Acquisition method, device and equipment of account opening information and readable storage medium
By characterizing the account opening application information of bank customers and using pre-trained machine learning models to predict account types and product types, the problem of offline communication and confirmation of account opening information is solved, and more efficient account opening business processing is achieved.
Patent Information
- Application Number
- CN202411538837.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-02-07
AI Technical Summary
In the prior art, bank customers and bank business managers confirm account opening information through offline communication, resulting in low business processing efficiency.
By obtaining the account opening application information of the target account, after performing feature processing, the feature data is input to the pre-trained machine learning model to predict the account type and product type, thereby automatically obtaining the account opening information.
It improves the accuracy and automation of account opening information, reduces the time for manual confirmation, and improves the efficiency of account opening business processing.
Smart Images
Figure CN119398898A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of data processing technology, and in particular to a method, device, equipment and readable storage medium for obtaining account opening information. Background Art
[0002] At present, the bank supervision business processing first requires customers to open an account in the bank. The current situation of account opening business processing is that customers and bank business managers confirm the account opening information that meets customer needs through offline communication. The most important account opening information is the account type and product type. Obviously, this offline communication method of confirming account opening information has the problem of low business processing efficiency. Summary of the invention
[0003] The present application provides a method, device, equipment and readable storage medium for obtaining account opening information, as follows:
[0004] A method for obtaining account opening information, comprising:
[0005] In response to the target account opening request, obtaining the target account opening application information as the target account opening application information, wherein the target account opening application information includes answer information of a plurality of account opening questions;
[0006] Performing feature processing on the target account opening application information to obtain feature data of the target account opening application information as target feature data;
[0007] Inputting the target feature data into an information prediction model to obtain a prediction result of account opening information output by the information prediction model, wherein the account opening information includes an account type and a product type; wherein the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, wherein the sample feature data includes historical feature data of historical account opening application information;
[0008] Based on the prediction result of the account opening information, the account opening information of the target account is obtained.
[0009] Optionally, the training process of the information prediction model includes:
[0010] Obtain historical account opening application information and historical account opening information corresponding to historical accounts;
[0011] Performing feature processing on the historical account opening application information to obtain feature data of the historical account opening application information as sample feature data;
[0012] Using the historical account opening information corresponding to the historical account as a label, labeling the sample feature data corresponding to the historical account;
[0013] Training a pre-built machine learning model using the sample feature data as input and the label of the sample feature data as target output;
[0014] When a preset training completion condition is reached, the trained machine learning model is obtained as the information prediction model, and the training completion condition includes that the number of iterations is greater than a preset maximum number threshold.
[0015] Optionally, the account opening application information includes the historical account opening application information and the target account opening application information, and feature processing is performed on the account opening application information to obtain feature data of the account opening application information, including:
[0016] Convert account opening application information in different data formats to obtain text data;
[0017] Performing data preprocessing on the text data;
[0018] Extract and analyze the pre-processed text data based on natural language processing technology to obtain key information of the text data, including but not limited to keywords;
[0019] Based at least on the key information, feature extraction is performed on the text data to obtain feature data of the account opening application information, wherein the feature data includes feature values of preset target feature items.
[0020] Optionally, the method further comprises:
[0021] Performing feature processing on the historical account opening application information to obtain candidate feature data of the historical account opening application information, wherein the candidate feature data includes feature values of preset candidate feature items;
[0022] Based on the candidate feature data of the historical account opening application information and the historical account opening information, performing a correlation analysis on the candidate feature data and the historical account opening information to obtain a correlation analysis result between each candidate feature item and the historical account opening information;
[0023] The candidate feature items that are strongly correlated with the historical account opening information as a result of the correlation analysis are used as target feature items.
[0024] Optionally, obtaining the account opening application information of the target account includes:
[0025] Generate a question-and-answer guide based on the target feature item and the account opening request of the target account, wherein the question-and-answer guide includes the plurality of account opening questions, so that the requester of the target account can answer based on the account opening questions;
[0026] Acquire response information generated by the requester of the target account based on the response to the account opening question.
