TWI732457B - Automatic fund depositing system and automatic fund depositing method - Google Patents

Abstract

An automatic fund depositing system comprises an account monitoring host and a fund transfer management host, wherein the account management host collects a current deposit amount of an account every predetermined period. The transfer management host is electrically connected to the account monitoring host and stores a machine learning model. The transfer management host drive the machine learning model to calculate an amount difference between the current deposit amount and a fixed amount and compare the amount difference with a lower limit of the amount difference and an upper limit of the amount difference for generating a deposit transfer amount during every predetermined period.

Description

Automatic saving system and automatic saving method

The invention relates to a financial transaction management system, especially a time deposit management system.

The existing automatic fixed deposit system is based on the actual income, the customer sets the fixed amount of the fixed deposit for the fixed deposit period, so as to prepare for the future education fund, travel fund or retirement fund. When the fixed deposit amount is too low, it will be difficult for financial managers to persuade customers to switch the fixed deposit to purchase other wealth management products, and the expense of fixed deposit interest will cause the burden of bank costs. Conversely, when the set deposit amount is too high, if the customer has a temporary need for funds and must terminate the contract, although the bank will obtain the additional payment for the termination of the contract from the customer, it will also lose the entire amount of the deposit, which makes the financial management staff unable to do so. Customers provide appropriate wealth management products to help customers earn higher returns than savings interest.

In view of this, there is indeed a need for an improved automatic savings system in practice, which can at least solve the above shortcomings.

The present invention is to provide an automatic saving system and an automatic saving method, which can adjust the customer's current fixed deposit transfer amount according to the customer's actual income and expenditure status.

An automatic deposit system disclosed according to an embodiment of the present invention includes: an account monitoring host that collects an existing deposit data of an account in each predetermined period, the existing deposit data including a deposit amount and a deposit time; and a transfer The management host is communicatively connected to the account monitoring host. The transfer management host stores a machine learning model. The machine learning model is a type of neural network. This type of neural network includes a first node, a second node, and a third node. Node and a fourth node, the first node is used to receive the deposit amount, a fixed amount, and an upper limit of the amount difference, the second node is used to receive the deposit amount, the fixed amount, and a lower limit of the amount difference, the first node The node and the second node are respectively connected to the third node, the fourth node is connected to the third node, a first weight and a second weight are connected between the third node and the fourth node, the fixed amount There is a third weight connected to the fourth node, the transfer management host is used to execute this type of neural network, and the first node and the second node are used to calculate an amount between the deposit amount and the fixed amount Difference, the third node is used to compare the amount difference, the lower limit of the amount difference and the upper limit of the amount difference, the fourth node is used to output a current fixed deposit transfer amount in each predetermined period, if the current fixed deposit transfer amount When the difference between a certain deposit transfer amount and a historical fixed deposit transfer amount of the account is less than 0, this type of neural network is used to increase the first weight based on the fixed deposit transfer amount difference and through a backward pass algorithm , Increase the second weight and decrease the third weight, wherein a first adjustment percentage of the first weight is less than a second adjustment percentage of the second weight and a third adjustment percentage of the third weight; if When the fixed deposit transfer amount difference is greater than 0, this type of neural network is used to increase the first weight, increase the second weight, and increase the first weight, increase the second weight, and increase the first weight based on the fixed deposit transfer amount difference and through the backward pass algorithm. Three weights, where the first adjustment percentage is greater than the second adjustment percentage and the third adjustment percentage; and a confirmation operation page, which has a certain deposit and transfer amount input field, a confirmation button, and a cancel button. The fixed deposit transfer amount input column has been filled in the current fixed deposit transfer amount. When the confirmation key is in the same state, the automatic savings system will transfer the account according to the current fixed deposit transfer amount.

