A component modular financial product design information classification method and system

Abstract

The application provides a component modular financial product design information classification method and system, and belongs to the field of information classification; solves the problem of complex information classification; and specifically as follows: step S1: obtaining classification information and financial product design information; step S2: obtaining financial product information, a product set and a classification set; performing word frequency analysis on the financial product information in the product set to obtain a product keyword list, combining the classification set, performing screening, and obtaining a product feature keyword list; step S3: analyzing the financial product design information through the product feature keyword list; obtaining a coincidence value list by calculating the coincidence value of the financial product design information and the product feature keyword; and step S4: judging the category of the financial product design information according to the coincidence value list; the application classifies the financial product design information by analyzing the financial product information, and reduces the classification difficulty of the financial product design information.

Description

TECHNICAL FIELD

[0001] The application relates to the field of information classification. BACKGROUND

[0002] The existing financial product design information classification method and system have the following disadvantages:

[0003] Classification standards are ambiguous or inconsistent: Different financial institutions or departments may adopt different classification standards, leading to the same type of information being classified into different categories in different systems, increasing the difficulty of information integration and sharing; for example, some institutions may classify according to the investment period of the product, while other institutions may classify according to the risk level of the product;

[0004] Single classification dimension: Some classification methods only consider a single dimension, such as only classifying by product type or only classifying by customer group, ignoring other important factors that may affect information classification, which may lead to incomplete information classification and cannot meet the diversified information query and analysis needs;

[0005] Classification hierarchy is not clear: unreasonable classification hierarchy setting leads to overly complex or overly simple information classification, which cannot effectively reflect the hierarchical relationship of information. SUMMARY

[0006] In view of the deficiencies of the prior art, the application aims to provide a component modularization financial product design information classification method and system, which aims to solve the problem of complex information classification.

[0007] In order to achieve the above-mentioned purpose, the application is realized by the following technical scheme: a component modularization financial product design information classification method, the classification method comprising:

[0008] Step S1: obtaining classification information and financial product design information;

[0009] Step S2: obtaining financial product information, product set and classification set according to the classification information; performing word frequency analysis on the financial product information in the product set to obtain a product keyword list, screening the product keyword list in combination with the classification set, extracting product feature words to obtain a product feature word list;

[0010] Step S3: analyzing the financial product design information through the product feature word list; calculating the coincidence value of the financial product design information and the product feature words according to the occurrence frequency of the product feature words in the financial product design information, counting the coincidence value to obtain a coincidence value list;

[0011] Step S4: judging the category of the financial product design information according to the consistent value list, combining the classification set in the classification information, and obtaining the category of the financial product design information.

[0012] Further, the specific steps of step S1 are as follows:

[0013] Step S11: obtaining the financial product information jr, taking the financial product information of the same category as a product set LB, recording the number of elements t in the product set LB, and obtaining LB={jr(1), jr(2), …, jr(t)};

[0014] Step S12: integrating the product sets of the same classification dimension to form a classification set FL, recording the number of product sets n, and obtaining FL={LB(1), LB(2), …, LB(n)};

[0015] Step S13: obtaining the classification dimension m; according to the classification dimension, the classification set is counted to form the classification information FX, FX={FL(1), FL(2), …, FL(m)}.

[0016] Further, the specific steps of step S2 are as follows:

[0017] Step S21: obtaining the financial product information in the product set through the product set, obtaining the word frequency list of the financial product information through word frequency analysis of the financial product information, processing the word frequency list of the financial product information in the product set, and obtaining the product keyword list;

[0018] Step S22: screening the product keyword list according to the classification set, obtaining the number n of product sets in the classification set, obtaining the product keyword list corresponding to the product set, and recording it as cgj(1) to cgj(n); comparing the product keyword lists, and removing the repeatedly appearing product keywords, specifically as follows:

[0019] Obtaining the product keyword number cgs of cgj(1); extracting the product keywords of cgj(1) and recording them as ccj(1) to ccj(cgs);

[0020] Respectively searching ccj(1) to ccj(cgs) in cgj(2), …, cgj(n); if ccj(1) to ccj(cgs) do not exist in cgj(2), …, cgj(n), it is judged as a product characteristic word, the product characteristic word is counted, and the product characteristic word list is obtained;

[0021] Obtaining the product characteristic word list of cgj(2) to cgj(n).

