Information processing method and device

Abstract

The invention discloses an information processing method and device, and relates to the technical field of big data processing. A specific embodiment of the method comprises the following steps: determining a plurality of user sets and a plurality of concept users; for each user set, member users are determined from the user sets; determining a member concept user corresponding to the member user from the plurality of concept users; determining feature attribute vectors of the member concept users corresponding to the member users; combining the user data and the feature attribute vectors corresponding to the member users to generate user samples corresponding to the member users; training the initial model by using the user samples corresponding to the member users in each user set to obtain a normalized model; determining a target user, and inputting user data of the target user into the normalized model to obtain a feature attribute vector of the target user; and performing information processing on the target user according to the feature attribute vector of the target user. According to the embodiment, the user processing process can become simple and efficient.

Description

Technical Field

[0001] The present invention relates to the field of big data processing technology, and in particular to an information processing method and device. Background Art

[0002] In order to facilitate the management of multiple users, multiple users are usually divided into user sets according to region, age, living and consumption habits, etc. For example, the following user sets can be set: Guangdong user set, Hong Kong user set, Macau user set, etc. Since the user characteristics, data sources and processing methods in each user set may be different, if user information processing is to be performed, it is necessary to perform it separately for different user sets, and the user processing process is relatively complicated and cumbersome. Summary of the invention

[0003] In view of this, an embodiment of the present invention provides an information processing method and device to normalize users from different user sets, and utilize user feature attribute vectors to perform unified information processing on users from different user sets, thereby making the user processing process simple and efficient.

[0004] In a first aspect, an embodiment of the present invention provides an information processing method, including:

[0005] Determine multiple user sets and multiple conceptual users;

[0006] For each user set: determining a member user from the user set; determining a member concept user corresponding to the member user from a plurality of concept users; determining a feature attribute vector of the member user corresponding to the member concept user; combining user data and feature attribute vector corresponding to the member user to generate a user sample corresponding to the member user;

[0007] Using user samples corresponding to member users in each of the user sets, an initial model is trained to obtain a normalized model;

[0008] Determine a target user, input user data of the target user into the normalization model, and obtain a feature attribute vector of the target user;

[0009] Information processing is performed on the target user according to the characteristic attribute vector of the target user.

[0010] Optionally, determining a member concept user corresponding to the member user from the plurality of concept users includes:

[0011] Determining concept mapping information corresponding to the user set;

[0012] Determine attribute information corresponding to the member user;

[0013] A member concept user corresponding to the member user is determined from the multiple concept users according to the concept mapping information and the attribute information corresponding to the member user.

[0014] Optionally, before combining the user data and the characteristic attribute vector corresponding to the member user to generate the user sample corresponding to the member user, the method further includes:

[0015] Determine the data source and processing method information corresponding to the user set;

[0016] According to the user identifier of the member user, obtaining the original information of the member user from the data source corresponding to the user set;

[0017] The processing method information is used to process the original data of the member user to generate user data corresponding to the member user.

[0018] Optionally, before inputting the user data of the target user into the normalization model to obtain the characteristic attribute vector of the target user, the method further includes:

[0019] Determine a target user set corresponding to the target user;

[0020] Determine the data source and processing method information corresponding to the target user set;

[0021] Acquire original information of the target user from a data source corresponding to the target user set according to the user identifier of the target user;

[0022] The original data of the target user is processed by using the processing mode information to generate user data corresponding to the target user.

[0023] Optionally, after inputting the user data of the target user into the normalization model to obtain the characteristic attribute vector of the target user, the method further includes:

[0024] Determining a target concept user corresponding to the target user from the plurality of concept users;

[0025] Determine a vector set corresponding to the target concept user;

[0026] In response to the characteristic attribute vector of the target user not being in the vector set, generating warning information for the target user.

[0027] Optionally, performing information processing on the target user according to the characteristic attribute vector of the target user includes:

[0028] Inputting the characteristic attribute vector of the target user into the user analysis model;

[0029] Determining the policy information corresponding to the target user according to the output information of the user analysis model;

[0030] Information processing is performed on the target user according to the policy information.

[0031] Optionally, performing information processing on the target user according to the characteristic attribute vector of the target user includes:

[0032] Obtaining user information of the target user;

[0033] Generate a user profile of the target user according to the user information and feature attribute vector of the target user;

[0034] Information processing is performed on the target user according to the user portrait of the target user.