An automatic deposit method disclosed in accordance with an embodiment of the present invention includes: collecting an existing deposit data of an account with an account monitoring host in each predetermined period, the existing deposit data including a deposit amount and a deposit time; management by transfer The host executes a machine learning model. The machine learning model is a type of neural network. This type of neural network receives a fixed amount, an upper limit of the amount difference, a lower limit of the amount difference, and the deposit amount; this type of neural network calculates the amount of the deposit. The amount difference between the deposit amount and a fixed amount; use this type of neural network to compare the amount difference with a lower limit of the amount difference and an upper limit of the amount difference; if the type of neural network determines that the amount difference is greater than zero and less than or equal to For the lower limit of the amount difference, use this type of neural network to output a current fixed deposit transfer amount, and the current fixed deposit transfer amount is less than the fixed amount; if the type of neural network determines that the amount difference is greater than the upper limit of the amount difference, use this type of neural network to determine that the amount difference is greater than the upper limit of the amount difference. The neural network outputs the current fixed deposit transfer amount, and the current fixed deposit transfer amount is greater than the fixed amount; if the certain deposit transfer amount difference between the current fixed deposit transfer amount and a historical fixed deposit transfer amount of the account is less than 0 At this time, this type of neural network is used to increase the first weight, increase the second weight, and decrease the third weight based on the fixed deposit transfer amount difference and through an inverse transfer algorithm, wherein the first weight is increased, the second weight is increased, and the third weight is decreased. A first adjustment percentage of the weight is less than a second adjustment percentage of the second weight and a third adjustment percentage of the third weight; if the fixed deposit is between the current fixed deposit transfer amount and the historical fixed deposit transfer amount When the transfer amount difference falls within a preset amount range, this type of neural network maintains the first weight, the second weight, and the third weight; if the fixed deposit transfer amount difference is greater than 0, the type of neural network The road is used to increase the first weight, increase the second weight, and increase the third weight based on the fixed deposit transfer amount difference and through the backward pass algorithm, wherein the first adjustment percentage is greater than the second adjustment Percentage and the third adjusted percentage.

The automatic saving system and automatic saving method disclosed in the present invention can plan a customized fixed deposit transfer amount and perform automatic fixed deposit transfer according to the actual personal financial income and expenditure status of the customer. When a customer has a higher demand for funds, the automatic savings system automatically reduces the customer’s fixed deposit transfer amount. On the contrary, when the customer’s funds are abundant, the automatic savings system automatically increases the customer’s fixed deposit amount, so the customer does not need to adjust by himself Fixed deposit transfer amount. To achieve the effect of simplifying the operation process.

The above description of the disclosure and the following description of the embodiments are used to demonstrate and explain the spirit and principle of the present invention, and to provide a further explanation of the scope of the patent application of the present invention.

The detailed features and advantages of the present invention will be described in detail in the following embodiments. The content is sufficient to enable anyone familiar with the relevant art to understand the technical content of the present invention and implement it accordingly, and according to the content disclosed in this specification, the scope of patent application and the drawings. Anyone who is familiar with relevant skills can easily understand the purpose and advantages of the present invention. The following examples further illustrate the viewpoints of the present invention in detail, but do not limit the scope of the present invention by any viewpoint.

