Query message processing method and device, equipment and storage medium

Abstract

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

Description

Technical Field

[0001] This disclosure relates to the fields of artificial intelligence and financial technology, and in particular to a query message processing method, apparatus, device, medium, and program product. Background Technology

[0002] Inter-financial inquiry and response services are crucial for ensuring the secure and efficient operation of payment systems. In related technologies, particularly for international remittance transactions, agent financial institutions need to forward inquiry or response messages for compliance purposes. This process, due to frequent inquiries and large data volumes, places high demands on personnel. Ensuring data accuracy and confidentiality also presents significant challenges for financial institutions, requiring substantial manpower and time, and also carries inherent risks, such as the potential for oversights or errors during manual operations. Summary of the Invention

[0003] In view of the above problems, this disclosure provides a query message processing method, apparatus, device, medium and program product.

[0004] According to a first aspect of this disclosure, a query message processing method is provided, comprising: receiving a query message sent by a first industry institution;

[0005] Based on the above query message, the first preset matching rule, and the first preset assembly rule, an assembled query message is generated;

[0006] The aforementioned assembly query message was sent to the second peer institution;

[0007] Receive the associated message sent by the aforementioned second industry entity in response to the aforementioned assembly query message;

[0008] Based on the aforementioned associated messages, the second preset matching rules, and the second preset assembly rules, an assembled associated message is generated;

[0009] And send the aforementioned assembly-related message to the aforementioned first industry institution.

[0010] According to embodiments of this disclosure, after sending the assembly-related message to the first peer institution, the method further includes: using a real-time recording platform to record the query message processing flow and related indicator parameters in real time.

[0011] According to embodiments of this disclosure, the above-mentioned generation of an assembled query message based on the query message, the first preset matching rule, and the first preset assembly rule includes:

[0012] The above query message is input into the target query message matching model, and a compliant query message that matches the first preset matching rule is output; and

[0013] Based on the above compliance query message and the first preset assembly rule, the above compliance query message is assembled to generate an assembled query message.

[0014] According to embodiments of this disclosure, the above-described target query message matching model is trained in the following manner:

[0015] Based on the query message business rules, the first preset matching rules mentioned above, and the sample query message dataset, feature extraction is performed on the sample query message dataset to obtain the sample query feature matrix;

[0016] Based on the above sample query message dataset and the above sample query feature matrix, an initial query message matching model is determined; wherein, the above sample query message dataset includes multiple sample query message data with the same attributes, and the above sample query feature matrix includes multiple feature vectors that correspond one-to-one with the multiple sample query message data.

[0017] Using the above sample query feature matrix, train the above initial query message matching model;

[0018] If the matching accuracy of the initial query message matching model is greater than or equal to a preset threshold, the target query message matching model is obtained.

[0019] According to embodiments of this disclosure, the query message processing method further includes: modifying the query message to obtain a modified query message that satisfies the first preset matching rule when the target query message matching model cannot output a compliant query message that matches the first preset matching rule; and

[0020] The modified query message is then input into the target query message matching model again, and a compliant query message that matches the first preset matching rule is output.

[0021] According to embodiments of this disclosure, the above-mentioned generation of assembled associated messages based on the aforementioned associated messages, the second preset matching rule, and the second preset assembly rule includes:

[0022] The aforementioned associated messages are input into the target associated message matching model, and the compliant associated messages that match the two preset matching rules are output; and

[0023] Based on the aforementioned compliance-related messages and the second preset assembly rule, the aforementioned compliance-related messages are assembled to generate an assembled related message.

[0024] According to embodiments of this disclosure, the above-mentioned target-related message matching model is trained in the following manner:

[0025] Based on the associated message business rules, the aforementioned second preset matching rules, and the sample associated message dataset, feature extraction is performed on the aforementioned sample associated message dataset to obtain the sample associated feature matrix;

[0026] Based on the aforementioned sample-related message dataset and the aforementioned sample-related feature matrix, an initial related message matching model is determined; wherein, the aforementioned sample-related message dataset includes multiple sample-related message data with the same attributes, and the aforementioned sample-related feature matrix includes multiple feature vectors that correspond one-to-one with the multiple aforementioned sample-related message data.

[0027] Using the aforementioned sample association feature matrix, the initial associated message matching model is trained; and

[0028] If the accuracy of the initial associated message matching model is greater than or equal to a preset threshold, the target associated message matching model is obtained.

[0029] According to embodiments of this disclosure, the above-mentioned query message processing method further includes:

[0030] If the target associated message matching model cannot output a compliant associated message that matches the second preset matching rule, the associated message is modified to obtain a modified associated message that satisfies the second preset matching rule; and

[0031] The modified associated message is input again into the target associated message matching model, and a compliant associated message that matches the second preset matching rule is output.

[0032] According to embodiments of this disclosure, after the above-described method utilizes a real-time recording platform to record the query message processing flow and related indicator parameters in real time, it further includes:

[0033] In response to the above query message processing flow, a query message analysis task is initiated to obtain the query message analysis results; and

[0034] Based on the above query message analysis results, a summary text of the query message analysis results is generated.

[0035] According to embodiments of this disclosure, the aforementioned relevant indicator parameters include at least one of the following: institutional parameters, time parameters, status parameters, quantity parameters, early warning parameters, and non-compliance parameters.

[0036] According to a second aspect of this disclosure, a query message processing apparatus is provided, comprising:

[0037] The first receiving module is used to receive query messages sent by the first peer institution;

[0038] The first generation module is used to generate an assembled query message based on the above query message, the first preset matching rule, and the first preset assembly rule;

[0039] The first sending module is used to send the above-mentioned assembly query message to the second peer institution;

[0040] The second receiving module is used to receive the associated message sent by the aforementioned second peer organization in response to the aforementioned query message;

[0041] The second generation module is used to generate an assembled associated message based on the aforementioned associated message, the second preset matching rule, and the second preset assembly rule; and

[0042] The second sending module is used to send the above-mentioned assembly association message to the above-mentioned first peer organization.