[0027] Optionally, the target account opening application information also includes the requesting party materials of the target account;
[0028] The step of obtaining the account opening application information of the target account further includes:
[0029] Generate a material guide according to the target feature item and the account opening request of the target account, wherein the material guide includes an identifier of the requesting party material of the target account;
[0030] Based on the material guide, the requesting party material of the target account is obtained.
[0031] Optionally, based on the prediction result of the account opening information, acquiring the account opening information of the target account includes:
[0032] Using the account type in the prediction result as the target account type of the target account;
[0033] Using the product type in the prediction result as the target product type of the target account;
[0034] Based on the target account type and the target product type, obtaining an account opening materials list of the target account, wherein the account opening materials list is used to list the identifiers of the materials required for account opening;
[0035] Generate account opening information of the target account, wherein the account opening information of the target account includes the account opening material list, the target account type, and the target product type.
[0036] An account opening information acquisition device, comprising: an application information acquisition unit, a feature processing unit, a model prediction unit and an account opening information acquisition unit;
[0037] The application information acquisition unit is used to respond to the target account opening request and acquire the target account opening application information as the target account opening application information, wherein the target account opening application information includes answer information of a plurality of account opening questions;
[0038] The feature processing unit is used to perform feature processing on the target account opening application information to obtain feature data of the target account opening application information as target feature data;
[0039] The model prediction unit is used to input the target feature data into the information prediction model to obtain a prediction result of the account opening information output by the information prediction model, wherein the account opening information includes an account type and a product type; wherein the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, wherein the sample feature data includes historical feature data of historical account opening application information;
[0040] The account opening information acquisition unit is used to acquire the account opening information of the target account based on the prediction result of the account opening information.
[0041] A device for acquiring account opening information, comprising: a memory and a processor;
[0042] The memory is used to store programs;
[0043] The processor is used to execute the program to implement each step of the method for obtaining account opening information.
[0044] A readable storage medium stores a computer program, which, when executed by a processor, implements each step of a method for obtaining account opening information.
[0045] It can be seen from the above technical solutions that the method, device, equipment and readable storage medium for obtaining account opening information provided in the embodiment of the present application, in response to the account opening request of the target account, obtains the account opening application information of the target account as the target account opening application information, performs feature processing on the target account opening application information, and obtains the feature data of the target account opening application information as the target feature data. The target feature data is input into the information prediction model to obtain the prediction result of the account opening information output by the information prediction model, and the account opening information includes the account type and the product type. Based on the prediction result of the account opening information, the account opening information of the target account is obtained. Since the target account opening application information includes the answer information of multiple account opening questions, the real-time and accuracy of the target account opening application information for the expression of the demand for account opening information are improved. Since the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, and the sample feature data includes the historical feature data of the historical account opening application information, therefore, based on the information prediction model, the account opening demand of the account opening request of the target account can be intelligently predicted, so that the present application can obtain the account type and product type of the target account based on the prediction result of the account opening information, and improve the efficiency of the account opening business. BRIEF DESCRIPTION OF THE DRAWINGS
[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0047] Figure 1 A flowchart of a method for obtaining account opening information provided in an embodiment of the present application;
[0048] Figure 2A schematic diagram of a process for constructing an information prediction model provided in an embodiment of the present application;
[0049] Figure 3 A schematic diagram of the structure of a device for obtaining account opening information provided in an embodiment of the present application;
[0050] Figure 4 A schematic diagram of the structure of a device for acquiring account opening information provided in an embodiment of the present application. DETAILED DESCRIPTION
[0051] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0052] At present, in order to address the problem of efficiency in account opening business processing caused by confirming customer account opening needs through offline communication, thereby determining the account type and product type, the keyword of the customer's account opening needs is generally input into a rule matching model, and the rule model outputs the account type and product type through matching the keywords with the preset rules, thereby achieving the purpose of automatically obtaining the account opening information. Obviously, the rule matching method cannot analyze the customer's account opening needs well, resulting in the rule matching results being unable to accurately match the user's actual account opening needs. Therefore, the present application provides a method for obtaining account opening information based on machine learning, which aims to realize online intelligent analysis of customer account opening needs, improve the accuracy of account opening information, and thus improve the efficiency of account opening business processing.
