TWI738610B - Recommended financial product and risk control system and implementation method thereof - Google Patents

Abstract

Recommended financial product and risk control system and implementation method thereof are disclosed. The present invention is configured to capture a voiceprint information under test by a personality analysis device, and analyze and compare the voiceprint information under test to obtain a voiceprint classification feature of the voiceprint information under test by a voiceprint analysis model and then search a personality analysis information according to the voiceprint classification feature. Further, the personality analysis information is analyzed to obtain a user’s financial credit information to determine a user’s potential credit risk as an evaluating reference for loan, and is compared to obtain a financial product information. In this way, the user can obtain a selection reference for financial products through the personality analysis information.

Description

Financial product recommendation and risk control management system and method

The present invention relates to a voiceprint recognition technology, in particular to a voiceprint information captured by a user through a personality analysis device to analyze the user’s personality, determine the user’s credit risk and recommend suitable financial products based on the user’s personality Financial product recommendation and risk control system and financial product recommendation methods.

According to the fact that there are currently many financial product projects, consumers can invest through different financial product projects. In order to increase the transaction volume of financial products, financial product providers usually contact consumers through direct contact or telephone interviews through salespersons. The content of the interview confirms consumer demand for specific financial products, and then recommends suitable financial products to consumers, or some financial product providers collect consumer demand through indirect contact (questionnaires or chatbots) consumers. However, Regardless of direct or indirect contact, consumer psychology will be vigilant or reserved, making interview results inaccurate. Therefore, financial product providers cannot provide financial products suitable for consumers, resulting in the financial products provided are not subject to consumption It is not possible to increase the sales volume of financial products. Among them, financial product providers cannot provide consumers with suitable financial products. Some factors may come from the influence of consumers’ personalities. As mentioned above, financial product providers are interviewing During the process, consumers’ personalities will be actively analyzed. However, consumers may still deceive or conceal during the interview. Based on this, how to prevent consumers from concealing their true personalities and accurately analyze their personalities and provide the most suitable consumers. Financial products, this is a problem that needs to be resolved.

In view of the above-mentioned problems, the inventor of the present invention has conducted research and improvement on voiceprint processing methods, financial product matching methods, and personality analysis methods based on years of experience in related industries; for this reason, the main purpose of the present invention is to provide a By collecting user's voiceprint information, analyze the financial product recommendation and risk control system and method suitable for the user's personality.

In order to achieve the above objectives, the financial product recommendation and risk control system and the financial product recommendation method of the present invention are mainly based on the analysis and comparison of a voiceprint analysis model after extracting a voiceprint information to be measured through a personality analysis device The voiceprint information to be tested is used to analyze a voiceprint classification feature of the voiceprint information to be tested, and a corresponding character analysis information is queried according to the voiceprint classification feature, and then a corresponding financial information is matched with the character analysis information. Commodity information. The present invention mainly establishes a voiceprint analysis model through supervised machine learning. The voiceprint analysis model uses at least one voiceprint sample information and at least one personality test information as training parameters. The personality analysis device is used by the user in any emotional state. The user's personality can be accurately analyzed, and the user's credit risk can be judged by the personality analysis information, and the most suitable financial product information can be matched. According to this, the present invention can achieve the following effects: (1) The voiceprint analysis model uses voiceprint sample information and personality test information as training parameters to predict the potential intelligence of the test subject, such as consumer preferences, consumer investment preferences, or consumer credit risk, and risk tolerance Wait for information (2) Predict the user's personality through supervised machine learning, which can eliminate emotional changes; (3) Personality test information can be electronic test questionnaires or physical test questionnaires. The content of the questionnaire involves psychological tests. Therefore, the voiceprint classification characteristics analyzed by the voiceprint analysis model and the corresponding personality analysis information, the analysis results are very consistent with the user's personality; (4) The present invention estimates the true personality of consumers by capturing voiceprint information, which can be provided to the financial service end, so that the financial service end can judge the consumer's credit risk, as a reference for borrowing or not; (5) The financial service end can also provide the most suitable financial products based on the true personalities of consumers, which can increase the sales volume of financial products.

In order for your reviewer to have a clear understanding of the purpose, technical features and effects of the present invention after implementation, the following descriptions and illustrations are used for illustration, please refer to it.