[0043] According to embodiments of this disclosure, the above-described apparatus further includes:

[0044] The recording module is used to record the query message processing flow and related indicator parameters in real time after the above-mentioned assembly-related message is sent to the above-mentioned first peer institution.

[0045] According to embodiments of this disclosure, the first generation module includes a first output submodule and a first assembly submodule.

[0046] The output submodule is used to input the above query message into the target query message matching model and output a compliant query message that matches the first preset matching rule; and

[0047] The assembly submodule is used to assemble the aforementioned compliance query message and the first preset assembly rule to generate an assembled query message.

[0048] According to embodiments of this disclosure, the above-described target query message matching model is trained in the following manner:

[0049] Based on the query message business rules, the first preset matching rules mentioned above, and the sample query message dataset, feature extraction is performed on the sample query message dataset to obtain the sample query feature matrix;

[0050] Based on the above sample query message dataset and the above sample query feature matrix, an initial query message matching model is determined; wherein, the above sample query message dataset includes multiple sample query message data with the same attributes, and the above sample query feature matrix includes multiple feature vectors that correspond one-to-one with the multiple sample query message data.

[0051] Using the above sample query feature matrix, train the above initial query message matching model;

[0052] If the matching accuracy of the initial query message matching model is greater than or equal to a preset threshold, the target query message matching model is obtained.

[0053] According to embodiments of this disclosure, the above-mentioned target query message matching model training method further includes:

[0054] If the target query message matching model cannot output a compliant query message that matches the first preset matching rule, the query message is modified to obtain a modified query message that meets the first preset matching rule; and

[0055] The modified query message is then input into the target query message matching model again, and a compliant query message that matches the first preset matching rule is output.

[0056] According to embodiments of this disclosure, the second generation module includes: a second output submodule and a second assembly submodule.

[0057] The second output submodule is used to input the aforementioned associated messages into the target associated message matching model and output compliant associated messages that match the aforementioned two preset matching rules; and

[0058] The second assembly submodule is used to assemble the aforementioned compliance-related messages based on the above-mentioned compliance-related messages and the second preset assembly rules, and generate an assembled related message.

[0059] According to embodiments of this disclosure, the above-mentioned target-related message matching model is trained in the following manner:

[0060] Based on the associated message business rules, the aforementioned second preset matching rules, and the sample associated message dataset, feature extraction is performed on the aforementioned sample associated message dataset to obtain the sample associated feature matrix;

[0061] Based on the aforementioned sample-related message dataset and the aforementioned sample-related feature matrix, an initial related message matching model is determined; wherein, the aforementioned sample-related message dataset includes multiple sample-related message data with the same attributes, and the aforementioned sample-related feature matrix includes multiple feature vectors that correspond one-to-one with the multiple aforementioned sample-related message data.

[0062] Using the aforementioned sample association feature matrix, the initial associated message matching model is trained; and

[0063] If the accuracy of the initial associated message matching model is greater than or equal to a preset threshold, the target associated message matching model is obtained.

[0064] According to embodiments of this disclosure, the above-mentioned target-related message matching model training method further includes:

[0065] If the target associated message matching model cannot output a compliant associated message that matches the second preset matching rule, the associated message is modified to obtain a modified associated message that satisfies the second preset matching rule; and

[0066] The modified associated message is input again into the target associated message matching model, and a compliant associated message that matches the second preset matching rule is output.

[0067] According to embodiments of this disclosure, the above-described apparatus further includes:

[0068] The startup module, after the real-time recording platform records the query message processing flow and related indicator parameters, responds to the query message processing flow by initiating a query message analysis task to obtain the query message analysis results; and

[0069] The generation module is used to generate a summary text of the query message analysis results based on the query message analysis results after the query message processing flow and related indicator parameters are recorded in real time using the real-time recording platform.

[0070] A third aspect of this disclosure provides an electronic device comprising: one or more processors; and a memory for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors perform the method described above.

[0071] A fourth aspect of this disclosure also provides a computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, cause the processor to perform the methods described above.

[0072] The fifth aspect of this disclosure also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described method.

[0073] According to the query message processing method, apparatus, equipment, storage medium, and program product provided in this disclosure, the following steps are taken: receiving a query message sent by a first industry peer; generating an assembled query message based on the query message, a first preset matching rule, and a first preset assembly rule; sending the assembled query message to a second industry peer; receiving an associated message sent by the second industry peer in response to the assembled query message; generating an assembled associated message based on the associated message, a second preset matching rule, and a second preset assembly rule; and sending the assembled associated message to the first industry peer. Because the assembled query message and the assembled associated message are generated according to the preset matching rule and the preset assembly rule, and the assembled message is sent to the corresponding industry peer, the compliant query and response processing is automated, significantly reducing manual intervention and improving the accuracy and confidentiality of message processing. Attached Figure Description

[0074] The foregoing contents, as well as other objects, features, and advantages of this disclosure, will become clearer from the following description of embodiments with reference to the accompanying drawings, in which:

[0075] Figure 1 The illustration schematically depicts an application scenario of a query message processing method, apparatus, device, storage medium, and program product according to embodiments of the present disclosure;

[0076] Figure 2 A flowchart illustrating a query message processing method according to an embodiment of the present disclosure is shown schematically.

[0077] Figure 3 A flowchart illustrating another message processing method according to an embodiment of this disclosure is shown schematically;

[0078] Figure 4 A flowchart illustrating yet another message processing method according to an embodiment of the present disclosure is shown schematically;

[0079] Figure 5 A schematic diagram illustrating the system architecture of a message processing method according to an embodiment of the present disclosure is shown.

[0080] Figure 6 A schematic block diagram of a query message processing apparatus according to embodiments of the present disclosure is shown; and

[0081] Figure 7 A block diagram schematically illustrates an electronic device suitable for implementing a query message processing method according to an embodiment of the present disclosure. Detailed Implementation

[0082] The embodiments of the present disclosure will now be described with reference to the accompanying drawings. However, it should be understood that these descriptions are exemplary only and are not intended to limit the scope of the disclosure. In the following detailed description, numerous specific details are set forth to provide a thorough understanding of the embodiments of the present disclosure for ease of explanation. However, it will be apparent that one or more embodiments may be practiced without these specific details. Furthermore, descriptions of well-known structures and techniques are omitted in the following description to avoid unnecessarily obscuring the concepts of the present disclosure.

