Product popularization method and device and electronic equipment
By acquiring information about the products to be promoted and user data, filtering target users, and determining appropriate promotion methods, the problem of user and product mismatch in financial product promotion is solved, achieving more efficient product promotion.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- INDUSTRIAL AND COMMERCIAL BANK OF CHINA
- Filing Date
- 2025-12-25
- Publication Date
- 2026-04-17
Smart Images
Figure CN121883121A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of financial technology, and more specifically, to a product promotion method, apparatus, and electronic device. Background Technology
[0002] Currently, when financial institutions promote financial products, they typically use a uniform promotional approach to reach all users, such as sending promotional text messages to all users. While this method is simple and easy to implement, there may be a mismatch between users and products, as well as between users and the promotional method. This can lead to poor promotional results for some operations, thereby reducing the effectiveness and efficiency of financial product promotion.
[0003] There is currently no effective solution to the problem of low effectiveness and efficiency in promoting financial products using related technologies. Summary of the Invention
[0004] The main objective of this application is to provide a product promotion method, apparatus, and electronic device to address the problem of low effectiveness and efficiency in the promotion of financial products in related technologies.
[0005] To achieve the above objectives, according to one aspect of this application, a product promotion method is provided. The method includes: obtaining product information of a product to be promoted, and determining description information of users to be promoted based on the product information; identifying target users matching the description information, and obtaining first user information and historical product purchase information of the target users; determining a target promotion method based on the first user information and historical product purchase information, wherein the target promotion method is a method of promoting the product to be promoted to the target users; and promoting the product to be promoted to the target users according to the target promotion method.
[0006] Optionally, determining the descriptive information of the users to be promoted based on the product information includes: obtaining the feature information of the product to be promoted based on the product information, and inputting the feature information into the profile generation model to obtain the user profile of the predicted user; obtaining M user indicator features, and determining the feature value range of each user indicator feature based on the user profile to obtain M feature value ranges; and generating descriptive information based on the M feature value ranges.
[0007] Optionally, determining the target user that matches the description information includes: selecting any preset user from the database, obtaining the second user information of the preset user, and determining the feature values of the preset user under various user indicator features based on the second user information to obtain M first feature values; determining whether all M first feature values match the description information; if all M first feature values match the description information, determining the preset user as the target user; if any one of the first feature values does not match the description information, determining that the preset user is not the target user.
[0008] Optionally, the profile generation model is trained as follows: obtain sample product information of multiple sample products, determine sample feature information based on the sample product information, and obtain the user profile of the sample user who purchased each sample product; take the sample feature information of each sample product and the corresponding user profile as a set of sample data to obtain multiple sets of first sample data, and use the multiple sets of first sample data as a training set to train the neural network model to obtain the profile generation model.
[0009] Optionally, determining the target promotion method based on the first user information and historical product purchase information includes: inputting the first user information into a promotion method prediction model to obtain prediction results, wherein the prediction results include multiple preset promotion methods and the success rate of each preset promotion method; determining the historical product promotion methods for each historical product based on historical product purchase information, and determining the proportion of each preset promotion method based on historical product promotion methods; determining the score of each preset promotion method based on the proportion and success rate of each preset promotion method, and determining the preset promotion method with the highest score as the target promotion method.
[0010] Optionally, the promotion method prediction model is trained as follows: multiple sample users and sample user information for each sample user are obtained, and the success rate of promoting the product to each sample user using each preset promotion method is obtained; the sample user information of each sample user and the corresponding preset promotion method and success rate are used as a set of sample data to obtain multiple sets of second sample data; the multiple sets of second sample data are used as a training set to train the neural network model to obtain the promotion method prediction model.
[0011] Optionally, after promoting the product to be promoted to the target users according to the target promotion method, the method further includes: obtaining the promotion effect data of the product to be promoted, and determining whether there are abnormal promotion indicator values of the product to be promoted based on the promotion effect data; if there are abnormal promotion indicator values of the product to be promoted, determining the abnormal reason for the abnormal promotion indicator values, and changing the product to be promoted according to the abnormal reason to obtain the updated product to be promoted.
[0012] To achieve the above objectives, according to another aspect of this application, a product promotion apparatus is provided. The apparatus includes: a first acquisition unit, configured to acquire product information of a product to be promoted, and determine description information of users to be promoted based on the product information; a first determination unit, configured to determine target users matching the description information, and acquire first user information and historical product purchase information of the target users; a second determination unit, configured to determine a target promotion method based on the first user information and historical product purchase information, wherein the target promotion method is a method of promoting the product to be promoted to the target users; and a promotion unit, configured to promote the product to be promoted to the target users according to the target promotion method.