Please refer to "Figure 1", which is a schematic diagram (1) of the composition of the present invention. As shown in the figure, the financial product recommendation and risk control system 1 of the present invention is mainly composed of a personality analysis device 10 and at least one The client information device 20 and at least one financial server device 30 are composed. In normal operation, at least one client information device 20 completes the information connection with the personality analysis device 10; the personality analysis device 10 can collect at least one voiceprint information And a personality test information corresponding to each voiceprint information, and using the voiceprint information and the personality test information as training parameters, a voiceprint analysis model is established through a supervised machine learning algorithm. The personality analysis device 10 can be a computer device, Moreover, after the voiceprint analysis model training is completed, the personality analysis device 10 can classify the newly input voiceprint information through the voiceprint analysis model, so that different voiceprint information can be classified in an appropriate voiceprint classification feature. And according to the voiceprint classification feature, a personality analysis information is compared; the client information device 20 can be operated by the user, and the client information device 20 can encode the user's voice signal into a voiceprint that can be processed and analyzed by the machine. Information (digital or analog). The client-side information device 20 can be a computer device, mobile communication device, wearable electronic device or embedded system, but it can be implemented by anyone who can collect sound signals and execute applications. To be limited, the user of the client information device 20 can be a consumer who has financial investment needs or borrowing needs; the financial service device 30 is installed on the financial service end, so that the financial service end is used for credit reporting. During the operation, the character analysis information compared by the client can be obtained, and the financial credit evaluation information or financial product information compared with the character analysis information. The financial service end can use the financial credit evaluation information as a reference for the evaluation of the credit investigation operation. , You can also recommend the most suitable financial product information for the client’s personality.

Please refer to "Figure 2" again, which is a schematic diagram of the composition of the present invention (2), and please refer to "Figure 1" in conjunction with the figure, the personality analysis device 10 of the present invention includes an arithmetic processing module Group 101, another voiceprint processing module 102, a data analysis module 103, a data storage module 104, and an information transmission module 105 complete information connection with the arithmetic processing module 101; (1) The arithmetic processing module 101 is used to run the personality analysis device 10 and drive the above-mentioned modules, and has functions such as logic operations, temporarily storing the results of the operations, and storing the position of the executed instructions. It can be a central processing unit (Central Processing Unit, CPU) or a microcontroller (Microcontroller Unit, MCU); (2) The voiceprint processing module 102 can perform a voiceprint processing operation after receiving the voiceprint information. The voiceprint processing operation includes at least a noise reduction process and a voiceprint sample capture, and the voiceprint information After the voiceprint processing operation, a voiceprint sample information is generated for the data analysis module 103 to retrieve the voiceprint sample information for subsequent processing and analysis. The voiceprint information can be digital or analog without compression or loss. Information such as compression, lossless compression, or a combination thereof; (3) The data analysis module 103 can execute a supervised machine learning algorithm, such as: Artificial Neural Network (ANN), support vector machine (SVM), nearest neighbor method (k nearest neighbor, KNN), Gaussian Mixture Model, Naive Bayes Classifier or Decision tree, but not limited to this, and the data analysis module 103 can Acquire voiceprint sample information and personality test information, and users can label the personality test information in advance, and analyze the voiceprint sample information and personality based on the label set by the user through a supervised machine learning algorithm The relevance of the test information is used to establish a voiceprint analysis model, in which several voiceprint classification features can be generated based on the labeling results. The voiceprint analysis model can be based on training parameters (voiceprint sample information and personality test information) and labeling results, from The labeling results analyze several voiceprint classification features, and the voiceprint analysis model can be based on the physical characteristics of the voiceprint information (training data) as the basis for judgment, such as: the frequency, volume, waveform, wave number, and speed of the voiceprint Or speaking speed, etc. The above examples are only examples and are not limited to this. Moreover, each voiceprint classification feature can correspond to specific personality analysis information. Among them, the voiceprint classification feature forms at least two categories, preferably There are seven types of voiceprint classification features, and each classification feature represents a different personality. Furthermore, the data analysis module 103 can further match the corresponding financial product information or financial credit evaluation information according to the personality analysis information; (4) The data storage module 104 includes a voiceprint database 1041 storing at least one voiceprint sample information; a personality test database 1042 storing at least one personality test information; a model database 1043 storing voiceprints Analysis model; a personality database 1044 stores at least one personality analysis information, each personality analysis information includes at least one consumption habit information, at least one investment habit information, and at least one credit risk information, and the consumption habit information affects consumption behavior For example, it’s easy to buy goods impulsively, hesitate to buy goods, and inquire about product evaluations before consumption. The investment habit information is the character traits that affect investment behavior. For example, a cautious personality will select investment targets The impulse of personality is easy to listen to others blindly invest, and the money concept is not good. The credit risk information is the personality characteristic that affects the financial credit evaluation level. For example, the personality with a high sense of responsibility will repay the loan on time after the loan is approved. Therefore, financial credit Better, on the other hand, a character with a poor sense of responsibility has a poorer financial credit rating; a financial product database 1045 stores at least one piece of financial product information, and the personality analysis information corresponds to the relevant financial product based on parameters such as consumption habits information and investment habits information Information, wherein each financial product information is set with a matching tag, and each matching tag corresponds to the associated personality analysis information, so that the personality analysis device 10 can search for matching tags with the personality analysis information through the matching tag Financial product information. In addition, the financial product information includes investment insurance policies, savings insurance, futures products, foreign exchange products, option products, fund products, stock products, and bond products. Each financial product information has corresponding consumption habits. And investment habits; a financial credit database 1046 stores at least one financial credit assessment information, said financial credit assessment information has multiple financial credit assessment levels, and different financial credit assessments can be compared based on the credit risk information of the personality analysis information Grade, for the financial service side to review the loan as a reference; (5) The information transmission module 105 can be connected to each client information device 20 via Internet information to receive and transmit information to the client information device 20.

