Method and device for determining investment questionnaire, equipment and medium

Abstract

The present application relates to the field of artificial intelligence and financial technology, and discloses a kind of investment questionnaire determination method, device, equipment and medium, method includes the basic data of each user, questionnaire survey data for each investment product, the questionnaire feedback data corresponding to each questionnaire survey data, the transaction condition data of each investment product and the product identifier of investment success investment product, as to be handled data;Each to-be-processed data is clustered to obtain the user category of user;According to the transaction condition data of target investment product under target user category and the questionnaire feedback data corresponding to target investment product, each questionnaire survey data of target investment product is filtered, and a predetermined number of candidate questionnaire survey data is obtained;According to candidate questionnaire survey data and the application condition of target investment product, target questionnaire survey data is obtained, so that target questionnaire survey data meets the characteristics of user and the characteristics of target investment product, and is more targeted.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of artificial intelligence and financial technology, and particularly relates to a method and device for determining an investment questionnaire, and a medium. BACKGROUND

[0002] With the rapid development of emerging technologies such as artificial intelligence and big data, on the one hand, the changes in customer groups and their behaviors have changed, and on the other hand, the investment industry has been assisted in improving various business activities by means of digitization. Compared with non-investment products, the purchase or application of investment products needs to meet some regulatory and qualification requirements. When a customer expresses an intention to purchase an investment product, a marketing representative will ask them a series of regulatory and qualification-related information by telephone, and finally match the most suitable investment product for the customer or inform the customer that there is no matching investment product.

[0003] The questionnaire design of information inquiry is crucial to the conversion of customer value, the improvement of customer experience, and the improvement of service efficiency of the marketing representative. At present, the questionnaire of information inquiry is mainly designed according to human experience, and the updating and iteration speed of personal experience cannot keep up with the change speed of customer groups. The existing investment questionnaire of investment products is often not suitable for customer groups, which reduces customer experience and affects the transaction success rate of investment products. SUMMARY

[0004] The embodiments of the present application provide a method and device for determining an investment questionnaire, and a medium, which realize determining a corresponding investment questionnaire for different groups of users, so that the user groups and the investment questionnaire of investment products are more suitable, improve user experience, and further improve the transaction success rate of investment products.

[0005] In a first aspect, the embodiments of the present application provide a method for determining an investment questionnaire, which comprises the following steps.

[0006] Obtaining basic data corresponding to each user, questionnaire survey data for each investment product, questionnaire feedback data corresponding to each questionnaire survey data, transaction condition data of each investment product, and product identifier of an investment product that is successful, as to-be-processed data;

[0007] Clustering each to-be-processed data to obtain a user category of each user;

[0008] According to the transaction condition data of a target investment product under a target user category, and the questionnaire feedback data corresponding to the target investment product, each questionnaire survey data of the target investment product is screened to obtain a preset number of candidate questionnaire survey data, wherein the target user category is any user category, and the target investment product refers to any investment product;

[0009] The target questionnaire data of the target investment product under the target user category is obtained according to each of the candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product.

[0010] In a second aspect, an embodiment of the present invention provides a device for determining an investment questionnaire, the device comprising:

[0011] A data acquisition module is configured to acquire basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data for each investment product, and product identifiers of successfully invested investment products, as data to be processed;

[0012] A user category acquisition module, configured to cluster the data to be processed to obtain a user category for each user;

[0013] a candidate questionnaire survey data acquisition module, configured to screen the questionnaire survey data of the target investment product under the target user category based on the transaction data of the target investment product and the questionnaire feedback data corresponding to the target investment product, to obtain a preset number of candidate questionnaire survey data, wherein the target user category is any user category and the target investment product is any investment product;

[0014] The target questionnaire survey data acquisition module is used to obtain the target questionnaire survey data of the target investment product under the target user category according to each candidate questionnaire survey data of the target investment product under the target user category and the application conditions of the target investment product.

[0015] In a third aspect, an embodiment of the present invention provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the method described in any one of the embodiments of the present invention are implemented.

[0016] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method in any embodiment of the present invention are implemented.

