TWM666241U - Analysis system of financial securities product value model based on artificial intelligence - Google Patents

Abstract

An analysis system of a financial securities product value model based on artificial intelligence is proposed. The analysis system of the financial securities product value model based on artificial intelligence includes a cloud server and a processor. The processor is implemented to perform a determining step, a data acquiring step, an analyzing step and a strategy generating step. The determining step is performed to determine that a customer is a long-term investing customer or a short-term investing customer. The data acquiring step is performed to acquire a plurality of long-term trading parameters or a short-term trading data. The analyzing step is performed to divide a plurality of financial securities products into a plurality of groups, and calculate a plurality of classify conditions corresponding to the groups and an importance value of each of the long-term trading parameters, and analyze a product relevance and a purchasing sequence. The strategy generating step is performed to generate a purchasing strategy according to the groups, the classify conditions, the importance value of each of the long-term trading parameters, the product relevance and the purchasing sequence. Thus, the analysis method and the system of the financial securities product value model based on artificial intelligence of the present disclosure can generate the purchasing strategy corresponding to specific customer.

Description

Financial securities product value model analysis system using artificial intelligence

The present invention relates to a product value model analysis system using artificial intelligence, and in particular to a financial securities product value model analysis system using artificial intelligence.

The investment forecasting system used to predict the future growth and investment return of financial securities products is based on the historical data of various financial securities products. However, most investment forecasts are very different from the actual situation, and the forecast results cannot be trusted by consumers.

In view of this, developing a financial securities product value model analysis system that uses artificial intelligence to analyze the investment characteristics of specific consumers using different prediction methods to provide consumers with financial securities product purchase strategies has become a goal worth developing for relevant industries.

Therefore, the purpose of the present invention is to provide a financial securities product value model analysis system using artificial intelligence, which analyzes corresponding purchase strategies based on different analysis steps according to the investment characteristics of different consumers.

According to an implementation method of the structural aspect of the present invention, a financial securities product value model analysis system using artificial intelligence is provided to predict a consumer's purchase strategy for multiple financial securities products. The financial securities product value model analysis system using artificial intelligence includes a cloud database and a processor. The cloud database includes multiple long-term transaction parameters and short-term transaction data for each financial securities product. The processor signal is connected to the cloud database and is configured to implement a determination step, a data collection step, an analysis step, and a strategy generation step. The determination step is to determine whether the consumer is a long-term investment customer or a short-term investment customer. The data collection step is to obtain one of these long-term trading parameters and short-term trading data of each financial securities product from the cloud database based on the long-term investment customers and the short-term investment customers. These long-term trading parameters and short-term trading data correspond to the long-term investment customers and the short-term investment customers respectively. The analysis step includes a long-term strategy analysis step and a short-term strategy analysis step. The long-term strategy analysis step is to divide these financial securities products into multiple groups and calculate the multiple classification conditions corresponding to these groups and an importance value of each long-term trading parameter. The short-term strategy analysis step is to drive the processor to analyze a product correlation and a purchase order of these financial securities products. The strategy generation step generates a purchase strategy based on these groups, these classification conditions, the importance values of each long-term transaction parameter, product relevance, and purchase order. When a consumer is judged to be a long-term investment customer, the processor executes a long-term strategy analysis step; when a consumer is judged to be a short-term investment customer, the processor executes a short-term strategy analysis step.

Thus, the new financial securities product value model analysis system using artificial intelligence collects corresponding transaction data for long-term investment or short-term investment according to the consumer's investment habits, analyzes it, and provides the consumer with a corresponding purchase strategy.

Other implementations of the aforementioned implementation method are as follows: The aforementioned financial securities product value model analysis system using artificial intelligence may further include a dynamic dialing device. The dynamic dialing device is signal-connected to the processor, and is used for the processor to obtain an Internet Protocol address to connect to the cloud database by signal. The processor includes a dialing monitoring module. The dialing monitoring module is used to monitor whether the dynamic dialing device can dial and connect to the cloud database by signal. When the dynamic dialing device cannot dial and connect to the cloud database, the dialing monitoring module drives the dynamic dialing device to obtain another Internet Protocol address to connect to the cloud database by signal.