[0083] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this disclosure. The terms “comprising,” “including,” etc., as used herein indicate the presence of the stated features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0084] All terms used herein (including technical and scientific terms) have the meanings commonly understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein are to be interpreted in a manner consistent with the context of this specification, and not in an idealized or overly rigid way.

[0085] When using expressions such as "at least one of A, B and C", they should generally be interpreted in accordance with the meaning that is commonly understood by those skilled in the art (e.g., "a system having at least one of A, B and C" should include, but is not limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B, a system having A and C, a system having B and C, and / or a system having A, B and C, etc.).

[0086] In the technical solution disclosed herein, the user information (including but not limited to user personal information, user image information, user device information, such as location information) and data (including but not limited to data used for analysis, stored data, and displayed data) involved are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant countries and regions, necessary confidentiality measures have been taken, and they do not violate public order and good morals. Corresponding operation entry points are provided for users to choose to authorize or refuse.

[0087] In related technologies, the processing of query and reply messages places high demands on personnel due to the frequency of queries and the large volume of data. Ensuring data accuracy and confidentiality also poses significant challenges for financial institutions, requiring substantial manpower and time, and also carries certain risks. Therefore, this disclosure provides a query message processing method that intelligently matches query and reply messages, assembles the matched compliant query and reply messages, and sends them to relevant peer institutions. This automates the processing of compliant queries and replies, significantly reducing manual intervention and improving the accuracy and confidentiality of message processing.

[0088] Embodiments of this disclosure provide a query message processing method, apparatus, device, storage medium, and program product. The method includes: receiving a query message sent by a first industry entity; generating an assembled query message based on the query message, a first preset matching rule, and a first preset assembly rule; sending the assembled query message to a second industry entity; receiving an association message sent by the second industry entity in response to the assembled query message; generating an assembled association message based on the association message, a second preset matching rule, and a second preset assembly rule; and sending the assembled association message to the first industry entity.

[0089] Figure 1The diagram illustrates an application scenario of the query message processing method according to an embodiment of the present disclosure.

[0090] like Figure 1 As shown, application scenario 100 according to this embodiment may include server 101, server 102, and server 103, and network 104 is used as a medium to provide communication links between server 101, server 102, and server 103. In this embodiment, server 101 may be a server located at an agency, server 102 may be a server located at a remittance agency, and server 103 may be a server located at a receiving agency. Network 104 may include various connection types, such as wired or wireless communication links or fiber optic cables, etc.

[0091] It should be noted that the query message processing method provided in this embodiment can generally be executed by server 101. Correspondingly, the query message processing device provided in this embodiment can generally be located in server 101. The query message processing method provided in this embodiment can also be executed by a server or server cluster that is different from server 101 and capable of communicating with server 102, server 103, and / or server 105. Correspondingly, the query message processing device provided in this embodiment can also be located in a server or server cluster that is different from server 105 and capable of communicating with server 102, server 103, and / or server 105.

[0092] It should be understood that Figure 1 The number of networks and servers shown is merely illustrative. Depending on implementation needs, there can be any number of networks and servers.

[0093] Figure 2 A flowchart illustrating a query message processing method according to an embodiment of the present disclosure is shown schematically.

[0094] like Figure 2 As shown, the query message processing method of this embodiment includes operations S210 to S260.

[0095] In operation S210, a query message is received from the first peer institution.

[0096] According to embodiments of this disclosure, the first interbank institution can be a receiving institution in a cross-border remittance transaction, or a receiving institution in a remittance transaction between different domestic financial institutions, such as Bank A, a receiving institution in a cross-border remittance transaction. The query message can be a message sent from the receiving institution overseas or domestically to the intermediary agent, for example, a query message sent by Bank A, the receiving institution in a cross-border remittance transaction, to Bank B, the intermediary agent.

[0097] In operation S220, an assembled query message is generated based on the query message, the first preset matching rule, and the first preset assembly rule.

[0098] According to embodiments of this disclosure, the first preset matching rule can be set based on the structural element rules of the query message, such as matching rules based on the message elements, attributes, and types contained in the query message structure. The first preset assembly rule can assemble the query message based on the business type, message elements, etc., and then generate an assembled query message. The message elements include, but are not limited to: query type, batch package to be queried / business to be queried, detailed business to be queried, currency symbol of the business to be queried, amount, bill number, name of the paying bank, query content, etc.

[0099] In operation S230, the assembly query message is sent to the second peer institution.

[0100] According to embodiments of this disclosure, the second interbank institution can be a remittance institution in cross-border remittance and transfer business, or a remittance institution in remittance and transfer business between different domestic financial institutions, such as Bank K, a remittance institution in a cross-border remittance and transfer business.

[0101] In operation S240, a related message is received by the second peer organization in response to the assembled query message.

[0102] According to embodiments of this disclosure, the associated message may be a reply message after a second peer organization has responded to the assembled query message.

[0103] In operation S250, an assembled associated message is generated based on the associated message, the second preset matching rule, and the second preset assembly rule.

[0104] According to embodiments of this disclosure, the second preset matching rule can be set based on the structural element rules of the associated message (i.e., query reply message), such as matching rules based on the message elements, attributes, and types contained in the structure of the associated message. The second preset assembly rule can assemble the associated message based on the business type, message elements, etc., and then generate an assembled associated message. The message elements include, but are not limited to: the original query application, query type, batch package to be queried / business to be queried, detailed business to be queried, currency symbol of the business to be queried, amount, query reply content, etc.

[0105] During operation S260, the assembly association message is sent to the first peer institution.

[0106] According to embodiments of this disclosure, for example, the specific content of an inquiry message sent by an overseas bank A may include the full name of the payment institution / person, the detailed address of the payment institution / person, the nature of the enterprise, the type of product and service, the purpose of payment, the intended use of the goods, and shipping records, etc.

