Query service processing method, system, device, equipment, medium and product

Abstract

The application relates to a query service processing method, system, device, equipment, medium and product. The method comprises the following steps: in response to a processing request of a to-be-queried service sent by a target organization, acquiring a query label of the to-be-queried service; determining an optimal query and reply label link of the to-be-queried service according to the query label, the target organization and a preset historical service query message database; generating a query and reply message of the to-be-queried service through the optimal query and reply label link, and sending the query and reply message to the target organization; wherein the historical service query message database stores query labels of query services of multiple organizations. The method can improve the query service processing efficiency, and the query and reply message is automatically generated and sent, the number of message interactions of the query service is reduced, and the query service processing efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of big data technology, and in particular to a query business processing method, system, device, equipment, medium and product. Background Technology

[0002] Inquiry services are a common business between banking institutions, and they are mainly implemented in the form of message transmission.

[0003] Taking cross-border inquiry scenarios as an example, in related technologies, the response to cross-border inquiries between banking institutions involves business personnel manually identifying the English semantics within the received inquiry messages, or manually judging the results based on standard phrases used in cross-border regulations. Afterwards, the personnel manually process the response within the system to complete the reply to the inquiry message. However, since different banking institutions may have non-native English speakers, this can lead to repeated confirmations and communications due to differing understandings of the same issue, resulting in a single inquiry requiring multiple interactions to complete a response.

[0004] Therefore, the methods for handling cross-border query business in related technologies have problems such as long processing flow and many message exchanges, resulting in low query business processing efficiency. Summary of the Invention

[0005] Therefore, it is necessary to provide a query business processing method, apparatus, equipment, medium, and product to address the aforementioned technical problems.

[0006] Firstly, this application provides a query business processing method, which includes:

[0007] In response to the processing request for the query business sent by the target institution, obtain the query tag of the query business;

[0008] Based on the query tags, target institutions, and a pre-set historical business query message database, the optimal query and response tag link for the business to be queried is determined; the historical business query message database stores query tags for query businesses of multiple institutions.

[0009] The query and reply message for the business to be queried is generated through the optimal query and reply tag link, and then sent to the target organization.

[0010] In one embodiment, obtaining the query tag of the service to be queried includes:

[0011] Extract the full message information from the query business; the full message information includes at least the sending organization, receiving organization, and remarks information of the query business;

[0012] Based on the full information of the message, generate query tags for the business to be queried.

[0013] In one embodiment, a query tag for the service to be queried is generated based on the full information of the message, including:

[0014] The query purpose of the business to be queried is obtained from the remarks information in the full message information;

[0015] Determine the query tags based on the purpose of the query.

[0016] In one embodiment, determining the query tag based on the query purpose of the service to be queried includes:

[0017] Perform semantic recognition processing on the query purpose to obtain the semantic recognition result;

[0018] Based on the mapping relationship between semantics and standardized phrases, determine the target standardized phrase corresponding to the query purpose;

[0019] Based on the mapping relationship between standardized phrases and tags, the tags corresponding to the target standardized phrases are determined as query tags.

[0020] In one embodiment, the optimal query and response tag link for the service to be queried is determined based on the query tag, the target organization, and preset historical business query message data, including:

[0021] Based on the query tag and the target organization, multiple candidate query response tag links are extracted from the historical business query message database; the candidate query response tag link represents the link associated with the query tag and belonging to the query response message of the target organization.

[0022] Select the optimal query response tag link from multiple candidate query response tag links.

[0023] In one embodiment, selecting the optimal query response tag link from multiple candidate query response tag links includes:

[0024] The tag that appears most frequently in the query response tag chain of multiple candidate queries is used as the target tag;

[0025] The optimal number of interaction nodes in the link is determined based on the number of tags in each candidate query response tag link.

[0026] Among multiple candidate query response tag links, the link that contains the target tag and has the number of interaction nodes equal to the number of interaction nodes in the optimal link is determined as the optimal query response tag link.

[0027] In one embodiment, the optimal query and response tag link includes at least one optimal query and response tag link;

[0028] Then, the query and response message for the queried business is generated through the optimal query and response tag link, including:

[0029] Generate query and response content based on the correlation between tags in each optimal query and response tag chain;

[0030] Based on the remaining information and reply content in the full message information of the query business, excluding the query purpose of the query business, a reply message is generated.

[0031] In one embodiment, query content is generated based on the correlation between tags in each optimal query-response tag chain, including:

[0032] Obtain the number of times each tag other than the first tag appears repeatedly in each optimal query response tag chain;

[0033] Tags that meet the preset requirement for the number of times a tag appears are designated as the first relevant tag of the first tag, and tags that do not meet the preset requirement are designated as the second relevant tag of the first tag.

[0034] Based on the query message corresponding to the first tag and the first related tag, generate the reply content and the query content of the second related tag;

[0035] Based on the responses and inquiries, generate a reply.

[0036] Secondly, this application also provides a query business processing system, which includes: a clearing system and a query business processing platform;

[0037] The clearing system is used to send the processing requests for the query business sent by the target institution to the query business processing platform;

[0038] The query business processing platform is used to determine the optimal query and response tag link for the business to be queried based on the query tag, target institution, and a preset historical business query message database. It then generates a response message for the business to be queried through the optimal query and response tag link and sends the response message to the clearing system. The historical business query message database stores query and response tags for query businesses of multiple institutions.

[0039] The clearing system is also used to send inquiry and response messages to the target institution.

[0040] In one embodiment, the query business processing platform includes a big data platform, a business management platform, and an artificial intelligence processing platform;

[0041] The clearing system is used to call the big data platform interface to send query messages to the big data platform, receive the full message information extracted from the query messages returned by the big data platform, and send the full message information to the business management platform.

[0042] The business management platform is used to extract the query purpose and receiving agency of the message to be queried from the full information of the message, as well as to determine the query tag corresponding to the query purpose, and send the receiving agency and query tag to the artificial intelligence processing platform;

[0043] The artificial intelligence processing platform is used to determine the optimal query and response tag link for the business to be queried based on query tags, target institutions, and historical business query message databases, and to generate a response message for the business to be queried through the optimal query and response tag link, and send the response message to the clearing system.

[0044] Thirdly, this application also provides a query service processing apparatus, which includes:

[0045] The tag acquisition module is used to obtain the query tags of the query business in response to the processing request sent by the target organization.

[0046] The link determination module is used to determine the optimal query and response tag link for the query business based on the query tag, the target institution, and the preset historical business query message database; the historical business query message database stores the query tags for query businesses of multiple institutions;

[0047] The message sending module is used to generate a query and reply message for the business to be queried through the optimal query and reply tag link, and send the query and reply message to the target organization.

[0048] Fourthly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the steps of the query business processing method described above.

[0049] Fifthly, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the query business processing method described above.

[0050] Sixthly, this application also provides a computer program product, which includes a computer program that, when executed by a processor, implements the steps of the query business processing method described above.

