Transaction message processing method and device, electronic equipment and storage medium

Abstract

The present disclosure provides a transaction message processing method and device, electronic equipment and storage medium, which can be applied to the technical field of big data and the technical field of financial technology. The transaction message processing method comprises the following steps: querying, from a message log center, a plurality of target transaction messages associated with a target institution in a target historical management period, taking the target institution identifier as a query field; performing classification processing on each target transaction message based on M statistical dimensions to generate a target classification result of the target transaction message under each statistical dimension, wherein M is a positive integer; generating a data label of each target transaction message according to the target classification result; determining the number of messages under N basic categories according to the data label of each target transaction message, wherein the M statistical dimensions contain N basic categories, and N is a positive integer; and determining a resource prediction corresponding to the target management period according to the number of messages under the N basic categories.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of big data, the technical field of financial technology, in particular to a transaction message processing method and device, equipment, medium and program product. BACKGROUND

[0002] The agent customer of a financial institution will deposit part of the resources in the financial institution to meet the needs of business transactions. Under the premise of meeting the use of resources, maintaining appropriate liquidity is the goal of resource optimization configuration for the agent customer.

[0003] At present, in the resource optimization configuration of the agent customer of the financial institution, it is mostly manually configured. Due to the influence of subjective factors, the resource configuration is usually unreasonable. In the process of manual configuration, business data needs to be called from different data systems for statistical analysis, and the frequent calling of data leads to low computer processing efficiency. SUMMARY

[0004] In view of the above problems, the present disclosure provides a transaction message processing method, device, equipment, medium and program product.

[0005] One aspect of the present disclosure provides a transaction message processing method, comprising:

[0006] querying a plurality of target transaction messages associated with a target institution in a target historical management period from a message log center taking the target institution identifier as a query field;

[0007] based on M statistical dimensions, classifying and processing each target transaction message to generate a target classification result of the target transaction message under each statistical dimension, wherein M is a positive integer;

[0008] According to the target classification result, a data label of each target transaction message is generated;

[0009] According to the data label of each target transaction message, the number of messages under N basic categories is determined, wherein the M statistical dimensions contain N basic categories, and N is a positive integer;

[0010] According to the number of messages under N basic categories, a resource prediction corresponding to the target management period is determined.

[0011] According to an embodiment of the present disclosure, wherein:

[0012] The target classification result of each target transaction message includes M classification result identifiers corresponding to M statistical dimensions;

[0013] The data label of each target transaction message includes M statistical fields corresponding to the M statistical dimensions, and adjacent two statistical fields are connected through a concatenation symbol.

[0014] According to an embodiment of the present disclosure, wherein the data label of each target transaction message is generated according to the target classification result, including:

[0015] The M classification result identifiers are taken as field values corresponding to the M statistical fields to generate the data label.

[0016] According to an embodiment of the present disclosure, wherein the number of messages under the N basic categories is determined according to the data label of each target transaction message, including:

[0017] A statistical instruction for counting the number of messages under a target basic category is received, wherein the target basic category is any one of the N basic categories;

[0018] Based on the statistical instruction, a target field value matching the target basic category under a target statistical dimension is determined;

[0019] Based on the target statistical field in the data label of the target transaction message, the target transaction message containing the target field value in the target statistical field is counted to generate the number of messages under the target basic category.

[0020] According to an embodiment of the present disclosure, wherein the M statistical dimensions include a transaction path type dimension, and the classification processing of each target transaction message based on the transaction path type dimension includes:

[0021] At least one transaction object identifier field of each transaction object participating in the transaction is extracted from the target transaction message, wherein the object identifier field includes a geographic location identifier bit;

[0022] According to the geographic location identifier bit in the object identifier field, a target classification result of the target transaction message under the transaction path type dimension is generated.

[0023] According to an embodiment of the present disclosure, wherein the M statistical dimensions include a transaction business type dimension;

[0024] The classification processing of each target transaction message based on the transaction business type dimension includes:

[0025] A predefined business description field is extracted from the target transaction message;

[0026] According to the predefined business description field, a target classification result of the target transaction message under the transaction business type dimension is generated.

[0027] According to an embodiment of the present disclosure, wherein the resource prediction quantity corresponding to the target management period is determined according to the number of messages under the N basic categories, including:

[0028] The number of messages under the N basic categories is input into the pre-constructed resource prediction model, and the resource prediction quantity corresponding to the target management period is output.

[0029] According to an embodiment of the present disclosure, the resource prediction model is constructed by the following method:

[0030] A plurality of historical transaction messages associated with the target institution in a predetermined historical time period are obtained from the message log center, wherein the predetermined historical time period includes a plurality of historical management periods;

[0031] Based on the M statistical dimensions, each historical transaction message is classified and processed;

[0032] According to the classification result of the historical transaction message, the number of historical messages under the N basic categories in each historical management period is determined;

[0033] The transaction volume field is extracted from the historical transaction message, so that the total amount of historical resource transactions corresponding to each historical management period is determined according to the transaction volume field;

[0034] According to the number of historical messages under the N basic categories in each historical management period, and the total amount of historical resource transactions corresponding to each historical management period, a resource prediction model is constructed.

[0035] Another aspect of the present disclosure provides a transaction message processing device, comprising:

[0036] The query module is configured to query a plurality of target transaction messages associated with the target institution in the target historical management period from the message log center by taking the target institution identifier as the query field;

[0037] The classification module is configured to classify and process each target transaction message based on M statistical dimensions, and generate a target classification result of the target transaction message under each statistical dimension, wherein M is a positive integer;

[0038] The marking module is configured to generate a data label of each target transaction message according to the target classification result;

[0039] The first determination module is configured to determine the number of messages under the N basic categories according to the data label of each target transaction message, wherein the M statistical dimensions include N basic categories, and N is a positive integer;

[0040] The second determination module is configured to determine the resource prediction quantity corresponding to the target management period according to the number of messages under the N basic categories.

[0041] According to an embodiment of the present disclosure, wherein:

[0042] The target classification result of each target transaction message includes M classification result identifiers corresponding to the M statistical dimensions.

[0043] The data label of each target transaction message includes M statistical fields corresponding to the M statistical dimensions, and adjacent two statistical fields are connected through a concatenation symbol.