[0017] In the scheme implemented by the above-mentioned investment questionnaire determination method, device, equipment and medium, the basic data corresponding to each user, the questionnaire survey data for each investment product, the questionnaire feedback data corresponding to each questionnaire survey data, the transaction status data of each investment product and the product identification of the successfully invested investment product can be obtained through the client as the data to be processed, and the various data to be processed are clustered to obtain the user category of each user. According to the transaction status data of the target investment product under the target user category and the questionnaire feedback data corresponding to the target investment, the various questionnaire survey data of the target investment product are screened to obtain a preset number of candidate questionnaire survey data. According to the various candidate questionnaire survey data of the target investment product under the target user category and the application conditions of the target investment product, the target questionnaire survey data of the target investment product under the target user category are obtained, and the target questionnaire survey data are fed back to the client. The technical solution of the embodiment of the present invention realizes obtaining the user category to which the user belongs based on the user's basic data, questionnaire survey data for each investment product, questionnaire feedback data corresponding to each questionnaire survey data, transaction status data of each investment product, and product identification of the successfully invested investment product, and then obtaining a preset number of candidate questionnaire survey data for the target investment product under the target user category. From these candidate questionnaire survey data, the target questionnaire survey data is obtained, so that the target questionnaire survey data conforms to the group characteristics of the user and the characteristics of the target investment product, making the target questionnaire survey data more targeted, improving the user experience, and thus improving the transaction success rate of the target investment product. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0019] Figure 1 This is a schematic diagram of an application environment of a method for determining an investment questionnaire in one embodiment of the present invention;

[0020] Figure 2 is a flow chart of a method for determining an investment questionnaire in one embodiment of the present invention;

[0021] Figure 3 It is a structural diagram of an investment questionnaire determination device in one embodiment of the present invention;

[0022] Figure 4 is a structural diagram of a computer device in one embodiment of the present invention;

[0023] Figure 5FIG. 2 is another structural diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0025] The method for determining the investment questionnaire provided by the embodiment of the present invention can be applied in the following cases: Figure 1 In an application environment, a client communicates with a server via a network. The server obtains, through the client, basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data for each investment product, and product identifiers of successfully invested investment products as data to be processed. The server clusters the data to be processed to obtain a user category for each user. Based on the transaction data of the target investment product under the target user category and the questionnaire feedback data corresponding to the target investment, the server screens the questionnaire data for the target investment product to obtain a preset number of candidate questionnaire data. Based on the candidate questionnaire data for the target investment product under the target user category and the application conditions of the target investment product, the server obtains target questionnaire data for the target investment product under the target user category, and feeds the target questionnaire data back to the client. The technical solution of the embodiment of the present invention realizes obtaining the user category to which the user belongs based on the user's basic data, questionnaire survey data for each investment product, questionnaire feedback data corresponding to each questionnaire survey data, transaction status data of each investment product, and product identification of the investment product in which the investment is successfully invested, and then obtaining a preset number of candidate questionnaire survey data of the target investment product under the target user category. From these candidate questionnaire survey data, the target questionnaire survey data is obtained, so that the target questionnaire survey data conforms to the group characteristics of the user and the characteristics of the target investment product, making the target questionnaire survey data more targeted, improving the user experience, and then improving the transaction success rate of the target investment product. Among them, the client can be but is not limited to various personal computers, laptops, smart phones, tablet computers and portable wearable devices. The server can be implemented with an independent server or a server cluster composed of multiple servers. The present invention is described in detail below through specific embodiments.

[0026] See also Figure 2 As shown, Figure 2 A flow chart of a method for determining an investment questionnaire provided in an embodiment of the present invention includes the following steps:

[0027] S110, obtaining basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data of each investment product, and product identification of the successfully invested investment product as data to be processed.

[0028] Among them, basic data includes the user's age group, gender, industry category, city level, etc. Investment products include financial products and fund products, etc. Questionnaire survey data includes questionnaires related to investment products, which are used to understand the compatibility between users and investment products, etc. Questionnaire feedback data refers to the data provided by users in response to questionnaire survey data. Transaction status data refers to whether the user ultimately purchases the investment product, etc. For example, transaction status data includes successful or failed transactions. A successful transaction means that the user purchased the investment product, and a failed transaction means that the user did not purchase the investment product. The product identifier can refer to the name of the investment product, etc. Of course, the product identifier can be expressed in English, numbers, or Chinese. The data to be processed can refer to the data obtained by combining the aforementioned basic data, the questionnaire data for each investment product, the questionnaire feedback data corresponding to each questionnaire data, the transaction status data for each investment product, and the product identifier of the investment product that has been successfully invested. The combination method can be sequential splicing, etc.

[0029] Specifically, the basic data of each user, the questionnaire data for each investment product, the questionnaire data for each investment product, the questionnaire feedback data corresponding to each questionnaire data, the transaction data of each investment product, and the product identification of the successful investment product are obtained to obtain the data to be processed, and prepare for the subsequent clustering of the data to be processed.

[0030] S120: Cluster the data to be processed to obtain a user category of each user.

[0031] Among them, user categories refer to different user groups obtained according to the characteristics of the data to be processed.

[0032] Specifically, by clustering the data to be processed of each user, multiple cluster sets are obtained, and the cluster category corresponding to each cluster set is used as the user category of the user corresponding to the data to be processed under the cluster set, so as to subsequently obtain the target questionnaire survey data of the investment products under each user category.