[0107] Taking Table 1 as an example, the generation of assembled query messages based on query messages, first preset matching rules, and first preset assembly rules is explained. Table 1 is a schematic diagram of assembled query messages according to an embodiment of this disclosure:

[0108] Table 1

[0109]

[0110] The assembled query message is sent to Bank H in China, and Bank H sends a related message (response message) in response to the assembled query message. The related message includes the full name of the payer / person, the detailed address of the payer / person, the nature of the enterprise, the type of product and service, the purpose of payment, the use of the goods, and the shipping record, etc.

[0111] Taking Table 2 as an example, the generation of assembled associated messages based on associated messages, the second preset matching rule, and the second preset assembly rule will be explained. Table 2 is a schematic diagram of assembled associated messages according to an embodiment of this disclosure:

[0112] Table 2

[0113]

[0114] According to embodiments of this disclosure, the process involves receiving a query message from a first industry peer; generating an assembled query message based on the query message, a first preset matching rule, and a first preset assembly rule; sending the assembled query message to a second industry peer; receiving an association message from the second industry peer in response to the assembled query message; generating an assembled association message based on the association message, a second preset matching rule, and a second preset assembly rule; and sending the assembled association message to the first industry peer. Because the assembled query message and the assembled association message are generated according to the preset matching rule and the preset assembly rule, and the assembled message is sent to the corresponding industry peer, automated processing of compliance queries and responses is achieved, significantly reducing manual intervention and improving the accuracy and confidentiality of message processing.

[0115] According to embodiments of this disclosure, after sending the assembled associated message to the first peer institution, the method further includes: using a real-time recording platform to record the query message processing flow and related indicator parameters in real time.

[0116] According to embodiments of this disclosure, the real-time recording platform can be a platform that monitors and records the processing flow and related indicator parameters of query messages in real time. The processing flow of query messages includes processing flows for compliant and non-compliant query messages and related messages. The related indicator parameters include, but are not limited to: institutional parameters, time parameters, status parameters, quantity parameters, warning parameters, and non-compliant parameters.

[0117] In one feasible embodiment, the real-time recording platform can be configured with various intelligent recording and monitoring conditions, including but not limited to process delays and duplicate processing. For example, if the query time and process of a certain query message are too long, or the same query message is forwarded multiple times, or the business volume of query messages surges or drops sharply at a certain moment, the recording platform will record and monitor the above-mentioned abnormal situations and take corresponding actions or issue alarms based on the abnormal situations.

[0118] According to embodiments of this disclosure, by utilizing a real-time recording platform to monitor and record the processing flow and related indicator parameters of query messages in real time, the processing process and results of each query or associated message (query reply message) can be recorded, and relevant data can be statistically analyzed to better grasp the progress and status of the query message processing flow, thereby achieving full-process monitoring and improving the processing accuracy of query messages.

[0119] According to embodiments of this disclosure, generating an assembled query message based on a 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 compliant query message that matches the first preset matching rule; and assembling a compliant query message based on the compliant query message and the first preset assembly rule to generate an assembled query message.

[0120] According to embodiments of this disclosure, the target query message matching model can be a neural network model employing deep learning algorithms, such as a BP neural network model, a convolutional neural network model (CNN), and a recurrent neural network model (RNN).

[0121] According to embodiments of this disclosure, identifying and matching query messages using a target query message matching model can improve the efficiency of query message matching and identification, and ultimately improve the processing efficiency of query messages.

[0122] Figure 3 A flowchart illustrating another message processing method according to an embodiment of the present disclosure is shown schematically.

[0123] According to embodiments of this disclosure, the target query message matching model is trained in the following manner, specifically as follows: Figure 3 As shown, the query message processing method of this embodiment includes operations S310 to S340.

[0124] In operation S310, based on the query message business rules, the first preset matching rules, and the sample query message dataset, feature extraction is performed on the sample query message dataset to obtain the sample query feature matrix.

[0125] According to embodiments of this disclosure, business rules can be processing rules for query message structures, whereby the query message structure includes message elements, attributes, types, and signature elements. For example, the attribute filling rule in the message structure of a query message might be [0..1] or [1..1]. If the attribute filling rule does not meet the above filling requirements, the system cannot perform recognition processing. The sample query message dataset can be a dataset composed of historical compliant query message data within a specific time period. The specific time period can be set according to actual conditions and is not limited here. For example, compliant query message data from the past two years can be collected to form a sample query message dataset. Then, by extracting key feature data and labeled data from the sample business dataset, a sample query feature matrix is ​​obtained. The key feature data may include query type (QueryType) data, original transaction data to be queried, currency symbol / amount data, etc. in the message elements. The labeled data may be the location label information corresponding to the key feature data. For example, the location label information of the query type (QueryType) data in the sample query message has the sequence number 4, the row number 5, and the column number 3 in the query message structure.

[0126] Then, using the acquired sample query message dataset and sample query feature matrix, the initial associated message matching model can be determined.

[0127] In operation S320, the initial query message matching model is determined based on the sample query message dataset and the sample query feature matrix.

[0128] According to embodiments of this disclosure, the sample query message dataset includes multiple sample query message data with the same attributes, and the sample query feature matrix includes multiple feature vectors that correspond one-to-one with the multiple sample query message data. The same attributes can refer to identical message elements within the sample query message data.

[0129] When operating S330, the initial query message matching model is trained using the sample query feature matrix.

[0130] In operation S340, if the accuracy of the initial query message matching model is greater than or equal to a preset threshold, the target query message matching model is obtained.

[0131] According to embodiments of this disclosure, the matching accuracy of the initial query message matching model can be obtained by evaluating the accuracy of the initial query message matching model. The accuracy evaluation method can be a cross-validation method, such as k-fold cross-validation or exhaustive cross-validation. When the matching accuracy of the initial query message matching model is greater than a preset threshold (e.g., 90%), the target query message matching model can be obtained and applied to the matching and identification of actual query messages. The preset threshold can be set according to business characteristics and actual conditions; the specific threshold is not limited here.

[0132] According to embodiments of this disclosure, features are extracted from received query messages, and a query message matching model is trained using historical query message data to generate a target query message matching model. By intelligently identifying and matching query messages, the speed and accuracy of query message processing are improved.