[0053] It should be noted that the method for obtaining account opening information provided in this application is applicable to smart devices (including mobile devices such as mobile phones, iPads, or PC computer devices) or servers (single-point servers or server clusters). Figure 1 A flowchart of a method for obtaining account opening information provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, this method specifically includes:
[0054] S101. In response to an account opening request of a target account, obtain account opening application information of the target account as target account opening application information.
[0055] In this embodiment, the target account opening application information includes answer information of multiple account opening questions. The account opening questions are generated based on at least the target account opening request, which includes basic information of the target account opening requester, such as the company name and company attributes.
[0056] Optionally, the target account opening application information also includes materials of the requesting party of the target account. An optional method for obtaining the target account opening application information specifically includes:
[0057] A question-and-answer guide is generated based on the target feature item and the target account's account opening request, and the target account's requester obtains answer information generated based on the account opening questions. The question-and-answer guide includes multiple account opening questions, so that the target account's requester can answer based on the account opening questions.
[0058] Generate material guidance based on target feature items and target account opening request, and retrieve target account requester materials from a preset database based on material guidance. Material guidance includes identification of target account requester materials. Requester materials include but are not limited to contract information, requester enterprise reports, historical account opening materials, market research reports and other historical pre-stored materials related to account opening requirements.
[0059] In this embodiment, the target feature item is a feature item that can characterize the account opening requirements, that is, information features related to the account opening information, such as account opening purpose keywords and regulatory requirement keywords, etc. The target feature item can be obtained based on the analysis of historical data, and an optional method for determining the target feature item can be referred to the following embodiment.
[0060] In summary, this step generates question-and-answer guidance and material guidance by generating an account opening request based on the target feature items and the target account. The question-and-answer guidance obtains dynamic account opening requirement information by guiding the requester to answer questions. The material guidance obtains static account opening requirement information by searching the requester's materials in a pre-stored database, thereby realizing online acquisition of account opening application materials for analyzing account opening requirements. The dynamic information is combined with the static information, thereby improving the comprehensiveness and real-time nature of the account opening application materials.
[0061] S102: Perform feature processing on the target account opening application information to obtain feature data of the target account opening application information as target feature data.
[0062] In this embodiment, the target feature data includes feature values of target feature items, wherein the target feature items include feature items that can characterize account opening requirements.
[0063] In this embodiment, there are multiple methods for acquiring target feature data, wherein an optional feature processing method includes:
[0064] A1. Convert the account opening application information in different data formats to obtain text data.
[0065] In this embodiment, the account opening application information may include information in different data formats such as image format, text format, and audio format, and the information in different data formats is uniformly converted into a text format for analysis. For example, based on optical character recognition (OCR) technology, the text and numbers in the scanned copy are converted into a text format. The specific format conversion method can be referred to in the prior art, and this embodiment will not be repeated here.
[0066] A2. Perform data preprocessing on text data.
[0067] In this embodiment, data preprocessing includes but is not limited to data cleaning, such as removing noise, stop words, punctuation marks, and numbers.
[0068] A3. Extract and analyze the pre-processed text data based on natural language processing technology to obtain the key information of the text data.
[0069] In this embodiment, key information includes but is not limited to keywords.
[0070] A4. Based on at least the key information, feature extraction is performed on the text data to obtain feature data of the account opening application information.
[0071] It should be noted that there are many methods for extracting target feature items, for example, extraction based on a feature extraction model, and details can be found in the prior art.
[0072] S103: Input the target feature data into the information prediction model to obtain the prediction result of the account opening information output by the information prediction model.
[0073] In this embodiment, the account opening information includes the account type and the product type. That is, the prediction result of the account opening information output by the information prediction model includes the prediction result of the account type and the prediction result of the product type.
[0074] In this embodiment, the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, and the sample feature data includes historical feature data of historical account opening application information. Among them, the specific structure of the machine learning model includes multiple types, and the specific training method can refer to the prior art.
[0075] S104. Based on the prediction result of the account opening information, obtain the account opening information of the target account.
