TWI855323B - Server for managing foreign currency transaction based on artificial intelligence - Google Patents

Abstract

A server for managing foreign currency transaction based on artificial intelligence is provided. The server includes a storage medium, a transceiver and a processor. The storage medium stores an artificial intelligence model. The transceiver is communicatively connected to a customer electronic device. The processor is coupled to the storage medium and the transceiver, wherein the processor receives a foreign currency transaction request from the customer electronic device through the transceiver; the processor analyzes the foreign currency transaction request by the artificial intelligence model to obtain an analysis result; the processor executes a foreign currency transaction corresponding to the analysis result.

Description

Servers that manage foreign currency transactions based on artificial intelligence

The present disclosure relates to a server for managing foreign currency transactions based on artificial intelligence.

When a customer requests a foreign currency transaction from a bank staff (for example, buying U.S. dollars from the bank, or selling U.S. dollars to the bank), the bank staff often receives foreign currency transactions from many customers in a short period of time, and the bank staff needs to manually input the content of the foreign currency transaction into the bank's system before conducting subsequent foreign currency transactions. This method has the problem that bank staff are prone to manual input errors, thus causing losses to the bank.

The server for managing foreign currency transactions based on artificial intelligence disclosed herein includes a storage medium, a transceiver, and a processor. The storage medium stores an artificial intelligence model. The transceiver is communicatively connected to a client electronic device. The processor is coupled to the storage medium and the transceiver, wherein the processor receives a foreign currency transaction request from the client electronic device through the transceiver; the processor uses the artificial intelligence model to parse the foreign currency transaction request to obtain a parsing result; and the processor executes a foreign currency transaction corresponding to the parsing result.

In order to make the above features and advantages of the present disclosure more clearly understood, embodiments are specifically cited below and described in detail with reference to the accompanying drawings.

Fig. 1 is a schematic diagram of a server 100 for managing foreign currency transactions based on artificial intelligence according to an embodiment of the present disclosure. Referring to Fig. 1, the server 100 includes a storage medium 110, a transceiver 120, and a processor 130. The server 100 in this embodiment may be set in a bank.

The storage medium 110 is, for example, any type of fixed or removable random access memory (RAM), read-only memory (ROM), flash memory, hard disk drive (HDD), solid state drive (SSD) or similar components or a combination of the above components, and is used to store multiple modules or various applications that can be executed by the processor 130. The storage medium 110 can store an artificial intelligence model. The purpose of the artificial intelligence model will be further explained later.

The transceiver 120 transmits and receives signals wirelessly or wiredly. The transceiver 120 can be communicatively connected to the client electronic device 200.

The processor 130 is, for example, a central processing unit (CPU), or other programmable general-purpose or special-purpose micro control unit (MCU), microprocessor, digital signal processor (DSP), programmable controller, application specific integrated circuit (ASIC), graphics processing unit (GPU), image signal processor (ISP), image processing unit (IPU), arithmetic logic unit (ALU), complex programmable logic device (CPLD), field programmable gate array (FPGA), or other similar components or combinations of the above components. The processor 130 may be coupled to the storage medium 110 and the transceiver 120 .

FIG. 2 is a flow chart of a method for managing foreign currency transactions based on artificial intelligence according to an embodiment of the present disclosure, wherein the method for managing foreign currency transactions based on artificial intelligence can be implemented by the server 100 shown in FIG. 1 .

Please refer to FIG. 1 and FIG. 2. In step S201, the processor 130 may receive a foreign currency transaction request from the client electronic device 200 via the transceiver 120. In one embodiment, the client electronic device 200 may be a traditional telephone. In other words, the client may use a traditional telephone to initiate a foreign currency transaction request to the bank that hosts the server 100 (i.e., the foreign currency transaction request is in the form of a voice message from the client using a traditional telephone), but the present disclosure is not limited thereto. For example, the client may also use the client electronic device 200 to initiate a foreign currency transaction request to the bank that hosts the server 100 using an Internet text message.

In step S202, the processor 130 may use the artificial intelligence model to parse the foreign currency transaction request to obtain a parsing result. Specifically, the processor 130 may use the artificial intelligence model to execute natural language understanding (NLU) technology to parse the foreign currency transaction request to obtain a parsing result. For example, the processor 130 may perform voice recognition and semantic understanding on the foreign currency transaction request. In detail, the artificial intelligence model in this embodiment may include but is not limited to a time delay neural network (TDNN), maximum entropy, support vector machine, gradient boosting decision tree, convolutional neural network (CNN) or long short term memory network (LSTM).

In step S203, the processor 130 may execute a foreign currency transaction corresponding to the parsing result.

The above steps S202 and S203 are further described below with reference to an example.

In one embodiment, a foreign currency transaction request may correspond to a foreign currency denomination, wherein the parsing result includes the foreign currency denomination. For example, the foreign currency transaction request may be "buy US$1,000", and the parsing result obtained by the processor 130 (parsing the foreign currency transaction request using an artificial intelligence model) may include the foreign currency denomination "US dollars". Based on this, when the server 100 receives the foreign currency transaction request, the personnel in the bank where the server 100 is set up may not need to manually input the foreign currency denomination "US dollars", thereby avoiding manual input errors that may occur by bank personnel (for example, it can avoid bank personnel mistakenly manually inputting the foreign currency denomination as "Japanese yen").