[0133] According to embodiments of this disclosure, the query message processing method further includes modifying the query message to obtain a modified query message that satisfies the first preset matching rule when the target query message matching model cannot output a compliant query message that matches the first preset matching rule; and inputting the modified query message back into the target query message matching model to output a compliant query message that matches the first preset matching rule.

[0134] According to embodiments of this disclosure, when a query message cannot be normally output by the target query message matching model, the query message is modified accordingly. If the modified query message meets the first preset matching rule, the modified query message is input into the target query message matching model again, and a compliant query message that meets the first preset matching rule is output. For example, if a query message lacks the bill number, it cannot be normally output by the target query message matching model. Through the verification process, the missing bill number is supplemented and verified, and then the message is input into the target query message matching model again, outputting a compliant query message that matches the first preset matching rule.

[0135] According to embodiments of this disclosure, generating an assembled associated message based on an associated 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 compliant associated message that matches the second preset matching rule; and assembling a compliant associated message based on the compliant associated message and the second preset assembly rule to generate an assembled associated message.

[0136] According to embodiments of this disclosure, the target-related message matching model can be a neural network model employing deep learning algorithms, such as a backpropagation neural network model, a convolutional neural network model (CNN), and a recurrent neural network model (RNN).

[0137] According to embodiments of this disclosure, identifying and matching associated messages through a target associated message matching model can improve the efficiency of associated message matching and identification, and ultimately improve the processing efficiency of associated messages.

[0138] Figure 4 A flowchart illustrating yet another message processing method according to an embodiment of the present disclosure is shown schematically.

[0139] According to embodiments of this disclosure, the target-related message matching model is trained in the following manner, specifically as follows: Figure 4 As shown, the associated message processing method in this embodiment includes operations S410 to S440.

[0140] In operation S410, based on the associated message business rules, the second preset matching rules, and the sample associated message dataset, feature extraction is performed on the sample associated message dataset to obtain the sample associated feature matrix.

[0141] According to embodiments of this disclosure, the business rules for associated messages (i.e., query and reply messages) can be processing rules for the associated message structure, wherein the associated message structure includes message elements, attributes, types, and signature elements, etc. For example, the attribute filling rule in the message structure of an associated message is [0..1] or [1..1]. When the attribute filling rule does not meet the above filling requirements, the system cannot perform identification processing. The sample associated message dataset can be a dataset composed of historical compliant associated message data within a specific time period in the past. The specific time period can be set according to the actual situation and is not limited here. For example, compliant associated message data within the past two years can be collected to form a sample associated message dataset. Then, by extracting key feature data and labeled data from the sample-related business dataset, a sample-related feature matrix is ​​obtained. The key feature data may include query type data, original transaction data, currency symbol / amount data, etc. in the message elements. The labeled data may be the location label information corresponding to the key feature data. For example, the location label information of the query type data in the sample-related message is number 5 in the query message structure, the row number is 6, and the column number is 3.

[0142] Then, using the acquired sample-related message dataset and sample-related feature matrix, the initial related message matching model can be determined.

[0143] In operation S420, the initial associated message matching model is determined based on the sample associated message dataset and the sample associated feature matrix.

[0144] According to embodiments of this disclosure, the sample-associated message dataset includes multiple sample-associated message data with the same attributes, and the sample association feature matrix includes multiple feature vectors that correspond one-to-one with the multiple sample-associated message data. The same attributes can refer to identical message elements within the sample-associated message data.

[0145] When operating S430, the initial associated message matching model is trained using the sample association feature matrix.

[0146] In operation S440, if the accuracy of the initial associated message matching model is greater than or equal to a preset threshold, the target associated message matching model is obtained.

[0147] According to embodiments of this disclosure, the matching accuracy of the initial associated message matching model can be obtained by evaluating the accuracy of the initial associated message matching model. The accuracy evaluation method can be a cross-validation method, such as k-fold cross-validation or exhaustive cross-validation. When the matching accuracy of the initial associated message matching model is greater than a preset threshold (e.g., 90%), the target associated message matching model can be obtained and applied to the matching and identification of actual associated (query and reply) messages. The preset threshold can be set according to business characteristics and actual conditions; the specific threshold is not limited here.

[0148] According to embodiments of this disclosure, features are extracted from received associated messages, and a matching model for associated messages is trained using historical associated message data to generate a target associated message matching model. By intelligently identifying and matching associated messages, the processing speed and accuracy of associated messages are improved.

[0149] According to embodiments of this disclosure, the query message processing method further includes modifying the associated message to obtain a modified associated message that satisfies the second preset matching rule when the target associated message matching model cannot output a compliant associated message that matches the second preset matching rule; and re-inputting the modified associated message into the target associated message matching model to output a compliant associated message that matches the second preset matching rule.

[0150] According to embodiments of this disclosure, when an associated message cannot be normally output by the target associated message matching model, the associated message undergoes corresponding landing modification processing. If the modified associated message meets the second preset matching rule, it is then input back into the target associated message matching model, outputting a compliant associated message that meets the second preset matching rule. For example, if a message element in an associated message lacks query content, it cannot be normally output by the target query message matching model. Through landing processing, the missing query content is supplemented and verified, and then the message is input back into the target query message matching model, outputting a compliant associated message that matches the second preset matching rule.

[0151] According to embodiments of this disclosure, after recording the query message processing flow and related indicator parameters in real time using a real-time recording platform, the method further includes: in response to the query message processing flow, initiating a query message analysis task to obtain query message analysis results; and generating a summary text of the query message analysis results based on the query message analysis results.

[0152] According to embodiments of this disclosure, query message analysis results can be obtained by utilizing big data analytics to analyze the patterns of compliant messages, non-compliant messages, and abnormal situations in the query business processing flow, and presenting the analysis results in the form of a summary text. The main content of the analysis includes, but is not limited to: query message processing time analysis, processing volume analysis, efficiency analysis, and anomaly monitoring and analysis. For example, message processing time analysis can involve statistically analyzing, analyzing, and visualizing processing time to determine the average, maximum, and minimum processing times, thereby optimizing message processing efficiency; processing volume analysis can involve analyzing message processing traffic and peak values, and can combine historical data for comparison and trend analysis to adjust business processes and optimize resource allocation; efficiency analysis can involve analyzing the processing flow of compliant query and reply messages to identify processing bottlenecks and limiting factors, and proposing optimization solutions; anomaly monitoring and analysis can involve monitoring and statistically analyzing abnormal situations and presenting them through visualization tools. The analysis results include the status and quality of the query messages. The summary text can be presented in formats including, but not limited to, tables and documents.