[0022] Further, the specific steps of the step S21 are as follows:

[0023] Step S211: text preprocessing is performed on the financial product information, expression symbols are removed, uniform resource locators are removed, and punctuation marks are removed to obtain an initial text;

[0024] Step S212: the initial text is segmented by jieba to obtain a segmentation list, a stop word table is obtained, the segmentation list is filtered according to the stop word table, the word frequency of the filtered segmentation list is counted, and a word frequency list is obtained;

[0025] Step S213: the word frequency list of the financial product information in the product set is obtained, the word frequency list is analyzed, and a product keyword list is obtained.

[0026] Further, the specific steps of the step S211 are as follows:

[0027] Remove the expression symbol: obtain the storage code bq1 of the first expression symbol in the computer, obtain the storage code bq2 of the last expression symbol in the computer, and delete the characters in the range [bq1, bq2] in the financial product information through a regular expression;

[0028] Remove the uniform resource locator: traverse the financial product information and compare it with http, if there is a character http, record the character position zf1, and find the first space position after the character, record it as zf2, and delete the statement in the financial product information with the character position zf1 to zf2;

[0029] Remove the punctuation mark: save the punctuation mark in a list, match the characters in the financial product information with the punctuation mark through a regular expression, and delete if they match.

[0030] Further, the specific steps of the step S212 are as follows:

[0031] The filtering of the segmentation list according to the stop word table is as follows: the segmentation list is operated in a loop, the segmentation is obtained, the segmentation is matched with the stop word table, and if the segmentation can be searched in the stop word table, the segmentation is deleted;

[0032] After the filtering is completed, the number of occurrences of the segmentation in the segmentation list is counted, which is as follows: the segmentation list is converted into a set to obtain a segmentation set, the segmentation elements in the segmentation set are traversed, the segmentation list is counted according to the segmentation elements, the number of occurrences of the segmentation elements is obtained, and the segmentation elements and the number of occurrences of the segmentation elements constitute a word frequency list.

[0033] Further, the specific steps of step S213 are as follows:

[0034] The number t of the financial product information in the product set is obtained, and the corresponding word frequency list is obtained, denoted as cp(c);

[0035] The first word frequency list cp(1) is taken as a standard list, the number of elements ysg in the standard list is obtained, and the elements in the standard list are denoted as bzl(1), bzl(2), …, bzl(ysg); cp(1), cp(2), …, cp(t) are judged in cycles according to bzl(1) to bzl(ysg);

[0036] If bzl(1) always exists in cp(1) to cp(t), it is judged that bzl(1) is a product keyword;

[0037] bzl(2) to bzl(ysg) are judged;

[0038] According to the judgment result, the product keywords are counted, the product keywords are sorted in descending order in combination with the number of occurrences of the elements in the word frequency list, and the product keyword list is obtained.

[0039] Further, the specific steps of step S3 are as follows:

[0040] Step S31: Obtain the number tgs of feature words in the product feature word list; the feature words in the product feature word list are denoted as tn, the sorting position of the feature words in the product feature word list is obtained, and the sorting position value px(tn) of the feature words is obtained;

[0041] Step S32: The feature words are judged in cycles in the financial product design information, the number of occurrences of the feature words in the financial product design information is recorded, the occurrence frequency pl(tn) is obtained, the feature word number tgs of the product feature word list, and the sorting position value px(tn) of the feature words are combined to calculate the coincidence value xfz of the financial product design information and the product feature words;

[0042] ;

[0043] Step S33: The coincidence value of the n product feature word lists and the financial product design information is calculated, and xfz(1) to xfz(n) are obtained; the coincidence value is analyzed, and the coincidence value list cfzl is obtained.

[0044] Further, the specific steps of step S33 are as follows:

[0045] Step S331: Obtain the consistent values xfz(1) to xfz(n), accumulate the consistent values to obtain the consistent total value xzz; calculate the consistent judgment value glz(i) according to the proportional relationship between the consistent value and the consistent total value, combined with the variance of the consistent value;

[0046] ;

[0047] xfz(i) represents the consistent value of the i-th product feature word list and the financial product design information;

[0048] Step S332: Obtain the maximum value in the consistent judgment value to obtain the maximum judgment value max, and analyze and judge the maximum judgment value:

[0049] If max> 50%, the consistent value calculation is valid, and the consistent value list cfzl is obtained by counting the consistent values; enter step S4;

[0050] If max≤50%, the consistent value calculation is invalid, and needs to be recalculated; enter step S333;

[0051] Step S333: Update the product feature word list, shield the last position of the product feature word list, obtain the frequency pl(tn) of the feature word in the financial product design information, the number of feature words tgs-1 of the product feature word list, and the sorting position value px(tn) of the feature word, calculate the updated consistent value, and repeat steps S331-S332.