[0051] The aforementioned query service processing method, apparatus, equipment, medium, and product obtain the query tag of the query service to be queried based on the processing request of the query service sent by the target organization, and determine the optimal query and reply tag link of the query service to be queried based on the query tag, the target organization, and a preset historical business query message database. Then, a reply message of the query service to be queried is generated through the optimal query and reply tag link and sent to the target organization. The historical business query message database stores query tags of query services from multiple organizations. This method, by pre-constructing a historical business query message database, allows for the retrieval of the optimal query-response tag link from the database for each query request. This enables the generation of the optimal response content based on the optimal query-response tag link, achieving fully automated processing and response message generation upon receiving a query message. This shortens the query processing flow and maintains processing speed even with numerous message interactions, effectively addressing the low efficiency of query response processing. Furthermore, by directly obtaining the optimal query-response tag link based on the query tag, target organization, and the pre-built historical business query message database, and generating and sending the response message, the method further reduces the number of message interactions, thereby improving query processing efficiency. Attached Figure Description

[0052] Figure 1 This is an application environment diagram of a query business processing method in one embodiment;

[0053] Figure 2 This is a flowchart illustrating a query service processing method in one embodiment;

[0054] Figure 3 This is a flowchart illustrating a method for obtaining query tags in one embodiment;

[0055] Figure 4 This is a flowchart illustrating a method for generating query tags in one embodiment;

[0056] Figure 5 This is a flowchart illustrating a method for determining query tags in one embodiment;

[0057] Figure 6 This is a flowchart illustrating the method for determining the optimal query and response tag link in one embodiment;

[0058] Figure 7 This is a flowchart illustrating a method for generating candidate query response tags in one embodiment.

[0059] Figure 8 This is a flowchart illustrating the method for selecting the optimal query and response tag link in one embodiment;

[0060] Figure 9 This is a flowchart illustrating a method for generating a reply message in one embodiment;

[0061] Figure 10 This is a flowchart illustrating a method for generating query content based on tag relevance in one embodiment;

[0062] Figure 11 This is a flowchart illustrating the query service processing system in one embodiment;

[0063] Figure 12 This is a schematic diagram of a query service processing platform in one embodiment;

[0064] Figure 13 This is a flowchart illustrating a query service processing method in one embodiment;

[0065] Figure 14 This is a structural block diagram of a query service processing method apparatus in one embodiment;

[0066] Figure 15 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0068] It should be understood that the terms "first," "second," etc., used in the claims, specification, and drawings of this application are used to distinguish different objects, not to describe a specific order. The term "comprising" as used in the specification and claims of this application indicates the presence of a described feature, integral, step, operation, element, and / or component, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof. It should also be understood that the terminology used in the specification of this application is merely for the purpose of describing specific embodiments and is not intended to limit this application. As used in the specification and claims of this application, unless the context clearly indicates otherwise, the singular forms "a," "an," and "the" are intended to include the plural forms.

[0069] The query service processing method provided in this application embodiment can be applied to, for example, Figure 1The application environment shown includes a first server 120 and a second server 140, with the first server 120 communicating with the second server 140 via a network. The first server 120 refers to the server running on the target organization, which is the organization that needs to process the query request. The second server refers to the server of the processing organization that handles the query request from the target organization. For example, in practical applications, when the target organization needs to process a query request, its server sends the processing request to the processing organization's server, combined with... Figure 1 In this embodiment, the server of the target organization is the first server, and the server of the processing organization is the second server. The execution entity in this application is the second server, i.e., the server of the processing organization. Both the first server 120 and the second server 140 can be implemented using independent servers or a server cluster composed of multiple servers; this application embodiment does not limit this.

[0070] In one embodiment, such as Figure 2 As shown, a query service processing method is provided. This embodiment illustrates the application of this method to the aforementioned application environment. It is understood that this method can also be applied to terminals, and further to systems including terminals and servers, and implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0071] Step 220: In response to the processing request for the query business sent by the target institution, obtain the query tag of the query business.

[0072] The target institution refers to the institution that sends the query message. Optionally, the target institution may be a banking institution or other institution, and this application does not limit this. The business to be queried refers to the business that the target institution needs to query. For example, taking a banking institution as an example, the business to be queried may be a loan business to be queried, an investment business to be queried, or a savings business to be queried, and this application does not limit this.

[0073] The query tag represents a query identifier for a service to be queried, and it can be composed of characters, numbers, or a combination thereof. In practical applications, each query service can correspond to one query tag, multiple query services can correspond to one query tag, or one query service can correspond to multiple query tags. This application embodiment does not limit this.

[0074] Taking a query service corresponding to multiple query tags as an example, there are multiple interactions between each target institution and processing institution for a query service. Each interaction generates a query message, and each query message can correspond to a query tag. In this case, the number of queries corresponds to the number of interactions.

[0075] Regarding the method of obtaining query tags, in one embodiment, query tags can be tags formed after defining the query purpose in the query business.

[0076] In another embodiment, the query tag may also be a query tag formed according to standardized phrases specified in the specifications required to be followed by the target agency and the processing agency.

[0077] In another embodiment, a query tag library can be pre-established. This query tag library contains multiple pre-defined correspondences between query service representations and corresponding query tags. When the application receives a processing request for a query service from a target organization, the corresponding query tag can be directly searched in the query tag library. This can improve the efficiency of query tag acquisition. Furthermore, since the query tag library is built based on historical real data, obtaining the query tag for a query service by querying the query tag library can also ensure its accuracy.

[0078] Step 240: Determine the optimal query and response tag link for the business to be queried based on the query tag, the target institution, and the preset historical business query message database; the historical business query message database stores the query tags for query businesses of multiple institutions.

[0079] The historical business query message database may include different target organizations, query messages for different business queries corresponding to each target organization, query tags corresponding to each query message, and query-response tag links corresponding to each query tag.

[0080] The query and response tag chain refers to the chain that is automatically executed when processing each query service. Naturally, the optimal query and response tag chain can be understood as the best processing chain when processing a query service. Therefore, for each query service, its optimal query and response tag chain can be obtained from the historical business query message database based on its query tag.

[0081] It should be understood that each query service may correspond to one optimal query and response tag link or multiple optimal query and response tag links, and this application embodiment does not limit this.

[0082] Optionally, taking a query service corresponding to multiple query tags as an example, assuming there are three interactions in the query service, and the corresponding query tags obtained from the query messages of each interaction are A, B, and C, then these query tags can be associated to form a query and response message chain belonging to the query service of the target organization.

[0083] Optionally, multiple candidate query response tag links can be extracted from the historical business query message database based on the query tag and the target organization. The candidate query response tag link represents the link associated with the query tag and belonging to the query response message of the target organization. The optimal query response tag link is selected from the multiple candidate query response tag links.

[0084] Step 260: Generate a query and reply message for the business to be queried through the optimal query and reply tag link, and send the query and reply message to the target institution.