FIG. 1 is a functional block diagram of the automatic deposit system according to the first embodiment of the present invention. As shown in FIG. 1, the automatic deposit system 100 includes an account monitoring host 10 and a transfer management host 12. The account monitoring host 10 communicates with the bank's internal server S through a wired or wireless network. The bank's internal server S stores the financial transaction data of all customers of the bank. The financial transaction data includes deposit information (including at least deposit amount and date of deposit), withdrawal information (including at least withdrawal amount and date of withdrawal), and transfer information (Include at least transfer amount, transfer date and transfer account). The account monitoring host 10 is used to collect deposit information and transfer information of the customer's account in each predetermined period, and the predetermined period is, for example, one month. The transfer management host 12 includes a processor 121 and an external memory 122, and the processor 121 is electrically connected to the external memory 122. The external memory 122 is used to store the customer's deposit information collected by the account monitoring host 10, the preset fixed amount, the difference between the deposit amount and the fixed amount, the preset upper limit and lower limit of the amount difference, and financial transfer data, etc. , Where the fixed amount is the monthly fixed deposit transfer amount preset by the customer in advance. The processor 121 communicates with the account monitoring host 10 via a wired or wireless network. The processor 121 further has an internal memory 123, and the internal memory 123 stores a machine learning model 13. The machine learning model 13 includes a class of neural network, fuzzy logic model, hidden Markov model, decision tree, Bayesian algorithm, conditional random domain or support vector machine. In one embodiment, the machine learning model 13 is, for example, class Neural network, and neural network-like can use the historical deposit data, historical transfer data, preset fixed amount, upper limit of the amount difference, and lower limit of the amount difference collected by the account monitoring host 10 for offline training in advance, making the analog-neural network directly When going online, upon receiving the real-time existing deposit information, the fixed deposit transfer amount that best meets the customized requirements can be calculated. The transfer management host 12 is used to execute the machine learning model 13 to drive the trained machine learning model 13 to calculate the difference between the customer’s deposit amount and the fixed amount, and to compare the difference with the lower limit and upper limit of the amount difference, respectively. The result of the comparison generates a certain amount of deposit and transfer in each predetermined period. In this embodiment, the predetermined period is every month. As a result, the machine learning model 13 of the automatic savings system 100 will adjust the current fixed deposit transfer amount according to the actual income and expenditure status of the customer every month. The transfer management host 12 further includes a drawing circuit 124. After the machine learning model 13 generates multiple data of the current fixed deposit transfer amount, the drawing circuit 124 can generate a certain deposit amount based on the multiple current fixed deposit transfer amounts and their corresponding transfer time. The curve and the fixed deposit amount curve are stored in the external memory 122. For example, if the machine learning model 13 generates the current fixed deposit transfer amount for a year, the drawing circuit 124 will generate a fixed deposit amount curve for the current year based on the current fixed deposit transfer amount for a whole year, thereby showing that the customer is in the current year. The fixed deposit transfer amount for each month of the year.

Furthermore, the transfer management host 12 can also communicate with the customer's mobile device or personal computer via a wireless network, so as to transmit the data of the fixed deposit amount curve to the customer's e-mail box. In addition, for the sake of information security, it is also possible to set that the customer’s mobile device or personal computer needs to install a designated application that matches the transfer management host 12 before it can communicate with the transfer management host 12 to receive the data of the fixed deposit amount curve. .

Fig. 2 is a functional block diagram of the automatic deposit system according to the second embodiment of the present invention. As shown in FIG. 2, the difference between the automatic savings system 200 of the second embodiment and the automatic savings system 100 of the first embodiment is that the automatic savings system 200 further includes an interest rate management host 20, which is connected via a wired or wireless network In communication with the processor 121 of the transfer management host 12 and the account monitoring host 10, the interest rate management host 20 is used to determine whether the average value of the customer’s current fixed deposit transfer amount during a predetermined period is greater than the fixed amount, thereby determining whether to adjust the customer’s Fixed deposit interest rate. For example, if the customer has more than six months of the current fixed deposit transfer amount higher than the fixed amount in the current year, so that the current year's current fixed deposit transfer amount is greater than the fixed amount, the interest rate of the automatic savings system 200 The management host 20 automatically increases the customer's fixed deposit interest rate in the next year, thereby achieving the effect of customized planning of the fixed deposit transfer amount.

The account monitoring host 10 is used to determine whether the existing deposit data of the account includes the deposit statement image files belonging to other banks in addition to the deposit data from the bank's internal server S of the bank. If the judgment result is negative, follow-up processing will be carried out directly based on the deposit information of the current bank. If the judgment result is affirmative, further identification is performed from the preset position in the deposit statement image file and the deposit balance is obtained. Then, update the existing deposit information with the sum of the deposit balance and the bank's deposit information.

In one embodiment, the preset position of the deposit amount in the deposit statement image file is obtained according to the following identification algorithm, which includes the following steps. Step 1: Each deposit statement image file is converted into grayscale image by RGB color space image. Step 2: Use the adaptive threshold value to convert the grayscale image into a binary image. Step 3: Perform horizontal projection and vertical projection on the binarized image. Step 4: Remove the blank area around the binarized image to obtain an image file for identification. Step 5: Use a classification algorithm to use the decimal point as an indicator to determine the position of each decimal point in the identification image file. Step 6: Obtain a numeric string along the horizontal direction based on the indicator, where the numeric string contains continuous Arabic numerals and commas or consecutive Arabic numerals. Step 7: Use optical character recognition (OCR) to identify keywords in the image file for identification, such as balance, balance, summary, or total. Step 8: Determine the number of horizontal reference lines or vertical reference lines that pass each number string, and use the number string with the largest number as the deposit amount in the deposit statement image file, where the horizontal parameter line or the vertical reference line passes The location of the keyword.