[0076] In this embodiment, the account opening information of the target account includes the target product type of the target account and the target account type of the target account. Optionally, the account type in the prediction result is used as the target account type of the target account, and the product type in the prediction result is used as the target product type of the target account.
[0077] Optionally, the target account opening information also includes: materials required for account opening.
[0078] This step also includes: based on the account type of the target account (i.e., the target account type) and the product type of the target account (i.e., the target product type), obtaining a list of account opening materials for the target account, where the list of account opening materials is used to list the identifiers of the materials required for account opening. This step prompts the account opening requester to submit the materials required for account opening by displaying the list of account opening materials, thereby improving the convenience of customer services and the customer account opening experience.
[0079] It can be seen from the above technical scheme that an account opening information acquisition method provided by an embodiment of the present application uses the real-time reply information of multiple account opening questions as the account opening application information of the target account, thereby improving the real-time and accuracy of the expression of the account opening requirements of the account opening applicant by the account opening application information, and inputting the target feature data obtained by feature processing into the information prediction model to obtain the prediction results of the account type and the product type output by the information prediction model. Since the account opening requirements of the account opening request of the target account can be intelligently predicted based on the information prediction model, the present application can obtain the account type and product type of the target account based on the prediction results of the account opening information, thereby improving the accuracy and automation of obtaining the account opening information.
[0080] Figure 2 An example of a method for constructing an information prediction model is given. Figure 2 As shown, the method includes:
[0081] S201. Obtain historical account opening application information and historical account opening information corresponding to historical accounts.
[0082] S202: Perform feature processing on the historical account opening application information to obtain candidate feature data of the historical account opening application information.
[0083] In this embodiment, the candidate feature data includes the feature values of the preset candidate feature items. It should be noted that the feature processing method can refer to the above embodiment.
[0084] S203. Based on the candidate feature data of the historical account opening application information and the historical account opening information, a correlation analysis is performed on the candidate feature data and the historical account opening information to obtain a correlation analysis result between each candidate feature item and the historical account opening information.
[0085] In this embodiment, the correlation analysis method includes but is not limited to principal component analysis. The specific correlation analysis implementation method can refer to the prior art.
[0086] S204. The candidate feature item that is strongly correlated with the historical account opening information as a result of the correlation analysis is used as the target feature item.
[0087] S205. Obtain characteristic data of historical account opening application information as sample characteristic data.
[0088] S206. Using the historical account opening information corresponding to the historical account as a label, label the sample feature data corresponding to the historical account.
[0089] S207: Train a pre-built machine learning model using the sample feature data as input and the label of the sample feature data as target output.
[0090] S208. When the preset training completion condition is reached, the trained machine learning model is obtained as an information prediction model.
[0091] In this embodiment, the training completion condition includes that the number of iterations is greater than a preset maximum number threshold.
[0092] It can be seen from the above technical solution that the embodiment of the present application provides a correlation analysis of candidate feature items to screen out target feature items, which can improve the degree of representation of the feature items for account opening needs and the strength of the correlation between the model input and output, thereby achieving the purpose of training the model better and faster. Moreover, since the feature items are screened to obtain the target feature items, the speed of feature processing is also improved, thereby further improving the speed of account opening information prediction.
[0093] Figure 3 A schematic diagram of the structure of a device for obtaining account opening information provided in an embodiment of the present application is shown. Figure 3 As shown, the device may include: an application information acquisition unit 301, a feature processing unit 302, a model prediction unit 303, and an account opening information acquisition unit 304;
[0094] The application information acquisition unit is used to respond to the target account opening request and acquire the target account opening application information as the target account opening application information, wherein the target account opening application information includes answer information of a plurality of account opening questions;
[0095] The feature processing unit is used to perform feature processing on the target account opening application information to obtain feature data of the target account opening application information as target feature data;
[0096] The model prediction unit is used to input the target feature data into the information prediction model to obtain a prediction result of the account opening information output by the information prediction model, wherein the account opening information includes an account type and a product type; wherein the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, wherein the sample feature data includes historical feature data of historical account opening application information;
[0097] The account opening information acquisition unit is used to acquire the account opening information of the target account based on the prediction result of the account opening information.