[0044] According to an embodiment of the present disclosure, the marking module comprises:

[0045] The generating unit is configured to generate the data label by taking the M classification result identifiers as field values corresponding to the M statistical fields.

[0046] According to an embodiment of the present disclosure, the first determining module comprises:

[0047] The receiving unit is configured to receive a statistical instruction for counting the number of messages under a target basic category, wherein the target basic category is any one of the N basic categories.

[0048] The first determining unit is configured to determine, based on the statistical instruction, a target field value that matches the target basic category under a target statistical dimension.

[0049] The statistical unit is configured to count, based on a target statistical field in the data label of the target transaction message, the target transaction message containing the target field value in the target statistical field, and generate the number of messages under the target basic category.

[0050] According to an embodiment of the present disclosure, the M statistical dimensions include a transaction path type dimension, and the classification module comprises:

[0051] The first extraction unit is configured to extract, from the target transaction message, at least one transaction object identifier field of each transaction object participating in the transaction, wherein the object identifier field includes a geographic location identifier bit.

[0052] The first classification unit is configured to generate, according to the geographic location identifier bit in the object identifier field, a target classification result of the target transaction message under the transaction path type dimension.

[0053] According to an embodiment of the present disclosure, the M statistical dimensions include a transaction business type dimension; and the classification module comprises:

[0054] The second extraction unit is configured to extract, from the target transaction message, a predefined business description field.

[0055] The second classification unit is configured to generate, according to the predefined business description field, a target classification result of the target transaction message under the transaction business type dimension.

[0056] According to an embodiment of the present disclosure, the second determining module comprises:

[0057] a prediction unit, configured to input the number of messages under the N basic categories into a pre-constructed resource prediction model, and output a resource prediction quantity corresponding to a target management period.

[0058] According to an embodiment of the present disclosure, the method further includes constructing a resource prediction model, and the constructing includes:

[0059] a obtaining unit, configured to obtain a plurality of historical transaction messages associated with the target institution within a predetermined historical time period from a message log center, wherein the predetermined historical time period includes a plurality of historical management periods;

[0060] a third classification unit, configured to classify each historical transaction message based on the M statistical dimensions;

[0061] a second determination unit, configured to determine the number of historical messages under the N basic categories within each historical management period according to the classification result of the historical transaction messages;

[0062] a third determination unit, configured to extract a transaction volume field from the historical transaction messages, so as to determine a historical total resource transaction amount corresponding to each historical management period according to the transaction volume field;

[0063] a constructing unit, configured to construct a resource prediction model according to the number of historical messages under the N basic categories within each historical management period and the historical total resource transaction amount corresponding to each historical management period.

[0064] Another aspect of the present disclosure provides an electronic device, including: one or more processors; 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 above transaction message processing method.

[0065] Another aspect of the present disclosure also provides a computer-readable storage medium having stored executable instructions, which are executed by a processor to cause the processor to perform the above transaction message processing method.

[0066] Another aspect of the present disclosure also provides a computer program product, including a computer program, which is executed by a processor to implement the above transaction message processing method.

[0067] According to the embodiments of the present disclosure, by classifying the transaction messages in the target historical management period, the number of messages under each basic category is obtained, and based on the number of messages under multiple basic categories, the resource prediction corresponding to the target management period is determined, which realizes the automatic resource optimization configuration of the financial institution for the agent customer, so that the agent customer of the financial institution can clearly store a reasonable amount of resources in the financial institution, so as to avoid that the amount of resources is too small to affect the daily transaction, and the amount of resources is too large to affect the customer's income due to the lack of liquidity of resources. At the same time, on the basis of realizing automatic configuration, the process of manually configuring the business data from different data systems for statistical analysis is avoided, and the efficiency of business processing and computer processing is accelerated. In addition, in the process of classifying and statistically processing the transaction messages, because it involves classification based on multiple dimensions, in the process of counting the messages of each basic category according to the classification result, the statistical method of labeling is adopted in the embodiments of the present disclosure. Because the data label of each target transaction message contains full classification result information based on multiple statistical dimensions, classification and statistical processing based on labels only needs to process the data of the label, without the need to frequently call the classification result for repeated statistical processing. Compared with the traditional method of separately counting each dimension, the present disclosure avoids the frequent calling of intermediate result data, simplifies the data processing process, improves the data processing efficiency, reduces the computer processing thread, improves the computer processing efficiency, and reduces the requirement for the internal performance of the computer. BRIEF DESCRIPTION OF DRAWINGS

[0068] The above and other objects, features and advantages of the present disclosure will become more apparent from the following description of embodiments of the present disclosure taken in conjunction with the accompanying drawings, in which:

[0069] Figure 1 An application scenario diagram of a transaction message processing method, device, equipment, medium and program product according to an embodiment of the present disclosure is schematically shown;

[0070] Figure 2 A flowchart of a transaction message processing method according to an embodiment of the present disclosure is schematically shown;

[0071] Figure 3 A flowchart of a method for constructing a resource prediction model according to an embodiment of the present disclosure is schematically shown;

[0072] Figure 4 A structural block diagram of a transaction message processing device according to an embodiment of the present disclosure is schematically shown;

[0073] Figure 5 A block diagram of an electronic device suitable for implementing a transaction message processing method according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0074] Hereinafter, embodiments of the present disclosure will be described with reference to the accompanying drawings. It is to be understood, however, that the description is merely exemplary and is intended to convey an understanding of the scope of the present disclosure. In the following detailed description of the embodiments, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present disclosure. However, it would be apparent to one skilled in the art that the embodiments, or one or more of the embodiments, can be practiced without these specific details. In other instances, well-known structures and methods have been omitted in order to avoid obscuring the present disclosure.

[0075] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of the present disclosure. The terms "comprising," "including," and the like as used herein specify the presence of stated features, steps, operations, and / or components, but do not preclude the presence or addition of one or more other features, steps, operations, or components.

[0076] All terms used herein, including technical and scientific terms, have the meanings commonly understood by one of ordinary skill in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the specification, and should not be interpreted in an idealized or overly formal manner.