[0052] A component modular financial product design information classification system, the classification system comprising:

[0053] Information acquisition module: acquire classification information and financial product design information;

[0054] Information processing module: acquire financial product information, product set, and classification set according to the classification information; perform word frequency analysis on the financial product information in the product set to obtain a product keyword list, filter the product keyword list combined with the classification set, extract product feature words, and obtain a product feature word list;

[0055] Information analysis module: analyze the financial product design information through the product feature word list; calculate the consistent value of the financial product design information and the product feature words according to the frequency of the product feature words in the financial product design information, count the consistent values, and obtain a consistent value list;

[0056] Information classification module: judge the category of the financial product design information according to the consistent value list, combined with the classification set in the classification information, and obtain the category of the financial product design information.

[0057] Compared with the prior art, the application has the beneficial effects of:

[0058] The classification standard is clear: the application obtains the commonness of the same category of products through longitudinal analysis of the same category of products, obtains the keywords of the products, performs longitudinal analysis on different categories of products, retains the unique keywords of the same category of products, and screens out the general keywords, thereby obtaining the classification standard.

[0059] The classification dimension is wide: the application analyzes the classified products under different dimensions, obtains the specific classification standard according to the different classification dimensions, and ensures the classification accuracy under different classification dimensions.

[0060] The classification level is clear: the application classifies the financial product design information through a three-layer structure, extracts the classification standard according to the products of the same category, screens the classification standard according to the products of different categories under the same classification dimension, and classifies the financial product design information of different dimensions according to the classification dimension. BRIEF DESCRIPTION OF DRAWINGS

[0061] Other features, objects and advantages of the application will become more apparent after reading the detailed description of the non-limiting embodiments with reference to the following drawings:

[0062] Figure 1 The figure is a schematic diagram of the method of the application;

[0063] Figure 2 The figure is a schematic diagram of the keyword processing of the application;

[0064] Figure 3 The figure is a schematic diagram of the feature word processing of the application

[0065] Figure 4 The figure is a schematic diagram of the information classification of the application

[0066] Figure 5 The figure is a schematic diagram of the system of the application. DETAILED DESCRIPTION

[0067] In order to make the above-mentioned purposes, features and advantages of the application more obvious and easy to understand, the application will be further described in detail below with reference to the drawings and specific embodiments. Embodiment one

[0068] Please refer to Figure 1 A component modularization financial product design information classification method comprises:

[0069] Step S1: obtaining classification information and financial product design information;

[0070] Step S11: Obtain financial product information jr, take the same category of financial product information as a product set, denoted as LB, obtain the number of elements t in the product set, and obtain LB={jr(1), jr(2), …, jr(t)};

[0071] It should be noted that: bonds, bank loans, financing leases IPO, private placement, equity crowdfunding all belong to financing products, and here LB represents the product set of financing products, and jr(1), jr(2), …, jr(t) represent bonds, bank loans, financing leases IPO, private placement, and equity crowdfunding.

[0072] Step S12: Integrate the product sets in the same classification dimension to form a classification set FL, record the number of product sets n; obtain FL={LB(1), LB(2), …, LB(n)};

[0073] It should be noted that: according to the function dimension, it can be divided into financing products, investment products, and risk management products, and here FL represents the classification set of the function dimension, and LB(1), LB(2), …, LB(n) represent the financing products, investment products, and risk management products.

[0074] Step S13: Obtain the classification dimension m; according to the classification dimension, count the classification set to form the classification information, denoted as FX, FX={FL(1), FL(2), …, FL(m)}.

[0075] It should be noted that: financial products can be classified according to multiple dimensions such as function, risk and return characteristics, and trading place, wherein according to the function, it can be divided into financing products, investment products, and risk management products.

