sample association message data; training an initial association message matching model by using a sample association feature matrix; and under the condition that the matching accuracy of the initial association message matching model is larger than or equal to a preset threshold value, obtaining a target association message matching model.

According to an embodiment of the present disclosure, the training method of the target association message matching model further includes: under the condition that the target associated message matching model can not output the compliant associated message matched with the second preset matching rule, modifying the associated message to obtain a modified associated message meeting the second preset matching rule; and inputting the modified association message into the target association message matching model again, and outputting the compliance association message matched with the second preset matching rule.

According to an embodiment of the present disclosure, the query message processing apparatus 600 further includes a starting module and a generating module.

The starting module is used for responding to the query message processing flow after the query message processing flow and the related index parameters are recorded in real time by utilizing the real-time recording platform, starting the query message analysis task and obtaining the query message analysis result.

The generating module is used for generating a summary text of the query message analysis result based on the query message analysis result after recording the query message processing flow and the related index parameters in real time by using the real-time recording platform.

According to an embodiment of the present disclosure, any of the first receiving module 610, the first generating module 620, the first transmitting module 630, the second receiving module 640, the second generating module 650, and the second transmitting module 660 may be combined in one module to be implemented, or any of the modules may be split into a plurality of modules. Alternatively, at least some of the functionality of one or more of the modules may be combined with at least some of the functionality of other modules and implemented in one module. According to embodiments of the present disclosure, at least one of the first receiving module 610, the first generating module 620, the first transmitting module 630, the second receiving module 640, the second generating module 650, and the second transmitting module 660 may be implemented at least in part as hardware circuitry, such as a Field Programmable Gate Array (FPGA), a Programmable Logic Array (PLA), a system-on-chip, a system-on-substrate, a system-on-package, an Application Specific Integrated Circuit (ASIC), or as hardware or firmware in any other reasonable manner of integrating or packaging the circuitry, or as any one of or a suitable combination of three of software, hardware, and firmware. Alternatively, at least one of the first receiving module 610, the first generating module 620, the first transmitting module 630, the second receiving module 640, the second generating module 650, and the second transmitting module 660 may be at least partially implemented as computer program modules, which when executed, may perform corresponding functions.

As shown in fig. 7, an electronic device 700 according to an embodiment of the present disclosure includes a processor 701 that can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 702 or a program loaded from a storage section 708 into a Random Access Memory (RAM) 703. The processor 701 may include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor and/or an associated chipset and/or a special purpose microprocessor (e.g., an Application Specific Integrated Circuit (ASIC)), or the like. The processor 701 may also include on-board memory for caching purposes. The processor 701 may comprise a single processing unit or a plurality of processing units for performing different actions of the method flows according to embodiments of the disclosure.

In the RAM703, various programs and data necessary for the operation of the electronic apparatus 700 are stored. The processor 701, the ROM702, and the RAM703 are connected to each other through a bus 704. The processor 701 performs various operations of the method flow according to the embodiments of the present disclosure by executing programs in the ROM702 and/or the RAM 703. Note that the program may be stored in one or more memories other than the ROM702 and the RAM 703. The processor 701 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in the one or more memories.

According to an embodiment of the present disclosure, the electronic device 700 may further include an input/output (I/O) interface 705, the input/output (I/O) interface 705 also being connected to the bus 704. The electronic device 700 may also include one or more of the following components connected to an input/output (I/O) interface 705: an input section 706 including a keyboard, a mouse, and the like; an output portion 707 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 708 including a hard disk or the like; and a communication section 709 including a network interface card such as a LAN card, a modem, or the like. The communication section 709 performs communication processing via a network such as the internet. The drive 710 is also connected to an input/output (I/O) interface 705 as needed. A removable medium 711 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is mounted on the drive 710 as necessary, so that a computer program read therefrom is mounted into the storage section 708 as necessary.

The present disclosure also provides a computer-readable storage medium that may be embodied in the apparatus/device/system described in the above embodiments; or may exist alone without being assembled into the apparatus/device/system. The computer-readable storage medium carries one or more programs which, when executed, implement methods in accordance with embodiments of the present disclosure.

According to embodiments of the present disclosure, the computer-readable storage medium may be a non-volatile computer-readable storage medium, which may include, for example, but is not limited to: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this disclosure, a computer-readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. For example, according to embodiments of the present disclosure, the computer-readable storage medium may include ROM702 and/or RAM703 and/or one or more memories other than ROM702 and RAM703 described above.

Embodiments of the present disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowcharts. The program code means for causing a computer system to carry out the query message processing method provided by the embodiments of the present disclosure when the computer program product is run on the computer system.