Other implementations of the aforementioned implementation method are as follows: The aforementioned long-term trading parameters may include a risk factor, a debt-to-equity ratio, a book value return rate, a price-to-book value ratio, a revenue growth rate, a market value, a turnover rate, a trading volume, a price per share, and a momentum factor. The long-term strategy analysis step includes a grouping step, a classification step, and a verification step. The grouping step is to classify these financial securities products into these groups based on a self-organizing mapping algorithm. These groups include a high return rate group, a medium return rate group, and a low return rate group. The classification step is to summarize these classification conditions corresponding to the high return rate group, the medium return rate group, and the low return rate group based on these long-term trading parameters of these financial securities products. The verification step is based on a deep neural network model to verify the importance value of each long-term trading parameter.

Other embodiments of the above-mentioned implementation method are as follows: The above-mentioned short-term strategy analysis step may include a correlation analysis step and a sequence analysis step. The correlation analysis step is to analyze the product correlation of these financial securities products based on a correlation analysis method. The sequence analysis step is to analyze the purchase order of these financial securities products based on a sequence analysis model.

Other embodiments of the aforementioned implementation method are as follows: The aforementioned financial securities product value model analysis system using artificial intelligence may further include a webcam device. The webcam device signal is connected to the processor, and the webcam device is used to capture a facial image of the consumer. The processor is further configured to implement a consumer identification step. The consumer identification step is to identify the facial image of the consumer according to a face recognition program. The consumer identification step is performed before the determination step.

The following will describe several embodiments of the present invention with reference to the drawings. For the sake of clarity, many practical details will be described together in the following description. However, it should be understood that these practical details should not be used to limit the present invention. In other words, in some embodiments of the present invention, these practical details are not necessary. In addition, in order to simplify the drawings, some commonly known structures and components will be shown in the drawings in a simple schematic manner; and repeated components may be represented by the same number.

In addition, in this article, when a certain component (or unit or module, etc.) is "connected" to another component, it may refer to that the component is directly connected to the other component, or it may refer to that the component is indirectly connected to the other component, that is, there are other components between the component and the other component. When it is clearly stated that a certain component is "directly connected" to another component, it means that there are no other components between the component and the other component. The terms first, second, third, etc. are only used to describe different components, and there is no restriction on the components themselves. Therefore, the first component can also be renamed as the second component. Moreover, the combination of components/units/circuits in this article is not a generally known, conventional or familiar combination in this field. Whether the components/units/circuits themselves are known cannot be used to determine whether their combination relationship is easy to be completed by ordinary knowledge in the technical field.

Please refer to FIG. 1, which is a flow chart of the financial securities product value model analysis method S10 using artificial intelligence of the first embodiment of the present invention. The financial securities product value model analysis method S10 using artificial intelligence is used to predict a consumer's purchase strategy for a plurality of financial securities products 10 (see FIG. 3). The financial securities product value model analysis method S10 using artificial intelligence includes a determination step S02, a data collection step S04, an analysis step S06, and a strategy generation step S08. The determination step S02 drives a processor 110 (see FIG. 3) to determine whether the consumer is a long-term investment customer or a short-term investment customer. The data collection step S04 is to drive the processor 110 to obtain one of a plurality of long-term trading parameters 121 (see FIG. 3 ) and a short-term trading data 122 (see FIG. 3 ) of each financial securities product 10 from a cloud database 120 (see FIG. 3 ) according to the long-term investment type customers and the short-term investment type customers. These long-term trading parameters 121 and short-term trading data 122 correspond to the long-term investment type customers and the short-term investment type customers, respectively. The analysis step S06 includes a long-term strategy analysis step S06a and a short-term strategy analysis step S06b. The long-term strategy analysis step S06a drives the processor 110 to divide these financial securities products 10 into a plurality of groups, and calculates a plurality of classification conditions corresponding to these groups and an importance value of each long-term trading parameter 121. The short-term strategy analysis step S06b drives the processor 110 to analyze a product correlation and a purchase order of these financial securities products 10. The strategy generation step S08 drives the processor 110 to generate a purchase strategy based on these groups, these classification conditions, the importance value of each long-term trading parameter 121, the product correlation and the purchase order. When the consumer is determined to be a long-term investment type customer, the processor 110 executes a long-term strategy analysis step S06a; when the consumer is determined to be a short-term investment type customer, the processor 110 executes a short-term strategy analysis step S06b.