[0077] In the case of using expressions similar to "at least one of A, B, and C, etc.", it should generally be interpreted to include any of the possibilities of one, two, or all of the items enumerated, unless otherwise specifically limited. For example, "a system having at least one of A, B, and C" should be interpreted to include a system having A alone, a system having B alone, a system having C alone, a system having both A and B, a system having both A and C, a system having both B and C, and / or a system having A, B, and C, etc.

[0078] In the embodiments of the present disclosure, the collection, updating, analysis, processing, use, transmission, provision, disclosure, storage, etc. of the data involved (for example, including but not limited to user personal information) comply with the relevant legal regulations, are used for legal purposes, and do not violate public order and good customs. In particular, necessary measures have been taken to prevent illegal access to user personal information data, and to maintain user personal information security, network security, and national security.

[0079] In the embodiments of the present disclosure, the authorization or consent of the user is obtained before the user personal information is acquired or collected.

[0080] It should be noted that the transaction message processing method, device, equipment, medium, and program product of the embodiments of the present disclosure can be applied to the field of big data technology, the field of financial technology, and can also be applied to any field other than the field of big data technology and the field of financial technology. The embodiments of the present disclosure do not limit the application field of the above transaction message processing method, device, equipment, medium, and program product.

[0081] Embodiments of the present disclosure provide a transaction message processing method, comprising: querying, from a message log center, a plurality of target transaction messages associated with a target institution within a target historical management period, taking the target institution identifier as a query field; performing classification processing on each target transaction message based on M statistical dimensions, to generate a target classification result of the target transaction message under each statistical dimension, wherein M is a positive integer; generating a data label of each target transaction message according to the target classification result; determining the number of messages under N basic categories according to the data label of each target transaction message, wherein the M statistical dimensions contain N basic categories, and N is a positive integer; and determining a resource prediction corresponding to the target management period according to the number of messages under the N basic categories.

[0082] Figure 1 An application scenario diagram of the transaction message processing method, apparatus, device, medium and program product according to embodiments of the present disclosure is schematically shown.

[0083] As shown in Figure 1 The application scenario 100 according to the embodiments can include a first terminal device 101, a second terminal device 102, a third terminal device 103, a network 104 and a server 105. The network 104 is a medium for providing a communication link between the first terminal device 101, the second terminal device 102, the third terminal device 103 and the server 105. The network 104 can include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0084] A user can use at least one of the first terminal device 101, the second terminal device 102 and the third terminal device 103 to interact with the server 105 through the network 104 to receive or send messages, etc. Various communication client applications can be installed on the first terminal device 101, the second terminal device 102 and the third terminal device 103, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc. (only as examples).

[0085] The first terminal device 101, the second terminal device 102 and the third terminal device 103 can be various electronic devices with display screens and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers and desktop computers, etc.

[0086] Server 105 can be a server that provides various services, such as a backend management server that supports websites browsed by users using the first terminal device 101, the second terminal device 102, and the third terminal device 103 (this is just an example). The backend management server can analyze and process data such as received user requests, and feed back the processing results (such as web pages, information, or data obtained or generated according to user requests) to the terminal devices.

[0087] In the application scenarios of this disclosure embodiment, a user can use at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103 to interact with the server 105 through the network 104. For example, the user can send a request to the server 105 to obtain the resource prediction amount for the target management period. In response to the user request, the server 105 can execute the transaction message processing method of this disclosure embodiment, query multiple target transaction messages associated with the target institution within the target historical management period from the message log center, and generate the resource prediction amount for the target management period by combining the classification and statistical results of the messages. The processing result is then returned to the user through at least one of the first terminal device 101, the second terminal device 102, and the third terminal device 103.

[0088] It should be noted that the transaction message processing method provided in this embodiment can generally be executed by server 105. Correspondingly, the transaction message processing device provided in this embodiment can generally be located in server 105. The transaction message processing method provided in this embodiment can also be executed by a server or server cluster that is different from server 105 and capable of communicating with the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105. Correspondingly, the transaction 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 the first terminal device 101, the second terminal device 102, the third terminal device 103, and / or server 105.

[0089] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0090] The following will be based on Figure 1 The described scene, through Figures 2 to 5 The transaction message processing method of the disclosed embodiments is described in detail.

[0091] Figure 2 A flowchart illustrating a transaction message processing method according to an embodiment of the present disclosure is shown schematically.

[0092] like Figure 2As shown, the transaction message processing method of this embodiment includes operation S201 to operation S205.

[0093] In operation S201, a plurality of target transaction messages associated with a target institution in a target historical management period are queried from a message log center with the target institution identifier as a query field.

[0094] According to an embodiment of the present disclosure, the target institution is an agent customer of a financial institution, which deposits part of resources in the financial institution to meet the needs of business transactions. The amount of resources deposited by the agent customer in the financial institution needs to be within a reasonable range. Too few resources deposited cannot meet the needs of daily business, and too many resources deposited will affect the customer's income due to the lack of liquidity of the excess resources. The embodiment of the present disclosure aims to determine how much resource amount the target institution is suitable for preinstalling in the financial institution to meet the resource use demand.

[0095] The target institution identifier is a unique identifier for identifying the target institution, which can be a combination of numbers or letters, for example. The plurality of target transaction messages associated with the target institution in the target historical management period are queried from the message log center with the target institution identifier as the query field, completing the collection of message information. The target transaction message can reflect the business information related to the target institution, for example, in the remittance transaction scenario, the information in the message includes the sending institution, the receiving institution, the transaction amount (resource transaction amount), the remittance institution, the receiving institution, the business description phrase, and the like.

[0096] According to an embodiment of the present disclosure, the timeliness requirement for data collection in the scenario of the present disclosure is not high, and the message log center can be associated with a relational database, such as PLSQL or DB2. Therefore, obtaining message data from the message log center can be reading data from the relational database.

[0097] Further, the message log center can also be associated with a distributed data lake. As the database data volume is growing and different types of data are increasing, if the traditional data storage method is used, it will cause waste of storage resources, and a large amount of storage resources are used to store expired data. Therefore, data collection can be performed by obtaining data from the distributed data lake. Using a distributed manner can not only reduce the performance and capacity problems when obtaining data from the traditional relational database, but also can protect customer information to a greater extent.

[0098] In operation S202, based on M statistical dimensions, each target transaction message is classified to generate a target classification result of the target transaction message under each statistical dimension, where M is a positive integer.