Please refer to "Figure 3", which shows the flow chart of the implementation of the present invention. Please also refer to "Figure 1" ~ "Figure 2". The financial product recommendation and risk control system 1 of the present invention mainly adopts The personality analysis device 10 establishes a voiceprint analysis model to analyze a personality analysis information of each voiceprint information, and compares at least one financial product information matched with the personality analysis information, wherein the financial product recommendation method is as follows: (1) One captures the voiceprint information to be tested and the personality test information S1: Please refer to "Figure 4" together. The figure shows the schematic diagram (1) of the implementation of the present invention. As shown in the figure, the plural voiceprint information D1 And input the personality test information D2 into a personality analysis device 10; (2) Once the voiceprint analysis model S2 is established: after the personality analysis device 10 captures the voiceprint information D1 and the personality test information D2, the voiceprint processing module 102 can perform a voiceprint processing operation on the voiceprint information D1. The voiceprint processing operation can process the voiceprint information D1 to reduce noise and capture the voiceprint sample. When the voiceprint information D1 completes the voiceprint processing operation, a voiceprint sample information D1' can be generated, and the personality analysis device 10 can The voiceprint sample information D1' and the personality test information D2 are stored in the data storage module 104, and the data analysis module 103 can retrieve the voiceprint sample information D1' and the personality test information D2 in the data storage module 104, where, Voiceprint sample information D1' is used as input data, personality test information D2 is used as target data, and personality test information D2 is marked, so that data analysis module 103 executes a supervised machine learning algorithm to calculate voiceprint sample information D1' and The corresponding weight of personality test information D2 is used to establish a voiceprint analysis model, and the voiceprint analysis model is stored in the data storage module 104 for comparison and classification by the data analysis module 103; (3) One captures the voiceprint information to be measured S3: Please refer to "Figure 5" for collocation. The figure shows the implementation diagram (2) of the present invention. As shown in the figure, when the voiceprint analysis model is established, the client After the information of the information device 20 is connected to the personality analysis device 10, the client information device 20 can further send a voiceprint information D3 to be measured to the personality analysis device 10; (4) Perform a voiceprint processing operation on the voiceprint information to be measured S4: After the personality analysis device 10 receives the voiceprint information to be measured D3, the voiceprint processing module 102 may perform a voiceprint processing operation on the voiceprint information to be measured D3 to Generate a voiceprint sample information D3' to be measured; (5) A voiceprint analysis model compares the voiceprint sample information to be tested S5: After the data analysis module 103 obtains the voiceprint sample information D3' to be tested, it can compare the voiceprint sample information D3' to be tested through the voiceprint analysis model A voiceprint classification feature of, and the data analysis module 103 can search the data storage module 104 for a corresponding personality analysis information based on the voiceprint classification feature; (6) 1. Compare the financial credit information with the character analysis information S6: The data analysis module 103 then uses the character analysis information as a matching condition to search the financial credit database 1046 to match the character analysis information to a financial credit corresponding to the character analysis information. For the credit evaluation information D4, the calculation processing module 101 then transmits the matched financial credit evaluation information D4 to the financial server device 30, so that the financial server can use the financial credit evaluation information D4 as a reference for evaluating whether to lend; (7) 1. Compare the financial product information with the character analysis information S7: The data analysis module 103 then searches the financial product database 1045 with the character analysis information as a matching condition, and matches a financial product corresponding to the character analysis information. For the commodity information D5, the arithmetic processing module 101 then transmits the matched financial commodity information D5 to the client information device 20.