The above-described functions defined in the system/apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 701. The systems, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

In one embodiment, the computer program may be based on a tangible storage medium such as an optical storage device, a magnetic storage device, or the like. In another embodiment, the computer program may also be transmitted, distributed over a network medium in the form of signals, downloaded and installed via the communication section 709, and/or installed from the removable medium 711. The computer program may include program code that may be transmitted using any appropriate network medium, including but not limited to: wireless, wired, etc., or any suitable combination of the foregoing.

In such an embodiment, the computer program may be downloaded and installed from a network via the communication portion 709, and/or installed from the removable medium 711. The above-described functions defined in the system of the embodiments of the present disclosure are performed when the computer program is executed by the processor 701. The systems, devices, apparatus, modules, units, etc. described above may be implemented by computer program modules according to embodiments of the disclosure.

According to embodiments of the present disclosure, program code for performing computer programs provided by embodiments of the present disclosure may be written in any combination of one or more programming languages, and in particular, such computer programs may be implemented in high-level procedural and/or object-oriented programming languages, and/or assembly/machine languages. Programming languages include, but are not limited to, such as Java, c++, python, "C" or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, partly on a remote computing device, or entirely on the remote computing device or server. In the case of remote computing devices, the remote computing device may be connected to the user computing device through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computing device (e.g., connected via the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams or flowchart illustration, and combinations of blocks in the block diagrams or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

Those skilled in the art will appreciate that the features recited in the various embodiments of the disclosure and/or in the claims may be provided in a variety of combinations and/or combinations, even if such combinations or combinations are not explicitly recited in the disclosure. In particular, the features recited in the various embodiments of the present disclosure and/or the claims may be variously combined and/or combined without departing from the spirit and teachings of the present disclosure. All such combinations and/or combinations fall within the scope of the present disclosure.

The embodiments of the present disclosure are described above. However, these examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. Although the embodiments are described above separately, this does not mean that the measures in the embodiments cannot be used advantageously in combination. The scope of the disclosure is defined by the appended claims and equivalents thereof. Various alternatives and modifications can be made by those skilled in the art without departing from the scope of the disclosure, and such alternatives and modifications are intended to fall within the scope of the disclosure.

Claims

1. A query message processing method, comprising:

receiving a query message sent by a first business entity;

Sending the assembled query message to a second peer organization;

receiving an associated message sent by the second peer entity in response to the assembled query message;

generating an assembly association message based on the association message, a second preset matching rule and a second preset assembly rule; and

and sending the assembly association message to the first business mechanism.

2. The method of claim 1, wherein after the sending the assembly association message to the first business entity, the method further comprises:

and recording the query message processing flow and related index parameters in real time by using a real-time recording platform.

3. The method of claim 1, wherein the generating an assembled query message based on the query message, a first preset matching rule, and a first preset assembly rule comprises:

4. The method of claim 3, wherein the target query message matching model is trained by:

Based on a query message service rule, the first preset matching rule and a sample query message data set, extracting features of the sample query message data set to obtain a sample query feature matrix;

determining an initial query message matching model based on the sample query message dataset and the sample query feature matrix; the sample query message data set comprises a plurality of sample query message data with the same attribute, and the sample query feature matrix comprises a plurality of feature vectors which are in one-to-one correspondence with the plurality of sample query message data;

training the initial query message matching model by utilizing the sample query feature matrix;

5. The method of claim 4, further comprising:

modifying the query message under the condition that the target query message matching model cannot output a compliance query message matched with the first preset matching rule, so as to obtain a modified query message meeting the first preset matching rule; and

6. The method of claim 1, wherein the generating the assembly association message based on the association message, the second preset matching rule, and the second preset assembly rule comprises:

and assembling the compliance association message based on the compliance association message and a second preset assembly rule, and generating an assembly association message.

7. The method of claim 6, wherein the target-associated message matching model is trained by:

Training the initial association message matching model by utilizing the sample association characteristic matrix; and

8. The method of claim 7, further comprising:

modifying the associated message under the condition that the target associated message matching model cannot output a compliance associated message matched with the second preset matching rule, so as to obtain a modified associated message meeting the second preset matching rule; and

9. The method of claim 2, wherein after the query message processing flow and the related index parameters are recorded in real time using the real-time recording platform, the method further comprises:

10. The method of claim 2, wherein the correlation index parameter comprises at least one of: the system comprises a mechanism parameter, a time parameter, a state parameter, a quantity parameter, an early warning parameter and a non-compliance parameter.

11. A query message processing apparatus comprising:

a second receiving module, configured to receive an association message sent by the second peer organization in response to the query packet;

12. An electronic device, comprising:

one or more processors;

storage means for storing one or more programs,

wherein the one or more programs, when executed by the one or more processors, cause the one or more processors to perform the method of any of claims 1-10.

13. A computer readable storage medium having stored thereon executable instructions which, when executed by a processor, cause the processor to perform the method according to any of claims 1 to 10.

14. A computer program product comprising a computer program which, when executed by a processor, implements the method according to any one of claims 1 to 10.