[0076] Step S2: According to the classification information, obtain the financial product information, product set, and classification set; perform word frequency analysis on the financial product information in the product set to obtain a product keyword list, filter the product keyword list in combination with the classification set, extract product feature words, and obtain a product feature word list;

[0077] Step S21: Obtain the financial product information in the product set through the product set, obtain the word frequency list of the financial product information through word frequency analysis on the financial product information, and process the word frequency list of the financial product information in the product set to obtain a product keyword list;

[0078] Step S211: Perform text preprocessing on the financial product information, remove emoticons, remove uniform resource locators, and remove punctuation symbols to obtain an initial text;

[0079] Step S2111: removing emoticons: obtaining the storage code bq1 of the first emoticon in the computer, obtaining the storage code bq2 of the last emoticon in the computer, deleting the characters in the range of [bq1, bq2] in the financial product information through regular expression;

[0080] Step S2112: removing uniform resource locator: traversing the financial product information, comparing with http, if there is a character http, recording the character position zf1, at the same time finding the first space position after the character, recording as zf2, deleting the statement in the financial product information with character position from zf1 to zf2;

[0081] It should be noted that: uniform resource locator is a method of identifying the address for completely describing the web page and other resources on the Internet, which is irrelevant to the text content.

[0082] Step S2113: removing punctuation: saving the punctuation in a list, matching the characters in the financial product information with the punctuation through regular expression, and deleting if they match;

[0083] Step S212: performing word segmentation operation on the initial text by jieba, splitting the text into words or phrases to obtain a word segmentation list, obtaining a stop word table, screening the word segmentation list according to the stop word table, and counting the word frequency in the screened word segmentation list to obtain a word frequency list;

[0084] Step S2121: screening the word segmentation list according to the stop word table, which is as follows: performing loop operation on the word segmentation list, obtaining the word segmentation, matching the word segmentation with the stop word table, and deleting the word segmentation if it can be searched in the stop word table;

[0085] Step S2122: after screening, counting the number of occurrences of the word segmentation in the word segmentation list, which is as follows: converting the word segmentation list into a set to obtain a word segmentation set, traversing the word segmentation elements in the word segmentation set, counting the number of occurrences of the word segmentation elements in the word segmentation list, and constructing a word frequency list from the word segmentation elements and the number of occurrences of the word segmentation elements;

[0086] It should be noted that: the word frequency list is in the following format: [{word segmentation element 1: times 1}, {word segmentation element 2: times 2}, {word segmentation element 3: times 3}].

[0087] It should be noted that: the stop word table is a tool for filtering out common words with little contribution to the semantic of the text in natural language processing (NLP) and information retrieval, which can use common stop word table or customize stop word table according to needs.

[0088] import re

[0089] import jieba

[0090] # Original text

[0091] text = "Hello! Welcome to visit https: / / example.com. This is a test, including the numbers 123 and punctuation!!!

[0092] # 1. Remove emojis

[0093] text = re.sub(r'[\U00010000-\U0010ffff]', '', text)

[0094] # 2. Remove URLs

[0095] text = re.sub(r'http\S+', '', text)

[0096] # 3. Remove punctuation marks

[0097] text = re.sub(r'[,。!?;:“”‘’()《》]', '', text)

[0098] # 4. Remove numbers

[0099] text = re.sub(r'\d+', '', text)

[0100] # 5. Word segmentation and stop word processing

[0101] stopwords = {"的", "了", "在"}

[0102] words = jieba.lcut(text)

[0103] filtered_words = [word for word in words if word not in stopwords]

[0104] # Output result

[0105] print(filtered_words) # Output: ['你好', '欢迎访问', '这是一个测试', '包含', '和标点']

[0106] Please refer to Figure 2; Step S213: obtaining a word frequency list of the financial product information in the product set, and analyzing the word frequency list to obtain a product keyword list;

[0107] Step S2131: obtaining the number t of the financial product information in the product set, and obtaining a word frequency list corresponding to the number t, denoted as cp(c), wherein 1≤c≤t;

[0108] Step S2132: taking the first word frequency list cp(1) as a standard list, obtaining the number ysg of elements in the standard list, and denoting the elements in the standard list as bzl(1), bzl(2), …, bzl(ysg); and performing cyclic judgment on cp(1), cp(2), …, cp(t) according to bzl(1), bzl(2), …, bzl(ysg);

[0109] If bzl(1) always exists in cp(1), cp(2), …, cp(t), it is determined that bzl(1) is a product keyword.

[0110] Similarly, bzl(2), …, bzl(ysg) are judged.

[0111] According to the judgment result, the product keywords are counted, and the product keywords are sorted in descending order in combination with the number of occurrences of the elements in the word frequency list. The product keyword list is obtained.

[0112] It should be noted that the word frequency list is [{token element 1: times 1}, {token element 2: times 2}, {token element 3: times 3}]. The product keywords are obtained by judging the token elements, and the keywords are sorted in combination with the number.