Specifically, the judgment step S02 drives the processor 110 to obtain the consumer's historical purchase and sale details, and judges whether the consumer is a long-term investment customer or a short-term investment customer based on the time difference between the consumer's previous purchase and sale of the same financial securities product 10. In this embodiment, when the time difference between the consumer's purchase and sale of the same financial securities product 10 is greater than or equal to 6 months, the judgment step S02 judges that the consumer is a long-term investment customer; when the time difference between the consumer's purchase and sale of the same financial securities product 10 is less than 6 months, the judgment step S02 judges that the consumer is a short-term investment customer, but the present invention is not limited to this.

Specifically, when the consumer is determined to be a long-term investment customer, the data collection step S04 is to drive the processor 110 to obtain the long-term trading parameters 121 of each financial securities product 10 from the cloud database 120. The long-term trading parameters 121 may include a risk factor β, a debt/equity ratio (D/E), a return on equity (ROE), a price-book ratio (P/B), a revenue growth rate, a market value, a turnover rate, a trading volume, a share price, and a momentum factor. These long-term trading parameters 121 corresponding to each financial securities product 10 can be shown in Table 1. The product code is the code corresponding to each financial securities product 10. When the consumer is determined to be a short-term investment customer, the data collection step S04 is to drive the processor 110 to obtain short-term transaction data 122 from the cloud database 120. In this embodiment, the short-term transaction data 122 can be the transaction details of the financial securities product 10 within five working days, but the present invention is not limited to this. Table 1 Product Code 1 2 3 4 Risk Factors 0.31 0.45 0.57 1.1 Debt-to-Equity Ratio 27.09 26.62 415.4 80.79 Return on Equity 5.72 4.77 -43.64 0.47 Price to Book Ratio 0.95 0.74 1.16 0.99 Revenue growth rate 8.56 2.74 14.65 -8.01 Market Cap 22.31 132.42 10.69 248.52 Turnover rate 41.56 6.53 136.19 119.42 Volume 73595 26233 102144 1978608 Stock Price 12.6 32.95 14.25 15 Kinetic Factor 9.14 16.1 85.08 42.12

Thus, the novel financial securities product value model analysis method S10 using artificial intelligence collects corresponding transaction data for long-term investment or short-term investment according to the consumer's investment habits, and provides the consumer with a corresponding purchase strategy. The following will explain the operation of the long-term strategy analysis step S06a and the short-term strategy analysis step S06b through a more detailed implementation example.

Please refer to Figure 1 and Figure 2. Figure 2 is a flow chart of the financial securities product value model analysis method S20 using artificial intelligence of the second embodiment of the present invention. The financial securities product value model analysis method S20 using artificial intelligence includes a determination step S12, a data collection step S14, an analysis step S16, and a strategy generation step S18. The analysis step S16 includes a long-term strategy analysis step S16a and a short-term strategy analysis step S16b. In the implementation method of FIG. 2, the determination step S12 and the data collection step S14 of the financial securities product value model analysis method S20 using artificial intelligence are respectively the same as the determination step S02 and the data collection step S04 of the financial securities product value model analysis method S10 using artificial intelligence in FIG. 1, and will not be repeated. In particular, the long-term strategy analysis step S16a may include a grouping step S161, a classification step S162, and a verification step S163. The short-term strategy analysis step S16b may include a correlation analysis step S164 and a sequence analysis step S165.

The grouping step S161 drives the processor 110 to group the financial securities products 10 into these groups according to a self-organizing map algorithm 111 (see FIG. 3 ). These groups include a high return rate group, a medium return rate group, and a low return rate group. Specifically, the grouping step S161 uses the self-organizing map algorithm 111 to analyze the long-term trading parameters 121 of each financial securities product 10 to group the plurality of financial securities products 10 into three groups (i.e., a high return rate group, a medium return rate group, and a low return rate group).