[0085] After determining the optimal query-response tagging link, the query and response process is carried out according to this optimal link until a response message is obtained. The response message refers to the final reply information generated after processing the query message sent by the target organization.

[0086] Based on the confirmed reply message, the processing of the query business can be completed by sending the reply message to the target organization. This can be done either by sending the reply message directly to the target organization after confirmation, or by waiting for a request from the target organization and then using the confirmed reply message as the response information feedback value based on that request.

[0087] In one embodiment, the method of generating a query response message for the service to be queried through the optimal query response tag link can be to obtain the correlation between tags in the optimal query response tag link and generate a query response message based on the correlation.

[0088] In another embodiment, a service query and response network model can be pre-trained. This model can be trained using a large amount of historical data and is specifically designed to generate query and response messages for query services. In application, the optimal query and response tag link for the service to be queried can be input into this service query and response network model, which can then directly output the query and response message for that service.

[0089] In the query service processing method of this application embodiment, the query tag of the query service to be queried is obtained according to the processing request of the query service sent by the target institution. The optimal query-response tag link for the query service to be queried is determined based on the query tag, the target institution, and a pre-set historical business query message database. Then, a response message for the query service to be queried is generated through the optimal query-response tag link and sent to the target institution. The historical business query message database stores query tags for query services from multiple institutions. Because the historical business query message database is pre-built, for each query service processing request, only its query tag needs to be obtained to retrieve its optimal query-response tag link from the historical business query message database. This allows for the generation of the optimal response content based on the optimal query-response tag link, achieving fully automated processing and response message generation after receiving the query message. This shortens the query service processing flow and does not affect the processing progress even with a large number of message interactions, effectively solving the problem of low efficiency in query message response processing. Meanwhile, based on query tags, target institutions, and a pre-set historical business query message database, the optimal query and reply tag link can be directly obtained, and a reply message can be generated and sent, further reducing the number of message interactions in the query business and thus further improving the efficiency of query business processing.

[0090] Figure 3 This is a flowchart of step 220 in the above embodiment. The method for obtaining the query tags of the service to be queried in this embodiment is as follows: Figure 3 As shown, the query business processing method includes steps 222 to 224, wherein,

[0091] Step 222: Extract the full message information from the business to be queried; the full message information includes at least the sending organization, receiving organization, and remarks information of the business to be queried.

[0092] The full message information refers to the information of all elements of each query message in the query business. For example, it includes at least the sending organization, receiving organization, and remarks information of the query business.

[0093] In this context, the sending agency refers to the sender of the query message, the receiving agency refers to the receiver of the query message, and the remarks information refers to the valid information, supplementary information, etc., contained in the query message.

[0094] For example, the remarks information refers to the remarks section in the inquiry message given to the collection agency, which may include: the currency of the original payment message, the payee of the original payment message, the payer of the original payment message, the amount of the original payment message, the interest accrual date of the original payment message, the identification number of the original payment message, the submission date of the original payment message, the interest accrual date of the original payment message, and the purpose of the inquiry message.

[0095] Taking cross-border fund inquiry and reply services as an example, the full information of the message includes not only the sending institution, the receiving institution, and the remarks, but also elements such as the remitter, currency, payee, receiving bank, reporting bank, and interest accrual date.

[0096] Specifically, one way to extract full information from a query message is to obtain all query messages sent by the target organization in the query message, split each query message into its elements, extract the required elements, and combine these elements into full information to obtain the full information of the query message.

[0097] Step 224: Generate query tags for the business to be queried based on the full information of the message.

[0098] Specifically, when generating query tags for a service to be queried based on the full message information, the full message information can be processed. For example, summary information can be generated based on key information in the full message information, and query tags can be generated based on the processing result. Alternatively, generating query tags for a service to be queried based on the full message information can reveal the query purpose of the service to be queried, and the query tags can be determined based on the query purpose. This application does not limit the specific method for generating query tags for a service to be queried.

[0099] In this embodiment, by extracting the full information of the message to be queried and generating query tags for the message based on the full information, the problem of invalid results generated during data processing occupying storage space can be solved, data processing time can be shortened, and thus the efficiency of query processing can be improved.

[0100] In one embodiment, such as Figure 4 As shown, the method for generating query tags for the service to be queried includes steps 420 to 440, wherein,

[0101] Step 420: Obtain the query purpose of the business to be queried based on the remarks information in the full message information.

[0102] This embodiment illustrates how to obtain the query purpose of a business request based on the appendix information in the full message. Specifically, the query purpose can be extracted by breaking down the elements in the appendix information. While the appendix information contains numerous elements, in practical applications, only a few elements are needed to retrieve the query result. Breaking down and extracting these elements solves the problem of invalid results generated during data processing occupying storage space, shortens data processing time, and improves the efficiency of query business processing.

[0103] Step 440: Determine the query tags based on the query purpose of the business to be queried.

[0104] Optionally, one possible way to determine the query tag based on the query purpose of the business to be queried is to determine the target standardized phrase corresponding to the query purpose based on the mapping relationship between semantics and standardized phrases; and to determine the tag corresponding to the target standardized phrase as the query tag based on the mapping relationship between standardized phrases and tags.

[0105] Then as Figure 5 As shown, the method for determining query tags based on the query purpose of the business to be queried includes steps 442 to 446, wherein,

[0106] Step 442: Perform semantic recognition processing on the query purpose to obtain the semantic recognition result.

[0107] Semantic recognition processing is a natural language processing technique. Optionally, it can be lexical analysis, syntactic analysis, pragmatic analysis, or contextual analysis; this application does not limit this. Specifically, it can involve analyzing the query purpose field of the appendix information in the query message and then recognizing it to obtain the semantic recognition result, so as to facilitate the semantics required for subsequent applications.

[0108] For example, taking cross-border clearing inquiry and response business as an example, in this scenario, if the inquiry message is in English, the purpose of the inquiry message can be:

[0109] WE HAVE FORWARDED YOUR QUERY FOR THE PAYMENT REFER-ENCE 204413171 TOTH E REMITTING PARTY HSBCHKHHHKH,WE WILL KEEP YOU INFORMED ONCE WE RECEIVE ARESPONSE.

[0110] Then, semantic recognition processing is performed on the query purpose to obtain three sets of recognition results: “FORWARDED YOUR QUERY”, “KEEP”, and “INFORMED”. These are the semantic recognition results of the query purpose.

[0111] Step 444: Based on the mapping relationship between semantics and standardized phrases, determine the target standardized phrase corresponding to the query purpose.

[0112] Specifically, the semantics obtained from semantic recognition are mapped to standardized phrases. Since a standardized phrase has only one unique semantics, there is a one-to-one correspondence between the semantics and the standardized phrases. This allows for the accurate acquisition of the standardized phrase corresponding to the query objective, and the standardized phrase is then identified as the target standardized phrase.