In addition to the above identification algorithms, fast winding neural network (FCNN), convolutional neural network (CNN), recurrent neural network (RNN) or long short-term memory neural network (LSTM) are based on multiple deposit pairs Sample bills are obtained through training. Since the format of the deposit statement graph file may be changed, and LSTM has the advantage of rapid learning of new samples, in this embodiment, the LSTM is used to obtain the default deposit amount in the deposit statement graph file position.

Fig. 3 is a flowchart of the automatic deposit method according to the first embodiment of the present invention. As shown in FIG. 3, in step 301, the account monitoring host 10 collects the customer's current deposit information in each predetermined period, and transmits the current deposit information to the external memory of the transfer management host 12 via a wired or wireless network. 122. The existing deposit information includes at least the deposit amount and the deposit date. In this embodiment, the predetermined period is set to one month.

In step 302, the processor 121 of the transfer management host 12 executes the machine learning model 13 to drive the machine learning model 13 to calculate the difference between the deposit amount and the fixed amount based on the deposit amount and the fixed amount input into the machine learning model 13 , And store the amount difference data in the external memory 122.

In step 303, the machine learning model 13 is used to compare the amount difference with the lower limit of the amount difference and the upper limit of the amount difference inputted into the machine learning model 13, and then steps 304, 305, 306 or 307 are selectively executed according to the result of the comparison. In addition, customers can also communicate with the transfer management host 12 through a designated application installed on a personal computer or mobile device, so as to reset the fixed amount entered in the machine learning model 13 through the function page provided by the online bank or mobile bank. The magnitude of the upper limit of the amount difference and the lower limit of the amount difference. In addition, the transfer management host 12 can also have a security mechanism. Even after connecting to the transfer management host 12 via a designated application, a password must be entered to reset the fixed amount, the upper limit of the amount difference and the lower limit of the amount difference to avoid non-bank customers Modify the data in the transfer management host 12 at will.

In step 304, if the machine learning model 13 determines that the amount difference is greater than zero and not greater than the lower limit of the amount difference, the machine learning model 13 is used to generate a derated deposit amount less than the fixed amount, and the derated deposit amount will be automatically deducted from the customer's current deposit account Transfer funds to the customer's fixed deposit account, and store the derated deposit amount and the transfer date in the external memory 122, where the derated deposit amount is the current fixed deposit transfer amount in line with the current customer's financial income and expenditure status. For example, the customer initially sets the monthly fixed deposit transfer amount to 10000 yuan, the lower limit of the amount difference is 2000 yuan, and the upper limit of the amount difference is 6000 yuan, which means the fixed amount and the lower limit of the amount difference input into the machine learning model 13 The upper limit of the difference with the amount is 10,000 yuan, 2,000 yuan and 6,000 yuan respectively. When the deposit amount in the customer's current deposit account is 11,000 yuan, the deposit amount entered in the machine learning model 13 is 11,000 yuan, and the machine learning model 13 is based on the entered deposit amount, fixed amount, lower limit of the amount difference, and upper limit of the amount difference Automatically reduce the fixed deposit transfer amount from 10,000 yuan to 9,000 yuan, and deduct the rated deposit amount to 9,000 yuan. Therefore, after the customer's current deposit account is automatically transferred through the machine learning model 13, the balance in the current deposit account is still 2,000 yuan, which will not be lower than the previously preset lower limit of the amount difference.