The classification step S162 drives the processor 110 to summarize the classification conditions corresponding to the high rate of return group, the medium rate of return group and the low rate of return group according to the long-term transaction parameters 121 of the financial securities products 10. The classification step S162 uses the decision tree classification (Classification And Regression Tree; CART) rule to derive the long-term transaction parameters 121 of the financial securities products 10 in the high rate of return group, the medium rate of return group and the low rate of return group, and then obtains the classification conditions of the high rate of return group, the medium rate of return group and the low rate of return group. The classification conditions of the high rate of return group, the medium rate of return group and the low rate of return group can be shown in Table 2. For example, when the value of the long-term trading parameter 121 of the financial securities product 10 meets the classification conditions, the financial securities product 10 can be directly predicted as a high return rate group, a medium return rate group or a low return rate group. β represents the risk factor; MOM represents the momentum factor. Table 2 Classification conditions Group 0.655＜β≤0.872 High return group MOM≤27.7 High return group 0.875＜β Medium return group β≤0.872 Low return group Turnover rate ≤139.62 Low return group

The verification step S163 drives the processor 110 to verify the importance value of each long-term trading parameter 121 according to a deep neural network (DNN) model 112 (see FIG. 3 ). The verification step S163 uses the deep neural network model 112 to analyze these long-term trading parameters 121 of the financial securities products 10 in the high return rate group, the medium return rate group, and the low return rate group to verify the importance value of each financial securities product 10. The importance value represents the importance of each long-term trading parameter 121 to the clustering result of the clustering step S161. The importance value of each long-term trading parameter 121 of the implementation method of FIG. 2 can be shown in Table 3. Thus, the novel financial securities product value model analysis method S20 using artificial intelligence groups the financial securities products 10 according to the long-term transaction parameters 121 of the financial securities products 10, and then provides a specific purchase strategy for the investment habits of specific consumers. Table 3 Long-term trading parameters Importance value Risk Factors 0.21 Turnover rate 0.16 Kinetic Factor 0.15 Volume 0.12 Stock Price 0.03 P/B Ratio 0.03 ROE 0.01 Rate of Return 0.01

The correlation analysis step S164 drives the processor 110 to analyze the product correlation of these financial securities products 10 according to a correlation analysis method 113 (see Figure 3). The correlation analysis step S164 calculates the probability of each financial securities product 10 being purchased at the same time through the correlation analysis method 113. The calculation results of the correlation analysis method 113 are shown in Table 4. The former item represents the financial securities product 10 sold by the former item; the latter item represents the financial securities product 10 sold after the former item is sold; the support degree is the probability of the latter item and the former item being sold at the same time; the credibility is the probability of the latter item being sold when the former item is sold. It can be seen from Table 4 that the probability of financial securities product A and financial securities product B being sold at the same time is 66.67%. Table 4 Previous The latter Support Credibility A B 0.1 66.67 C D 0.065 50 C E 0.066 50 F D 0.066 50 F G 0.066 50

The order analysis step S165 drives the processor 110 to analyze the purchase order of these financial securities products 10 according to an order analysis model 114 (see Figure 3). The order analysis model 114 is used to analyze the purchase order between each financial securities product 10. Please refer to Table 5. Table 5 lists the purchase order between financial securities product A and other financial securities products B, C, D and E. It can be seen from Table 5 that the probability that consumers purchase financial securities product B first and then purchase financial securities product A is 96.8%; the probability of purchasing financial securities product C and then purchasing financial securities product A is 83.3%. Table 5 Product Code Credibility B 96.8% C 83.3% D 64.7% E 52.94%

When the consumer is determined to be a long-term investment customer, the strategy generation step S18 generates a purchase strategy based on the groups, classification conditions, and importance values of the corresponding long-term transaction parameters 121 calculated in the grouping step S161, the classification step S162, and the verification step S163. For example, the strategy generation step S18 may apply the long-term transaction parameters 121 of the financial securities product 10 previously purchased by the consumer to the classification conditions, and judge the consumer's investment habits to purchase high-risk and high-return financial securities products 10 or low-risk and low-return financial securities products 10 based on the classification conditions of the aforementioned financial securities products 10, and then recommend to the consumer financial securities products 10 that belong to the same group as the aforementioned financial securities products 10.