[0113] The standardized phrases are those specified in the guidelines that the target and processing agencies must follow.

[0114] For example, taking cross-border clearing inquiry and reply business as an example, in this scenario, if the inquiry and reply message is in English, the correspondence between semantics and standardized phrases is shown in Table 1 below.

[0115] Table 1

[0116]

[0117]

[0118] In Table 1 above, except for NARR, each standardized phrase has a unique meaning. The phrase interpretation can be directly retrieved based on its meaning, and the message can be further defined to form a query tag.

[0119] Step 446: Based on the mapping relationship between standardized phrases and tags, determine the tags corresponding to the target standardized phrases as query tags.

[0120] Specifically, the target standardized phrases and tags are mapped to obtain a one-to-one correspondence between the tags and the target standardized phrases. Therefore, the standardized phrases corresponding to the tags can be accurately obtained. The target standardized phrases are then mapped to the tags, and the resulting tags are determined as query tags.

[0121] For example, taking cross-border clearing inquiry and response business as an example, the final determined inquiry tags could be "Incoming Remittance Status Inquiry," "Refunded Remittance Status Inquiry," "Modification Wire Acceptance Notice," "Provide Payment Instruction Information," "Provide Compliance Information," "Incoming Remittance Application for Refund / Cancellation," "Incoming Remittance Application for Refund / Cancellation (Urgent)," "Debit Account Notification," "Credit Account Notification," "Fee Claim Wire," "Document Business Related Messages," "Payment Instruction Information Inquiry," "Compliance Information Inquiry," "Reassurance Wire," "Outgoing Remittance Confirmation Cancellation," etc. The above is only an example of one scenario, and the scenarios or businesses applicable to the embodiments of this application are not limited to this.

[0122] In this embodiment, since the target standardized phrase and the query tag have a unique correspondence, and a standardized phrase has only a unique semantic meaning, the query tag and the semantic meaning have a one-to-one correspondence. At the same time, the semantic meaning is obtained from the query purpose, so the query tag and the query purpose also have a one-to-one correspondence. However, the query purpose is extracted from the query purpose, so the query tag and the query message also have a one-to-one correspondence. Therefore, the query message corresponding to the query tag can be accurately obtained, which further improves the efficiency of query business processing.

[0123] Figure 6This is a flowchart of step 240 in the above embodiment. The method for determining the optimal query and response tag link for the service to be queried in this embodiment is as follows: Figure 6 As shown, the method for determining the optimal query and response tag link for the service to be queried includes steps 242 to 244, wherein,

[0124] Step 242: Based on the query tag and the target organization, extract multiple candidate query response tag links from the historical business query message database. The candidate query response tag link represents the link associated with the query tag and belonging to the query response message of the target organization.

[0125] Specifically, when a target organization queries a specific service and sends a query message, due to the presence of non-English speaking languages, it will repeatedly query and reply to this service until no new related responses or replies are found. Since each query message carries a unique query tag, these mutual message replies form a query-reply tag chain, which is stored in the historical service query message database. Furthermore, multiple query-reply tag chains may exist for the same service from the same organization; these chains are designated as candidate query-reply tag chains.

[0126] For example, such as Figure 7 As shown, assume the target institution is a bank and the retrieval institution is the processing institution:

[0127] The processing unit receives a query message from a bank regarding a status query, obtains the query tag A from the query message, manually replies with a response to the query message with query tag A, generates a reply message and sends it, marking the reply message as A'. There is a one-to-one correspondence between query tag A and reply message A'. The bank then queries and replies with a query message with query tag B (referred to as query message B) in response to the reply message with reply message A'. The processing unit manually replies with a reply message with reply message B' in response to query message B. The bank then queries and replies with a query message with query tag C (referred to as query message C) in response to the reply message with reply message B'. The processing unit manually replies with a reply message with reply message C' in response to query message C. At this point, no further related responses are received, and the interaction ends, thus forming a query-reply tag chain. This link is historical data, stored in the historical business query message database, and can be used as a candidate query response label link. The overall query response label link is A-A'-B-B'-C-C', and can be further divided into other classification methods such as query response label links ABC (only for query messages) and query response label links A'-B'-C' (only for response messages).

[0128] Step 244: Select the optimal query response tag link from multiple candidate query response tag links.

[0129] Specifically, the tag that appears most frequently in multiple candidate query response tag links is obtained as the target tag. The optimal number of interaction nodes for each link is determined based on the number of tags in each candidate query response tag link. The link that contains the target tag and has the number of interaction nodes equal to the optimal number of interaction nodes is determined as the optimal query response tag link.

[0130] In this embodiment, the optimal query and response tag link can be directly obtained based on query tags, target institutions, and a preset historical business query message database. This query and response tag link is based on historical experience, which makes the subsequent generated query and response messages more accurate in responding to the query content, minimizes the number of interactions in actual applications, and further improves the efficiency of query business processing.

[0131] Figure 8 This is a flowchart of step 244 in the above embodiment. The method for filtering the optimal query and response tag link in this embodiment is as follows: Figure 8 As shown, the method for selecting the optimal query and response tag link includes steps 244a to 244c, wherein,

[0132] Step 244a: Obtain the tag that appears most frequently in the multiple candidate query response tag links as the target tag.

[0133] Step 244b: Determine the optimal number of interaction nodes for each link based on the number of tags in each candidate query response tag link.

[0134] One method to determine the optimal number of link interaction nodes is to take the median.

[0135] Step 244c: Among the multiple candidate query response tag links, the link that contains the target tag and whose number of interaction nodes is equal to the number of interaction nodes of the optimal link is determined as the optimal query response tag link.

[0136] Among them, there is at least one optimal query response tag link.

[0137] For example, assuming the method for determining the optimal number of link interaction nodes is to take the median, and the query message with query label A is denoted as A, then the multiple candidate query response label links for the query message are "ABC", "ACD", "ACRES" and "AF".

[0138] If query tag C appears most frequently across multiple candidate query response tag links, then query tag C will be selected as the target tag. Furthermore, if the median number of query response tag link interactions is 3, then the optimal query response tag links for the query message are "ABC" and "ACD".

[0139] In this embodiment, the method for selecting the optimal query and reply tag link is determined based on the number of tags and the number of interaction nodes in the overall link. This effectively reflects the target organization's query content preferences, making the subsequent generated query and reply messages more accurate in responding to the query content. It also minimizes the number of interactions in actual applications and improves the efficiency of query business processing.

[0140] Figure 9 This is a flowchart of step 260 in the above embodiment. The method for generating the query response message for the service to be queried in this embodiment is as follows: Figure 9 As shown, the method for generating a query response message for the service to be queried includes steps 262 to 264, wherein,

[0141] Step 262: Generate the query content based on the correlation between tags in each optimal query query tag link.