[0113] Please refer to Figure 3 Step S22: screening the product keyword list according to the classification set to obtain a product feature keyword list;

[0114] Step S221: obtaining the number n of the product set in the classification set, and obtaining the product keyword list corresponding to the product set, denoted as cgj(1), cgj(2), …, cgj(n);

[0115] Step S222: traversing cgj(1), cgj(2), …, cgj(n), and comparing the product keyword lists to remove the repeatedly appearing product keywords, as follows:

[0116] Obtaining the number cgs of product keywords of cgj(1); and extracting the product keywords of cgj(1), denoted as ccj(1), ccj(2), …, ccj(cgs);

[0117] The ccj (1), ccj (2),..., ccj (cgs) are respectively searched for the cgj (2),..., cgj (n); if the ccj (1), ccj (2),..., ccj (cgs) do not exist in the cgj (2),..., cgj (n), it is judged as a product feature word, and a product feature word list is obtained by counting the product feature word;

[0118] The product feature word list of the cgj (2),..., cgj (n) is obtained by the same method.

[0119] In the searching process of the cgj (2), the cgj (2) is searched one by one by the ccj (1), ccj (2),..., ccj (cgs).

[0120] It should be noted that the product feature word list is obtained by traversing and judging on the basis of the product keyword list, which does not affect the original order of the product keyword list, so the arrangement order of the product feature word list and the product keyword list is consistent, that is, the descending order of the word frequency.

[0121] Step S3: The financial product design information is analyzed by the product feature word list; the consistent value of the financial product design information and the product feature word list is calculated according to the appearance frequency of the product feature word in the financial product design information; the consistent value is counted to obtain a consistent value list.

[0122] Step S31: The number of feature words tgs of the product feature word list is obtained; the feature word in the product feature word list is denoted as tn, the sorting position of the feature word in the product feature word list is obtained, and the sorting position value px (tn) of the feature word is obtained.

[0123] Step S32: The feature word in the financial product design information is cyclically judged, the appearance frequency of the feature word in the financial product design information is recorded, and the appearance frequency pl (tn) is obtained; the number of feature words tgs of the product feature word list and the sorting position value px (tn) of the feature word are combined to calculate the consistent value xfz of the financial product design information and the product feature word.

[0124] ;

[0125] If there is a product feature word list [A, B, C], the sorting position value is 1, 2, and 3; the cyclic judgment of A, B, and C in the financial product design information is performed to obtain the appearance frequency, 10, 20, and 30.

[0126] The formula is calculated as follows: , and the xfz=30 is obtained.

[0127] Step S33: According to steps S31-S32, the matching values of the n product feature word lists and the financial product design information are calculated to obtain xfz(1), xfz(2), …, xfz(n), and the matching value list cfzl is obtained by analyzing the matching values;

[0128] Step S331: The matching values xfz(1), xfz(2), …, xfz(n) are obtained, the matching values are accumulated to obtain the total matching value xzz, and the matching judgment value glz(i) is obtained by calculating the proportional relationship between the matching values and the total matching value and combining the variance of the matching values;

[0129] ;

[0130] It should be noted that: the matching judgment value is obtained by multiplying the proportional relationship between the matching values and the total matching value and the variance of the matching values, wherein the proportional relationship between the matching values and the total matching value judges the proportion of the matching values, and the variance weights the proportion, (the variance is a statistical quantity for measuring the dispersion degree of a group of data, and by introducing the variance, the error caused by small difference of the matching values is avoided, and the matching values with large difference are given higher weight to provide calculation accuracy), and the matching values of the product feature word list and the financial product design information are more intuitively judged according to the judgment value;

[0131] It should be noted that: the variance is a statistical quantity for measuring the dispersion degree of a group of data, and the matching judgment value is more accurate when calculated by the variance;

[0132] Step S332: The maximum value in the matching judgment value is obtained to obtain the maximum judgment value max, and the maximum judgment value is analyzed and judged:

[0133] If max> 50%, the matching value calculation is valid, the matching value list cfzl is obtained by counting the matching values; and step S4 is entered.

[0134] If max≤50%, the matching value calculation is invalid, and needs to be recalculated; and step S333 is entered.

[0135] Step S333: The product feature word list is updated, the last position of the product feature word list is shielded, the occurrence frequency pl(tn) of the feature word in the financial product design information, the number of feature words tgs-1 of the product feature word list, and the sorting position value px(tn) of the feature word are calculated to obtain the updated matching value, and steps S331-S332 are repeated.