In step 305, if the machine learning model 13 determines that the amount difference is greater than the lower limit of the amount difference and not greater than the upper limit of the amount difference, the machine learning model 13 transfers a fixed amount from the customer's current deposit account to the customer's time deposit, and transfers the fixed amount The transfer date and the transfer date are stored in the external memory 122. For example, the customer initially sets the monthly fixed deposit transfer amount to 10,000 yuan, the lower limit of the amount difference is 2,000 yuan, and the upper limit of the amount difference is 6,000 yuan. When the customer’s current deposit account has a deposit of 15,000 yuan, the machine learning model 13 calculates that the amount difference is 5,000 yuan and determines that the amount difference is between the preset upper limit of the amount difference and the lower limit of the amount difference, then the machine learning model 13 Automatically transfer a fixed amount (10,000 yuan) from the customer's current deposit account to the customer's time deposit. Therefore, after the customer's current deposit account is transferred through the machine learning model 13, the balance in the account is still 5000 yuan, which is between the upper limit of the amount difference and the lower limit of the amount difference.

In step 306, if the machine learning model 13 determines that the amount difference is greater than the upper limit of the amount difference, the machine learning model 13 generates an incremental deposit amount greater than the fixed amount and transfers the incremental deposit amount from the customer's current deposit account to the customer's time deposit Account, and store the increased rated deposit amount and the corresponding transfer date in the external memory 122, where the increased rated deposit amount is the current fixed deposit transfer amount that conforms to the current customer's financial income and expenditure status. For example, the customer initially sets the monthly fixed deposit amount to 10,000 yuan, the lower limit of the amount difference is 2,000 yuan, and the upper limit of the amount difference is 6,000 yuan. When the deposit amount in the customer's current deposit account is 20,000 yuan, the machine learning model 13 calculates that the amount difference is 10,000 yuan and the determined amount difference is higher than the preset upper limit of the amount difference, then the machine learning model 13 changes the fixed deposit amount from 10,000 yuan Raise it to 14,000 yuan, and increase the deposit amount to 14,000 yuan. Therefore, after the customer's current deposit account is transferred through the machine learning model 13, the balance in the current deposit account is 6000 yuan, which will not exceed the upper limit of the amount difference.

In step 307, if the machine learning model 13 determines that the amount difference is less than zero, which means that the deposit amount in the customer's current deposit account is lower than the preset fixed amount, the machine learning model 13 does not transfer the account. In other embodiments, when the machine learning model 13 does not transfer funds, it further sends a short message to the customer's mobile device to inform the customer that the account balance is insufficient.

FIG. 4 is a schematic diagram of an embodiment of a machine learning model of the automatic deposit system of FIG. 2. As shown in Figure 4, the neural network as the machine learning model 13 includes a first node N1 to a fourth node N4, where the first node N1 and the second node N2 are input nodes and the functions are both [|( The first input data)-(the second input data) |-(the third input data)], which means the first input data minus the absolute value of the second input data and then the third input data. The three input data of the first node N1 are the deposit amount, the fixed amount, and the upper limit of the amount difference. The deposit amount, the fixed amount, and the upper limit of the amount difference are the first to third input data of the first node N1, respectively. The three input data of the second node N2 are the deposit amount, the fixed amount, and the lower limit of the amount difference. The deposit amount, the fixed amount, and the lower limit of the amount difference are the first to third input data of the second node N2, respectively. The absolute value of the difference between the deposit amount and the fixed amount is the amount difference.

The third node N3 is an intermediate node and its function is to determine whether [amount difference-upper limit of amount difference] and [amount difference-lower limit of amount difference] are greater than 0, where the amount difference is the difference between the deposit amount and the fixed amount. The fourth node N4 is the output node and its function is the sum of the three input data, and the three input data of the fourth node N4 are (amount difference-amount difference upper limit) * first weight W1, (amount difference-amount Difference lower limit) * second weight W2, and (fixed amount) * third weight W3. The output of the fourth node N4 of the similar neural network is the current month's current fixed deposit transfer amount.