[0033] S130 , screening the questionnaire survey data of the target investment product according to the transaction data of the target investment product under the target user category and the questionnaire feedback data corresponding to the target investment product to obtain a preset number of candidate questionnaire survey data.

[0034] The target user category is any user category, and the target investment product is any investment product.

[0035] Specifically, based on the transaction data of the target investment products under the target user category and the questionnaire feedback data corresponding to the target investment products, the questionnaire survey data of the target investment products under the target user category are screened to obtain a preset number of candidate questionnaire survey data. Through this step, the screening of the various questionnaire survey data of the target investment products under the target user category is achieved, so that the accuracy of obtaining the target questionnaire survey data based on the candidate questionnaire survey data is better.

[0036] S140 : Obtain target questionnaire data of the target investment product under the target user category according to each candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product.

[0037] Among them, the application conditions may refer to the conditions that users meet when selecting investment products for trading, including but not limited to age group, annual salary, credit conditions, etc.

[0038] In an embodiment of the present invention, target questionnaire data of the target investment product under the target user category is obtained based on the candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product, so that the target questionnaire data meets the characteristics of the application conditions of the target investment product and the characteristics of the target user category. When users under the target user category provide feedback on the target questionnaire data of the target investment product, the user experience is improved.

[0039] The method for determining the investment questionnaire of the embodiment of the present invention can obtain the basic data corresponding to each user, the questionnaire survey data for each investment product, the questionnaire feedback data corresponding to each questionnaire survey data, the transaction status data of each investment product and the product identification of the successfully invested investment product as the data to be processed, cluster the various data to be processed to obtain the user category of each user, and screen the various questionnaire survey data of the target investment product according to the transaction status data of the target investment product under the target user category and the questionnaire feedback data corresponding to the target investment to obtain a preset number of candidate questionnaire survey data, and obtain the target questionnaire survey data of the target investment product under the target user category according to the various candidate questionnaire survey data of the target investment product under the target user category and the application conditions of the target investment product. The technical solution of the embodiment of the present invention realizes obtaining the user category to which the user belongs based on the user's basic data, questionnaire survey data for each investment product, questionnaire feedback data corresponding to each questionnaire survey data, transaction status data of each investment product, and product identification of the successfully invested investment product, and then obtaining a preset number of candidate questionnaire survey data for the target investment product under the target user category. From these candidate questionnaire survey data, the target questionnaire survey data is obtained, so that the target questionnaire survey data conforms to the group characteristics of the user and the characteristics of the target investment product, making the target questionnaire survey data more targeted, improving the user experience, and thus improving the transaction success rate of the target investment product.

[0040] In another embodiment of the present invention, the basic data corresponding to each user, the questionnaire data for each investment product, the questionnaire feedback data corresponding to each questionnaire data, the transaction status data of each investment product, and the product identification of the successfully invested investment product are obtained as the data to be processed, including: obtaining the initial basic data of each user, and performing data cleaning, missing value filling and outlier removal operations on the initial basic data in sequence to obtain the basic data; obtaining the initial questionnaire data for each investment product of each user and the questionnaire feedback data corresponding to each initial questionnaire data; performing semantic representation on the initial questionnaire data to obtain the semantic data corresponding to the initial questionnaire data as the questionnaire data; representing the basic data of the user, the questionnaire data for each investment product, the questionnaire feedback data corresponding to each initial questionnaire data, the transaction status data of each investment product, and the identification of the successfully invested investment product in the form of a vector to obtain the data to be processed.

[0041] In the embodiment of the present invention, the initial basic data of each user is obtained and preprocessed, including data cleaning, filling missing values ​​and removing outliers, to obtain the basic data S 1a. Obtaining the initial questionnaire data of each investment product of each user and the questionnaire feedback data corresponding to each initial questionnaire data may be obtaining the initial questionnaire data and the corresponding questionnaire feedback data within a preset time period. The user's basic data, the questionnaire data of each investment product, the questionnaire feedback data corresponding to each initial questionnaire data, the transaction status data of each investment product, and the identifier of the successfully invested investment product are represented in the form of a vector to obtain the data to be processed. The embodiment of the present invention implements a data preprocessing stage to obtain the data to be processed, ensures the accuracy of the data to be processed, and avoids affecting the subsequent calculation of user categories, etc.

[0042] The preset time period can be one month, three months, etc. Optionally, preliminary screening is performed on the questionnaire data and questionnaire feedback data to ensure that the number of users, number of questions, basic user data, and distribution of successful investment product transactions involved in each type of questionnaire data are consistent with the distribution of the full data set, thereby increasing the accuracy and reliability of subsequent user categories, candidate questionnaire data, and target questionnaire data. Initial questionnaire data for each investment product for each user and questionnaire feedback data corresponding to each initial questionnaire data are obtained.