[0136] Please refer to Figure 4 Step S4: The category of the financial product design information is judged according to the matching value list, and the category of the financial product design information is obtained by combining the category set in the classification information.

[0137] Step S41: According to the consistent value list, the product set corresponding to the maximum consistent value is obtained, and the category of the financial product design information is obtained;

[0138] For example, if the consistent value list is [10, 20, 30], the product set corresponding to the consistent value list is financing products, investment products, and risk management products; and the category of the financial product design information is determined to be risk management products.

[0139] Step S42: According to the classification information, the classification dimension m is obtained, the corresponding consistent value list under different classification dimensions is obtained, the category lb of the financial product design information is obtained according to the product set corresponding to the maximum consistent value, and lb(1), lb(2), …, lb(m) are obtained; and the category of the financial product design information is formed.

[0140] For example, the classification dimension is classified according to function, risk and return characteristics, and trading place,

[0141] The consistent value list under the function dimension is obtained, and the category of the financial product design information is determined to be risk management products according to the product set corresponding to the maximum consistent value.

[0142] The consistent value list under the risk and return characteristics dimension is obtained, and the category of the financial product design information is determined to be high-risk products according to the product set corresponding to the maximum consistent value.

[0143] The consistent value list under the trading place is obtained, and the category of the financial product design information is determined to be an over-the-counter product according to the product set corresponding to the maximum consistent value.

[0144] The risk management products, high-risk products, and over-the-counter products form the category of the financial product design information.

[0145] It should be noted that the consistent value list is the consistent value of different categories under the same classification dimension and the financial product design information, such as classifying the financial product design information into financing products, investment products, and risk management products according to the function dimension; according to the risk and return characteristics dimension, the financial product design information belongs to low-risk products; and the classification of the financial product design information is obtained by combining the classification results of all classification dimensions.

[0146] Step S43: The financial product design information is encrypted and stored according to the category of the financial product design information, as follows:

[0147] According to the classification dimension m, the number of encryption times is determined; that is, two times of encryption are performed according to the function and risk and return characteristics dimensions.

[0148] Obtaining the belonging categories lb(1), lb(2), …, lb(m) of the financial product design information under different classification dimensions; encoding the text of the belonging categories to obtain the encoding values;

[0149] For example, the encoding corresponding to the function dimension is: 111001011000101010011111111010001000001110111101111001111011101110110100111001011011101010100110;

[0151] Lengthening the encoding values in equal proportion to the length of the financial product design information; obtaining the encrypted values;

[0152] It should be noted that equal proportion lengthening refers to lengthening the length of the encoding values to be consistent with the length of the text of the financial product design information. For example, if the length of the text of the financial product design information is 10, the length of the encoding is 3, and the specific value is 101. After lengthening, the value is 101 101 101 1.

[0153] According to the value of the current position of the password value, the financial product design information is mapped. The information corresponding to 0 is mapped to the horizontal axis, and the information corresponding to 1 is mapped to the vertical axis. The information on the horizontal axis and the vertical axis is alternately stored to complete the first encryption and obtain the encrypted text.

[0154] Combined with the classification dimension m, m encrypted values are obtained. For each encrypted value (a total of m), the mapping and alternate storage process of the first encryption is repeated.

[0155] In each repetition, according to the encrypted value, it is determined how to map the encrypted text to the horizontal axis and the vertical axis,

[0156] Each repetition generates a new encrypted text. The encrypted text is used as the input of the next encryption and is mapped with the encrypted value. After m times of encryption, the encrypted information is obtained.

[0157] For example, the information is "Jiayi Bingshi 1234", and the encrypted value is 10101100. Jiayi Bingshi 1234 corresponds to 10101100, respectively. The information on the horizontal axis is "Yi Bingshi 34", and the information on the vertical axis is "Ji Bingshi 12". After alternate storage, it is "Yi Ji Bingshi 3142". Embodiment two

[0158] Please refer to Figure 5 A component modular financial product design information classification system comprises:

[0159] Information acquisition module: acquiring classification information and financial product design information;

[0160] The information processing module: according to the classification information, obtaining the financial product information, product set, classification set; performing word frequency analysis on the financial product information in the product set to obtain a product keyword list, screening the product keyword list in combination with the classification set, extracting product feature words to obtain a product feature word list;