[0099] The classification of the target transaction message is based on multiple different statistical dimensions to classify each message respectively, for example, based on statistical dimension 1, the classification result of transaction message A is that it belongs to category 1; based on statistical dimension 2, the classification result of transaction message A is that it belongs to category 2; based on statistical dimension 3, the classification result of transaction message A is that it belongs to category 3; therefore, each target transaction message obtains M classification results based on M statistical dimensions.

[0100] In operation S203, according to the target classification result, the data label of each target transaction message is generated; each target transaction message generates a data label, and the data label contains the full classification result information based on M statistical dimensions. For example, the data label of transaction message A is 1-2-3, which indicates that based on statistical dimension 1, statistical dimension 2, and statistical dimension 3, the classification result of transaction message A is category 1, category 2, and category 3, respectively.

[0101] In operation S204, according to the data label of each target transaction message, the number of messages under N basic categories is determined, wherein the M statistical dimensions contain N basic categories, and N is a positive integer. For example, there are 2 statistical dimensions: statistical dimension 1 and statistical dimension 2; statistical dimension 1 contains 3 basic categories, and statistical dimension 2 contains 4 basic categories; therefore, the 2 statistical dimensions contain 7 basic categories. The target classification result of the target transaction message based on statistical dimension 1 is one of the 3 basic categories contained in statistical dimension 1; the target classification result of the target transaction message based on statistical dimension 2 is one of the 4 basic categories contained in statistical dimension 2.

[0102] Since the data label of each target transaction message contains the full classification result information based on M statistical dimensions, the number of messages under each basic category in the target historical management period can be counted based on the data label.

[0103] In operation S205, according to the number of messages under N basic categories, the resource prediction quantity corresponding to the target management period is determined.

[0104] The resource amount corresponding to the target management period has a certain positive correlation with the message amount of the target management period, and the resource amount can be predicted according to the message amount. However, because the target management period is a future management period, the actual message amount of the target management period is unknown. In the method of the embodiment of the present disclosure, the message amount in the target historical management period is used as a reference for the message amount in the future target management period, and the resource amount in the future target management period is predicted based on the message amount in the historical management period. The historical management period can be the adjacent last management period or other specified management period; for example, the target management period is next month (August), and the target historical management period is last month (July); for example, the target management period is the next month (August) of this year, and the target historical management period is the same period (August) of last year.

[0105] According to the embodiment of the present disclosure, by classifying the transaction messages in the target historical management period, the message amounts in each basic category are obtained, and based on the message amounts in multiple basic categories, the resource prediction amount corresponding to the target management period is determined, which realizes the automatic resource optimization configuration of the financial institution for the agent customer, so that the agent customer of the financial institution can clearly store a reasonable amount of resources in the financial institution, so as to avoid that the amount of resources stored is too small to affect the daily transaction, and the amount of resources stored is too much to affect the customer's income due to the lack of liquidity of resources. At the same time, on the basis of realizing automatic configuration, the process of manually configuring the business data from different data systems for statistical analysis is avoided, and the efficiency of business processing and computer processing is accelerated. In addition, in the process of classifying and statistically processing the transaction messages, because classification based on multiple dimensions is involved, in the process of counting the messages in each basic category according to the classification results, the embodiment of the present disclosure adopts a labeling statistical method. Because the data label of each target transaction message contains full classification result information based on multiple statistical dimensions, classification and statistical processing based on the label only needs to process the data of the label, without the need to frequently call the classification result for repeated statistical processing. Compared with the traditional method of separately counting each dimension, the embodiment of the present disclosure avoids the frequent calling of intermediate result data, simplifies the data processing process, improves the data processing efficiency, reduces the computer processing thread, improves the computer processing efficiency, and reduces the requirement for the internal performance of the computer.

[0106] According to the embodiment of the present disclosure, specifically, the M statistical dimensions can include two statistical dimensions, which are a transaction path type dimension and a transaction business type dimension. Each target transaction message needs to be classified and processed based on the two statistical dimensions.

[0107] Among them, the classification and processing of each target transaction message based on the transaction path type dimension includes:

[0108] extracting, from the target transaction message, an object identifier field of each of the at least one transaction object involved in the transaction, wherein the object identifier field includes a geographical location identifier bit; and generating a target classification result of the target transaction message in a transaction path type dimension according to the geographical location identifier bit in the object identifier field.

[0109] Specifically, the at least one transaction object involved in the transaction includes, for example, a receiving agency, a sending agency, a resource transfer-out agency, and a resource receiving agency, wherein the resource transfer-out agency and the resource receiving agency are two agencies involved in an actual business transaction, and the receiving agency and the sending agency are the receiving and sending agencies of the transaction message. The sending agency and the resource transfer-out agency can be the same agency or different agencies, and the receiving agency and the resource receiving agency can be the same agency or different agencies.

[0110] The target transaction message includes the object identifier fields of the receiving agency, the sending agency, the resource transfer-out agency, and the resource receiving agency, wherein the object identifier field can be a preset code and can include a plurality of identifier bits, and the plurality of identifier bits include a geographical location identifier bit. For example, the object identifier of the receiving agency, the sending agency, the resource transfer-out agency, and the resource receiving agency is an identification code composed of a plurality of numbers or letters, such as ABCD-EF-GH-XXX, wherein the first 4 bits ABCD are agency identifier bits for identifying a financial agency, and the 5th and 6th bits EF are geographical location identifier bits for identifying a geographical area where the financial agency is located.

[0111] According to an embodiment of the present disclosure, according to the geographical location identifier bits in the object identifier fields of the plurality of transaction objects involved in the target transaction message, the target classification result of the target transaction message in the transaction path type dimension can be determined.

[0112] For example, the classification result in the transaction path type dimension can include three classification results: domestic transaction, cross-border transaction, and overseas transaction. Based on this, the classification of the target transaction message in the transaction path type dimension can be:

[0113] In the case where the geographical location identifier bits of the plurality of transaction objects (the receiving agency, the sending agency, the resource transfer-out agency, and the resource receiving agency) are the same and all correspond to the same target country (the country where the financial agency is located), the target classification result of the target transaction message in the transaction path type dimension is determined to be that the target transaction message involves a domestic transaction.