In other embodiments, the storage medium 110 may store a bank account number in domestic currency and a bank account number in foreign currency. If the parsing result corresponds to a customer foreign currency purchase transaction, the processor 130 may use the bank account number in domestic currency and the bank account number in foreign currency to perform a bank foreign currency sale transaction corresponding to the customer foreign currency purchase transaction. Assuming that the parsing result indicates that the customer wants to "buy" U.S. dollars, and the parsing result includes a customer identification (e.g., the customer's ID number), the processor 130 may use the bank account number in domestic currency and the bank account number in foreign currency to perform a bank "sell" U.S. dollars operation. For example, the processor 130 may perform a bank "selling" U.S. dollars operation based on the bank's exchange rate for "selling" U.S. dollars, the customer's local currency account number (stored in the storage medium 110 and corresponding to the customer's identification), the customer's foreign currency account number (stored in the storage medium 110 and corresponding to the customer's identification), the bank's local currency account number, and the bank's foreign currency account number.

On the other hand, if the parsing result corresponds to a customer foreign currency sale transaction, the processor 130 may use the bank's domestic currency account number and the bank's foreign currency account number to perform a bank foreign currency purchase transaction corresponding to the customer's foreign currency sale transaction. Assuming that the parsing result indicates that the customer wants to "sell" U.S. dollars, and the parsing result includes the customer identification (e.g., the customer's ID number), the processor 130 may use the bank's domestic currency account number and the bank's foreign currency account number to perform a bank "buy" U.S. dollars operation. For example, the processor 130 may perform a bank "purchase" operation of U.S. dollars based on the bank's exchange rate for "purchasing" U.S. dollars, the customer's local currency account number (stored in the storage medium 110 and corresponding to the customer's identification), the customer's foreign currency account number (stored in the storage medium 110 and corresponding to the customer's identification), the bank's local currency account number, and the bank's foreign currency account number.

In summary, the server for managing foreign currency transactions based on artificial intelligence disclosed herein can automatically analyze the foreign currency transaction request using an artificial intelligence model to execute the corresponding foreign currency transaction after receiving the foreign currency transaction request from the customer. Based on this, bank personnel no longer need to manually input the content of foreign currency transactions (for example, the customer wants to buy foreign currency, or the customer wants to sell foreign currency, etc.) to the bank's system, thus greatly avoiding the chance of bank personnel making mistakes when manually inputting. In particular, the server for managing foreign currency transactions based on artificial intelligence disclosed herein can also automatically execute the bank's foreign currency sale transactions when a customer wants to buy foreign currency, and/or automatically execute the bank's foreign currency purchase transactions when a customer wants to sell foreign currency, thereby avoiding the errors that bank personnel often make when manually inputting, thereby improving the efficiency of the bank's management of foreign currency transactions.

Although the present disclosure has been disclosed as above by way of embodiments, it is not intended to limit the present disclosure. Any person having ordinary knowledge in the relevant technical field may make some changes and modifications without departing from the spirit and scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the definition of the attached patent application scope.

100: Server for managing foreign currency transactions based on artificial intelligence 110: Storage medium 120: Transceiver 130: Processor 200: Customer electronic device S201, S202, S203: Steps

FIG1 is a schematic diagram of a server for managing foreign currency transactions based on artificial intelligence according to an embodiment of the present disclosure. FIG2 is a flow chart of a method for managing foreign currency transactions based on artificial intelligence according to an embodiment of the present disclosure.

100: Server for managing foreign currency transactions based on artificial intelligence

110: Storage media

120: Transceiver

130: Processor

200:Customer electronic devices

Claims (2)

A server for managing foreign currency transactions based on artificial intelligence comprises: a storage medium storing an artificial intelligence model, and storing a bank's domestic currency account number and a bank's foreign currency account number; a transceiver communicatively connected to a client electronic device; and a processor coupled to the storage medium and the transceiver, wherein the processor receives a foreign currency transaction request from the client electronic device through the transceiver, wherein the foreign currency transaction request is a text message, wherein the foreign currency transaction request corresponds to a foreign currency denomination, and wherein the parsing result includes the foreign currency denomination, thereby avoiding errors that occur when the foreign currency denomination is manually input; the processor parses the foreign currency transaction request using the artificial intelligence model to obtain a solution. analysis result; the processor executes a foreign currency transaction corresponding to the analysis result; if the analysis result is a foreign currency purchase transaction of the customer, the processor uses the bank's domestic currency account number and the bank's foreign currency account number to execute a bank's foreign currency sale transaction corresponding to the customer's foreign currency purchase transaction to avoid the manually input foreign currency transaction request from being mistyped. If the parsing result is a foreign currency sale transaction of the customer, the processor uses the bank's domestic currency account and the bank's foreign currency account to execute the bank's foreign currency purchase transaction corresponding to the customer's foreign currency sale transaction to avoid the manually input foreign currency transaction request being mistakenly input as the bank's foreign currency sale transaction. A server for managing foreign currency transactions based on artificial intelligence as described in claim 1, wherein the processor uses the artificial intelligence model to execute natural language understanding technology to parse the foreign currency transaction request to obtain the parsing result.

Images