[0161] The information analysis module: analyzing the financial product design information through the product feature word list; calculating the coincidence value of the financial product design information and the product feature words according to the occurrence frequency of the product feature words in the financial product design information, and counting the coincidence value to obtain a coincidence value list;

[0162] The information classification module: judging the category of the financial product design information according to the coincidence value list, and obtaining the category of the financial product design information in combination with the classification set in the classification information;

[0163] The above formulas are all dimensionless values calculated, the formula is obtained by collecting a large amount of data to simulate the most real situation, and the preset parameters in the formula are set by the person skilled in the art according to the actual situation, such as the weight coefficient and the proportion coefficient, the size of which is set to quantify each parameter to obtain a specific value for subsequent comparison, and the size of the weight coefficient and the proportion coefficient only needs to not affect the proportional relationship between the parameters and the quantized value.

[0164] Finally, it should be noted that: the above-described embodiments are only specific implementations of the present application, which are used to illustrate the technical solutions of the present application, but not to limit it, the protection scope of the present application is not limited to this, although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art within the technical range disclosed by the present application can still modify or easily think of changes to the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to some technical features; and these modifications, changes or replacements do not make the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and all should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for classifying information in modular financial product design, characterized in that, Classification methods include: Step S1: Obtain classification information and financial product design information; Step S2: Based on the classification information, obtain financial product information, product set, and category set; perform word frequency analysis on the financial product information within the product set to obtain a product keyword list; combine the category set to filter the product keyword list, extract product feature words, and obtain a product feature word list. Step S3: Analyze the financial product design information through the product feature word list; calculate the match value between the financial product design information and the product feature words based on the frequency of their occurrence in the financial product design information, and obtain a match value list. The specific steps of step S3 are as follows: Step S31: Obtain the number of feature words tgs in the product feature word list; denote the feature words in the product feature word list as tn, obtain the sorting position of the feature words in the product feature word list, and get the sorting position value px(tn). Step S32: Iteratively judge the feature words in the financial product design information, record the number of times the feature words appear in the financial product design information, and obtain the frequency of occurrence pl(tn); combine the number of feature words tgs in the product feature word list and the ranking value of the feature words px(tn) to calculate the consistency value xfz between the financial product design information and the product feature words; ； Step S33: Calculate the matching value between the list of n product feature words and the financial product design information to obtain xfz(1) to xfz(n), analyze the matching value to obtain the matching value list cfzl; The specific steps of step S33 are as follows: Step S331: Obtain matching values ​​xfz(1) to xfz(n), accumulate the matching values ​​to obtain the total matching value xzz; calculate the matching judgment value glz(i) based on the ratio of matching values ​​to the total matching value and the variance of the matching values. ； xfz(i) represents the match value between the i-th product feature word list and the financial product design information; Step S332: Obtain the maximum value among the matching judgment values ​​to get the maximum judgment value max, and analyze and judge the maximum judgment value: If max > 50%, the matching value calculation is valid. The matching values ​​are statistically analyzed to obtain the matching value list cfzl; proceed to step S4; If max≤50%, the matching value calculation is invalid and needs to be recalculated; proceed to step S333. Step S333: Update the product feature word list, mask the last word in the product feature word list, obtain the frequency of the feature word in the financial product design information pl(tn), the number of feature words in the product feature word list tgs-1, and the ranking value of the feature word px(tn) and calculate to obtain the updated consistency value. Repeat steps S331-S332. Step S4: Determine the category of financial product design information based on the matching value list, and combine it with the category set in the classification information to obtain the category of financial product design information.

2. The method for classifying information in modular financial product design according to claim 1, characterized in that, The specific steps of step S1 are as follows: Step S11: Obtain financial product information jr, group financial product information of the same category into a product set, denoted as LB, obtain the number of elements t in the product set, and get LB={jr(1),jr(2),……,jr(t)}; Step S12: Integrate product sets with the same classification dimension to form a classification set FL, and record the number of product sets n; obtain FL={LB(1), LB(2), ..., LB(n)}; Step S13: Obtain the classification dimension m; perform statistics on the classification set according to the classification dimension to form classification information, denoted as FX, FX={FL(1), FL(2), ..., FL(m)}.