In this embodiment, the neural network has an online learning mechanism. If the output of the fourth node N4 of the neural network is less than the historical fixed deposit transfer amount of the same month in the previous year, for example, the current value of January 2020 The fixed deposit transfer amount is less than the historical fixed deposit transfer amount in January 2019, then the neural network will base the fixed deposit transfer amount between the current fixed deposit transfer amount in the current month and the historical fixed deposit transfer amount in the same month of the previous year The first weight W1 is increased, the second weight W2 is increased, and the third weight W3 is decreased. The adjustment percentage of the first weight W1 is less than the adjustment percentage of the second weight W2 and the third weight W3. For example, the adjustment percentage for increasing the first weight W1 is 12%, the adjustment percentage for increasing the second weight W2 is 20%, and the adjustment percentage for decreasing the third weight W3 is 20%. The above adjustment percentage is an example , Not limited to this.

If the difference between the current fixed deposit transfer amount in the current year of the neural network and the historical fixed deposit transfer amount in the same month of the previous year falls within a preset amount range, the neural network maintains the current first A weight W1, a second weight W2, and a third weight W3.

If the current fixed-deposit transfer amount in the current year of the analogous neural network is greater than the historical fixed-deposit transfer amount in the same month of the previous year, the analog-neural network will base on the current fixed-deposit transfer amount in the current year and the history of the same month in the previous year The difference between the fixed deposit transfer amount and the reverse transfer algorithm is used to increase the first weight W1, the second weight W2, and the third weight W3, where the adjustment percentage of the first weight W1 is greater than The adjustment percentage ratio of the second weight W2 to the third weight W3, for example, the adjustment percentage of increasing the first weight W1 is 20%, the adjustment percentage of increasing the second weight W2 is 12%, and the adjustment of increasing the third weight W3 The percentage rate is 12%. The above percentage rate is an example, not limited to this.

Fig. 5 is a flowchart of the automatic deposit method according to the second embodiment of the present invention. As shown in FIG. 5, the difference between the automatic deposit method of the second embodiment and the automatic deposit method of the first embodiment is that it further includes using the interest rate management host 20 to determine whether the average value of the fixed deposit transfer amount of the account within a predetermined period is greater than the predetermined period. Set a fixed amount. If the average value is greater than the fixed amount, the fixed deposit interest rate of the account will be increased.

In other embodiments, before the account monitoring host 10 of the automatic savings system collects the deposit information of the account in each predetermined period, the machine learning model 13 of the automatic savings system can also undergo offline learning, taking a neural network as an example based on the collected data. Historical deposit data (including deposit amount and deposit date) and historical transfer data (including transfer amount and transfer date) of the account can be based on the above historical deposit data and historical transfer data and combined with the fixed amount and amount preset by the machine learning model 13 The upper limit of the difference and the lower limit of the amount difference are used for offline training, so that the fixed deposit transfer amount output by the machine learning model 13 can be consistent with the personal financial transaction behavior of each account.

In this way, the more historical financial transaction data collected, the fixed deposit transfer calculated when the neural network after offline training receives real-time deposit data, fixed amount, lower limit of amount difference, and upper limit of amount difference The amount will also be more in line with the customer's income and expenditure situation, so as to achieve the effect of personalized planning and arrangement of fixed deposit transfer. Furthermore, when the external memory 122 stores the data of the fixed deposit transfer amount for each month of the previous year, the neural network can also use the fixed deposit amount curve of the previous year as the basis for adjusting the weight.

In other embodiments, the automatic savings system can analyze the customer's transaction details over the years. When the annual premium, tuition payment month, or mortgage balance has been reduced, there are more funds to save. This can be done when the customer logs in to the automatic savings system A prompt message appears to remind customers whether they need to modify the setting conditions of automatic savings (fixed amount, upper limit of amount difference, and lower limit of amount difference) and display the current fixed deposit plan.

In other embodiments, after the automatic savings system calculates the fixed deposit transfer amount, it does not perform the fixed deposit transfer by itself, and can first output a confirmation operation page to the user's personal computer or mobile communication device, and the confirmation interface will The current fixed deposit transfer amount calculated by the automatic savings system is first filled in the certain deposit transfer amount input column on the confirmation operation page.