When the consumer is determined to be a short-term investment customer, the strategy generation step S18 generates a purchase strategy based on the product correlation and purchase order calculated by the correlation analysis step S164 and the order analysis step S165. Specifically, when the financial securities products 10 with higher product correlation and higher purchase order probability analyzed by the correlation analysis step S164 and the order analysis step S165 are financial securities products 10 of the same industry type, the strategy generation step S18 recommends the financial securities products 10 of the aforementioned industry type to the short-term investment customer, but the present invention is not limited thereto.

Please refer to Figures 1, 2 and 3. Figure 3 is a block diagram of a financial securities product value model analysis system 100 using artificial intelligence in the third embodiment of the present invention. The financial securities product value model analysis system 100 using artificial intelligence is used to predict a consumer's purchase strategy for a plurality of financial securities products 10. The financial securities product value model analysis system 100 using artificial intelligence includes a processor 110 and a cloud database 120. The cloud database 120 includes a plurality of long-term transaction parameters 121 and a short-term transaction data 122 for each financial securities product 10. The processor 110 is signal-connected to the cloud database 120 and is configured to implement the financial securities product value model analysis methods S10 and S20 using artificial intelligence. Specifically, the processor 110 may be a central processing unit (CPU), a virtual private server (VPS) or other electronic computing devices, and the cloud database 120 may be a memory or other storage devices, but the present invention is not limited thereto.

Please refer to Figures 4 and 5. Figure 4 is a block diagram of the financial securities product value model analysis system 100a using artificial intelligence in the fourth embodiment of the present invention; Figure 5 is a flow chart of the financial securities product value model analysis method S30 using artificial intelligence in the fifth embodiment of the present invention. The financial securities product value model analysis system 100a using artificial intelligence includes a processor 110a and a cloud database 120. In the embodiment of Figure 4, the cloud database 120 of the financial securities product value model analysis system 100a using artificial intelligence operates in the same manner as the cloud database 120 of the financial securities product value model analysis system 100 using artificial intelligence in the embodiment of Figure 3, and will not be described in detail. In particular, the financial securities product value model analysis system 100a using artificial intelligence may further include a webcam device 130 and a dynamic dialing device 140. The processor 110a may include a dialing monitoring module 116. The processor 110a is configured to implement the financial securities product value model analysis method S30 using artificial intelligence.

The financial securities product value model analysis method S30 using artificial intelligence includes a determination step S22, a data collection step S25, an analysis step S26, and a strategy generation step S28. The analysis step S26 includes a long-term strategy analysis step S26a and a short-term strategy analysis step S26b. The long-term strategy analysis step S26a may include a grouping step S261, a classification step S262, and a verification step S263. The short-term strategy analysis step S26b may include a correlation analysis step S264 and a sequence analysis step S265. In the implementation method of FIG. 5, the determination step S22, data collection step S25, analysis step S26, strategy generation step S28, long-term strategy analysis step S26a, short-term strategy analysis step S26b, clustering step S261, classification step S262, verification step S263, correlation analysis step S264 and first-order analysis step S265 of the financial securities product value model analysis method S30 using artificial intelligence are respectively connected to the second The determination step S12, data collection step S14, analysis step S16, strategy generation step S18, long-term strategy analysis step S16a, short-term strategy analysis step S16b, grouping step S161, classification step S162, verification step S163, correlation analysis step S164 and sequence analysis step S165 of the financial securities product value model analysis method S20 of the embodiment of the figure are the same and will not be repeated. In particular, the financial securities product value model analysis method S30 using artificial intelligence may further include a consumer identification step S21, an automatic dialing step S23 and a dialing monitoring step S24. The consumer identification step S21 is performed before the determination step S22, and the automatic dialing step S23 and the dialing monitoring step S24 are performed before the data collection step S25.