3. The method for classifying information in modular financial product design according to claim 1, characterized in that, The specific steps of step S2 are as follows: Step S21: Obtain financial product information within the product set; perform word frequency analysis on the financial product information to obtain a word frequency list; process the word frequency list of financial product information within the product set to obtain a product keyword list. Step S22: Based on the category set, filter the product keyword list to obtain the number n of product sets within the category set, and obtain the product keyword list corresponding to each product set, denoted as cgj(1) to cgj(n); compare the product keyword lists and remove duplicate product keywords, as follows: Get the number of product keywords cgs of cgj(1); extract the product keywords of cgj(1) and record them as ccj(1) to ccj(cgs); Search for ccj(1) to ccj(cgs) against cgj(2), ..., cgj(n) respectively; if ccj(1) to ccj(cgs) do not exist in cgj(2), ..., cgj(n), then they are determined to be product feature words, and product feature words are counted to obtain a list of product feature words; Obtain the product feature word list from cgj(2) to cgj(n).

4. The method for classifying information in modular financial product design according to claim 3, characterized in that, The specific steps of step S21 are as follows: Step S211: Perform text preprocessing on the financial product information by removing emojis, Uniform Resource Locators (URLs), and punctuation marks to obtain the initial text; Step S212: Perform word segmentation on the initial text using jieba to split the text into words or phrases, obtain a word segmentation list, obtain a stop word list, filter the word segmentation list according to the stop word list, and count the word frequencies in the filtered word segmentation list to obtain a word frequency list; Step S213: Obtain the word frequency list of financial product information within the product set, analyze the word frequency list, and obtain the product keyword list.

5. The modular financial product design information classification method and system according to claim 4, characterized in that, The specific steps of step S211 are as follows: Remove emojis: Obtain the storage code bq1 of the first emoji in the computer, obtain the storage code bq2 of the last emoji in the computer, and delete the characters encoded in the financial product information within the range [bq1, bq2] using regular expressions; Remove Uniform Resource Locators (URLs): Traverse the financial product information and compare it with http. If the character "http" exists, record the character position zf1. At the same time, find the first space position after the character and record it as zf2. Delete the statements in the financial product information with character positions from zf1 to zf2. Remove punctuation marks: Store punctuation marks in a list, and use regular expressions to match characters in the financial product information with the punctuation marks. If a match is found, delete the punctuation marks.

6. The method for classifying information in modular financial product design according to claim 4, characterized in that, The specific steps of step S212 are as follows: The word segmentation list is filtered based on the stop word list as follows: the word segmentation list is looped through to obtain the word segments, and the word segments are matched with the stop word list. If the word segment can be retrieved in the stop word list, the word segment is deleted. After filtering, the frequency of each word segment in the word segmentation list is counted as follows: the word segmentation list is converted into a set to obtain the word segmentation set. The word segmentation elements in the word segmentation set are traversed, and the word segmentation list is counted in a loop according to the word segmentation elements to obtain the frequency of each word segmentation element. The word frequency list is constructed from the word segmentation elements and their frequency of occurrence.

7. The method for classifying information in modular financial product design according to claim 4, characterized in that, The specific steps of step S213 are as follows: Get the number t of financial product information in the product set, and get the corresponding word frequency list, denoted as cp(c); Take the first word frequency list cp(1) as the standard list, get the number of elements ysg in the standard list, and denote the elements in the standard list as bzl(1), bzl(2), ... bzl(ysg); perform a loop judgment on cp(1), cp(2), ..., cp(t) based on bzl(1) to bzl(ysg); If bzl(1) always exists in cp(1) to cp(t), then bzl(1) is determined to be a product keyword; Make a judgment on bzl(2) to bzl(ysg); Based on the judgment results, the product keywords are statistically analyzed, and combined with the frequency of occurrence of elements in the word frequency list, the product keywords are sorted in descending order to obtain the product keyword list.

8. A modular financial product design information classification system, applicable to the modular financial product design information classification method according to any one of claims 1-7, characterized in that, Classification systems include: Information Acquisition Module: Acquires categorized information and financial product design information; Information processing module: Based on classification information, obtain financial product information, product sets, and category sets; perform word frequency analysis on the financial product information within the product sets to obtain a list of product keywords; combine with the category sets to filter the list of product keywords, extract product feature words, and obtain a list of product feature words; Information Analysis Module: Analyzes financial product design information through a list of product feature words; calculates the match value between financial product design information and product feature words based on the frequency of their occurrence in the financial product design information, and obtains a match value list. Information Classification Module: Based on the list of matching values, the module determines the category of financial product design information and combines it with the category set in the classification information to obtain the category of financial product design information.

Images