In summary, the financial product recommendation and risk control system 1 of the present invention can provide financial product demanders or financial product providers with inputting the voiceprint information D3 to be tested, and the personality analysis device 10 can analyze the voiceprint information D3 based on the voiceprint information to be tested. Generate personality analysis information D4, and then use personality analysis information D4 to determine the user’s financial credit evaluation information and financial product information. The financial server can use the financial credit evaluation information as a reference for the user’s credit information, effectively improving the accuracy of credit evaluation In addition, the financial service end can analyze the information based on the personality to match the most appropriate combination of financial products. If the user is a financial product demander, the financial product demander can select the most suitable financial product based on their own personality characteristics. If the user is a financial product provider, the user can find a combination of financial products suitable for the user based on the user's voiceprint data to achieve a match between the demander and the product provider.

Please refer to "Figure 6", which is another embodiment (1) of the present invention. Please refer to "Figure 3" ~ "Figure 5" together, and proceed to the step "Comparing Financial Product Information with Personality Analysis Information S6", After the data analysis module 103 matches the financial product information D5, the arithmetic processing module 101 can simultaneously transmit the personality analysis information and the financial product information D5 to the client information device 20, and the user can check the personality through the client information device 20 Whether the analysis information conforms to their own personality, if not, the user can create a correction message D6 through the client information device 20, and send the correction message D6 to the personality analysis device 10, so that the data analysis module 103 can be corrected based on The message D6 corrects the label assigned by the voiceprint sample information D3' to be tested to correct the voiceprint analysis model, wherein the correction message D6 can set matching personality analysis information so that the data analysis module 103 can modify according to The personality analysis information of the message D6 searches for the corresponding label, and further modifies the voiceprint analysis model.

Please refer to "Figure 7". The figure shows another embodiment (2) of the present invention. As shown in the figure, the financial server device 30 has a communication capture module 301, and the financial server device 30 is connected to Personality analysis device 10, the communication capture module 301 can capture a communication signal (ie, call voice signal) of the telephone system, and convert the communication signal format into voiceprint information to be measured for the personality analysis device 10 to perform The analysis and comparison means that the financial industry can capture the interviewee’s voice (that is, the voiceprint information to be measured) through telephone interviews, and after analysis by the personality analysis device 10, the interviewee can be quickly matched Suitable financial products.

In summary, the financial product recommendation and risk control system and method of the present invention include a personality analysis device and at least one client information device. When implemented, the financial product recommendation and risk control system mainly uses the personality analysis device to capture Take a voiceprint information to be measured, analyze and compare the voiceprint information to be measured based on a voiceprint analysis model to analyze a voiceprint classification feature of the voiceprint information to be measured, and query the corresponding one according to the voiceprint classification feature. Personality analysis information, the personality analysis device matches a financial credit evaluation information or a financial product information corresponding to the personality analysis information, so that the financial service terminal can use the financial credit evaluation information as an auxiliary judgment reference for credit investigation. The financial service terminal It also provides corresponding financial product information to the user based on the user’s personality. According to this, after the present invention is implemented, it can indeed provide a financial product that collects the user’s voiceprint information and analyzes the financial product suitable for the user’s personality. The purpose of recommendation and risk control system and financial product recommendation method.

The above are only preferred embodiments of the present invention, and are not intended to limit the scope of implementation of the present invention; anyone who is familiar with this technique can make equal changes and modifications without departing from the spirit and scope of the present invention. Should be covered within the scope of the patent of the present invention.

To sum up, the present invention has patent requirements such as "industrial applicability", "novelty" and "advancedness"; the applicant filed an application for a patent for invention with the Bureau in accordance with the provisions of the Patent Law.

1: Financial product recommendation and risk control system 10: Personality analysis device 101: Operation processing module 102: Voiceprint processing module 103: Data Analysis Module 104: data storage module 1041: Voiceprint Database 1042: Personality Test Database 1043: Model Database 1044: Personality Database 1045: Financial Commodity Database 1046: Financial Credit Database 105: Information Transmission Module 106: Quiz Module 20: Client information device 30: Financial server device 301: Communication capture module D1: Voiceprint information D2: Personality test information D1’: Voiceprint sample information D3: Voiceprint information to be tested D4: Financial credit assessment information D3’: Voiceprint sample information to be tested D5: Financial product information D6: Correction message S1: Capture voiceprint information and personality test information to be tested S2: Establish a voiceprint analysis model S3: Acquire voiceprint information to be measured S4: Perform voiceprint processing on the voiceprint information to be measured S5: The voiceprint analysis model compares the sample information of the voiceprint to be measured S6: Compare financial credit information with personality analysis information S7: Compare financial product information with personality analysis information

Figure 1 is a schematic diagram (1) of the composition of the present invention. Figure 2 is a schematic diagram (2) of the composition of the present invention. Figure 3 is a flow chart of the implementation of the present invention. Figure 4 is a schematic diagram (1) of the implementation of the present invention. Figure 5 is a schematic diagram (2) of the implementation of the present invention. Figure 6 shows another embodiment (1) of the present invention. Figure 7 shows another embodiment (2) of the present invention.