[0142] Specifically, the number of times each tag other than the first tag appears in each optimal query-response tag link is obtained. Tags whose number of times they appear meets the preset requirements are designated as the first related tags of the first tag, and tags whose number of times they do not meet the preset requirements are designated as the second related tags of the first tag. Based on the query-response messages corresponding to the first tag and the first related tags, the response content and the query content of the second related tags are generated. Based on the response content and the query content, the query-response content is generated.

[0143] Step 264: Generate a query reply message based on the remaining information and reply content in the full message information of the query business, excluding the query purpose of the query business.

[0144] Specifically, the content of the reply is included as the remarks part of the reply message. Based on the remaining information in the full message information of the business to be queried, excluding the purpose of the query, the reply message is generated and sent to the target organization.

[0145] In this embodiment, the query and reply content is generated based on the correlation between tags in each optimal query and reply tag link, and then the query and reply message is generated. This makes the generated query and reply content more targeted and minimizes the number of interactions in actual applications. At the same time, having machines replace manual query and reply can further improve the efficiency of query business processing.

[0146] Figure 10This is a flowchart of step 262 in the above embodiment. This embodiment describes the method for generating query content based on tag relevance. For example... Figure 10 As shown, the method for generating query and reply content based on tag relevance includes steps 262a to 262d, wherein,

[0147] Step 262a: Obtain the number of times each tag other than the first tag appears repeatedly in each optimal query response tag link.

[0148] Step 262b: Labels whose repetition frequency meets the preset requirement are designated as the first related labels of the first label, and labels that do not meet the preset requirement are designated as the second related labels of the first label.

[0149] One of the preset requirements is that the tag appears the most times.

[0150] Step 262c: Based on the query message corresponding to the first tag and the first related tag, generate the reply content and the query content of the second related tag.

[0151] Step 262d: Generate the reply content based on the response and inquiry content.

[0152] For example, assuming the preset requirement is that the tag appears the most times, and a query message with query tag A is denoted as A, then the optimal query response tag chain for the query message only is "ABC" or "ACD":

[0153] Therefore, query tag C is the most frequently occurring tag besides query tag A (i.e., the first tag in each optimal query response tag chain) (i.e., it meets the preset requirement). Thus, query tag C is the first relevant tag, and query tags B and D are the second relevant tags. Therefore, the response content A' for query tag A and the response content C' for query tag C are concatenated to generate the reply content. Simultaneously, query content for query tags B and D is generated, and the reply content and the query content are concatenated to generate the response content.

[0154] In this embodiment, the number of times a tag appears repeatedly is obtained from the optimal query and response tag link, and the tag correlation is used to generate the response content. This allows for more targeted responses to the query message. At the same time, setting the query content also enables subsequent query tag extraction and responses to the re-query message for the query business, thereby forming a complete query business processing flow, replacing manual processing of query business, and further improving the efficiency of query business processing.

[0155] In one embodiment, such as Figure 11As shown, a query business processing system is provided. In this embodiment, the system includes: a clearing system 1120 and a query business processing platform 1140.

[0156] The clearing system 1120 is used to send the processing request for the query business sent by the target institution to the query business processing platform;

[0157] The query business processing platform 1140 is used to determine the optimal query and reply tag link for the business to be queried based on the query tag, the target institution, and the preset historical business query message database, and to generate a reply message for the business to be queried through the optimal query and reply tag link and send the reply message to the clearing system; the historical business query message database stores query and reply tags for query businesses of multiple institutions.

[0158] The clearing system 1120 is also used to send inquiry and reply messages to the target institution.

[0159] In the aforementioned query service processing system, the clearing system is used to send the processing request for the query service sent by the target institution to the query service processing platform; the query service processing platform is used to determine the optimal query and reply tag link for the query service based on the query tag, the target institution, and the preset historical business query message database, and to generate a reply message for the query service through the optimal query and reply tag link, and send the reply message to the clearing system; the historical business query message database stores query and reply tags for query services of multiple institutions; the clearing system is also used to send reply messages to the target institution.

[0160] In practical applications, due to the presence of non-English-speaking countries among different banking institutions, traditional methods rely on manual semantic recognition and result judgment upon receiving query messages. This inevitably leads to repeated confirmations and communications between different institutions based on differing interpretations of the same question, requiring multiple interactions to complete a single query response, resulting in low query processing efficiency. This application addresses this by semantically recognizing the query purpose in the query message's remarks. The query tags are determined through the mapping relationship between semantic recognition results, standardized phrases, and query tags, replacing the potential misunderstandings inherent in manual semantic recognition and improving query processing efficiency. Furthermore, based on query tags, target institutions, and a pre-defined historical query message database, the optimal query-response tag link can be directly obtained, and a response message can be generated and sent, further reducing the number of message interactions in the query process and thus further improving query processing efficiency.

[0161] Figure 12This is a schematic diagram of the architecture of the query business processing platform 1140 in the above embodiment. The query business processing platform in this embodiment includes a big data platform 1142, a business management platform 1144, and an artificial intelligence processing platform 1146, wherein...

[0162] The clearing system 1120 is used to call the interface of the big data platform 1142 to send the query message to the big data platform 1142, receive the full message information extracted from the query message returned by the big data platform 1142, and send the full message information to the business management platform 1144.

[0163] The business management platform 1144 is used to extract the query purpose and receiving agency of the message to be queried from the full information of the message, as well as to determine the query tag corresponding to the query purpose, and send the receiving agency and query tag to the artificial intelligence processing platform 1146.

[0164] The artificial intelligence processing platform 1146 is used to determine the optimal query and reply tag link for the business to be queried based on the query tag, target institution and historical business query message database, and generate a reply message for the business to be queried through the optimal query and reply tag link, and send the reply message to the clearing system 1120.

[0165] In this embodiment, the query message contains numerous elements. However, in practical applications, only a few elements are needed to perform a query response. By splitting and separating these elements and extracting the full amount of information, the problem of invalid information generating invalid results that occupy storage space and increase data processing time can be solved. At the same time, based on the query tag, target organization, and preset historical business query message database, the optimal query response tag link can be directly obtained, and a response message can be generated and sent, further reducing the number of message interactions in the query business and thus further improving the efficiency of query business processing.

[0166] In one specific embodiment, such as Figure 13 As shown, a query business processing method is provided, including:

[0167] Step 1300: In response to the processing request for the query service sent by the target organization, extract the full message information from the query service; the full message information includes at least the sending organization, receiving organization, and remarks information of the query service.

[0168] Assume the target institution is a bank, the receiving institution is a processing institution, and the query is for the status of a specific inflow. Specifically, the processing institution's clearing system responds to the bank's processing request by receiving a query message from the bank requesting a status check on the inflow. Simultaneously, it calls the big data platform interface to send the query message to the big data platform. The big data platform receives the query message, breaks it down into its constituent elements, extracts the necessary elements, and assembles these elements into complete information. The clearing system receives the complete message information extracted from the query message from the big data platform and sends this complete message information to the business management platform.