[0013] Optionally, the first acquisition unit includes: a first acquisition module, used to acquire feature information of the product to be promoted based on product information, and input the feature information into a profile generation model to obtain a user profile of the predicted user; a second acquisition module, used to acquire M user indicator features, and determine the feature value range of each user indicator feature based on the user profile to obtain M feature value ranges; and a generation module, used to generate descriptive information based on the M feature value ranges.
[0014] Optionally, the first determining unit includes: a first determining module, configured to select any preset user from the database, obtain second user information of the preset user, and determine the feature values of the preset user under various user indicator features based on the second user information, thereby obtaining M first feature values; a judging module, configured to judge whether all M first feature values conform to the description information; a second determining module, configured to determine that the preset user is a target user if all M first feature values conform to the description information; and a third determining module, configured to determine that the preset user is not a target user if any one of the first feature values does not conform to the description information.
[0015] Optionally, the profile generation model is trained using the following apparatus: a second acquisition unit, used to acquire sample product information of multiple sample products, determine sample feature information based on the sample product information, and acquire user profiles of sample users who purchase each sample product; and a first training unit, used to take the sample feature information of each sample product and the corresponding user profile as a set of sample data to obtain multiple sets of first sample data, and use the multiple sets of first sample data as a training set to train the neural network model to obtain the profile generation model.
[0016] Optionally, the second determining unit includes: a prediction module, used to input the first user information into the promotion method prediction model to obtain a prediction result, wherein the prediction result includes multiple preset promotion methods and the success rate of each preset promotion method; a fourth determining module, used to determine the historical product promotion method for each historical product based on historical product purchase information, and to determine the proportion of each preset promotion method based on the historical product promotion method; and a fifth determining module, used to determine the score of each preset promotion method based on the proportion and success rate of each preset promotion method, and to determine the preset promotion method with the highest score as the target promotion method.
[0017] Optionally, the promotion method prediction model is trained using the following devices: a third acquisition unit, used to acquire multiple sample users and sample user information for each sample user, and to acquire the success rate of promoting the product to each sample user using each preset promotion method; a third determination unit, used to take the sample user information of each sample user and the corresponding preset promotion method and success rate as a set of sample data to obtain multiple sets of second sample data; and a second training unit, used to train the neural network model using multiple sets of second sample data as a training set to obtain the promotion method prediction model.
[0018] Optionally, the device further includes: a fourth acquisition unit, used to acquire promotion effect data of the product to be promoted, and determine whether there are abnormal promotion indicator values of the product to be promoted based on the promotion effect data; and a fourth determination unit, used to determine the abnormality cause of the abnormal promotion indicator value when there is an abnormal promotion indicator value of the product to be promoted, and to change the product to be promoted based on the abnormality cause to obtain an updated product to be promoted.
[0019] To achieve the above objectives, according to another aspect of this application, an electronic device is provided, the electronic device including a memory storing an executable program; and a processor for running the program, wherein the program executes the above-described product promotion method when it runs.
[0020] To achieve the above objectives, according to another aspect of this application, a computer program product is provided, including computer instructions that, when executed by a processor, implement the steps of the product promotion method described above.
[0021] In this embodiment, the process involves obtaining product information of the product to be promoted and determining the description information of the users to be promoted based on the product information; identifying target users who match the description information and obtaining the first user information and historical product purchase information of the target users; determining the target promotion method based on the first user information and historical product purchase information, wherein the target promotion method is the method of promoting the product to be promoted to the target users; and promoting the product to be promoted to the target users according to the target promotion method. By identifying target users associated with the product to be promoted and determining the promotion method acceptable to the target users, and then promoting the product to be promoted to the target users according to the finally determined promotion method, the purpose of accurately determining the product promotion target and the product promotion method is achieved, thereby realizing the technical effect of improving the efficiency and effectiveness of product promotion, and thus solving the technical problem of low effectiveness and efficiency of financial product promotion operations in related technologies. Attached Figure Description
[0022] The accompanying drawings, which form part of this application, are used to provide a further understanding of this application. The illustrative embodiments and descriptions of this application are used to explain this application and do not constitute an undue limitation of this application. In the drawings:
[0023] Figure 1 A hardware structure block diagram of a computer terminal for implementing a product promotion method is shown.
[0024] Figure 2 This is a flowchart of a product promotion method provided according to Embodiment 1 of this application;
[0025] Figure 3 This is a schematic diagram of a product promotion device provided according to Embodiment 2 of this application;
[0026] Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation
[0027] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. This application will now be described in detail with reference to the accompanying drawings and embodiments.
[0028] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.
[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.
[0030] It should be noted that the product promotion methods, devices, and electronic devices defined in this disclosure can be used in the fintech field, or in any field other than fintech. The application fields of the product promotion methods, devices, and electronic devices defined in this disclosure are not limited.