[0043] Optionally, the question data in the questionnaire survey data has an order, and the question feedback data in the questionnaire feedback data has an order. According to the principle of correspondence, the order of the question data and the corresponding question feedback data is consistent. Optionally, the question data can be obtained from a preset information question library. Semantic information of the question data is extracted and vectorized based on the pre-trained target model. The target model can be a bag-of-words vector model and a bidirectional encoder representation model (BidirectionalEncoder Representation from Transformers, BERT), etc. For example, the vector representation of the user's questionnaire data can be a coding sequence V 1a =[v1,v2,…,v n ], where v represents the vectorized representation of the question data in the questionnaire survey data, n represents the sequence number of the question data, and a represents the user ID. The coded sequence is the questionnaire survey data of user a. In the embodiment of the present invention, the user's questionnaire feedback data can be obtained based on the user's first reply data to the questionnaire survey data. The sequence of questionnaire feedback data is represented by C 1a =[c1,c2,…,c n], where c represents the user's feedback data on the question data. The understanding of the question in the questionnaire feedback data also includes two types of understanding: meeting the question conditions and not meeting the question conditions. That is, the questionnaire feedback data includes three situations: meeting the question conditions, not meeting the question conditions, and not understanding the question. Through the semantic information of the reply data, the question understanding is obtained, and then it is further judged whether the user's reply data meets the question conditions. For example, the question data is: Are you between 30 and 40 years old? If the reply data is: yes, the question conditions are met. If the reply data is: no, the question conditions are not met. Optionally, c=1 indicates that the question conditions are met, c=0 indicates that the question conditions are not met, and c=-1 indicates that the question is not understood. Each user has a transaction status data y for the questionnaire survey data of each investment product. a , y = 1 means the transaction is successful, y = 0 means the transaction is unsuccessful. The product identifier of the investment product with a successful transaction can be p a Then the data to be processed by user a can be expressed as X 1a =[S 1a ,V 1a ,C 1a ,y a ,p a ].

[0044] In another embodiment of the present invention, the questionnaire survey data includes multiple question data, the questionnaire feedback data includes multiple question feedback data, each of the question data has corresponding question feedback data in the questionnaire feedback data, the question feedback data includes question understanding or question not understanding, and the transaction status data includes transaction success or transaction failure; the transaction status data of the target investment product under the target user category and the questionnaire feedback data corresponding to the target investment product are screened to obtain a preset number of candidate questionnaire survey data, including: under the target user category, the transaction status data and the questionnaire feedback data of the target investment product are processed separately to obtain the transaction success rate of each questionnaire survey data of the target investment product and the question understanding rate of each question data in the questionnaire survey data; according to the transaction success rate and the question understanding rate, the questionnaire survey data of the target investment product under the target user category are screened to obtain a preset number of candidate questionnaire survey data.

[0045] The questionnaire survey data includes a plurality of question data, each user has corresponding questionnaire feedback data for each questionnaire survey data, and each question data in the questionnaire survey data has corresponding question feedback data in the questionnaire feedback data. The question feedback data includes any one of question understanding and question misunderstanding, the question understanding can indicate that the user understands the question data, and the question misunderstanding can indicate that the user does not understand the question data. The question understanding rate refers to the question data, and the question understanding rate of each user is obtained by the question feedback data, for example, the number of question understanding is divided by the number of all question feedback data, and the obtained value is used as the question understanding rate of the question data. The transaction success rate refers to the transaction condition data of each target user in the target user category for the target investment product, for example, the number of users who successfully transact is divided by the total number of all users, and the obtained value is used as the transaction success rate.

[0046] Specifically, under the target user category, the transaction condition data and the questionnaire feedback data of the target investment product are processed respectively to obtain the transaction success rate of each questionnaire survey data of the target investment product and the question understanding rate of each question data in the questionnaire survey data. According to the transaction success rate and the question understanding rate, each questionnaire survey data of the target investment product under the target user category is screened to obtain a preset number of candidate questionnaire survey data, and the scheme of the embodiment of the application realizes the acquisition of the candidate questionnaire survey data and improves the association degree of the candidate questionnaire survey data and the user.

[0047] In another embodiment of the application, the target questionnaire survey data of the target investment product under the target user category is obtained according to the target investment product under the target user category and the application condition of the target investment product, including: obtaining the question understanding rate of each question data according to the question data and the question feedback data corresponding to the question data in each questionnaire survey data; similarity calculation is performed on each candidate questionnaire survey data and the application condition to obtain the similarity of each candidate questionnaire survey data and the application condition; and the target questionnaire survey data of the target investment product under the target user category is obtained according to the similarity and the question understanding rate of each question data in the candidate questionnaire survey data.