[0169] Step 1302: Obtain the query purpose of the business to be queried based on the remarks information in the full message information.

[0170] The business management platform performs element breakdown based on the remarks information in the full message information, and extracts the query purpose from them.

[0171] Step 1304: Perform semantic recognition processing on the query purpose to obtain the semantic recognition result.

[0172] The business management platform performs field analysis on the query purpose of the remarks in the query message and then identifies it to obtain the semantic recognition result.

[0173] Step 1306: Based on the mapping relationship between semantics and standardized phrases, determine the target standardized phrase corresponding to the query purpose.

[0174] The business management platform maps the semantics obtained from semantic recognition to standardized phrases. Since a standardized phrase has only one unique semantics, there is a one-to-one correspondence between the semantics and the standardized phrase. This allows the platform to accurately obtain the standardized phrase corresponding to the query purpose and identify the standardized phrase as the target standardized phrase.

[0175] Step 1308: Based on the mapping relationship between standardized phrases and tags, the tag corresponding to the target standardized phrase is determined as the query tag.

[0176] The business management platform maps target standardized phrases and tags to obtain a one-to-one correspondence between tags and target standardized phrases. Therefore, it can accurately obtain the standardized phrase corresponding to the tag and determine the tag as the query tag. The business management platform sends the receiving agency and query tag to the artificial intelligence processing platform.

[0177] Step 1310: Based on the query tag and the target organization, extract multiple candidate query response tag links from the preset historical business query message database; the candidate query response tag link represents the link associated with the query tag and belonging to the query response message of the target organization; the historical business query message database stores the query tags of the query business of multiple organizations.

[0178] Let A be the query message with query tag A. Then, the AI ​​processing platform extracts multiple candidate query response tag links from the preset historical business query message database based on the query tag and the target organization as “ABC”, “ACD”, “ACRES”, and “AF”.

[0179] Step 1312: Obtain the tag that appears most frequently in the multiple candidate query response tag links as the target tag.

[0180] Let A be the query message with query tag A. If the multiple candidate query response tag links are “ABC”, “ACD”, “ACRES”, and “AF”, then the tag that appears most frequently is query tag C. The artificial intelligence processing platform will then use query tag C as the target tag.

[0181] Step 1314: Determine the optimal number of interaction nodes in the link based on the number of tags in the candidate query reply tag link;

[0182] Assuming the method for determining the optimal number of link interaction nodes is to take the median, let the query message with query label A be denoted as A. Then, the multiple candidate query reply label links are “ABC”, “ACD”, “ACRES”, and “AF”. The median number of query reply label link interactions is 3. Therefore, the artificial intelligence processing platform obtains the optimal number of link interaction nodes as 3.

[0183] Step 1316: Among the multiple candidate query response tag links, the link that contains the target tag and whose number of interaction nodes is equal to the number of interaction nodes of the optimal link is determined as the optimal query response tag link.

[0184] The method to determine the optimal number of interaction nodes in the link is to take the median. Let the query message with query label A be denoted as A. Then, the multiple candidate query reply label links are “ABC”, “ACD”, “ACRES”, and “AF”. Then, the query label C appears the most times in the multiple candidate query reply label links. So, the query label C is taken as the target label. And, the number of interaction nodes in the query reply label link is 3, which is the median. Therefore, the optimal query reply label links obtained by the artificial intelligence processing platform are “ABC” and “ACD”.

[0185] Step 1318: If the optimal query and response tag link includes at least one optimal query and response tag link, then obtain the number of times the other tags, excluding the first tag, appear repeatedly in each optimal query and response tag link.

[0186] The AI ​​processing platform is pre-set to require the tag to appear the most times. Query messages with query tag A are denoted as A, and the optimal query response tag links are “ABC” and “ACD”. The number of times each tag other than the first tag appears in each optimal query response tag link is 2.

[0187] Step 1320: Labels whose repetition frequency meets the preset requirement are designated as the first related labels of the first label, and labels that do not meet the preset requirement are designated as the second related labels of the first label.

[0188] The AI ​​processing platform has a preset requirement that the tag should appear the most times. Let A be the query message with query tag A. The optimal query response tag link is “ABC” and “ACD”. Then, query tag C is the tag that appears the most times besides query tag A (i.e. the first tag in each optimal query response tag link) (i.e., it meets the preset requirement). Therefore, query tag C is the first relevant tag, and query tags B and D are the second relevant tags.

[0189] Step 1322: Based on the query message corresponding to the first tag and the first related tag, generate the reply content and the query content of the second related tag;

[0190] Suppose that the first relevant tag obtained by the artificial intelligence processing platform is query tag C, and the second relevant tags are query tag B and query tag D. Then, the corresponding query content A' for query tag A and the corresponding query content C' for query tag C will be concatenated to generate the reply content. At the same time, query content for query tags B and query tag D will be generated.

[0191] Step 1324: Generate the reply content based on the response and inquiry content.

[0192] The AI ​​processing platform combines the response content A' for query tag A and the response content C' for query tag C to generate the reply content, and combines the query content for query tags B and D to generate the response content.

[0193] Step 1326: Generate a query reply message based on the remaining information and reply content in the full message information of the query business, excluding the query purpose of the query business.

[0194] The AI ​​processing platform generates a response message based on the remaining information and response content in the full message of the query business, excluding the query purpose, and sends the response message to the clearing system. The clearing system then sends the response message to the target institution.

[0195] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some of the steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least a portion of the steps or stages of other steps.

[0196] In one embodiment, such as Figure 14 As shown, a query service processing device 1400 is provided, including: a tag acquisition module 1402, a link determination module 1404, and a message sending module 1406, wherein:

[0197] The tag acquisition module 1402 is used to acquire the query tag of the query service in response to the processing request of the query service sent by the target organization.

[0198] The link determination module 1404 is used to determine the optimal query and response tag link for the query business based on the query tag, the target institution, and the preset historical business query message database; the historical business query message database stores the query tags for query businesses of multiple institutions.

[0199] The message sending module 1406 is used to generate a query and reply message for the service to be queried through the optimal query and reply tag link, and send the query and reply message to the target organization.

[0200] In one embodiment, the tag acquisition module 1402 includes:

[0201] The full information extraction unit extracts the full information of the message from the business to be queried; the full information of the message includes at least the sending organization, receiving organization, and remarks information of the business to be queried;

[0202] The query tag generation unit generates query tags for the business to be queried based on the full information of the message.

[0203] In one embodiment, the query tag generation unit includes:

[0204] The query purpose acquisition sub-unit obtains the query purpose of the business to be queried based on the remarks information in the full message information;

[0205] The query tags are used to obtain sub-units, and the query tags are determined based on the query purpose of the business to be queried.