S1: Capture voiceprint information and personality test information to be tested

S2: Establish a voiceprint analysis model

S3: Acquire voiceprint information to be measured

S4: Perform voiceprint processing on the voiceprint information to be measured

S5: The voiceprint analysis model compares the sample information of the voiceprint to be measured

S6: Compare credit risk and financial product information with personality analysis information

Claims (10)

A financial product recommendation and risk control method. A personality analysis device captures a voiceprint information to be tested, and a corresponding financial credit evaluation information or financial product information is analyzed by a voiceprint analysis model, which includes: the The personality analysis device inputs a plurality of voiceprint information and a plurality of personality test information into the personality analysis device; the personality analysis device performs a voiceprint processing operation on the voiceprint information to generate a voiceprint sample information, and the voiceprint sample Information labels each personality test information, and builds the voiceprint analysis model based on the voiceprint sample information and each of the personality test information that have been marked; a client information device sends the voiceprint information to be tested to the A personality analysis device that performs the voiceprint processing operation on the voiceprint information to be tested to generate a voiceprint sample information to be tested; the personality analysis device obtains the voiceprint sample information to be tested, and then uses the voice The voiceprint analysis model compares a voiceprint classification feature of the voiceprint sample information to be tested, and the voiceprint analysis model is based on the voiceprint frequency, volume, waveform, wave number, speed of sound, and speed of speech in the voiceprint information As a judgment basis; and the personality analysis device compares a corresponding personality analysis information based on the voiceprint classification feature, and matches the corresponding financial credit evaluation information or the financial product information based on the personality analysis information. The financial product recommendation and risk control method according to claim 1, wherein after the personality analysis device receives a correction message, the personality analysis device modifies the label of the voiceprint sample information to be tested. The financial product recommendation and risk control method according to claim 1, wherein the voiceprint processing operation includes a noise reduction process and a voiceprint sample capture. The financial product recommendation and risk control method according to claim 1, wherein the personality analysis information includes one or a combination of consumption habit information, investment habit information, and credit risk information. A financial product recommendation and risk control management system, comprising: a client information device storing a voiceprint information to be measured; a personality analysis device, which completes information connection with the client information device, and the personality analysis device includes a calculation processing Module, another voiceprint processing module and a data analysis module complete the information connection with the arithmetic processing module; the arithmetic processing module is used to run the personality analysis device; the voiceprint processing module is based on a voiceprint In the processing operation, the acquired voiceprint information to be tested is processed into a voiceprint sample information, and the voiceprint sample information is used as input data, and a personality test information is used as output data. Test information annotation; the data analysis module is based on a voiceprint analysis model to compare the voiceprint information to be tested, and the voiceprint analysis model is based on the voiceprint frequency, volume, and volume in the voiceprint information. Waveform, wave number, speed of sound, and speech speed are used as the judgment basis to compare a voiceprint classification feature of the voiceprint sample information, and the voiceprint classification feature corresponds to a personality analysis information; the data analysis module uses the personality The analysis information matches a corresponding financial credit evaluation information or a financial product information; and a financial server device completes the information connection with the personality analysis device, and the financial server device is used to receive the financial credit evaluation information. The financial product recommendation and risk control system according to claim 5, wherein a data storage module completes information connection with the arithmetic processing module, and the data storage module includes a voiceprint database and a personality test database , A model database, a personality database and a financial credit database. The financial product recommendation and risk control system according to claim 5, wherein the financial server device includes a communication capture module, and the communication capture module captures a communication signal format and converts it into the voiceprint to be tested News. The financial product recommendation and risk control system according to claim 5, wherein the data analysis module matches the corresponding financial product information with the personality analysis information, and then transmits the financial product information to the client Information device. The financial product recommendation and risk control system according to claim 5, wherein the voiceprint processing operation includes a noise reduction process and a voiceprint sample capture. The financial product recommendation and risk control system according to claim 5, wherein the personality analysis information includes consumption habit information and investment habit information.

Images