[0035] In a second aspect, an embodiment of the present invention provides an information processing device, including:

[0036] A user determination module, used to determine multiple user sets and multiple conceptual users;

[0037] The sample generation module is used for: for each user set: determining a member user from the user set; determining a member concept user corresponding to the member user from a plurality of concept users; determining a feature attribute vector corresponding to the member concept user; combining user data and feature attribute vector corresponding to the member user to generate a user sample corresponding to the member user;

[0038] A model training module, used to train an initial model using user samples corresponding to member users in each of the user sets to obtain a normalized model;

[0039] A vector generation module, used to determine a target user, input the user data of the target user into the normalization model, and obtain a characteristic attribute vector of the target user;

[0040] The information processing module is used to perform information processing on the target user according to the characteristic attribute vector of the target user.

[0041] Optionally, the sample generation module is specifically used to:

[0042] Determining concept mapping information corresponding to the user set;

[0043] Determine attribute information corresponding to the member user;

[0044] A member concept user corresponding to the member user is determined from the multiple concept users according to the concept mapping information and the attribute information corresponding to the member user.

[0045] Optionally, the sample generation module is further used to:

[0046] Determine the data source and processing method information corresponding to the user set;

[0047] According to the user identifier of the member user, obtaining the original information of the member user from the data source corresponding to the user set;

[0048] The processing method information is used to process the original data of the member user to generate user data corresponding to the member user.

[0049] Optionally, the vector generation module is further used for:

[0050] Determine a target user set corresponding to the target user;

[0051] Determine the data source and processing method information corresponding to the target user set;

[0052] Acquire original information of the target user from a data source corresponding to the target user set according to the user identifier of the target user;

[0053] The original data of the target user is processed by using the processing mode information to generate user data corresponding to the target user.

[0054] Optionally, the vector generation module is further used for:

[0055] Determining a target concept user corresponding to the target user from the plurality of concept users;

[0056] Determine a vector set corresponding to the target concept user;

[0057] In response to the characteristic attribute vector of the target user not being in the vector set, generating warning information for the target user.

[0058] In a third aspect, an embodiment of the present invention provides an electronic device, including:

[0059] one or more processors;

[0060] A storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any of the above embodiments.

[0061] In a fourth aspect, an embodiment of the present invention provides a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the above embodiments.

[0062] In a fifth aspect, an embodiment of the present invention provides a computer program product, including a computer program, which implements the method described in any of the above embodiments when executed by a processor.

[0063] An embodiment of the above invention has the following advantages or beneficial effects: conceptual users are set by using the dimensions corresponding to user processing, regardless of different user sets. The initial model is trained using user samples corresponding to member users in each user set to obtain a normalized model. The user sample includes: user data corresponding to the member user and the characteristic attribute vector of the conceptual user corresponding to the member user. The user data of the target user is input into the normalized model to obtain the characteristic attribute vector of the target user, and information processing is performed on the target user based on the characteristic attribute vector of the target user. Therefore, the scheme of the embodiment of the present application can perform normalization processing on users from different user sets, and then use the characteristic attribute vector of the user to uniformly perform information processing on users from different user sets, making the user processing process simple and efficient.

[0064] The further effects of the above-mentioned non-conventional optional manner will be described below in conjunction with the specific implementation manner. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0066] Figure 1 is a flowchart of an information processing method provided by the first embodiment of the present invention;

[0067] Figure 2 is a flowchart of an information processing method provided by the second embodiment of the present invention;

[0068] Figure 3 is a flowchart of an information processing method provided by the third embodiment of the present invention;

[0069] Figure 4 It is a schematic diagram of the construction process of a normalization model provided by the present invention;

[0070] Figure 5 is a structural schematic diagram of an information processing device provided by an embodiment of the present invention;

[0071] Figure 6 It is a schematic diagram of the structure of a computer system of a terminal device or a server suitable for implementing an embodiment of the present invention. DETAILED DESCRIPTION

[0072] The following is a description of exemplary embodiments of the present invention in conjunction with the accompanying drawings, including various details of the embodiments of the present invention to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0073] The acquisition, transmission, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0074] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned, and they should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0075] Figure 1 is a flowchart of an information processing method provided by the first embodiment of the present invention, such as Figure 1 As shown, the method includes:

[0076] Step 101: Determine multiple user sets and multiple conceptual users.