[0031] It should be noted that the information collected, first user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, and displayed data) used in this application are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, storage, use, processing, transmission, provision, disclosure, and application of related data all comply with the relevant laws, regulations, and standards of the relevant regions, have taken necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse use. If the user chooses to refuse, the process will proceed to the expert decision-making process. For example, this system has an interface with relevant users or institutions. Before obtaining relevant information, a request to obtain the information needs to be sent to the aforementioned user or institution through the interface. After receiving consent from the aforementioned user or institution, the relevant information is obtained. Users can view the purpose of data use in real time through the authorization interface and have the right to withdraw authorization or delete data at any time. After the authorization is withdrawn, the system will terminate the relevant data processing within 24 hours.
[0032] The embodiments or examples disclosed herein are not exhaustive, but merely illustrative of some embodiments or examples, and are not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment or example can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment or example can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment or example can be arbitrarily interchanged. Furthermore, optional methods or examples in a particular embodiment or example can be arbitrarily combined; moreover, embodiments or examples can be arbitrarily combined. For example, some or all steps of different embodiments or examples can be arbitrarily combined, and a particular embodiment or example can be arbitrarily combined with optional methods or examples of other embodiments or examples.
[0033] Example 1
[0034] According to an embodiment of this application, an embodiment of a product promotion method is also provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.
[0035] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing a product promotion method is shown. Figure 1 As shown, the computer terminal 10 (or mobile device) may include one or more processors 102 (shown as 102a, 102b, ..., 102n in the figure) 102 (processor 102 may include, but is not limited to, processing devices such as microprocessors or programmable logic devices), a memory 104 for storing data, and a transmission device 106 for communication functions. In addition, it may also include: a display, an input / output interface, a universal serial bus port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.
[0036] It should be noted that the aforementioned one or more processors 102 and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10 (or mobile device). As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).
[0037] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the product promotion method in this embodiment. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby realizing the aforementioned product promotion method. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0038] The transmission device 106 is used to receive or send data via a network. Specific examples of the network described above may include a wireless network provided by the communication provider of the computer terminal 10. In one example, the transmission device 106 includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 106 may be a Radio Frequency (RF) module, used for wireless communication with the Internet.
[0039] The display may be, for example, a touchscreen LCD display that allows the user to interact with the user interface of the computer terminal 10 (or mobile device).
[0040] Under the aforementioned operating environment, this application provides the following: Figure 2 The product promotion methods shown. Figure 2 This is a flowchart of the product promotion method provided in Embodiment 1 of this application, such as... Figure 2 As shown, the method includes:
[0041] Step S201: Obtain product information of the product to be promoted, and determine the description information of the users to be promoted based on the product information.
[0042] It should be noted that the executing entity in this embodiment can be a product promotion system. This system can determine the corresponding target users based on product information and determine the promotion method that matches the target users, thereby improving the effectiveness and efficiency of product promotion operations.
[0043] It should be noted that the "product to be promoted" refers to financial products that need to be promoted, such as newly launched wealth management products. Product information is a detailed description of the financial product, which may include product features, expected returns, risk management strategies, etc. Promotional users are virtual users representing the target customer group with a high degree of relevance to the product to be promoted. Description information is a feature description of the target customer group extracted based on the product information, used to screen potential customers.
[0044] For example, the system first collects and organizes all relevant information about the product to be promoted, including but not limited to product type, service content, and expected returns. Then, it generates description information of virtual promotional users based on the product information, thereby determining the target customer characteristics of the virtual promotional users of the product to be promoted, such as age, gender, and financial product usage.
[0045] Step S202: Identify target users who match the description information, and obtain the target users' first user information and historical product purchase information.
[0046] It should be noted that historical product purchase information refers to the target user's past records of purchasing financial products, including purchase frequency and product type.
[0047] For example, after determining the description information, target users who match the description information can be identified, thereby determining whether the product to be promoted can be promoted to the target users. For instance, the system retrieves user information from a database for multiple users and analyzes whether the user information of each user meets the description information requirements of the credit product to be promoted, thereby selecting target users from multiple users to perform product promotion operations.
[0048] Furthermore, after identifying the target users, it is necessary to obtain their primary user information and historical product purchase information, such as transaction information of users in financial institutions and whether they have used similar financial products before, in order to further determine the product promotion methods to be promoted to the target users.
[0049] Step S203: Determine the target promotion method based on the first user information and historical product purchase information, wherein the target promotion method is the way to promote the product to be promoted to the target user.
[0050] For example, after determining the first user information and historical product purchase information, the system will determine the first promotion method matching the target user based on the first user information and the second promotion method matching the target user based on the historical product purchase information. Thus, the system will jointly determine the target promotion method with the highest matching degree with the target user based on the first and second promotion methods, thereby improving the accuracy of promotion method selection.
[0051] Step S204: Promote the product to be promoted to the target users according to the target promotion method.
[0052] For example, once the target promotion method is determined, the product can be promoted to the target users through the target promotion method, thereby achieving the technical effect of improving the effectiveness and efficiency of the promotion operation of the product to be promoted.