[0048] In an embodiment of the present invention, the question comprehension rate of each question data is obtained based on the question data in each questionnaire data and the question feedback data corresponding to the question data. A similarity calculation is performed between each candidate questionnaire data and the application conditions to obtain the similarity between each candidate questionnaire data and the application conditions. Optionally, the candidate questionnaire data and the application conditions can be vectorized and the two vectors can be used to perform similarity calculation. Based on the similarity and the question comprehension rate of each question data in the candidate questionnaire data, the target questionnaire call-out data for the target investment product under the target user category is obtained. Optionally, the similarity is sorted from large to small, and the question comprehension rate of each question data is sorted from large to small. Then, a preset number of candidate questionnaire data with both similarity and question comprehension rates ranked high are selected as the target questionnaire data. Of course, the candidate questionnaire data with both similarity and question comprehension rates ranked high can be selected as the target questionnaire data, thereby improving the matching degree between the target questionnaire data and the target investment product and the target user category, thereby improving the experience of the target users under the target user category.

[0049] In another embodiment of the present invention, the target questionnaire data of the target investment product under the target user category is obtained based on the similarity and the question understanding rate of each question data in the candidate questionnaire data, including: taking the candidate questionnaire data with the highest similarity under the target user category as the questionnaire data to be updated; obtaining each question data to be updated corresponding to the question data under each question type based on the question type of each question data in the questionnaire data to be updated; obtaining the target question data of each question type based on the question understanding rate of each question data to be updated; and determining the target questionnaire data of the target investment product under the target user category based on each target question data.

[0050] Each question data has a corresponding question type, each question type includes multiple question data, and the question data to be updated refers to question data of the same question type as the question data.

[0051] Specifically, the candidate questionnaire data with the highest similarity under the target user category is used as the questionnaire data to be updated. Through this step, a candidate questionnaire data that best matches the application conditions of the target investment product can be screened out from the candidate questionnaire data. However, the expression of the question data in the candidate questionnaire data needs to be determined based on the question comprehension rate. That is, based on the question type of each question data in the questionnaire data to be updated, the individual question data to be updated corresponding to the question data under each question type are obtained. Based on the question comprehension rate of each question data to be updated for each question type, the target question data for each question type are obtained. In this way, based on the target question data, the target questionnaire data for the target investment product under the target user category is obtained, so that the target questionnaire data is the most compatible with the application conditions of the target investment product, and the expression of the question data in the target questionnaire data is also the best, so that the target questionnaire data is optimized.

[0052] In another embodiment of the present invention, the similarity calculation between each candidate questionnaire data and the application conditions is performed to obtain the similarity between each candidate questionnaire data and the application conditions, including: obtaining multiple application sub-conditions of the target investment product based on the application rules of the target investment product; obtaining the application conditions based on the multiple application sub-conditions; respectively representing the candidate questionnaire data and the application conditions by vectors to obtain a questionnaire vector and an application condition vector; performing similarity calculation between the questionnaire vector and the application condition vector to obtain the similarity between each questionnaire data and the application conditions.

[0053] The application rules may refer to conditions that the user must meet corresponding to the investment product. For example, if the application rules include an age limit between 30 and 40, the corresponding application sub-condition is that the user's age is in the range of [30-40].

[0054] Specifically, according to the application rules of the target investment product, multiple application sub-conditions of the target investment product are determined, and based on the multiple application sub-conditions, the application conditions are obtained. The candidate questionnaire data and the application conditions are respectively vectorized and represented, and then the obtained questionnaire vector and the application condition vector are similarity calculated to obtain the similarity between the two. The solution of the embodiment of the present invention realizes the calculation of the similarity between the questionnaire data and the application conditions, and simplifies the complexity of the calculation through the solution of vector calculation of similarity.

[0055] In another embodiment of the present invention, the method for obtaining questionnaire feedback data includes: obtaining user response data to each question data in questionnaire survey data; and obtaining questionnaire feedback data of the questionnaire survey data based on semantic information of each response data.

[0056] For example, if the question data is: Are you between 30 and 40 years old? and the response data is: Yes, then the questionnaire feedback data is question understanding.

[0057] In an embodiment of the present invention, the user's response data to each question data in the questionnaire survey data is obtained, and then semantic information is extracted from the response data. Based on the semantic information of the response data obtained, questionnaire feedback data of the questionnaire survey data is obtained. This step realizes the acquisition of questionnaire feedback data, and the acquisition of questionnaire feedback data through the semantic information of the response data improves the accuracy of the questionnaire feedback data.