The webcam 130 is connected to the processor 110a. The webcam 130 is used to capture a facial image of the consumer. The processor 110a is further configured to implement a consumer identification step S21. The consumer identification step S21 is to drive the webcam 130 to capture a facial image of the consumer and identify the facial image of the consumer according to a face recognition program 115. Specifically, after the consumer identification step S21 drives the network camera 130 to capture the consumer's facial image, the processor 110a is driven to capture the feature value in the facial image through an artificial intelligence algorithm, and compares it with the feature values of other facial images recorded in the cloud database 120 to identify the current consumer's identity.

The dynamic dialing device 140 is connected to the processor 110a and is used to perform the automatic dialing step S23. The automatic dialing step S23 drives the dynamic dialing device 140 to obtain an Internet Protocol (IP) address, so that the processor 110a is connected to the cloud database 120.

The dial monitoring step S24 is to drive the dial monitoring module 116 to monitor whether the dynamic dialing device 140 can dial and connect to the cloud database 120 by signal. When the dynamic dialing device 140 cannot dial and connect to the cloud database 120, the dial monitoring module 116 drives the dynamic dialing device 140 to obtain another Internet protocol address to connect to the cloud database 120 by signal.

Specifically, the data collection step S25 is to drive a crawler program by the processor 110a to collect the long-term trading parameters 121 and short-term trading data 122 of the plurality of financial securities products 10 in the cloud database 120. However, when the crawler program connects to the cloud database 120 and crawls data through the same Internet protocol address signal for multiple times, the cloud database 120 may block the aforementioned Internet protocol address signal from connecting to the cloud database 120. Therefore, the new financial securities product value model analysis system 100a using artificial intelligence continuously monitors the dialing status of the dynamic dialing device 140 through the dialing monitoring module 116, generates another Internet protocol address when the dynamic dialing device 140 fails to dial, and drives the dynamic dialing device 140 to dial through another Internet protocol address.

Thus, the new financial securities product value model analysis system 100a using artificial intelligence ensures that the processor 110a stably collects the long-term transaction parameters 121 and short-term transaction data 122 corresponding to each financial securities product 10 in the cloud database 120 through the dial monitoring module 116, so as to perform subsequent purchase strategy analysis.

From the above implementation, it can be seen that the new type has the following advantages. First, according to the investment habits of consumers, corresponding transaction data is collected for long-term investment or short-term investment for analysis, and corresponding purchase strategies are given to consumers; second, financial securities products are grouped according to these long-term transaction parameters of financial securities products, and then specific purchase strategies are given according to the investment habits of specific consumers; third, through the dial monitoring module, it is ensured that the processor stably collects the long-term transaction parameters and short-term transaction data corresponding to each financial securities product in the cloud database, so as to carry out subsequent purchase strategy analysis.

Although the present invention has been disclosed in the form of implementation as above, it is not intended to limit the present invention. Anyone skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the scope defined in the attached patent application.

100,100a: Financial securities product value model analysis system using artificial intelligence 10: Financial securities product 110,110a: Processor 111: Self-organizing map algorithm 112: Deep neural network model 113: Correlation analysis method 114: Order analysis model 115: Face recognition program 116: Dial monitoring module 120: Cloud database 121: Long-term transaction parameters 122: Short-term transaction data 130: Network camera device 140: Dynamic dialing device S10,S20,S30: Financial securities product value model analysis method using artificial intelligence S02,S12,S22: Judgment step S04, S14, S25: Data collection step S06, S16, S26: Analysis step S06a, S16a, S26a: Long-term strategy analysis step S06b, S16b, S26b: Short-term strategy analysis step S161, S261: Grouping step S162, S262: Classification step S163, S263: Verification step S164, S264: Correlation analysis step S165, S265: Sequence analysis step S08, S18, S28: Strategy generation step S21: Consumer identification step S23: Automatic dialing step S24: Dialing monitoring step

Figure 1 is a flow chart of the method for analyzing the value model of financial securities products using artificial intelligence in the first embodiment of the present invention; Figure 2 is a flow chart of the method for analyzing the value model of financial securities products using artificial intelligence in the second embodiment of the present invention; Figure 3 is a block diagram of the system for analyzing the value model of financial securities products using artificial intelligence in the third embodiment of the present invention; Figure 4 is a block diagram of the system for analyzing the value model of financial securities products using artificial intelligence in the fourth embodiment of the present invention; and Figure 5 is a flow chart of the method for analyzing the value model of financial securities products using artificial intelligence in the fifth embodiment of the present invention.