[0098] Optionally, the device also includes a model building unit, which is used to: obtain historical account opening application information and historical account opening information corresponding to the historical account; perform feature processing on the historical account opening application information to obtain feature data of the historical account opening application information as sample feature data; use the historical account opening information corresponding to the historical account as a label to label the sample feature data corresponding to the historical account; use the sample feature data as input and the label of the sample feature data as a target output to train a pre-built machine learning model; when a preset training completion condition is met, obtain the trained machine learning model as the information prediction model, and the training completion condition includes the number of iterations being greater than a preset maximum number threshold.
[0099] Optionally, the account opening application information includes the historical account opening application information and the target account opening application information, and the feature processing unit is used to perform feature processing on the account opening application information to obtain feature data of the account opening application information, including: the feature processing unit is specifically used to:
[0100] Convert account opening application information in different data formats to obtain text data;
[0101] Performing data preprocessing on the text data;
[0102] Extract and analyze the pre-processed text data based on natural language processing technology to obtain key information of the text data, including but not limited to keywords;
[0103] Based at least on the key information, feature extraction is performed on the text data to obtain feature data of the account opening application information, wherein the feature data includes feature values of preset target feature items.
[0104] Optionally, the device further includes a feature correlation analysis unit, which is used to perform feature processing on the historical account opening application information to obtain candidate feature data of the historical account opening application information, wherein the candidate feature data includes feature values of preset candidate feature items; based on the candidate feature data of the historical account opening application information and the historical account opening information, a correlation analysis is performed on the candidate feature data and the historical account opening information to obtain a correlation analysis result between each candidate feature item and the historical account opening information; and a candidate feature item that is strongly correlated with the correlation analysis result of the historical account opening information is used as a target feature item.
[0105] Optionally, the application information acquisition unit is used to acquire the account opening application information of the target account, including: the application information acquisition unit is specifically used to:
[0106] Generate a question-and-answer guide based on the target feature item and the account opening request of the target account, wherein the question-and-answer guide includes the multiple account opening questions, so that the requester of the target account can answer based on the account opening questions; and obtain answer information generated by the requester of the target account based on the account opening questions.
[0107] Optionally, the target account opening application information also includes the requesting party materials of the target account;
[0108] The application information acquisition unit is used to obtain the account opening application information of the target account, and also includes: the application information acquisition unit is used to: generate material guidelines based on the target feature items and the account opening request of the target account, the material guidelines including the identification of the requesting party materials of the target account; based on the material guidelines, obtain the requesting party materials of the target account.
[0109] Optionally, the account opening information acquisition unit is used to acquire the account opening information of the target account based on the prediction result of the account opening information, including: the account opening information acquisition unit is specifically used to:
[0110] Using the account type in the prediction result as the target account type of the target account;
[0111] Using the product type in the prediction result as the target product type of the target account;
[0112] Based on the target account type and the target product type, obtaining an account opening materials list of the target account, wherein the account opening materials list is used to list the identifiers of the materials required for account opening;
[0113] Generate account opening information of the target account, wherein the account opening information of the target account includes the account opening material list, the target account type, and the target product type.
[0114] Figure 4 A schematic diagram of the structure of a device for obtaining account opening information provided in an embodiment of the present application is shown, and the device may include: at least one processor 401, at least one communication interface 402, at least one memory 403 and at least one communication bus 404;
[0115] In the embodiment of the present application, the number of the processor 401, the communication interface 402, the memory 403, and the communication bus 404 is at least one, and the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404;
[0116] The processor 401 may be a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present invention;
[0117] The memory 403 may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory;
[0118] The memory stores a program, and the processor can execute the program stored in the memory to implement the steps of a method for obtaining account opening information provided in an embodiment of the present application, as follows:
[0119] A method for obtaining account opening information, comprising:
[0120] In response to the target account opening request, obtaining the target account opening application information as the target account opening application information, wherein the target account opening application information includes answer information of a plurality of account opening questions;
[0121] Performing feature processing on the target account opening application information to obtain feature data of the target account opening application information as target feature data;
[0122] Inputting the target feature data into an information prediction model to obtain a prediction result of account opening information output by the information prediction model, wherein the account opening information includes an account type and a product type; wherein the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, wherein the sample feature data includes historical feature data of historical account opening application information;
[0123] Based on the prediction result of the account opening information, the account opening information of the target account is obtained.