[0058] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0059] In one embodiment, a device for determining an investment questionnaire is provided, and the device for determining an investment questionnaire corresponds to the method for determining an investment questionnaire in the above embodiment. Figure 3 As shown, the investment questionnaire determination device includes: a data acquisition module 410, a user category acquisition module 420, a candidate questionnaire data acquisition module 430 and a target questionnaire data acquisition module 440. The functional modules are described in detail as follows:

[0060] The data acquisition module 410 is used to obtain the basic data corresponding to each user, the questionnaire data for each investment product, the questionnaire feedback data corresponding to each questionnaire data, the transaction data of each investment product, and the product identification of the successfully invested investment product as the data to be processed; the user category acquisition module 420 is used to cluster each of the data to be processed to obtain the user category of each user; the candidate questionnaire data acquisition module 430 is used to screen each of the questionnaire data of the target investment product under the target user category according to the transaction data of the target investment product under the target user category and the questionnaire feedback data corresponding to the target investment product to obtain a preset number of candidate questionnaire data, wherein the target user category is any user category and the target investment product refers to any investment product; the target questionnaire data acquisition module 440 is used to obtain the target questionnaire data of the target investment product under the target user category according to each of the candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product.

[0061] In another embodiment of the present invention, the questionnaire survey data includes a plurality of question data, the questionnaire feedback data includes a plurality of question feedback data, each question data has corresponding question feedback data in the questionnaire feedback data, the question feedback data includes whether the question is understood or not understood, and the transaction status data includes whether the transaction is successful or failed;

[0062] The candidate questionnaire data acquisition module 430 is further configured to:

[0063] Under the target user category, the transaction data and the questionnaire feedback data of the target investment product are processed respectively to obtain the transaction success rate of each questionnaire data of the target investment product and the question comprehension rate of each question data in the questionnaire data;

[0064] The questionnaire survey data of the target investment product under the target user category are screened according to the transaction success rate and the question understanding rate to obtain a preset number of candidate questionnaire survey data.

[0065] In another embodiment of the present invention, the target questionnaire data acquisition module 440 is further configured to:

[0066] Obtaining a question comprehension rate for each question data according to the question data in each questionnaire survey data and the question feedback data corresponding to the question data;

[0067] Calculating the similarity between each candidate questionnaire survey data and the application conditions to obtain the similarity between each candidate questionnaire survey data and the application conditions;

[0068] The target questionnaire data of the target investment product under the target user category is obtained according to the similarity and the question comprehension rate of each question data in the candidate questionnaire data.

[0069] In another embodiment of the present invention, the target questionnaire data acquisition module 440 is further configured to:

[0070] taking the candidate questionnaire data with the highest similarity under the target user category as the questionnaire data to be updated;

[0071] According to the question type of each question data in the questionnaire survey data to be updated, obtaining each question data to be updated corresponding to the question data under each question type;

[0072] Based on the question comprehension rate of each of the to-be-updated question data of each question type, target question data of each question type is obtained respectively;

[0073] Based on each of the target question data, target questionnaire survey data for the target investment product under the target user category is determined.

[0074] In another embodiment of the present invention, the target questionnaire data acquisition module 440 is further configured to:

[0075] Obtaining multiple application sub-conditions for the target investment product according to the application rules of the target investment product;

[0076] Obtaining the application condition according to the plurality of application sub-conditions;

[0077] Respectively representing the candidate questionnaire data and the application conditions by vectors to obtain a questionnaire vector and an application condition vector;

[0078] A similarity calculation is performed on the questionnaire survey vector and the application condition vector to obtain a similarity between each questionnaire survey data and the application condition.

[0079] In another embodiment of the present invention, the apparatus further comprises:

[0080] The questionnaire feedback data acquisition module is used to obtain the user's response data for each question in the questionnaire data;

[0081] According to the semantic information of each of the reply data, questionnaire feedback data of the questionnaire survey data is obtained.

[0082] In another embodiment of the present invention, the data acquisition module 410 is further configured to:

[0083] Obtaining the initial basic data of each user, and performing data cleaning, filling missing values, and removing outliers on the initial basic data in sequence to obtain basic data;

[0084] Obtaining initial questionnaire data for each investment product of each user and questionnaire feedback data corresponding to each initial questionnaire data;

[0085] Performing semantic representation on the initial questionnaire survey data to obtain semantic data corresponding to the initial questionnaire survey data as the questionnaire survey data;

[0086] The user's basic data, the questionnaire data of each investment product, the questionnaire feedback data corresponding to each initial questionnaire data, the transaction data of each investment product and the identifier of the successfully invested investment product are represented in vector form to obtain the data to be processed.