[0206] In one embodiment, querying the tag to determine the subunit includes:

[0207] The semantic recognition subunit performs semantic recognition processing on the query purpose to obtain the semantic recognition result;

[0208] The target standardized phrase determination subunit is based on the mapping relationship between semantics and standardized phrases to determine the target standardized phrase corresponding to the query purpose;

[0209] The query tag determines the sub-unit. Based on the mapping relationship between standardized phrases and tags, the tag corresponding to the target standardized phrase is determined as the query tag.

[0210] In one embodiment, the link determination module 1404 includes:

[0211] The candidate link extraction unit extracts multiple candidate query response tag links from the historical business query message database based on the query tag and the target organization; the candidate query response tag link represents the link associated with the query tag and belonging to the query response message of the target organization.

[0212] The optimal link filtering unit filters the optimal query response tag link from multiple candidate query response tag links.

[0213] In one embodiment, the optimal link filtering unit includes:

[0214] The target tag acquisition sub-unit retrieves the tag that appears most frequently in the query response tag chain among multiple candidate tags as the target tag;

[0215] The node number determination subunit determines the optimal number of interactive nodes in the link based on the number of tags in each candidate query reply tag link.

[0216] The optimal link determination subunit identifies the link among multiple candidate query response tag links that contains the target tag and whose number of interaction nodes is equal to the number of interaction nodes of the optimal link as the optimal query response tag link.

[0217] In one embodiment, if the optimal query-response tag link includes at least one optimal query-response tag link; the message sending module 1406 includes:

[0218] The query response content generation unit generates query response content based on the correlation between tags in each optimal query response tag link;

[0219] The query and reply message generation unit generates a query and reply message based on the remaining information and reply content in the full information of the message of the query business, excluding the query purpose of the query business.

[0220] In one embodiment, if the optimal query-response tag link includes at least one optimal query-response tag link; the response message generation unit includes:

[0221] The tag count acquisition subunit acquires the number of times each tag, excluding the first tag, appears repeatedly in each optimal query response tag chain;

[0222] The related label setting sub-unit sets the first related label of the first label when the number of times the label appears meets the preset requirements, and sets the second related label of the first label when the number of times the label does not meet the preset requirements.

[0223] The response content generation subunit generates response content and query content for the second relevant tag based on the query message corresponding to the first tag and the first related tag.

[0224] The reply content generation sub-unit generates reply content based on the reply content and the inquiry content.

[0225] Specific limitations regarding the query processing device can be found in the limitations of the query processing method described above, and will not be repeated here. Each module in the aforementioned query processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in the computer device in hardware form, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each module.

[0226] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 15 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores query processing data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a query processing method.

[0227] Those skilled in the art will understand that Figure 15The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specifically, the computer device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements.

[0228] In one embodiment, a computer device is also provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0229] In response to the processing request for the query business sent by the target institution, obtain the query tag of the query business;

[0230] Based on the query tags, target institutions, and a pre-set historical business query message database, the optimal query and response tag link for the business to be queried is determined; the historical business query message database stores query tags for query businesses of multiple institutions.

[0231] The query and reply message for the business to be queried is generated through the optimal query and reply tag link, and then sent to the target organization.

[0232] In one embodiment, the processor obtains the query tags for the business to be queried, and performs the following steps when executing a computer program:

[0233] Extract the full message information from the query business; the full message information includes at least the sending organization, receiving organization, and remarks information of the query business;

[0234] Based on the full information of the message, generate query tags for the business to be queried.

[0235] In one embodiment, a query tag for the service to be queried is generated based on the full information of the message. When the processor executes the computer program, it performs the following steps:

[0236] The query purpose of the business to be queried is obtained from the remarks information in the full message information;

[0237] Determine the query tags based on the purpose of the query.

[0238] In one embodiment, the processor determines the query tag based on the query purpose of the business to be queried, and performs the following steps when executing the computer program:

[0239] Perform semantic recognition processing on the query purpose to obtain the semantic recognition result;

[0240] Based on the mapping relationship between semantics and standardized phrases, determine the target standardized phrase corresponding to the query purpose;

[0241] Based on the mapping relationship between standardized phrases and tags, the tags corresponding to the target standardized phrases are determined as query tags.

[0242] In one embodiment, based on the query tag, target institution, and preset historical business query message data, the optimal query and response tag link for the business to be queried is determined. When the processor executes the computer program, it implements the following steps:

[0243] Based on the query tag and the target organization, multiple candidate query response tag links are extracted from the historical business query message database; the candidate query response tag link represents the link associated with the query tag and belonging to the query response message of the target organization.

[0244] Select the optimal query response tag link from multiple candidate query response tag links.

[0245] In one embodiment, the processor, when executing a computer program, performs the following steps to select the optimal query response tag link from a plurality of candidate query response tag links:

[0246] The tag with the most occurrences in the query response tag chain among multiple candidate queries is used as the target tag;

[0247] The optimal number of interaction nodes in the link is determined based on the number of tags in each candidate query response tag link.

[0248] Among multiple candidate query response tag links, the link that contains the target tag and has the number of interaction nodes equal to the number of interaction nodes in the optimal link is determined as the optimal query response tag link.

[0249] In one embodiment, if the optimal query-response tag link includes at least one optimal query-response tag link, then a query-response message for the service to be queried is generated through the optimal query-response tag link, and the processor executes the following steps when executing the computer program:

[0250] Generate query and response content based on the correlation between tags in each optimal query and response tag chain;

[0251] Based on the remaining information and reply content in the full message information of the query business, excluding the query purpose of the query business, a reply message is generated.

[0252] In one embodiment, query content is generated based on the correlation between tags in each optimal query response tag chain. When the processor executes the computer program, it performs the following steps:

[0253] Obtain the number of times each tag other than the first tag appears repeatedly in each optimal query response tag chain;

[0254] Tags that meet the preset requirement for the number of times a tag appears are designated as the first relevant tag of the first tag, and tags that do not meet the preset requirement are designated as the second relevant tag of the first tag.

[0255] Based on the query message corresponding to the first tag and the first related tag, generate the reply content and the query content of the second related tag;

[0256] Based on the responses and inquiries, generate a reply.

[0257] In one embodiment, the query business processing system includes: a clearing system and a query business processing platform;

[0258] The clearing system is used to send the processing requests for the query business sent by the target institution to the query business processing platform;

[0259] The query business processing platform is used to determine the optimal query and response tag link for the business to be queried based on the query tag, target institution, and a preset historical business query message database. It then generates a response message for the business to be queried through the optimal query and response tag link and sends the response message to the clearing system. The historical business query message database stores query and response tags for query businesses of multiple institutions.

[0260] The clearing system is also used to send inquiry and response messages to the target institution.

[0261] In one embodiment, the query business processing platform includes a big data platform, a business management platform, and an artificial intelligence processing platform;

[0262] The clearing system is used to call the big data platform interface to send query messages to the big data platform, receive the full message information extracted from the query messages returned by the big data platform, and send the full message information to the business management platform.