[0053] It should be noted that in this embodiment, user authorization is required to obtain and use user information before the information can be obtained. If the user does not authorize or refuses to authorize, no user information can be obtained and used.
[0054] It should be noted that after identifying the target users, it is necessary to determine whether the target users have a need for product promotion. Only if the target users have a need for product promotion and have expressed to the financial institution that they need product promotion, can product promotion be carried out to the target users. Otherwise, product promotion to users is prohibited.
[0055] The product promotion method provided in this application involves: obtaining product information of the product to be promoted; determining the description information of the users to be promoted based on the product information; identifying target users who match the description information and obtaining the first user information and historical product purchase information of the target users; determining the target promotion method based on the first user information and historical product purchase information, wherein the target promotion method is the method of promoting the product to be promoted to the target users; and promoting the product to be promoted to the target users according to the target promotion method. By identifying target users associated with the product to be promoted and determining the promotion method acceptable to the target users, and then promoting the product to be promoted to the target users according to the finally determined promotion method, the method achieves the purpose of accurately determining the product promotion target and the product promotion method, thereby improving the technical effect of improving the efficiency and effectiveness of product promotion, and solving the technical problem of low effectiveness and efficiency of financial product promotion operations in related technologies.
[0056] To accurately determine the descriptive information, optionally, in the product promotion method provided in this application embodiment, determining the descriptive information of the promotion users of the product to be promoted based on the product information includes: obtaining the feature information of the product to be promoted based on the product information, and inputting the feature information into the profile generation model to obtain the user profile of the predicted user; obtaining M user indicator features, and determining the feature value range of each user indicator feature based on the user profile to obtain M feature value ranges; and generating descriptive information based on the M feature value ranges.
[0057] It should be noted that feature information refers to the key attributes of the financial products or services to be promoted, including but not limited to product type, service content, expected returns, risk level, and target customer preferences. The user profile generation model is a machine learning or deep learning-based model used to analyze feature information and construct user profiles for target users, i.e., a set of user features. User indicator features are multiple key parameters describing the target user, such as age and financial product usage history.
[0058] For example, when generating descriptive information, the system first needs to collect and organize the feature information of the product to be promoted, and then input the feature information into a pre-trained user profile generation model. This model can adopt a deep neural network structure, and through multi-level feature extraction and learning, determine the user profile of the predicted user with a high degree of matching with the product.
[0059] Furthermore, after obtaining the user profile of the predicted users, the system will analyze M user indicator features based on the user profile and determine the feature value range of each indicator. For example, for the age indicator, the model may, based on product positioning, lock the target user age range between 18 and 35 years old. By comprehensively considering all indicators, the system will generate descriptive information containing M feature value ranges for subsequent target user screening.
[0060] Finally, the feature value ranges are combined into descriptive information to obtain complete and multi-dimensional descriptive information for predicting users who have a high degree of matching with the product to be promoted. For example, the descriptive information can be features such as being between 35 and 55 years old, having investment experience, and preferring one-on-one consulting services.
[0061] This embodiment improves the accuracy of filtering target users by accurately generating descriptive information, thereby increasing the accuracy of product promotion operations.
[0062] To accurately select target users, optionally, in the product promotion method provided in this application embodiment, determining the target user that matches the description information includes: selecting any preset user from the database, obtaining the second user information of the preset user, and determining the feature values of the preset user under various user indicator characteristics based on the second user information to obtain M first feature values; determining whether all M first feature values match the description information; if all M first feature values match the description information, determining the preset user as the target user; if any one of the first feature values does not match the description information, determining that the preset user is not the target user.
[0063] For example, the system selects a preset user from the financial institution's customer database for evaluation and retrieves the preset user's secondary user information, which includes the preset user's basic attributes and historical behavioral data. For instance, suppose the system randomly selects a user with customer number 1 and then retrieves the user's detailed information from the database, including age, gender, transaction information, and records of purchased financial services.
[0064] Furthermore, based on the second user information, the system calculates the actual characteristic values of the preset user under M user indicator characteristics. This step may involve data cleaning, format conversion, and statistical analysis to improve the accuracy and reliability of the characteristic values. For example, the system might calculate that customer 1's age characteristic value is 32 years old, and that their product purchase characteristics from financial institutions include two fixed-rate loans and one high-risk investment fund.
[0065] Furthermore, the system compares the calculated first feature value with the description information, checking whether each feature value falls within the feature value range defined in the description information. If all feature values meet the requirements of the description information, the user is considered a potential target user. For example, suppose the age range defined in the description information is 25-35 years old, and the product purchase characteristic is at least one loan experience. Then, Customer 1's age characteristics meet the requirements, and their purchase history also meets the conditions, so the system marks them as a target user.