[0114] In the case that at least one of the geographical location identification bits of the multiple transaction objects (the receiving agency, the sending agency, the resource transfer-out agency, and the resource receiving agency) corresponds to the target country (the country where the financial institution is located), and at least one corresponds to a non-target country (a country where the financial institution is not located), it is determined that the target transaction message involves cross-border transactions in the target classification result of the transaction path type dimension.

[0115] In the case that the geographical location identification bits of the multiple transaction objects (the receiving agency, the sending agency, the resource transfer-out agency, and the resource receiving agency) all correspond to non-target countries (countries where the financial institution is not located), and correspond to at least two different non-target countries, it is determined that the target transaction message involves overseas transactions in the target classification result of the transaction path type dimension.

[0116] According to the embodiments of the present disclosure, according to the above method, the message is classified according to the geographical location identification bits in the object identification field, and the target classification result of the target transaction message in the transaction path type dimension can be generated. Subsequently, the number of messages in each category can be counted based on the classification result.

[0117] According to the embodiments of the present disclosure, based on the transaction business type dimension, the classification processing of each target transaction message includes: extracting a predefined business description field from the target transaction message; and generating a target classification result of the target transaction message in the transaction business type dimension according to the predefined business description field.

[0118] According to the embodiments of the present disclosure, the target transaction message includes a predefined business description field, and the predefined business description field includes descriptions of transaction details such as business background, transaction purpose, transaction content, and transaction object of the transaction. For the predefined business description field, a machine learning method can be used to identify the phrase content, and then classify the message.

[0119] For example, if the predefined business description field contains the word "goods", it is considered that the transaction message involves goods trade; if the predefined business description field contains the word "service", it is considered that the target transaction message involves service trade, and so on. The classification result in the transaction business type dimension includes, for example, five business types of financial institution position adjustment type, goods trade type, service trade type, investment and financing type, and other payment type. Based on this, the target transaction message can be classified in the transaction business type dimension to obtain the classification result, which is one of the above-mentioned five business types.

[0120] According to an embodiment of the present disclosure, after determining the number of messages under each of the N basic categories, the resource prediction corresponding to the target management period can be determined according to the number of messages under the N basic categories. The specific method comprises: inputting the number of messages under the N basic categories into a pre-constructed resource prediction model, and outputting the resource prediction corresponding to the target management period.

[0121] The resource prediction model may, for example, adopt a multiple linear regression model as shown in the following formula (1):

[0122]

[0123] wherein Z is the resource prediction, a and ξ are constants, wherein ξ is an error constant; X i is an explanatory variable under the transaction path type dimension, b i is a regression coefficient under the transaction path type dimension, Y i is an explanatory variable under the transaction business type dimension, c i is a regression coefficient under the transaction business type dimension.

[0124] For example, the classification results under the transaction path type dimension may, for example, include three classification results: domestic transaction type, cross-border transaction type, and overseas transaction type; the classification results under the transaction business type dimension include five classification results: financial institution position adjustment type, goods trade type, service trade type, investment and financing type, and other payment type. The number of messages under the above eight basic categories is counted as the explanatory variable. The number of messages under the domestic transaction type is X1, the number of messages under the cross-border transaction type is X2, and the number of messages under the overseas transaction type is X3. The number of messages under the financial institution position adjustment type is Y1, the number of messages under the goods trade type is Y2, the number of messages under the service trade type is Y3, the number of messages under the investment and financing type is Y4, and the number of messages under the other payment type is Y5. The resource prediction model is shown in the following formula (2).

[0125] Z = a + b1X1 + b2X2 + b3X3 + c1Y1 + c2Y2 + c3Y3 + c4Y4 + c5Y5 + ξ Formula (2)

[0126] According to an embodiment of the present disclosure, the above resource prediction model calculates the resource prediction based on the number of messages under multiple dimension categories, considers the influence of multiple dimension message quantities, and the prediction result is more accurate.

[0127] According to an embodiment of the present disclosure, after classifying each target transaction message based on the M statistical dimensions, the number of messages under the N basic categories contained in the M statistical dimensions needs to be determined according to the classification results.

[0128] The target classification result of each target transaction message includes M classification result identifiers corresponding to the M statistical dimensions.

[0129] Further, the data label of each target transaction message can be generated according to the target classification result, specifically including: taking the M classification result identifiers as field values corresponding to the M statistical fields to generate the data label. The data label of each target transaction message includes M statistical fields corresponding to the M statistical dimensions, and adjacent two statistical fields are connected through a concatenation symbol.

[0130] For example, the classification result of transaction message A based on the transaction path type dimension is that it belongs to category 1-inland transaction, and the classification result of transaction message A based on the transaction business type dimension is that it belongs to category 2-goods trade type. The classification result identifiers of these two dimensions are 1 and 2 respectively. The data label of transaction message A generated according to the classification result is 1-2, which represents the classification result based on the transaction path type dimension-category 1, and the classification result based on the transaction business type dimension-category 2.

[0131] For example, the classification result of transaction message A based on the transaction path type dimension is that it belongs to category 2-cross-border transaction, and the classification result of transaction message A based on the transaction business type dimension is that it belongs to category 2-goods trade type. The classification result identifiers of these two dimensions are 2 and 2 respectively. The data label of transaction message A generated according to the classification result is 2-2, which represents the classification result based on the transaction path type dimension-category 2, and the classification result based on the transaction business type dimension-category 2.

[0132] According to an embodiment of the present disclosure, after generating the data label of each transaction message, the number of messages under the target basic category can be determined according to the data label of each target transaction message, specifically including the following operations:

[0133] Operation 1, receiving a statistical instruction for counting the number of messages under a target basic category, wherein the target basic category is any one of the N basic categories;

[0134] Operation 2, determining a target field value matching the target basic category under a target statistical dimension based on the statistical instruction; the target statistical dimension is the statistical dimension to which the target basic category belongs.

[0135] Operation 3, counting the target transaction messages containing the target field value in the target statistical field in the data label of the target transaction message based on the target statistical field in the M statistical fields in the data label of the target transaction message, to generate the number of messages under the target basic category. The target statistical field is the statistical field in the data label corresponding to the target statistical dimension.