There is a confirmation button and a cancel button on the confirmation operation page. When the customer confirms that the current deposit transfer amount in the fixed deposit transfer amount input column is correct, no additional adjustment is required. The customer only needs to press the confirm button, then The automatic savings system then performs fixed deposit transfers. If the customer thinks that the current fixed deposit transfer amount in the fixed deposit transfer amount input column needs to be adjusted, they can also press the cancel button, and then enter the new current fixed deposit transfer amount in the fixed deposit transfer amount input column, and then press the confirm button. Then the automatic savings system will perform the fixed deposit transfer based on the newly entered current fixed deposit transfer amount. In this way, the operation process of the fixed deposit transfer can be greatly simplified, so as to reduce the situation that the automatic deposit system transfers the wrong fixed deposit amount.

In summary, the automatic savings system and automatic savings method disclosed in the present invention can plan a customized fixed deposit transfer amount and perform automatic fixed deposit transfer based on the actual personal financial income and expenditure of the customer. When a customer has a higher demand for funds, the automatic savings system automatically reduces the customer’s fixed deposit transfer amount. On the contrary, when the customer’s funds are abundant, the automatic savings system automatically increases the customer’s fixed deposit amount, so the customer does not need to adjust by himself Fixed deposit transfer amount. To achieve the effect of simplifying the operation process.

Although the present invention is disclosed in the foregoing embodiments, it is not intended to limit the present invention. All changes and modifications made without departing from the spirit and scope of the present invention fall within the scope of the patent protection of the present invention. For the scope of protection defined by the present invention, please refer to the attached scope of patent application.

100: automatic savings system 10: Account monitoring host 12: Transfer management host 121: processor 122: external memory 123: Internal memory 124: drawing circuit 13: machine learning model 200: automatic savings system 20: Interest rate management host S: Bank's internal server N1~N4: the first node to the fourth node W1~W3: the first weight ~ the third weight

FIG. 1 is a functional block diagram of the automatic deposit system according to the first embodiment of the present invention. Fig. 2 is a functional block diagram of the automatic deposit system according to the second embodiment of the present invention. Fig. 3 is a flowchart of the automatic deposit method according to the first embodiment of the present invention. Fig. 4 is a schematic diagram of an embodiment of a machine learning model of the automatic savings system of Fig. 2 Fig. 5 is a flowchart of the automatic deposit method according to the second embodiment of the present invention.

100: automatic savings system

10: Account monitoring host

12: Transfer management host

121: processor

122: external memory

123: Internal memory

124: drawing circuit

13: machine learning model

S: Bank's internal server

Claims (9)