[0077] To facilitate the management of multiple users, multiple users can be divided into multiple user sets according to dimensions such as region, age, and living consumption habits. For example, the following user sets can be set according to the region dimension: Guangdong user set, Hong Kong user set, Macau user set, etc. The following user sets can also be set according to the age dimension: children user set, youth user set, middle-aged and elderly user set, etc.

[0078] Conceptual users are obtained by ignoring user sets and dividing users according to the dimensions corresponding to user information processing. The dimensions corresponding to conceptual users are independent of the dimensions corresponding to user sets. For example, multiple user sets are set according to the regional dimension, and user information processing is used to analyze user consumption habits. The dimension corresponding to user information processing is consumption attribute. The regional dimension and the consumption attribute dimension are different dimensions. Based on the consumption attribute dimension, the following conceptual users can be set: high-consumption users, medium-consumption users, and low-consumption users.

[0079] For another example, multiple user sets are set according to the age dimension, and the user information processing is used to analyze the user's region. The dimension corresponding to the user information processing is the region. The age dimension and the region dimension are different dimensions. The following conceptual users can be set according to the region dimension: Beijing users, Tianjin users, Hebei users, etc.

[0080] Step 102: for each user set: determine a member user from the user set; and determine a member concept user corresponding to the member user from a plurality of concept users.

[0081] According to the business needs of user information processing, multiple concept users and concept mapping information corresponding to each concept user can be set. According to the concept mapping information corresponding to each concept user, the member concept user corresponding to the member user is determined. For example, the concept users include: high-consumption users and low-consumption users. The concept mapping information corresponding to the high-consumption user is that the monthly consumption amount is greater than 3,000, and the concept mapping information corresponding to the low-consumption user is that the monthly consumption amount is not greater than 3,000.

[0082] Furthermore, for each user set, concept mapping information corresponding to each concept user can be set respectively. Determine the concept mapping information corresponding to the user set; determine the attribute information corresponding to the member user; and determine the member concept user corresponding to the member user from multiple concept users based on the concept mapping information and the attribute information corresponding to the member user.

[0083] According to the business needs of user information processing, for each user set, the concept mapping information corresponding to each concept user is set. The attribute information corresponding to the member user is the user information corresponding to the concept mapping information. For each user set, according to the concept mapping information, the member users in the user set are divided into different concept users.

[0084] For example, user sets include: Beijing user sets, Tianjin user sets, etc. Concept users include: high-consumption users and low-consumption users. The attribute information is the monthly consumption amount of the member user. The concept mapping information of the Beijing user set corresponding to high-consumption users is that the monthly consumption amount is greater than 3,000. The concept mapping information of the Tianjin user set corresponding to high-consumption users is that the monthly consumption amount is greater than 2,500. It can be seen that the concept mapping information of high-consumption users corresponding to the Beijing user set and the Tianjin user set is different.

[0085] Step 103: Determine the characteristic attribute vector of the member concept user corresponding to the member user; combine the user data and the characteristic attribute vector corresponding to the member user to generate a user sample corresponding to the member user.

[0086] The characteristic attribute vector is used to characterize the measurement value of the user's corresponding concept dimension. The concept dimension is the basis for dividing concept users. For example, according to the consumption attribute dimension, the following concept users are set: high consumption users, medium consumption users, and low consumption users. The characteristic attribute vector is used to characterize the measurement value of the user's consumption attribute.

[0087] The feature attribute vector can be physically meaningful or not. For example, if the concept dimension is consumption attribute, if the feature attribute vector can be physically meaningful, then the feature attribute vector can be the mortgage feature vector value, the catering consumption feature vector value, the credit card limit vector value, etc. The value of the feature attribute vector can be a manually marked value or a result value of data analysis and mining, etc.

[0088] If the characteristic attribute vector has no physical meaning, we can first define the attribute vector related to the concept dimension, and then process the related attribute vector through the analysis model or method to obtain the characteristic attribute vector. The characteristic attribute vector has no clear physical meaning, but it can represent the measurement value of the concept dimension.

[0089] User data is user-related data, which can be selected according to business needs. User data includes data related to the user's conceptual dimension.

[0090] Step 104: Use user samples corresponding to member users in each user set to train an initial model to obtain a normalized model.

[0091] An initial model, such as a neural network model, can be selected according to requirements. The initial model is trained to obtain a normalized model. The normalized model is used to normalize or standardize the metric values ​​corresponding to users from different user sets. The metric value is the metric value of the user corresponding to the concept dimension.