[0136] For example, after receiving a statistical instruction for counting the number of messages of a target basic category-inland transaction type, it is determined that the statistical dimension to which the inland transaction type belongs is the transaction path type dimension, and it is determined that the target field value matched with the inland transaction type under the transaction path type dimension is "1", that is, the inland transaction type corresponds to category 1. Then, according to the value of the statistical field corresponding to the transaction path type dimension in the data label of the plurality of transaction messages, the messages with the value of the statistical field corresponding to the transaction path type dimension equal to "1" are counted to generate the message number statistical result of the inland transaction type.

[0137] According to an embodiment of the present disclosure, in the process of counting the number of messages under a plurality of basic categories, a plurality of statistical dimensions are involved, and therefore the statistical processing logic is relatively complicated. In the embodiment of the present disclosure, a category label is generated for a message, and the category label contains classification result information under each statistical dimension. Therefore, the number of messages under each category can be counted only by identifying the label, and the frequent calling of message classification results is reduced, and the computer processing efficiency is improved.

[0138] According to an embodiment of the present disclosure, a resource prediction model can be trained in advance, Figure 3 A method flowchart for constructing a resource prediction model according to an embodiment of the present disclosure is schematically shown. As shown in Figure 3 The resource prediction model can be constructed by the following operations S301-S305:

[0139] In operation S301, a plurality of historical transaction messages associated with a target institution in a predetermined historical time period are obtained from a message log center, wherein the predetermined historical time period includes a plurality of historical management periods.

[0140] For example, historical transaction messages in the last ten years are obtained, and assuming that one year is one management period, the message data includes ten management periods.

[0141] In operation S302, each historical transaction message is classified based on M statistical dimensions; the classification method is described in the foregoing embodiments.

[0142] In operation S303, according to the classification result of the historical transaction message, the number of historical messages under N basic categories in each historical management period is determined; the method for determining the number of messages under each basic category is described in the foregoing embodiments.

[0143] In operation S304, the transaction volume field is extracted from the historical transaction message, so that the total amount of historical resource transactions corresponding to each historical management period is determined according to the transaction volume field.

[0144] The field including the transaction volume (such as the transaction amount) in the transaction message can extract the transaction volume from each transaction message and summarize to obtain the total amount of transactions in each management period as the resource prediction Z.

[0145] In operation S305, according to the number of historical messages under N basic categories in each historical management period and the total amount of historical resource transactions corresponding to each historical management period, a resource prediction model is constructed.

[0146] The resource prediction model as shown in formula (1) obtains the linear relationship between the explanatory variable and the explained variable according to the known values: the resource prediction Z (explained variable) in each management period, the explanatory variable X in the transaction path type dimension in each management period i , and the explanatory variable Y in the transaction business type dimension in each management period i , solves the constant a, the regression coefficient b of the transaction path type dimension i , and the regression coefficient c of the transaction business type dimension i , and constructs the resource prediction model.

[0147] For the error constant ξ in the model, the data results can be put back to the distributed data lake for learning, and the error constant ξ is continuously corrected with the update of data.

[0148] Based on the above transaction message processing method, the present disclosure also provides a transaction message processing device. The device will be described in detail below. Figure 4

[0149] Figure 4 The structure block diagram of the transaction message processing device according to the embodiment of the present disclosure is schematically shown.

[0150] As shown in Figure 4 , the transaction message processing device 400 of this embodiment includes a query module 401, a classification module 402, a marking module 403, a first determination module 404, and a second determination module 405.

[0151] The query module 401 is configured to query a plurality of target transaction messages associated with a target institution in a target historical management period from the message log center with the target institution identifier as the query field.

[0152] ​The classification module 402 is used to classify each target transaction message based on M statistical dimensions and generate the target classification results of the target transaction message under each statistical dimension, where M is a positive integer;

[0153] The tagging module 403 is used to generate data tags for each target transaction message based on the target classification results;

[0154] The first determining module 404 is used to determine the number of messages under N basic categories based on the data tags of each target transaction message, wherein M statistical dimensions contain N basic categories, and N is a positive integer;

[0155] The second determining module 405 is used to determine the resource forecast amount corresponding to the target management cycle based on the number of messages under N basic categories.

[0156] According to embodiments of this disclosure, transaction messages within the target historical management period are classified and processed by a classification module 402, a tagging module 403, and a first determination module 404 to obtain the number of messages under each basic category. Then, based on the number of messages under multiple basic categories, a second determination module 405 determines the resource forecast corresponding to the target management period. This enables financial institutions to automatically optimize resource allocation for their agency clients, allowing them to clearly define the reasonable amount of resources to store in the financial institution. This avoids the situation where too few resources affect daily transactions, or too many resources lead to a lack of liquidity and affect client revenue. Furthermore, by achieving automated configuration, the process of frequently calling business data from different data systems for statistical analysis is eliminated, thus accelerating the efficiency of business processing and computer processing. Furthermore, in the process of classifying and statistically processing transaction messages, since classification based on multiple dimensions is involved, the embodiments of this disclosure implement a tagging statistical method through a classification module 402, a tagging module 403, and a first determination module 404 during the statistical processing of messages of each basic category based on the classification results. Since the data tags of each target transaction message contain full classification result information based on multiple statistical dimensions, classification and statistics based on tags only require data processing of the tags, without the need for frequent calls to the classification results for repeated statistical processing. Compared with the traditional method of performing statistics based on each dimension separately, it eliminates the frequent calls to intermediate result data, simplifies the data processing process, improves data processing efficiency, reduces computer processing threads, improves computer processing efficiency, and reduces the requirements for computer internal performance.

[0157] According to an embodiment of the present disclosure, the target classification result of each target transaction message includes M classification result identifiers corresponding to M statistical dimensions; and the data label of each target transaction message includes M statistical fields corresponding to the M statistical dimensions, and two adjacent statistical fields are connected by a concatenation symbol.

[0158] According to an embodiment of the present disclosure, the marking module 403 includes a generation unit configured to generate the data label by taking the M classification result identifiers as field values corresponding to the M statistical fields.

[0159] According to an embodiment of the present disclosure, the first determination module 404 includes a receiving unit, a first determination unit, and a statistical unit.