[0087] The present invention provides a device for determining an investment questionnaire, which obtains basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data of each investment product, and product identification of successfully invested investment products as data to be processed, clusters each data to be processed to obtain a user category for each user, and screens each questionnaire data of the target investment product according to the transaction data of the target investment product under the target user category and the questionnaire feedback data corresponding to the target investment to obtain a preset number of candidate questionnaire data, and obtains target questionnaire data of the target investment product under the target user category according to each candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product. The technical solution of the embodiment of the present invention realizes obtaining the user category to which the user belongs based on the user's basic data, questionnaire survey data for each investment product, questionnaire feedback data corresponding to each questionnaire survey data, transaction status data of each investment product, and product identification of the successfully invested investment product, and then obtaining a preset number of candidate questionnaire survey data for the target investment product under the target user category. From these candidate questionnaire survey data, the target questionnaire survey data is obtained, so that the target questionnaire survey data conforms to the group characteristics of the user and the characteristics of the target investment product, making the target questionnaire survey data more targeted, improving the user experience, and thus improving the transaction success rate of the target investment product.

[0088] The specific definitions of the investment questionnaire determination device can be found in the definitions of the investment questionnaire determination method described above and will not be repeated here. Each module within the aforementioned investment questionnaire determination device may be implemented in whole or in part via software, hardware, or a combination thereof. Each of these modules may be embedded in or independent of a processor within a computer device in hardware form, or may be stored in a computer device memory in software form, allowing the processor to call and execute the corresponding operations of each module.

[0089] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 4 As shown. The computer device includes a processor, memory, network interface, and database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external client via a network connection. When executed by the processor, the computer program implements the functions or steps on the server side of a method for determining an investment questionnaire.

[0090] In one embodiment, a computer device is provided. The computer device may be a client, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, memory, a network interface, a display screen, and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and computer program in the non-volatile storage medium to run. The network interface of the computer device is used to communicate with an external server via a network connection. When executed by the processor, the computer program implements the client-side functions or steps of a method for determining an investment questionnaire.

[0091] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the following steps are performed:

[0092] Obtaining basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data for each investment product, and product identifiers of successfully invested investment products as data to be processed;

[0093] Clustering the data to be processed to obtain a user category for each user;

[0094] screening the questionnaire data of the target investment products according to the transaction data of the target investment products under the target user category and the questionnaire feedback data corresponding to the target investment products to obtain a preset number of candidate questionnaire data, wherein the target user category is any user category and the target investment product is any investment product;

[0095] The target questionnaire data of the target investment product under the target user category is obtained according to each of the candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product.

[0096] In the computer device of an embodiment of the present invention, when the processor executes the computer program, it obtains the user category to which the user belongs based on the user's basic data, the questionnaire data for each investment product, the questionnaire feedback data corresponding to each questionnaire data, the transaction status data of each investment product, and the product identification of the successfully invested investment product, and then obtains a preset number of candidate questionnaire data for the target investment product under the target user category. From these candidate questionnaire data, the target questionnaire data is obtained, so that the target questionnaire data conforms to the group characteristics of the user and the characteristics of the target investment product, making the target questionnaire data more targeted, improving the user experience, and thus improving the transaction success rate of the target investment product.

[0097] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0098] Obtaining basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data for each investment product, and product identifiers of successfully invested investment products as data to be processed;

[0099] Clustering the data to be processed to obtain a user category for each user;

[0100] screening the questionnaire data of the target investment products according to the transaction data of the target investment products under the target user category and the questionnaire feedback data corresponding to the target investment products to obtain a preset number of candidate questionnaire data, wherein the target user category is any user category and the target investment product is any investment product;

[0101] The target questionnaire data of the target investment product under the target user category is obtained according to each of the candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product.

[0102] The computer-readable storage medium of an embodiment of the present invention, when the computer program is executed by the processor, obtains the user category to which the user belongs based on the user's basic data, the questionnaire data for each investment product, the questionnaire feedback data corresponding to each questionnaire data, the transaction status data of each investment product, and the product identification of the successfully invested investment product, and then obtains a preset number of candidate questionnaire data for the target investment product under the target user category. From these candidate questionnaire data, the target questionnaire data is obtained, so that the target questionnaire data conforms to both the user group characteristics and the characteristics of the target investment product, making the target questionnaire data more targeted, improving the user experience, and thus improving the transaction success rate of the target investment product.

[0103] It should be noted that the above functions or steps that can be implemented by the computer-readable storage medium or computer device can be found in the relevant descriptions of the server side and the client side in the aforementioned method embodiment. To avoid repetition, they will not be described one by one here.

[0104] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0105] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0106] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for determining an investment questionnaire, characterized in that: include: Obtaining basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data for each investment product, and product identifiers of successfully invested investment products as data to be processed; Clustering the data to be processed to obtain a user category for each user; screening the questionnaire data of the target investment products according to the transaction data of the target investment products under the target user category and the questionnaire feedback data corresponding to the target investment products to obtain a preset number of candidate questionnaire data, wherein the target user category is any user category and the target investment product is any investment product; The target questionnaire data of the target investment product under the target user category is obtained according to each of the candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product.