[0066] This embodiment accurately identifies and filters target users who match the description information by comparing the second user information and the description information, thus achieving the technical effect of accurately determining the target users and improving the accuracy and effectiveness of subsequent product promotion operations.
[0067] To improve the accuracy of the profile generation model, optionally, in the product promotion method provided in this application embodiment, the profile generation model is trained in the following manner: obtaining sample product information of multiple sample products, determining sample feature information based on the sample product information, and obtaining the user profile of the sample user who purchased each sample product; taking the sample feature information of each sample product and the corresponding user profile as a set of sample data to obtain multiple sets of first sample data, and using the multiple sets of first sample data as a training set to train the neural network model to obtain the profile generation model.
[0068] For example, the first step is to extract multiple sold financial products from the financial institution's database as sample products. These products should cover different categories and service areas to improve the model's generalization ability. Then, each sample product is analyzed in depth to identify its core features and construct sample feature information.
[0069] Furthermore, it is necessary to obtain detailed user information for all sample users who have purchased the aforementioned sample products, including but not limited to age, types of products purchased, historical transaction records, investment preferences, etc., and to use data mining and statistical analysis methods to construct a user profile for each sample user. The user profile should comprehensively reflect the user's financial behavior and preference characteristics, providing rich information for model training.
[0070] The sample feature information of each sample product is associated with the corresponding sample user profile to form a set of training data, namely the first sample data. For example, the feature information of sample loan product A is bound to user profile 1 who has purchased the product. The above process is repeated until all sample product and user data have been processed, forming a training set containing multiple sets of first sample data.
[0071] After obtaining the constructed training set, the neural network model can be trained using the training set. The model structure can include an input layer, multiple hidden layers, and an output layer. The input layer receives sample feature information, the hidden layers are responsible for feature learning and transformation, and the output layer generates user profile predictions. The weights of the neural network are continuously adjusted using the backpropagation algorithm to minimize the error between the predicted profile and the actual profile.
[0072] During training, a subset of data is reserved as a validation set to periodically evaluate the model's performance, including metrics such as prediction accuracy and recall. Based on the model evaluation results, adjustments to the network structure, parameter settings, or algorithm optimization may be necessary to improve the model's accuracy and generalization ability.
[0073] This embodiment uses historical user data to train the model, thereby improving the accuracy of the model's output results.
[0074] To accurately determine the target promotion method, optionally, in the product promotion method provided in this application embodiment, determining the target promotion method based on the first user information and historical product purchase information includes: inputting the first user information into a promotion method prediction model to obtain a prediction result, wherein the prediction result includes multiple preset promotion methods and the success rate of each preset promotion method; determining the historical product promotion method for each historical product based on the historical product purchase information, and determining the proportion of each preset promotion method based on the historical product promotion method; determining the score of each preset promotion method based on the proportion and success rate of each preset promotion method, and determining the preset promotion method with the highest score as the target promotion method.
[0075] For example, when determining the target promotion method, a two-dimensional evaluation method can be used for comprehensive evaluation. First, the target user's first user information is input into a pre-trained promotion method prediction model, and the model outputs a success rate prediction value containing multiple preset promotion methods, providing a quantitative basis for subsequent strategy selection. The model structure can include an input layer, multiple hidden layers, and an output layer. The input layer receives sample feature information, the hidden layer is responsible for feature learning and transformation, and the output layer generates promotion methods.
[0076] Furthermore, we can analyze the target users' historical product purchase information, identify the promotion methods used for each product in the past, and calculate the percentage of each preset promotion method that successfully reaches the target users based on historical records, that is, the frequency of that method in the historical product promotion methods.
[0077] Based on the predicted success rate of each promotion method under the model prediction dimension and the frequency value under the historical promotion dimension, the comprehensive score of each preset promotion method can be calculated. The comprehensive score can be calculated by weighted summation to obtain the score of each preset promotion method under the comprehensive consideration of the two dimensions.
[0078] Finally, after obtaining the scores of each preset promotion method, the promotion method with the highest score can be determined as the target promotion method, thus achieving the technical effect of accurately determining the target promotion method.
[0079] This embodiment determines the evaluation criteria under two dimensions, comprehensively determines the score of each preset promotion method based on the evaluation criteria value, and determines the promotion method with the highest score as the target promotion method, thus achieving the technical effect of accurately determining the target promotion method.
[0080] To improve the accuracy of the model output, optionally, in the product promotion method provided in this application embodiment, the promotion method prediction model is trained in the following manner: acquiring multiple sample users and sample user information for each sample user, and acquiring the success rate of promoting the product to each sample user using each preset promotion method; taking the sample user information of each sample user and the corresponding preset promotion method and success rate as a set of sample data to obtain multiple sets of second sample data; using the multiple sets of second sample data as a training set to train the neural network model to obtain the promotion method prediction model.