[0160] The receiving unit is configured to receive a statistical instruction for counting the number of messages under a target basic category, where the target basic category is any one of the N basic categories; the first determination unit is configured to determine a target field value that matches the target basic category under a target statistical dimension based on the statistical instruction; and the statistical unit is configured to count the target transaction messages containing the target field value in the target statistical field based on the target statistical field in the data label of the target transaction message, and generate the number of messages under the target basic category.

[0161] According to an embodiment of the present disclosure, the M statistical dimensions include a transaction path type dimension, and the classification module 402 includes a first extraction unit and a first classification unit.

[0162] The first extraction unit is configured to extract at least one transaction object identifier field of each transaction object participating in a transaction from the target transaction message, where the object identifier field includes a geographic location identifier bit; and the first classification unit is configured to generate a target classification result of the target transaction message under the transaction path type dimension according to the geographic location identifier bit in the object identifier field.

[0163] According to an embodiment of the present disclosure, the M statistical dimensions include a transaction business type dimension; and the classification module 402 includes a second extraction unit and a second classification unit.

[0164] The second extraction unit is configured to extract a predefined business description field from the target transaction message; and the second classification unit is configured to generate a target classification result of the target transaction message under the transaction business type dimension according to the predefined business description field.

[0165] According to an embodiment of the present disclosure, the second determination module 405 includes a prediction unit configured to input the number of messages under the N basic categories into a pre-constructed resource prediction model, and output a resource prediction quantity corresponding to a target management period.

[0166] According to an embodiment of the present disclosure, the device further comprises a construction module configured to construct the resource prediction model, the construction module comprising an acquisition unit, a third classification unit, a second determination unit, a third determination unit, and a construction unit.

[0167] The acquisition unit is configured to acquire, from the message log center, a plurality of historical transaction messages associated with the target institution within a predetermined historical time period, wherein the predetermined historical time period comprises a plurality of historical management periods; the third classification unit is configured to classify each historical transaction message based on the M statistical dimensions; the second determination unit is configured to determine, according to the classification result of the historical transaction messages, the number of historical messages under the N basic categories in each historical management period; the third determination unit is configured to extract a transaction volume field from the historical transaction messages, so as to determine, according to the transaction volume field, the total amount of historical resource transactions corresponding to each historical management period; and the construction unit is configured to construct the resource prediction model according to the number of historical messages under the N basic categories in each historical management period and the total amount of historical resource transactions corresponding to each historical management period.

[0168] According to an embodiment of the present disclosure, any one or more of the query module 401, the classification module 402, the marking module 403, the first determination module 404, and the second determination module 405 can be combined in one module, or any one of them can be split into multiple modules. Alternatively, at least part of the function of one or more of these modules can be combined with at least part of the function of other modules, and implemented in one module. According to an embodiment of the present disclosure, at least one of the query module 401, the classification module 402, the marking module 403, the first determination module 404, and the second determination module 405 can be at least partially implemented as a hardware circuit, such as a field programmable gate array (FPGA), a programmable logic array (PLA), a system on chip, a system on board, a system on package, an application specific integrated circuit (ASIC), or any other reasonable way of integrating or packaging a circuit, etc. hardware or firmware, or in any one of software, hardware and firmware three implementation ways or in any appropriate combination of any of them. Alternatively, at least one of the query module 401, the classification module 402, the marking module 403, the first determination module 404, and the second determination module 405 can be at least partially implemented as a computer program module, which can perform corresponding functions when the computer program module is run.

[0169] Figure 5 A block diagram of an electronic device suitable for implementing the transaction message processing method according to an embodiment of the present disclosure is schematically shown.

[0170] As Figure 5As shown, the electronic device 500 according to embodiments of the present disclosure includes a processor 501 that can perform various appropriate actions and processes according to programs stored in a read only memory (ROM) 502 or loaded into a random access memory (RAM) 503 from a storage section 508. The processor 501 can include, for example, a general purpose microprocessor (e.g., a CPU), an instruction set processor, and / or a related chipset and / or a dedicated microprocessor (e.g., an application specific integrated circuit (ASIC)), and the like. The processor 501 can also include an on-board memory for cache use. The processor 501 can include a single processing unit or multiple processing units for executing different actions of the method processes according to embodiments of the present disclosure.

[0171] In the RAM 503, various programs and data required for the operation of the electronic device 500 are stored. The processor 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. The processor 501 performs various operations of the method processes according to embodiments of the present disclosure by executing the programs in the ROM 502 and / or the RAM 503. Note that the programs can also be stored in one or more memories other than the ROM 502 and the RAM 503. The processor 501 can also perform various operations of the method processes according to embodiments of the present disclosure by executing the programs stored in the one or more memories.

[0172] According to embodiments of the present disclosure, the electronic device 500 can further include an input / output (I / O) interface 505 that is also connected to the bus 504. The electronic device 500 can further include one or more of the following components connected to the input / output (I / O) interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a display such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the input / output (I / O) interface 505 as necessary. A removable medium 511 such as a magnetic disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 510 as necessary, so that a computer program read out therefrom is installed in the storage section 508 as necessary.

[0173] The present disclosure also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments, or exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present disclosure.

[0174] According to an embodiment of the present disclosure, the computer readable storage medium can be a non-volatile computer readable storage medium, which can include, but is not limited to, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any appropriate combination thereof. In the present disclosure, the computer readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present disclosure, the computer readable storage medium can include one or more memories of the ROM 502 and / or the RAM 503 described above and / or one or more memories other than the ROM 502 and the RAM 503.

[0175] The embodiments of the present disclosure also include a computer program product, which includes a computer program containing program codes for executing the methods shown in the flowcharts. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the transaction message processing method provided by the embodiments of the present disclosure.

[0176] The above functions defined in the system / apparatus of the embodiments of the present disclosure are performed when the computer program is executed by the processor 501. According to an embodiment of the present disclosure, the system, apparatus, module, unit, etc. described above can be implemented by computer program modules.

[0177] In one embodiment, the computer program can rely on a tangible storage medium such as an optical storage medium, a magnetic storage medium, etc. In another embodiment, the computer program can also be transmitted, distributed, and downloaded in the form of a signal via a network medium, and be downloaded and installed via the communication part 509 and / or installed from the detachable medium 511. The program codes contained in the computer program can be transmitted via any appropriate network medium, including but not limited to wireless, wired, etc., or any appropriate combination thereof.