[0124] Optionally, the training process of the information prediction model includes:
[0125] Obtain historical account opening application information and historical account opening information corresponding to historical accounts;
[0126] Performing feature processing on the historical account opening application information to obtain feature data of the historical account opening application information as sample feature data;
[0127] Using the historical account opening information corresponding to the historical account as a label, labeling the sample feature data corresponding to the historical account;
[0128] Training a pre-built machine learning model using the sample feature data as input and the label of the sample feature data as target output;
[0129] When a preset training completion condition is reached, the trained machine learning model is obtained as the information prediction model, and the training completion condition includes that the number of iterations is greater than a preset maximum number threshold.
[0130] Optionally, the account opening application information includes the historical account opening application information and the target account opening application information, and feature processing is performed on the account opening application information to obtain feature data of the account opening application information, including:
[0131] Convert account opening application information in different data formats to obtain text data;
[0132] Performing data preprocessing on the text data;
[0133] Extract and analyze the pre-processed text data based on natural language processing technology to obtain key information of the text data, including but not limited to keywords;
[0134] Based at least on the key information, feature extraction is performed on the text data to obtain feature data of the account opening application information, wherein the feature data includes feature values of preset target feature items.
[0135] Optionally, the method further comprises:
[0136] Performing feature processing on the historical account opening application information to obtain candidate feature data of the historical account opening application information, wherein the candidate feature data includes feature values of preset candidate feature items;
[0137] Based on the candidate feature data of the historical account opening application information and the historical account opening information, performing a correlation analysis on the candidate feature data and the historical account opening information to obtain a correlation analysis result between each candidate feature item and the historical account opening information;
[0138] The candidate feature items that are strongly correlated with the historical account opening information as a result of the correlation analysis are used as target feature items.
[0139] Optionally, obtaining the account opening application information of the target account includes:
[0140] Generate a question-and-answer guide based on the target feature item and the account opening request of the target account, wherein the question-and-answer guide includes the plurality of account opening questions, so that the requester of the target account can answer based on the account opening questions;
[0141] Acquire response information generated by the requester of the target account based on the response to the account opening question.
[0142] Optionally, the target account opening application information also includes the requesting party materials of the target account;
[0143] The step of obtaining the account opening application information of the target account further includes:
[0144] Generate a material guide according to the target feature item and the account opening request of the target account, wherein the material guide includes an identifier of the requesting party material of the target account;
[0145] Based on the material guide, the requesting party material of the target account is obtained.
[0146] Optionally, based on the prediction result of the account opening information, acquiring the account opening information of the target account includes:
[0147] Using the account type in the prediction result as the target account type of the target account;
[0148] Using the product type in the prediction result as the target product type of the target account;
[0149] Based on the target account type and the target product type, obtaining an account opening materials list of the target account, wherein the account opening materials list is used to list the identifiers of the materials required for account opening;
[0150] Generate account opening information of the target account, wherein the account opening information of the target account includes the account opening material list, the target account type, and the target product type.
[0151] It should be noted that the specific implementation method of each step of the method for obtaining account opening information provided in the embodiment of the present application can be found in the above embodiment and will not be repeated here.
[0152] The embodiment of the present application further provides a readable storage medium, which can store a computer program suitable for execution by a processor. When the computer program is executed by the processor, the steps of a method for obtaining account opening information provided in the embodiment of the present application are implemented as follows:
[0153] A method for obtaining account opening information, comprising:
[0154] In response to the target account opening request, obtaining the target account opening application information as the target account opening application information, wherein the target account opening application information includes answer information of a plurality of account opening questions;
[0155] Performing feature processing on the target account opening application information to obtain feature data of the target account opening application information as target feature data;
[0156] Inputting the target feature data into an information prediction model to obtain a prediction result of account opening information output by the information prediction model, wherein the account opening information includes an account type and a product type; wherein the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, wherein the sample feature data includes historical feature data of historical account opening application information;
[0157] Based on the prediction result of the account opening information, the account opening information of the target account is obtained.