An automatic savings system includes: an account monitoring host, which collects an existing deposit data of an account in each predetermined period, the existing deposit information includes a deposit amount and a deposit time; a transfer management host, which is communicatively connected to the account monitoring Host, the transfer management host stores a machine learning model, the machine learning model is a type of neural network, the type of neural network includes a first node, a second node, a third node and a fourth node, the first A node is used to receive the deposit amount, a fixed amount, and an upper limit of the amount difference, the second node is used to receive the deposit amount, the fixed amount, and a lower limit of the amount difference, the first node and the second node are respectively connected to The third node, the fourth node are connected to the third node, a first weight and a second weight are connected between the third node and the fourth node, and there is a connection between the fixed amount and the fourth node The third weight, the transfer management host is used to execute this type of neural network, the first node and the second node are used to calculate an amount difference between the deposit amount and the fixed amount, and the third node is used to compare The amount difference, the lower limit of the amount difference, and the upper limit of the amount difference, the fourth node is used to output a current fixed deposit transfer amount in each predetermined period, if the current fixed deposit transfer amount and a historical fixed deposit transfer of the account When the difference between a certain deposit and transfer amount between the amounts is less than 0, this type of neural network is used to increase the first weight, increase the second weight, and adjust the difference based on the fixed deposit and transfer amount through an inverse pass algorithm. Decrease the third weight, where a first adjustment percentage of the first weight is less than a second adjustment percentage of the second weight and a third adjustment percentage of the third weight; if the difference between the fixed deposit transfer amount is greater than 0 , This type of neural network is used according to the fixed deposit transfer amount difference and through the backward pass algorithm To increase the first weight, increase the second weight, and increase the third weight, wherein the first adjustment percentage is greater than the second adjustment percentage and the third adjustment percentage; and a confirmation operation page for the confirmation operation The page is equipped with a certain deposit and transfer amount input column, a confirmation button and a cancel button. The fixed deposit and transfer amount input column has been filled with the current fixed deposit and transfer amount. When the confirmation button is in a consistent state, the automatic savings system is based on The current fixed deposit transfer amount is transferred; wherein the transfer management host further includes a drawing circuit that generates a certain deposit amount curve for the current year based on a current fixed deposit transfer amount in a whole year and sets the fixed amount through a network The deposit curve is sent to an e-mail box of a customer. The automatic savings system according to claim 1, wherein the predetermined period is one month. The automatic deposit system according to claim 1, wherein the transfer management host includes a processor and an external memory, the processor is electrically connected to the external memory, the processor further has an internal memory, and the internal The memory is used to store this type of neural network, and the external memory is used to store the existing deposit data, the fixed amount, the upper limit of the amount difference, and the lower limit of the amount difference. The processor drives the neural network based on the existing deposit The data, the fixed amount, the upper limit of the amount difference, and the lower limit of the amount difference are used to generate the current fixed deposit transfer amount in each predetermined period. The automatic savings system according to claim 1, further comprising an interest rate management host, the interest rate management host is communicatively connected to the transfer management host and the account monitoring host, and the interest rate management host is used to determine the fixed deposit amount for a predetermined period Whether the average value is greater than the fixed amount to determine whether to increase the fixed deposit interest rate of the account. The automatic savings system according to claim 4, wherein the predetermined period is the past year. An automatic saving method is implemented by an automatic saving system. The automatic saving method includes: collecting an existing deposit data of an account in each predetermined period by an account monitoring host of the automatic saving system, and the existing deposit data includes a deposit Amount and a deposit time; a machine learning model is executed by a transfer management host of the automatic savings system. The machine learning model is a type of neural network. This type of neural network receives a fixed amount, an upper limit of the amount difference, and an amount The lower limit of the difference and the amount of the deposit; use this type of neural network to calculate the difference between the amount of the deposit and a fixed amount; use this type of neural network to compare the difference with a lower limit of the amount difference and an upper limit of the amount difference; if This type of neural network determines that the amount difference is greater than zero and less than or equal to the lower limit of the amount difference, and uses this type of neural network to output a current fixed deposit transfer amount, and the current fixed deposit transfer amount is less than the fixed amount; if this type of neural network The network determines that the amount difference is greater than the upper limit of the amount difference, and uses this type of neural network to output the current fixed deposit transfer amount, and the current fixed deposit transfer amount is greater than the fixed amount; if the current fixed deposit transfer amount is equal to the amount of the account When the fixed deposit transfer amount difference between the historical fixed deposit transfer amounts is less than 0, this type of neural network uses the fixed deposit transfer amount difference and an inverse transfer algorithm to increase the first weight and increase the A second weight and lowering the third weight, wherein a first adjustment percentage of the first weight is less than a second adjustment percentage of the second weight and a third adjustment percentage of the third weight; If the fixed deposit transfer amount difference between the current fixed deposit transfer amount and the historical fixed deposit transfer amount falls within a preset amount range, this type of neural network maintains the first weight, the second weight, and the The third weight; and if the fixed deposit transfer amount difference is greater than 0, this type of neural network is used to increase the first weight and increase the first weight based on the fixed deposit transfer amount difference and through the backward pass algorithm Second weight and increase the third weight, wherein the first adjustment percentage is greater than the second adjustment percentage and the third adjustment percentage; and a drawing circuit of the transfer management host is used to transfer a current fixed deposit for a whole year The amount generates a certain deposit amount curve for the current year, and the fixed deposit amount curve is sent to an e-mail box of a customer through a network. The automatic saving method according to claim 6, wherein the predetermined period is one month. The automatic deposit method described in claim 6 further includes that if the neural network determines that the amount difference is less than zero, then the neural network does not perform the transfer. The automatic savings method described in claim 6 further includes determining whether the average value of the fixed deposit transfer amount of the account in a predetermined period is greater than the fixed amount, and if it is greater than the fixed amount, the fixed deposit interest rate of the account is increased.

Images