[0178] In such embodiments, the computer program can be downloaded and installed from the network through the communication section 509, and / or installed from the removable media 511. When the computer program is executed by the processor 501, the above-described functions defined in the system of the embodiments of the present disclosure are executed. According to the embodiments of the present disclosure, the system, device, apparatus, module, unit, and the like described above can be implemented by computer program modules.

[0179] According to the embodiments of the present disclosure, the program code for executing the computer program provided by the embodiments of the present disclosure can be written in any combination of one or more programming languages, and specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming language, and / or assembly / machine language. The programming language includes, but is not limited to, such as Java, C++, python, "C" language or similar programming language. The program code can be executed entirely on the user computing device, partially on the user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, connected through the Internet by using an Internet service provider).

[0180] The flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowcharts or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the drawings. For example, two blocks noted in succession can in fact be executed substantially concurrently or in the reverse order, depending on the functionality involved. It should also be noted that each block in the flowcharts or block diagrams, and combinations of blocks in the flowcharts or block diagrams, can be implemented by dedicated hardware-based systems that perform the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0181] Those skilled in the art can understand that the features described in various embodiments of the present disclosure and / or claims can be combined or / and integrated, even if such combinations or integrations are not explicitly described in the present disclosure. In particular, the features described in various embodiments of the present disclosure and / or claims can be combined and / or integrated in various combinations, without departing from the spirit and teachings of the present disclosure. All these combinations and / or integrations fall within the scope of the present disclosure.

[0182] The above describes embodiments of the present disclosure. However, these embodiments are merely for illustrative purposes, and are not intended to limit the scope of the present disclosure. Although each embodiment is described above separately, this does not mean that the measures in each embodiment cannot be advantageously used in combination. The scope of the present disclosure is defined by the appended claims and their equivalents. Those skilled in the art can make various substitutions and modifications without departing from the scope of the present disclosure, and all such substitutions and modifications shall fall within the scope of the present disclosure.

Claims

1. A transaction message processing method, comprising: querying, from a message log center, a plurality of target transaction messages associated with a target institution within a target historical management period, with a target institution identifier as a query field; performing classification processing on each of the target transaction messages based on M statistical dimensions, to generate a target classification result of the target transaction message under each of the statistical dimensions, wherein M is a positive integer; and the target classification result of each of the target transaction messages comprises M classification result identifiers corresponding to the M statistical dimensions; generating a data label of each of the target transaction messages by taking the M classification result identifiers as field values corresponding to the M statistical fields; and the data label of each of the target transaction messages comprises M statistical fields corresponding to the M statistical dimensions, and two adjacent statistical fields are connected by a concatenation symbol; determining a message quantity under N basic categories according to the data label of each of the target transaction messages, wherein the M statistical dimensions include the N basic categories, and N is a positive integer; determining a resource prediction quantity corresponding to a target management period according to the message quantity under the N basic categories.

2. The method of claim 1, wherein, The determining of the message quantity under the N basic categories according to the data label of each of the target transaction messages comprises: receiving a statistical instruction for counting a message quantity under a target basic category, wherein the target basic category is any one of the N basic categories; determining a target field value matching the target basic category under a target statistical dimension based on the statistical instruction; counting target transaction messages containing the target field value in the target statistical field based on a target statistical field in the data label of the target transaction message, to generate the message quantity under the target basic category.

3. The method of claim 1, wherein, The M statistical dimensions include a transaction path type dimension, and the classification processing of each of the target transaction messages based on the transaction path type dimension comprises: extracting at least one transaction object identifier field of each of the transaction objects from the target transaction message, wherein the object identifier field includes a geographic location identifier bit; generating a target classification result of the target transaction message under the transaction path type dimension according to the geographic location identifier bit in the object identifier field.

4. The method of claim 3, wherein, The M statistical dimensions include a transaction business type dimension, and the classification processing of each of the target transaction messages based on the transaction business type dimension comprises: extracting a predefined business description field from the target transaction message; generating a target classification result of the target transaction message under the transaction business type dimension according to the predefined business description field.

5. The method according to any one of claims 1 to 4, wherein, The determining of the resource prediction quantity corresponding to the target management period according to the message quantity under the N basic categories comprises: inputting the message quantity under the N basic categories into a pre-constructed resource prediction model, and outputting the resource prediction quantity corresponding to the target management period.

6. The method of claim 5, wherein, The resource prediction model is constructed by the following method: obtaining a plurality of historical transaction messages associated with the target institution within a predetermined historical time period from the message log center, wherein the predetermined historical time period comprises a plurality of historical management periods; performing classification processing on each of the historical transaction messages based on the M statistical dimensions; determining the number of historical messages under the N basic categories within each of the historical management periods according to the classification results of the historical transaction messages; extracting a transaction volume field from the historical transaction messages to determine the total amount of historical resource transactions corresponding to each of the historical management periods according to the transaction volume field; constructing the resource prediction model according to the number of historical messages under the N basic categories within each of the historical management periods and the total amount of historical resource transactions corresponding to each of the historical management periods.

7. A transaction message processing apparatus, comprising: a query module configured to query a plurality of target transaction messages associated with a target institution within a target historical management period from a message log center with the target institution identifier as a query field; a classification module configured to perform classification processing on each of the target transaction messages based on M statistical dimensions to generate target classification results of the target transaction messages under each of the statistical dimensions, wherein M is a positive integer; and each of the target classification results of the target transaction messages comprises M classification result identifiers corresponding to the M statistical dimensions; a marking module comprising a generation unit configured to generate a data label of each of the target transaction messages by taking the M classification result identifiers as field values corresponding to the M statistical fields; and each of the data labels of the target transaction messages comprises M statistical fields corresponding to the M statistical dimensions, and adjacent two of the statistical fields are connected by a concatenation symbol; a determination module configured to determine the number of messages under N basic categories according to the data label of each of the target transaction messages, wherein the M statistical dimensions comprise the N basic categories, and N is a positive integer; the determination module is configured to determine a resource prediction value corresponding to the target management period according to the number of messages under the N basic categories.

8. An electronic device, comprising: one or more processors; a storage device configured to store 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 according to any one of claims 1-6.

9. 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 1-6.

10. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-6.

Images