2. The method for determining an investment questionnaire according to claim 1, characterized in that: The questionnaire survey data includes a plurality of question data, the questionnaire feedback data includes a plurality of question feedback data, each question data has corresponding question feedback data in the questionnaire feedback data, the question feedback data includes whether the question is understood or not understood, and the transaction status data includes whether the transaction is successful or failed; The step of screening the questionnaire survey data of the target investment product according to the transaction data of the target investment product under the target user category and the questionnaire feedback data corresponding to the target investment product to obtain a preset number of candidate questionnaire survey data includes: Under the target user category, the transaction data and the questionnaire feedback data of the target investment product are processed respectively to obtain the transaction success rate of each questionnaire data of the target investment product and the question comprehension rate of each question data in the questionnaire data; The questionnaire survey data of the target investment product under the target user category are screened according to the transaction success rate and the question understanding rate to obtain a preset number of candidate questionnaire survey data.

3. The method for determining an investment questionnaire according to claim 2, wherein: The step of obtaining target questionnaire data of the target investment product under the target user category based on each candidate questionnaire data of the target investment product under the target user category and the application conditions of the target investment product includes: Obtaining a question comprehension rate for each question data according to the question data in each questionnaire survey data and the question feedback data corresponding to the question data; Calculating the similarity between each candidate questionnaire survey data and the application conditions to obtain the similarity between each candidate questionnaire survey data and the application conditions; The target questionnaire data of the target investment product under the target user category is obtained according to the similarity and the question comprehension rate of each question data in the candidate questionnaire data.

4. The method for determining an investment questionnaire according to claim 3, wherein: The step of obtaining the target questionnaire data of the target investment product under the target user category based on the similarity and the question comprehension rate of each question data in the candidate questionnaire data includes: taking the candidate questionnaire data with the highest similarity under the target user category as the questionnaire data to be updated; According to the question type of each question data in the questionnaire survey data to be updated, obtaining each question data to be updated corresponding to the question data under each question type; Based on the question comprehension rate of each of the to-be-updated question data of each question type, target question data of each question type is obtained respectively; Based on each of the target question data, target questionnaire survey data for the target investment product under the target user category is determined.

5. The method for determining an investment questionnaire according to claim 3, wherein: The calculating the similarity between each candidate questionnaire survey data and the application conditions to obtain the similarity between each candidate questionnaire survey data and the application conditions includes: Obtaining multiple application sub-conditions for the target investment product according to the application rules of the target investment product; Obtaining the application condition according to the plurality of application sub-conditions; Respectively representing the candidate questionnaire data and the application conditions by vectors to obtain a questionnaire vector and an application condition vector; A similarity calculation is performed on the questionnaire survey vector and the application condition vector to obtain a similarity between each questionnaire survey data and the application condition.

6. The method for determining an investment questionnaire according to claim 2, wherein: The method for obtaining questionnaire feedback data includes: Obtain the user's response data for each question in the questionnaire data; According to the semantic information of each of the reply data, questionnaire feedback data of the questionnaire survey data is obtained.

7. The method for determining an investment questionnaire according to claim 1, wherein: The obtaining of basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data for each investment product, and product identifiers of successfully invested investment products as data to be processed includes: Obtaining the initial basic data of each user, and performing data cleaning, filling missing values, and removing outliers on the initial basic data in sequence to obtain basic data; Obtaining initial questionnaire data for each investment product of each user and questionnaire feedback data corresponding to each initial questionnaire data; Performing semantic representation on the initial questionnaire survey data to obtain semantic data corresponding to the initial questionnaire survey data as the questionnaire survey data; The user's basic data, the questionnaire data of each investment product, the questionnaire feedback data corresponding to each initial questionnaire data, the transaction data of each investment product and the identifier of the successfully invested investment product are represented in vector form to obtain the data to be processed.

8. A device for determining an investment questionnaire, characterized in that: include: A data acquisition module is configured to acquire basic data corresponding to each user, questionnaire data for each investment product, questionnaire feedback data corresponding to each questionnaire data, transaction data for each investment product, and product identifiers of successfully invested investment products, as data to be processed; A user category acquisition module, configured to cluster the data to be processed to obtain a user category for each user; a candidate questionnaire survey data acquisition module, configured to screen the questionnaire survey data of the target investment product under the target user category based on the transaction data of the target investment product and the questionnaire feedback data corresponding to the target investment product, to obtain a preset number of candidate questionnaire survey data, wherein the target user category is any user category and the target investment product is any investment product; The target questionnaire survey data acquisition module is used to obtain the target questionnaire survey data of the target investment product under the target user category according to each candidate questionnaire survey data of the target investment product under the target user category and the application conditions of the target investment product.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images