[0263] The business management platform is used to extract the query purpose and receiving agency of the message to be queried from the full information of the message, as well as to determine the query tag corresponding to the query purpose, and send the receiving agency and query tag to the artificial intelligence processing platform;

[0264] The artificial intelligence processing platform is used to determine the optimal query and response tag link for the business to be queried based on query tags, target institutions, and historical business query message databases, and to generate a response message for the business to be queried through the optimal query and response tag link, and send the response message to the clearing system.

[0265] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon that, when executed by a processor, implements the steps in the above method embodiments.

[0266] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps in the above method embodiments.

[0267] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical storage, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0268] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0269] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A query business processing method, characterized in that, The method includes: In response to a processing request for a query service sent by a target organization, the query tag of the query service is obtained; Based on the query tags, the target organization, and a preset historical business query message database, the optimal query and response tag link for the business to be queried is determined; the historical business query message database stores query tags for the query businesses of multiple organizations and the query and response tag link corresponding to each query tag; wherein, one query and response tag link includes query tags corresponding to multiple query messages from multiple interactions between the target organization and the processing organization for a business to be queried; The query and reply message for the service to be queried is generated through the optimal query and reply tag link, and the query and reply message is sent to the target institution. The step of obtaining the query tags for the service to be queried includes: Extract the full message information from the query service; the full message information includes at least the sending organization, receiving organization, and remarks information of the query service. The query purpose of the service to be queried is obtained from the remarks information in the full message information; The query objective is subjected to semantic recognition processing to obtain the semantic recognition result; Based on the mapping relationship between semantics and standardized phrases, the target standardized phrase corresponding to the query purpose is determined; wherein, the standardized phrase is specified in the specifications that the target organization and the processing organization need to follow; Based on the mapping relationship between standardized phrases and tags, the tags corresponding to the target standardized phrases are determined as the query tags.

2. The method according to claim 1, characterized in that, The step of determining the optimal query and response tag link for the service to be queried based on the query tag, the target institution, and a preset historical business query message database includes: Based on the query tag and the target organization, multiple candidate query response tag links are extracted from the historical business query message database; the candidate query response tag link represents a link associated with the query tag and belonging to the query response message of the target organization; The optimal query response tag link is selected from the multiple candidate query response tag links.

3. The method according to claim 2, characterized in that, The step of selecting the optimal query response tag link from the plurality of candidate query response tag links includes: The query tag that appears most frequently in the multiple candidate query response tag links is taken as the target tag; The optimal number of interaction nodes for each link is determined based on the number of query tags in each candidate query response tag link. The link that contains the target tag and whose number of interaction nodes is equal to the number of interaction nodes of the optimal link among the multiple candidate query response tag links is determined as the optimal query response tag link.

4. The method according to claim 1, characterized in that, If the optimal query and response tag link includes at least one optimal query and response tag link; The step of generating the query response message for the service to be queried through the optimal query response tag link includes: The query content is generated based on the correlation between query tags in each optimal query and response tag link; The reply message is generated based on the remaining information in the full message information of the service to be queried, excluding the query purpose of the service to be queried, and the reply content.

5. The method according to claim 4, characterized in that, The step of generating response content based on the correlation between query tags in each of the optimal query response tag links includes: Obtain the number of times each query tag other than the first query tag appears repeatedly in each optimal query response tag link; The query tags whose recurrence count meets a preset requirement are designated as the first related tags of the first query tag, and the query tags that do not meet the preset requirement are designated as the second related tags of the first tag; Based on the query response message corresponding to the first query tag and the first related tag, generate the response content and the query content of the second related tag; The reply content is generated based on the response content and the inquiry content.

6. A query service processing system, characterized in that, The system includes: a clearing system and a query business processing platform; The clearing system is used to send the processing request for the query business sent by the target institution to the query business processing platform; The query service processing platform is used to determine the optimal query-response tag link for the service to be queried based on the query tag, the target institution, and a preset historical service query message database, and to generate a response message for the service to be queried through the optimal query-response tag link, and send the response message to the clearing system; the historical service query message database stores query tags for multiple institution query services and query-response tag links corresponding to each query tag; wherein, one query-response tag link includes query tags corresponding to multiple query messages from multiple interactions between the target institution and the processing institution for a service to be queried; The clearing system is also used to send the inquiry and reply message to the target institution; The clearing system is specifically used to extract full message information from the query service; the full message information includes at least the sending organization, receiving organization, and remarks information of the query service; obtain the query purpose of the query service based on the remarks information in the full message information; perform semantic recognition processing on the query purpose to obtain semantic recognition results; determine the target standardized phrase corresponding to the query purpose based on the mapping relationship between semantics and standardized phrases; wherein, the standardized phrase is specified in the specifications to be followed by the target organization and the processing organization; and determine the tag corresponding to the target standardized phrase as the query tag based on the mapping relationship between the standardized phrase and the tag.

7. The system according to claim 6, characterized in that, The query processing platform includes a big data platform, a business management platform, and an artificial intelligence processing platform; The clearing system is used to call the big data platform interface to send the query business to the big data platform, receive the full message information extracted from the query business returned by the big data platform, and send the full message information to the business management platform. The business management platform is used to extract the query purpose and receiving agency of the business to be queried from the full information of the message, and to determine the query tag corresponding to the query purpose, and send the receiving agency and the query tag to the artificial intelligence processing platform; The artificial intelligence processing platform is used to determine the optimal query and response tag link for the business to be queried based on the query tag, the target institution, and the historical business query message database, and to generate a response message for the business to be queried through the optimal query and response tag link, and send the response message to the clearing system.

8. A query service processing device, characterized in that, The device includes: The tag acquisition module is used to acquire the query tag of the query service in response to the processing request of the query service sent by the target organization. The link determination module is used to determine the optimal query and response tag link for the service to be queried based on the query tag, the target institution, and a preset historical business query message database. The historical business query message database stores query tags for query services of multiple institutions and query and response tag links corresponding to each query tag. Among them, a query and response tag link includes query tags corresponding to multiple query messages from multiple interactions between the target institution and the processing institution for a service to be queried. The message sending module is used to generate a query and reply message for the service to be queried through the optimal query and reply tag link, and send the query and reply message to the target institution; The tag acquisition module is specifically used to extract full message information from the service to be queried; the full message information includes at least the sending organization, receiving organization, and remarks information of the service to be queried; obtain the query purpose of the service to be queried based on the remarks information in the full message information; perform semantic recognition processing on the query purpose to obtain semantic recognition results; determine the target standardized phrase corresponding to the query purpose based on the mapping relationship between semantics and standardized phrases; wherein, the standardized phrase is specified in the specifications to be followed by the target organization and the processing organization; and determine the tag corresponding to the target standardized phrase as the query tag based on the mapping relationship between the standardized phrase and the tag.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 5.

11. A computer program product, comprising a computer program, characterized in that, When the computer program processor executes, it implements the steps of the method according to any one of claims 1 to 5.

Images