10: Financial securities products

100: Financial securities product value model analysis system using artificial intelligence

110: Processor

111: Self-organizing map algorithm

112: Deep Neural Network Model

113: Correlation analysis method

114: Sequential analysis model

120: Cloud database

121: Long-term trading parameters

122: Short-term trading data

Claims (5)

A financial securities product value model analysis system using artificial intelligence is used to predict a consumer's purchase strategy for multiple financial securities products. The financial securities product value model analysis system using artificial intelligence includes: A cloud database, including multiple long-term transaction parameters and short-term transaction data of each financial securities product; and A processor, which is signal-connected to the cloud database and configured to implement operations including the following steps: A judgment step, which is to judge whether the consumer is a long-term investment customer or a short-term investment customer; A data collection step is to obtain one of the long-term transaction parameters and the short-term transaction data of each financial securities product from the cloud database based on the long-term investment customer and the short-term investment customer, wherein the long-term transaction parameters and the short-term transaction data correspond to the long-term investment customer and the short-term investment customer respectively; An analysis step, including: A long-term strategy analysis step is to divide the financial securities products into multiple groups, and calculate the multiple classification conditions corresponding to the groups and an importance value of each long-term transaction parameter; and A short-term strategy analysis step is to drive the processor to analyze a product correlation and a purchase order of the financial securities products; and A strategy generation step is to generate the purchase strategy based on the groups, the classification conditions, the importance values of each of the long-term transaction parameters, the product relevance and the purchase order; Wherein, when the consumer is judged to be the long-term investment customer, the processor executes the long-term strategy analysis step; when the consumer is judged to be the short-term investment customer, the processor executes the short-term strategy analysis step. The financial securities product value model analysis system using artificial intelligence as described in claim 1 further includes: A dynamic dialing device, which is connected to the processor by signal and used for the processor to obtain an Internet Protocol address to connect to the cloud database by signal; The processor includes: A dialing monitoring module, which is used to monitor whether the dynamic dialing device can dial and connect to the cloud database by signal, wherein when the dynamic dialing device cannot dial and connect to the cloud database, the dialing monitoring module drives the dynamic dialing device to obtain another Internet Protocol address to connect to the cloud database by signal. The financial securities product value model analysis system using artificial intelligence as described in claim 1, wherein the long-term trading parameters include a risk factor, a debt-to-equity ratio, a book value return rate, a price-to-book ratio, a revenue growth rate, a market value, a turnover rate, a trading volume, a share price and a momentum factor, and the long-term strategy analysis step includes: A grouping step, which is to divide the financial securities products into the groups according to a self-organizing mapping algorithm, wherein the groups include a high return rate group, a medium return rate group and a low return rate group; A classification step, which is to summarize the classification conditions corresponding to the high return rate group, the medium return rate group and the low return rate group according to the long-term trading parameters of the financial securities products; and A verification step is to verify the importance value of each long-term trading parameter based on a deep neural network model. The financial securities product value model analysis system using artificial intelligence as described in claim 1, wherein the short-term strategy analysis step includes: A correlation analysis step, which is to analyze the product correlation of the financial securities products according to a correlation analysis method; and A sequence analysis step, which is to analyze the purchase order of the financial securities products according to a sequence analysis model. The financial securities product value model analysis system using artificial intelligence as described in claim 1 further includes: A network camera device, signal-connected to the processor, the network camera device is used to capture a facial image of the consumer; Wherein, the processor is further configured to implement: A consumer identification step, which is to identify the facial image of the consumer according to a face recognition program; Wherein, the consumer identification step is performed before the determination step.

Images