[0081] For example, when training the promotion method prediction model, multiple sample users are first drawn from the customer database of financial institutions to cover different types of users, thereby improving the model's generalization ability. For each sample user, detailed sample user information is collected, including but not limited to basic demographic data, financial transaction history, and a list of purchased products. Simultaneously, the success rate of promoting products to sample users using various preset promotion methods (such as telephone, email, social media, etc.) is recorded, i.e., the ratio of end users responding and completing a purchase.
[0082] The sample user information, promotion methods used, and corresponding success rates collected in the above steps are used to construct a set of training data, namely the second sample data. A corresponding second sample data is created for each participating sample user, forming a training dataset containing multiple records.
[0083] Furthermore, the constructed second sample dataset is used as the training set to train the neural network model, resulting in a promotion method prediction model. The model architecture includes an input layer, multiple hidden layers, and an output layer. The input layer receives sample user information, the hidden layers are responsible for feature extraction and weight adjustment, and the output layer predicts the success rate of different preset promotion methods. During training, the model learns the intrinsic relationship between sample user information and the success rate of promotion methods, adjusting the weights through a backpropagation algorithm to minimize the gap between the predicted success rate and the actual success rate.
[0084] This embodiment uses historical product promotion data to train the model, thereby improving the accuracy of the model's output results.
[0085] Optionally, in the product promotion method provided in this application embodiment, after promoting the product to be promoted to the target user according to the target promotion method, the method further includes: obtaining the promotion effect data of the product to be promoted, and determining whether there are abnormal promotion indicator values of the product to be promoted based on the promotion effect data; if there are abnormal promotion indicator values of the product to be promoted, determining the abnormal reason for the abnormal promotion indicator values, and changing the product to be promoted according to the abnormal reason to obtain the updated product to be promoted.
[0086] It should be noted that promotional performance data refers to data collected during actual promotional activities regarding metrics such as the acceptance rate, engagement rate, and conversion rate of the product to be promoted among the target user group. Abnormal promotional metrics are those exceeding the normal fluctuation range or failing to meet expectations in the promotional performance data, which may indicate problems with product design, promotional strategy, or target user positioning. The cause of the anomaly is the root cause of the abnormal promotional metric value. Product modification involves adjusting the product design, purchase process, and other aspects after identifying the cause of the anomaly to improve product attractiveness and market performance, resulting in an updated product to be promoted.
[0087] For example, after a product is promoted to target users through targeted promotion methods, the system begins to collect promotion performance data, including but not limited to user click-through rate, number of details queries, actual purchase quantity, and customer feedback ratings. The data is collected through a real-time monitoring platform and may involve various data sources such as online behavior tracking, sales data analysis, and user surveys. For instance, assuming a new credit card product is being promoted, the system records key indicators such as click-through rate, application volume, activation rate, and first-time transaction ratio among the target user group, as well as user satisfaction ratings for the credit card's features.
[0088] Furthermore, statistical methods, such as outlier detection algorithms, can be used to identify abnormal promotion indicator values in the promotion effect data that deviate from the normal distribution. When abnormal promotion indicator values are found, it is necessary to analyze the reasons for the anomalies. Possible reasons include product design defects, user experience problems, incorrect market positioning, and inappropriate promotion channels.
[0089] Finally, after determining the cause of the anomaly, changes can be made to the product to be promoted based on the cause. This can include changing the product content or the product promotion process, resulting in an updated product to be promoted. For example, if the anomaly metric is an activation rate that is too low, and the cause is that the online activation process for the new credit card is too complicated, causing users to abandon it, then the activation process can be adjusted to obtain an updated product to be promoted.
[0090] This embodiment achieves the technical effect of improving the success rate and efficiency of product promotion operations by monitoring promotion effect data and adjusting the products and promotion process of the products to be promoted based on abnormal promotion indicator values.
[0091] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.
[0092] Example 2
[0093] This application also provides a product promotion device. It should be noted that the product promotion device of this application can be used to execute the product promotion method provided in the above embodiments. The product promotion device provided in this application is described below.
[0094] According to an embodiment of this application, an apparatus for implementing the above-described product promotion method is also provided. Figure 3 This is a schematic diagram of a product promotion device provided according to Embodiment 2 of this application, such as... Figure 3 As shown, the device includes:
[0095] The first acquisition unit 31 is used to acquire product information of the product to be promoted and determine the description information of the promotion users of the product to be promoted based on the product information.
[0096] The first determining unit 32 is used to determine the target user that matches the description information, and to obtain the target user's first user information and historical product purchase information.
[0097] The second determining unit 33 is used to determine the target promotion method based on the first user information and historical product purchase information, wherein the target promotion method is the way to promote the product to be promoted to the target user.
[0098] Promotion unit 34 is used to promote the product to be promoted to target users according to the target promotion method.