[0158] Optionally, the training process of the information prediction model includes:
[0159] Obtain historical account opening application information and historical account opening information corresponding to historical accounts;
[0160] Performing feature processing on the historical account opening application information to obtain feature data of the historical account opening application information as sample feature data;
[0161] Using the historical account opening information corresponding to the historical account as a label, labeling the sample feature data corresponding to the historical account;
[0162] Training a pre-built machine learning model using the sample feature data as input and the label of the sample feature data as target output;
[0163] When a preset training completion condition is reached, the trained machine learning model is obtained as the information prediction model, and the training completion condition includes that the number of iterations is greater than a preset maximum number threshold.
[0164] Optionally, the account opening application information includes the historical account opening application information and the target account opening application information, and feature processing is performed on the account opening application information to obtain feature data of the account opening application information, including:
[0165] Convert account opening application information in different data formats to obtain text data;
[0166] Performing data preprocessing on the text data;
[0167] Extract and analyze the pre-processed text data based on natural language processing technology to obtain key information of the text data, including but not limited to keywords;
[0168] Based at least on the key information, feature extraction is performed on the text data to obtain feature data of the account opening application information, wherein the feature data includes feature values of preset target feature items.
[0169] Optionally, the method further comprises:
[0170] Performing feature processing on the historical account opening application information to obtain candidate feature data of the historical account opening application information, wherein the candidate feature data includes feature values of preset candidate feature items;
[0171] Based on the candidate feature data of the historical account opening application information and the historical account opening information, performing a correlation analysis on the candidate feature data and the historical account opening information to obtain a correlation analysis result between each candidate feature item and the historical account opening information;
[0172] The candidate feature items that are strongly correlated with the historical account opening information as a result of the correlation analysis are used as target feature items.
[0173] Optionally, obtaining the account opening application information of the target account includes:
[0174] Generate a question-and-answer guide based on the target feature item and the account opening request of the target account, wherein the question-and-answer guide includes the plurality of account opening questions, so that the requester of the target account can answer based on the account opening questions;
[0175] Acquire response information generated by the requester of the target account based on the response to the account opening question.
[0176] Optionally, the target account opening application information also includes the requesting party materials of the target account;
[0177] The step of obtaining the account opening application information of the target account further includes:
[0178] Generate a material guide according to the target feature item and the account opening request of the target account, wherein the material guide includes an identifier of the requesting party material of the target account;
[0179] Based on the material guide, the requesting party material of the target account is obtained.
[0180] Optionally, based on the prediction result of the account opening information, acquiring the account opening information of the target account includes:
[0181] Using the account type in the prediction result as the target account type of the target account;
[0182] Using the product type in the prediction result as the target product type of the target account;
[0183] Based on the target account type and the target product type, obtaining an account opening materials list of the target account, wherein the account opening materials list is used to list the identifiers of the materials required for account opening;
[0184] Generate account opening information of the target account, wherein the account opening information of the target account includes the account opening material list, the target account type, and the target product type.
[0185] It should be noted that the method, device, equipment and readable storage medium for obtaining account opening information provided by the present invention can be used in the financial field or other fields. It can be used in the financial field or other fields. For example, it can be used in the application scenario of account opening business handling in the financial field. Other fields are any fields other than the financial field, for example, the field of artificial intelligence technology. The above is only an example and does not limit the application field of the method, device, equipment and readable storage medium for obtaining account opening information provided by the present invention.
[0186] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.
[0187] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.
[0188] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for obtaining account opening information, characterized in that: include: In response to the target account opening request, obtaining the target account opening application information as the target account opening application information, wherein the target account opening application information includes answer information of a plurality of account opening questions; Performing feature processing on the target account opening application information to obtain feature data of the target account opening application information as target feature data; Inputting the target feature data into an information prediction model to obtain a prediction result of account opening information output by the information prediction model, wherein the account opening information includes an account type and a product type; wherein the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, wherein the sample feature data includes historical feature data of historical account opening application information; Based on the prediction result of the account opening information, the account opening information of the target account is obtained.