[0153] According to embodiments of this disclosure, by analyzing the query message processing flow, summarizing the processing results and presenting them in text, high-quality data support is provided for security decisions. This makes it easier for financial institution managers and system developers to understand the system performance more clearly and improve its performance, thereby effectively improving the compliance level of financial institutions and reducing financial risks.

[0154] According to embodiments of this disclosure, the relevant indicator parameters include at least one of the following: institutional parameters, time parameters, status parameters, quantity parameters, early warning parameters, and non-compliance parameters.

[0155] In one feasible embodiment, the organization parameter can be the processing organization of the query message and / or related message; the time parameter can be the processing time of the query message and / or related message; the status parameter can be the processing status of the query message and / or related message, such as unprocessed, processing, or completed; the quantity parameter can be the number of query messages and / or related messages processed; the warning parameter can be the warning parameters for abnormal situations of query messages and / or related messages, such as warning threshold, number of warnings, and warning frequency; and the non-compliance parameter can be the parameters for the corresponding landing processing of query messages and / or related messages, such as the processing volume and / or processing time of landing processing.

[0156] Figure 5 A schematic diagram illustrating the system architecture of a message processing method according to an embodiment of the present disclosure is provided.

[0157] According to embodiments of this disclosure, such as Figure 5 As shown, in cross-border or domestic remittance transactions, the remittance institution sends a remittance message for a specific remittance transaction to the agent. The agent receives and verifies the remittance message and sends it to the receiving institution. The receiving institution generates a query message based on the received remittance message according to the business processing rules and sends the query message to the agent. The agent matches and assembles the query message according to relevant rules, generating an assembled query message that conforms to the matching rules and sends it to the remittance institution. The remittance institution receives the query message and processes the response to form a related message (i.e., a query reply message), which is then sent to the agent. The agent matches and assembles the related message according to relevant rules, generating an assembled related message that conforms to the matching rules and sends it to the receiving institution, thus completing the processing of the query reply message.

[0158] Based on the above query message processing method, this disclosure also provides a query message processing apparatus. The following will be combined with... Figure 6 The device is described in detail.

[0159] Figure 6 A schematic block diagram of a query message processing apparatus according to an embodiment of the present disclosure is shown.

[0160] like Figure 6 As shown, the query message processing device 600 of this embodiment includes a first receiving module 610, a first generating module 620, a first sending module 630, a second receiving module 640, a second generating module 650, and a second sending module 660.

[0161] The first receiving module 610 is used to receive a query message sent by the first peer organization. In one embodiment, the first receiving module 610 can be used to perform the operation S210 described above, which will not be repeated here.

[0162] The first generation module 620 is used to generate an assembled query message based on the query message, the first preset matching rule, and the first preset assembly rule. In one embodiment, the first generation module 620 can be used to perform the operation S220 described above, which will not be repeated here.

[0163] The first sending module 630 is used to send the assembled query message to the second peer organization. In one embodiment, the first sending module 630 can be used to perform the operation S230 described above, which will not be repeated here.

[0164] The second receiving module 640 is used to receive the associated message sent by the second peer organization in response to the query message. In one embodiment, the second receiving module 640 can be used to perform the operation S240 described above, which will not be repeated here.

[0165] The second generation module 650 is used to generate an assembled associated message based on the associated message, the second preset matching rule, and the second preset assembly rule. In one embodiment, the second generation module 650 can be used to perform the operation S250 described above, which will not be repeated here.

[0166] The second sending module 660 is used to send the assembly association message to the first peer organization. In one embodiment, the second sending module 660 can be used to perform the operation S260 described above, which will not be repeated here.

[0167] According to an embodiment of this disclosure, the query message processing device 600 further includes a recording module, which is used to record the query message processing flow and related indicator parameters in real time using a real-time recording platform after the assembled associated message is sent to the first peer institution.

[0168] According to embodiments of this disclosure, the first generation module includes a first output submodule and a first assembly submodule.

[0169] The first output submodule is used to input the query message into the target query message matching model and output a compliant query message that matches the first preset matching rule.

[0170] The first assembly submodule is used to assemble compliant query messages and generate assembled query messages based on compliant query messages and the first preset assembly rules.

[0171] According to embodiments of this disclosure, the target query message matching model is trained as follows: based on query message business rules, a first preset matching rule, and a sample query message dataset, features are extracted from the sample query message dataset to obtain a sample query feature matrix; based on the sample query message dataset and the sample query feature matrix, an initial query message matching model is determined; wherein, the sample query message dataset includes multiple sample query message data with the same attributes, and the sample query feature matrix includes multiple feature vectors that correspond one-to-one with the multiple sample query message data; the initial query message matching model is trained using the sample query feature matrix; and the target query message matching model is obtained when the matching accuracy of the initial query message matching model is determined to be greater than or equal to a preset threshold.

[0172] According to embodiments of this disclosure, the target query message matching model training method further includes: modifying the query message to obtain a modified query message that satisfies the first preset matching rule when the target query message matching model cannot output a compliant query message that matches the first preset matching rule; and inputting the modified query message back into the target query message matching model to output a compliant query message that matches the first preset matching rule.

[0173] According to embodiments of this disclosure, the second generation module includes: a second output submodule and a second assembly submodule.

[0174] The second output submodule is used to input the associated message into the target associated message matching model and output a compliant associated message that matches the two preset matching rules.

[0175] The second assembly submodule is used to assemble compliant associated messages and generate assembled associated messages based on compliant associated messages and second preset assembly rules.