[0099] The product promotion device provided in this application embodiment acquires product information of the product to be promoted by a first acquisition unit 31 and determines the description information of the promotion users of the product to be promoted based on the product information; a first determination unit 32 determines the target users that match the description information and acquires the first user information and historical product purchase information of the target users; a second determination unit 33 determines the target promotion method based on the first user information and historical product purchase information, wherein the target promotion method is the method of promoting the product to be promoted to the target users; and a promotion unit 34 promotes the product to be promoted to the target users according to the target promotion method. By determining the target users associated with the product to be promoted and determining the promotion method acceptable to the target users, and then promoting the product to be promoted to the target users according to the finally determined promotion method, the device achieves the purpose of accurately determining the product promotion target and the product promotion method, thereby achieving the technical effect of improving the efficiency and effectiveness of product promotion, and thus solving the technical problem of low effectiveness and efficiency of financial product promotion operations in related technologies.
[0100] Optionally, in the product promotion device provided in this application embodiment, the first acquisition unit 31 includes: a first acquisition module, used to acquire feature information of the product to be promoted according to product information, and input the feature information into a profile generation model to obtain a user profile of the predicted user; a second acquisition module, used to acquire M user indicator features, and determine the feature value range of each user indicator feature according to the user profile to obtain M feature value ranges; and a generation module, used to generate descriptive information according to the M feature value ranges.
[0101] Optionally, in the product promotion device provided in this application embodiment, the first determining unit 32 includes: a first determining module, used to select any preset user from the database, obtain the second user information of the preset user, and determine the feature values of the preset user under various user indicator features based on the second user information to obtain M first feature values; a judging module, used to judge whether all M first feature values conform to the description information; a second determining module, used to determine that the preset user is a target user when all M first feature values conform to the description information; and a third determining module, used to determine that the preset user is not a target user when any one of the first feature values does not conform to the description information.
[0102] Optionally, in the product promotion device provided in this application embodiment, the profile generation model is trained by the following device: a second acquisition unit, used to acquire sample product information of multiple sample products, determine sample feature information based on the sample product information, and acquire user profiles of sample users who purchase each sample product; a first training unit, used to take the sample feature information of each sample product and the corresponding user profile as a set of sample data to obtain multiple sets of first sample data, and use the multiple sets of first sample data as a training set to train the neural network model to obtain the profile generation model.
[0103] Optionally, in the product promotion device provided in this application embodiment, the second determining unit 33 includes: a prediction module, used to input the first user information into the promotion method prediction model to obtain a prediction result, wherein the prediction result includes multiple preset promotion methods and the success rate of each preset promotion method; a fourth determining module, used to determine the historical product promotion method of each historical product based on historical product purchase information, and determine the proportion of each preset promotion method based on the historical product promotion method; and a fifth determining module, used to determine the score of each preset promotion method based on the proportion and success rate of each preset promotion method, and determine the preset promotion method with the highest score as the target promotion method.
[0104] Optionally, in the product promotion apparatus provided in this application embodiment, the promotion method prediction model is trained by the following apparatus: a third acquisition unit, used to acquire multiple sample users and sample user information of each sample user, and to acquire the success rate of promoting the product to each sample user using each preset promotion method; a third determination unit, used to take the sample user information of each sample user and the corresponding preset promotion method and success rate as a set of sample data to obtain multiple sets of second sample data; and a second training unit, used to train the neural network model using multiple sets of second sample data as a training set to obtain the promotion method prediction model.
[0105] Optionally, in the product promotion device provided in the embodiments of this application, the device further includes: a fourth acquisition unit, used to acquire promotion effect data of the product to be promoted, and determine whether there are abnormal promotion indicator values of the product to be promoted based on the promotion effect data; and a fourth determination unit, used to determine the abnormal cause of the abnormal promotion indicator value when there is an abnormal promotion indicator value of the product to be promoted, and to change the product to be promoted based on the abnormal cause to obtain an updated product to be promoted.
[0106] It should be noted that the first acquisition unit 31, the first determination unit 32, the second determination unit 33, and the extension unit 34 mentioned above correspond to steps S201 to S204 in Embodiment 1. The instances and application scenarios implemented by each of the above units and the corresponding steps are the same, but are not limited to the content disclosed in Embodiment 1. It should be noted that the above modules or units can be hardware or software components stored in memory (e.g., memory 104) and processed by one or more processors (e.g., processors 102a, 102b, ..., 102n). The above modules can also be part of a device and can run in the computer terminal 10 provided in Embodiment 1.
[0107] Example 3
[0108] Embodiments of this application may provide an electronic device. Figure 4 This is a structural block diagram of an electronic device according to an embodiment of this application. Figure 4 As shown, the electronic device may include: one or more ( Figure 4 (Only one is shown) processor 1002, memory 1004, memory controller, and peripheral interface, wherein the peripheral interface is connected to the radio frequency module, audio module and display.