2. The method according to claim 1, characterized in that The training process of the information prediction model includes: Obtain historical account opening application information and historical account opening information corresponding to historical accounts; Performing feature processing on the historical account opening application information to obtain feature data of the historical account opening application information as sample feature data; Using the historical account opening information corresponding to the historical account as a label, labeling the sample feature data corresponding to the historical account; Training a pre-built machine learning model using the sample feature data as input and the label of the sample feature data as target output; When a preset training completion condition is reached, the trained machine learning model is obtained as the information prediction model, and the training completion condition includes that the number of iterations is greater than a preset maximum number threshold.
3. The method according to claim 2, characterized in that The account opening application information includes the historical account opening application information and the target account opening application information. The account opening application information is subjected to feature processing to obtain feature data of the account opening application information, including: Convert account opening application information in different data formats to obtain text data; Performing data preprocessing on the text data; Extract and analyze the pre-processed text data based on natural language processing technology to obtain key information of the text data, including but not limited to keywords; Based at least on the key information, feature extraction is performed on the text data to obtain feature data of the account opening application information, wherein the feature data includes feature values of preset target feature items.
4. The method according to claim 3, characterized in that: The method further comprises: Performing feature processing on the historical account opening application information to obtain candidate feature data of the historical account opening application information, wherein the candidate feature data includes feature values of preset candidate feature items; Based on the candidate feature data of the historical account opening application information and the historical account opening information, performing a correlation analysis on the candidate feature data and the historical account opening information to obtain a correlation analysis result between each candidate feature item and the historical account opening information; The candidate feature item that is strongly correlated with the historical account opening information as a result of the correlation analysis is used as the target feature item.
5. The method according to claim 4, characterized in that The obtaining of the target account opening application information includes: Generate a question-and-answer guide based on the target feature item and the account opening request of the target account, wherein the question-and-answer guide includes the plurality of account opening questions, so that the requester of the target account can answer based on the account opening questions; Acquire response information generated by the requester of the target account based on the response to the account opening question.
6. The method according to claim 5, characterized in that The target account opening application information also includes the requesting party materials of the target account; The step of obtaining the account opening application information of the target account further includes: Generate a material guide according to the target feature item and the account opening request of the target account, wherein the material guide includes an identifier of the requesting party material of the target account; Based on the material guide, the requesting party material of the target account is obtained.
7. The method according to claim 6, characterized in that The acquiring the account opening information of the target account based on the prediction result of the account opening information includes: Using the account type in the prediction result as the target account type of the target account; Using the product type in the prediction result as the target product type of the target account; Based on the target account type and the target product type, obtaining an account opening materials list of the target account, wherein the account opening materials list is used to list the identifiers of the materials required for account opening; Generate account opening information of the target account, wherein the account opening information of the target account includes the account opening material list, the target account type, and the target product type.
8. A device for obtaining account opening information, characterized in that: include: Application information acquisition unit, feature processing unit, model prediction unit and account opening information acquisition unit; The application information acquisition unit is used to respond to the target account opening request and acquire the target account opening application information as the target account opening application information, wherein the target account opening application information includes answer information of a plurality of account opening questions; The feature processing unit is used to perform feature processing on the target account opening application information to obtain feature data of the target account opening application information as target feature data; The model prediction unit is used to input the target feature data into the information prediction model to obtain a prediction result of the account opening information output by the information prediction model, wherein the account opening information includes an account type and a product type; wherein the information prediction model includes a machine learning model pre-trained based on sample feature data with historical account opening information as a label, wherein the sample feature data includes historical feature data of historical account opening application information; The account opening information acquisition unit is used to acquire the account opening information of the target account based on the prediction result of the account opening information.
9. A device for obtaining account opening information, characterized in that: include: Memory and processor; The memory is used to store programs; The processor is used to execute the program to implement each step of the method for obtaining account opening information according to any one of claims 1 to 7.
10. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, each step of the method for obtaining account opening information according to any one of claims 1 to 7 is implemented.