[0176] According to embodiments of this disclosure, the target associated message matching model is trained as follows: based on associated message business rules, a second preset matching rule, and a sample associated message dataset, features are extracted from the sample associated message dataset to obtain a sample associated feature matrix; based on the sample associated message dataset and the sample associated feature matrix, an initial associated message matching model is determined; wherein, the sample associated message dataset includes multiple sample associated message data with the same attributes, and the sample associated feature matrix includes multiple feature vectors that correspond one-to-one with the multiple sample associated message data; the initial associated message matching model is trained using the sample associated feature matrix; and when the matching accuracy of the initial associated message matching model is determined to be greater than or equal to a preset threshold, a target associated message matching model is obtained.

[0177] According to embodiments of this disclosure, the training method for the target associated message matching model further includes: modifying the associated message to obtain a modified associated message that satisfies the second preset matching rule when the target associated message matching model cannot output a compliant associated message that matches the second preset matching rule; and inputting the modified associated message back into the target associated message matching model to output a compliant associated message that matches the second preset matching rule.

[0178] According to embodiments of this disclosure, the query message processing apparatus 600 further includes a startup module and a generation module.

[0179] The startup module is used to record the query message processing flow and related indicator parameters in real time using the real-time recording platform. In response to the query message processing flow, it starts the query message analysis task and obtains the query message analysis results.

[0180] The generation module is used to generate a summary text of the query message analysis results based on the query message analysis results after the real-time recording platform records the query message processing flow and related indicator parameters in real time.

[0181] According to embodiments of this disclosure, any plurality of modules among 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 can be combined into one module, or any one of these modules can be split into multiple modules. Alternatively, at least part of the functionality of one or more of these modules can be combined with at least part of the functionality of other modules and implemented in one module. According to embodiments of this 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 can be at least partially implemented as hardware circuitry, such as a field-programmable gate array (FPGA), a programmable logic array (PLA), a system-on-a-chip, a system-on-a-substrate, a system-on-package, an application-specific integrated circuit (ASIC), or implemented in hardware or firmware by any other reasonable means of integrating or packaging the circuitry, or implemented in any one of software, hardware, and firmware methods, or in a suitable combination of any of these methods. Alternatively, at least one of the first receiving module 610, the first generating module 620, the first sending module 630, the second receiving module 640, the second generating module 650, and the second sending module 660 may be implemented at least partially as a computer program module, which can perform corresponding functions when the computer program module is run.

[0182] Figure 7 A block diagram schematically illustrates an electronic device suitable for implementing a query message processing method according to an embodiment of the present disclosure.

[0183] like Figure 7 As shown, an electronic device 700 according to an embodiment of the present disclosure includes a processor 701, which 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 portion 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)), etc. The processor 701 may also include onboard memory for caching purposes. The processor 701 may include a single processing unit or multiple processing units for performing different actions of the method flow according to an embodiment of the present disclosure.

[0184] RAM 703 stores various programs and data required for the operation of electronic device 700. Processor 701, ROM 702, and RAM 703 are interconnected via bus 704. Processor 701 performs various operations of the method flow according to embodiments of the present disclosure by executing programs in ROM 702 and / or RAM 703. It should be noted that the programs may also be stored in one or more memories other than ROM 702 and RAM 703. Processor 701 may also perform various operations of the method flow according to embodiments of the present disclosure by executing programs stored in said one or more memories.

[0185] According to embodiments of this disclosure, the electronic device 700 may further include an input / output (I / O) interface 705, which is also connected to a bus 704. The electronic device 700 may also include one or more of the following components connected to the input / output (I / O) interface 705: an input section 706 including a keyboard, mouse, etc.; an output section 707 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the input / output (I / O) interface 705 as needed. A removable medium 711, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 710 as needed so that computer programs read from it can be installed into the storage section 708 as needed.

[0186] This disclosure also provides a computer-readable storage medium, which may be included in the device / apparatus / system described in the above embodiments; or it may exist independently and not assembled into the device / apparatus / system. The computer-readable storage medium carries one or more programs that, when executed, implement the method according to the embodiments of this disclosure.

[0187] According to embodiments of this disclosure, the computer-readable storage medium can be a non-volatile computer-readable storage medium, such as including, but not limited to: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, according to embodiments of this disclosure, the computer-readable storage medium may include ROM 702 and / or RAM 703 and / or one or more memories other than ROM 702 and RAM 703 described above.

[0188] Embodiments of this disclosure also include a computer program product comprising a computer program containing program code for performing the methods shown in the flowchart. When the computer program product is run on a computer system, the program code enables the computer system to implement the query message processing method provided in the embodiments of this disclosure.

[0189] When the computer program is executed by the processor 701, it performs the functions defined in the system / apparatus of this disclosure embodiments. According to embodiments of this disclosure, the systems, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0190] In one embodiment, the computer program may rely on a tangible storage medium such as an optical storage device or a magnetic storage device. In another embodiment, the computer program may also be transmitted and distributed in the form of signals over a network medium, and may be downloaded and installed via the communication section 709, and / or installed from a removable medium 711. The program code contained in the computer program can be transmitted using any suitable network medium, including but not limited to: wireless, wired, etc., or any suitable combination thereof.

[0191] In such an embodiment, the computer program can be downloaded and installed from a network via the communication section 709, and / or installed from the removable medium 711. When the computer program is executed by the processor 701, it performs the functions defined in the system of this disclosure embodiment. According to embodiments of this disclosure, the systems, devices, apparatuses, modules, units, etc., described above can be implemented by computer program modules.

[0192] According to embodiments of this disclosure, program code for executing the computer programs provided in embodiments of this disclosure can be written in any combination of one or more programming languages. Specifically, these computational programs can be implemented using high-level procedural and / or object-oriented programming languages, and / or assembly / machine languages. Programming languages ​​include, but are not limited to, languages ​​such as Java, C++, Python, "C", or similar programming languages. The program code can execute entirely on a user's computing device, partially on a user's device, partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0193] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this disclosure. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0194] Those skilled in the art will understand that the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways, even if such combinations or combinations are not explicitly described in this disclosure. In particular, the features described in the various embodiments and / or claims of this disclosure can be combined or combined in various ways without departing from the spirit and teachings of this disclosure. All such combinations and / or combinations fall within the scope of this disclosure.