[0109] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the methods and apparatus in the embodiments of this application. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby implementing the above-described methods. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
[0110] Those skilled in the art will understand that Figure 4 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones, tablets, handheld computers, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 4 This does not limit the structure of the aforementioned electronic device. For example, electronic devices may also include components that are more... Figure 4 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 4 The different configurations shown.
[0111] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.
[0112] Example 4
[0113] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the product promotion method provided in Embodiment 1.
[0114] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.
[0115] Embodiments of this application also provide a computer program product, which, when executed on a data processing device, is a program adapted to perform the steps of a product promotion method.
[0116] Embodiments of this application also provide a computer-readable storage medium, which includes a stored executable program, wherein, when the executable program is running, it controls the device where the computer-readable storage medium is located to perform the above-described product promotion method.
[0117] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.
[0118] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.
[0119] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.
[0120] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0121] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0122] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard drive, magnetic disk, or optical disk.
[0123] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.
Claims
1. A product promotion method, characterized in that, include: Obtain product information of the product to be promoted, and determine the description information of the users to be promoted based on the product information; Identify target users who match the description information, and obtain the target users' first user information and historical product purchase information; The target promotion method is determined based on the first user information and the historical product purchase information, wherein the target promotion method is the method of promoting the product to be promoted to the target user; The product to be promoted is promoted to the target users according to the target promotion method.
2. The method according to claim 1, characterized in that, The description information of the users to be promoted for the product to be promoted, determined based on the product information, includes: Based on the product information, the feature information of the product to be promoted is obtained, and the feature information is input into the profile generation model to obtain the user profile of the predicted user. Obtain M user indicator features, and determine the feature value range of each user indicator feature based on the user profile to obtain M feature value ranges; The description information is generated based on the M feature value intervals.
3. The method according to claim 2, characterized in that, Identifying target users who match the described information includes: Select any preset user from the database, obtain the second user information of the preset user, and determine the feature values of the preset user under various user indicator features based on the second user information to obtain M first feature values; Determine whether all M first feature values conform to the description information; If all M first feature values match the description information, the preset user is determined to be the target user; If any of the first feature values does not match the description information, it is determined that the preset user is not the target user.
4. The method according to claim 2, characterized in that, The portrait generation model is trained in the following manner: Obtain sample product information for multiple sample products, determine sample feature information based on the sample product information, and obtain a user profile of the sample user who purchased each sample product. The sample feature information of each sample product and the corresponding user profile are used as a set of sample data to obtain multiple sets of first sample data. The multiple sets of first sample data are then used as a training set to train the neural network model to obtain the profile generation model.
5. The method according to claim 1, characterized in that, Determining the target promotion method based on the first user information and the historical product purchase information includes: The first user information is input into the promotion method prediction model to obtain the prediction result, wherein the prediction result includes multiple preset promotion methods and the success rate of each preset promotion method; Based on the historical product purchase information, determine the historical product promotion method for each historical product, and determine the proportion of each preset promotion method based on the historical product promotion method; The score for each preset promotion method is determined based on its proportion and success rate, and the preset promotion method with the highest score is determined as the target promotion method.
6. The method according to claim 5, characterized in that, The promotion method prediction model is trained in the following way: Obtain multiple sample users, as well as sample user information for each sample user, and obtain the success rate of promoting products to each sample user using various preset promotion methods; Each sample user's sample user information, along with the corresponding preset promotion method and success rate, is used as a set of sample data to obtain multiple sets of second sample data. The neural network model is trained using the multiple sets of second sample data as a training set to obtain the prediction model of the generalization method.
7. The method according to claim 1, characterized in that, After promoting the product to be promoted to the target users according to the target promotion method, the method further includes: Obtain the promotion effect data of the product to be promoted, and determine whether there are any abnormal promotion indicator values for the product to be promoted based on the promotion effect data; If the product to be promoted has the abnormal promotion indicator value, determine the cause of the abnormality of the abnormal promotion indicator value, and modify the product to be promoted according to the cause of the abnormality to obtain the updated product to be promoted.
8. A product promotion device, characterized in that, include: The first acquisition unit is used to acquire product information of the product to be promoted, and determine the description information of the promotion users of the product to be promoted based on the product information. The first determining unit is used to determine the target user that matches the description information, and to obtain the target user's first user information and historical product purchase information; The second determining unit is used to determine a target promotion method based on the first user information and the historical product purchase information, wherein the target promotion method is a method of promoting the product to be promoted to the target user; The promotion unit is used to promote the product to be promoted to the target user according to the target promotion method.
9. A computer program product comprising computer instructions, characterized in that, When the computer instructions are executed by the processor, they implement the steps of the product promotion method according to any one of claims 1 to 7.
10. An electronic device, characterized in that, include: Memory, which stores executable programs; A processor for running the program, wherein the program, when running, performs the product promotion method according to any one of claims 1 to 7.