[0195] The embodiments of this disclosure have been described above. However, these embodiments are for illustrative purposes only and are not intended to limit the scope of this disclosure. Although various embodiments have been described above, this does not mean that the measures in the various embodiments cannot be used advantageously in combination. The scope of this disclosure is defined by the appended claims and their equivalents. Various substitutions and modifications can be made by those skilled in the art without departing from the scope of this disclosure, and all such substitutions and modifications should fall within the scope of this disclosure.

Claims

1. A query message processing method applied to a server of an agency, comprising: receiving a query message sent by a first correspondent bank; generating an assembled query message based on the query message, a first preset matching rule and a first preset assembly rule, comprising: inputting the query message into a target query message matching model to output a compliant query message matched with the first preset matching rule, wherein the first preset matching rule is set according to a structural element rule of a query message; assembling the compliant query message based on the compliant query message and the first preset assembly rule to generate an assembled query message, wherein the first preset assembly rule is a rule for assembling according to a business type and a message element; sending the assembled query message to a second correspondent bank, wherein the second correspondent bank is a remittance agency; receiving an associated message sent by the second correspondent bank in response to the assembled query message; generating an assembled associated message based on the associated message, a second preset matching rule and a second preset assembly rule, wherein the second preset matching rule is set according to a structural element rule of an associated message, and the second preset assembly rule is a rule for assembling according to a message element of an associated message; and sending the assembled associated message to the first correspondent bank; and recording a query message processing flow and related index parameters in real time by using a real-time recording platform, wherein the processing flow comprises processing flows of compliant and non-compliant query messages and associated messages. The target query message matching model is trained in the following manner: based on a query message business rule, the first preset matching rule and a sample query message data set, performing feature extraction on 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 data set and the sample query feature matrix, wherein the sample query message data set comprises a plurality of sample query message data of the same attribute, and the sample query feature matrix comprises a plurality of feature vectors corresponding to the plurality of sample query message data; training the initial query message matching model by using the sample query feature matrix; and obtaining the target query message matching model in a case where a matching accuracy of the initial query message matching model is greater than or equal to a preset threshold. 3.The method of claim 2, further comprising: in a case where the target query message matching model cannot output a compliant query message matched with the first preset matching rule, modifying the query message to obtain a modified query message satisfying the first preset matching rule; and inputting the modified query message into the target query message matching model again to output a compliant query message matched with the first preset matching rule. The generating of the assembled associated message based on the associated message, the second preset matching rule and the second preset assembly rule comprises: inputting the associated message into a target associated message matching model to output a compliant associated message matched with the second preset matching rule; and ​ ​ ​ ​ ​ ​ 2. The method of claim 1, wherein, ​ ​ ​ ​ ​ ​ ​ ​ ​ 4. The method of claim 1, wherein, ​ ​ Assemble the compliance-related message based on the compliance-related message and a second preset assembly rule to generate an assembled related message.

5. The method of claim 4, wherein, The target-related message matching model is trained in the following manner: Based on the related message business rule, the second preset matching rule and the sample-related message data set, feature extraction is performed on the sample-related message data set to obtain a sample-related feature matrix; Based on the sample-related message data set and the sample-related feature matrix, an initial related message matching model is determined; wherein the sample-related message data set includes a plurality of sample-related message data of the same attribute, and the sample-related feature matrix includes a plurality of feature vectors corresponding to the plurality of sample-related message data; The initial related message matching model is trained using the sample-related feature matrix; and In a case where the initial related message matching model matching accuracy is greater than or equal to a preset threshold, the target-related message matching model is obtained.

6. The method of claim 5, further comprising: In a case where the target-related message matching model cannot output a compliance-related message matched with the second preset matching rule, modifying the related message to obtain a modified related message that satisfies the second preset matching rule; and Inputting the modified related message into the target-related message matching model again to output a compliance-related message matched with the second preset matching rule.

7. The method of claim 1, wherein, After the real-time recording platform records the query message processing flow and related index parameters in real time, the method further comprises: In response to the query message processing flow, starting a query message analysis task to obtain a query message analysis result; and Based on the query message analysis result, generating a summary text of the query message analysis result.

8. The method of claim 1, wherein, The related index parameters include at least one of the following: an agency parameter, a time parameter, a state parameter, a quantity parameter, a warning parameter and a non-compliance parameter.

9. A query message processing device applied to a server of an agency, comprising: A first receiving module for receiving a query message sent by a first peer agency; A first generating module for generating an assembled query message based on the query message, a first preset matching rule and a first preset assembly rule, comprising: A first output sub-module for inputting the query message into a target query message matching model to output a compliance query message matched with the first preset matching rule, wherein the first preset matching rule is set according to the structural element rule of the query message; A first assembly sub-module for assembling the compliance query message based on the compliance query message and a first preset assembly rule to generate an assembled query message, wherein the first preset assembly rule is a rule for assembling according to the business type and the message element; A first sending module for sending the assembled query message to a second peer agency, wherein the second peer agency is a remittance agency; A second receiving module for receiving a related message sent by the second peer agency in response to the assembled query message; A first receiving module for receiving a query message sent by a first peer agency; a second generation module, configured to generate an assembled associated message based on the associated message, a second preset matching rule and a second preset assembly rule, the second preset matching rule being set according to a structural element rule of the associated message, and the second preset assembly rule being a rule for assembling message elements of the associated message; and a second sending module, configured to send the assembled associated message to the first same industry institution. The device further comprises: a recording module, configured to, after the assembled associated message is sent to the first same industry institution, record a query message processing flow and related index parameters in real time by using a real-time recording platform, the processing flow including a processing flow of compliant and non-compliant query messages and associated messages. 10.An electronic device, comprising: one or more processors; a storage device for storing one or more programs, wherein the one or more programs, when executed by the one or more processors, enable the one or more processors to perform the method according to any one of claims 1-8. 11.A computer-readable storage medium having stored thereon executable instructions that, when executed by a processor, cause the processor to perform the method according to any one of claims 1-8. 12.A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-8.

Images