[0092] Step 105: Determine the target user, input the user data of the target user into the normalization model, and obtain the characteristic attribute vector of the target user.

[0093] Step 106: Perform information processing on the target user according to the characteristic attribute vector of the target user.

[0094] The characteristic attribute vector makes users from different user sets comparable. According to the characteristic attribute vector of the target user, information processing can be uniformly performed on the target users from different user sets. For example, according to the characteristic attribute vector of the target user, the policy information of the target user can be determined. According to the characteristic attribute vector of the target user, the user profile level of the target user can also be constructed.

[0095] In one embodiment of the present invention, information processing is performed on the target user based on the characteristic attribute vector of the target user, including: inputting the characteristic attribute vector of the target user into a user analysis model; determining policy information corresponding to the target user based on output information of the user analysis model; and performing information processing on the target user based on the policy information.

[0096] Policy information can be set according to business needs. Policy information may include: marketing strategy, reminder strategy, delivery channel, delivery frequency, etc. According to the marketing strategy, information push processing or sales recommendation processing can be performed on the target users. It is also possible to send reminder information or recommendation information to the target users through the delivery channel and delivery frequency. The delivery channel may include: phone, email, SMS, etc.

[0097] In the scheme of the embodiment of the present invention, the user samples corresponding to the member users in each user set are used to train the initial model to obtain a normalized model. The user samples include: user data corresponding to the member users and feature attribute vectors of the concept users corresponding to the member users. The user data of the target user is input into the normalized model to obtain the feature attribute vector of the target user, and information processing is performed on the target user according to the feature attribute vector of the target user. Therefore, the scheme of the embodiment of the present application can perform normalization processing on users from different user sets, and perform unified information processing on users from different user sets using the feature attribute vectors of the users, so that the user processing process becomes simple and efficient.

[0098] In one embodiment of the present invention, before the user data of the target user is input into the normalization model to obtain the characteristic attribute vector of the target user, it also includes: determining a target user set corresponding to the target user; determining a data source and processing method information corresponding to the target user set; obtaining the original information of the target user from the data source corresponding to the target user set according to the user identifier of the target user; and performing information processing on the original data of the target user using the processing method information to generate user data corresponding to the target user.

[0099] The data source may be a database, a data acquisition address, etc. The processing method may be a calculation formula, a calculation model, etc. The data source and processing method information corresponding to different user sets. For example, the user sets include: Guangdong user set, Hong Kong user set, Macau user set, etc. The data source corresponding to the Guangdong user set may be the relevant data of Guangdong users in Guangdong. The data source corresponding to the Hong Kong user set may be the relevant data of Hong Kong users in Hong Kong.

[0100] The data source corresponding to the user set may be one or more. Different data sources correspond to different processing information. For example, the data source corresponding to the Beijing user set may be the relevant data of Beijing users in Beijing, the relevant data of Beijing users in Tianjin, and the relevant data of Beijing users in Hebei.

[0101] After obtaining the original information of the target user from the data source corresponding to the user set, the processing method information corresponding to the data source is determined, and the original data is processed according to the calculation formula or calculation model corresponding to the processing method information to generate user data corresponding to the target user.

[0102] If there are multiple data sources corresponding to the user set, for each data source: determine the processing method information corresponding to the data source, and perform information processing on the original data of the target user in the data source according to the calculation formula or calculation model corresponding to the processing method information to generate the user data corresponding to the data source. Merge the user data corresponding to each data source to generate the user data corresponding to the target user.

[0103] In one embodiment of the present invention, after the user data of the target user is input into the normalized model to obtain the characteristic attribute vector of the target user, it also includes: determining a target concept user corresponding to the target user from multiple concept users; determining a vector set corresponding to the target concept user; and generating an alarm message for the target user in response to the characteristic attribute vector of the target user not existing in the vector set.

[0104] A vector set is set for each concept user. The vector set is used to store the characteristic attribute vector corresponding to the concept user. Each vector set includes at least one characteristic attribute vector. If the characteristic attribute vector of the target user exists in the vector set, the characteristic attribute vector of the target user is correct, and subsequent information processing steps can be performed. If the characteristic attribute vector of the target user does not exist in the vector set, the characteristic attribute vector of the target user is wrong, and an alarm message is generated for the target user so that relevant personnel can troubleshoot possible problems. By setting a vector set for a concept user and defining the value range of the characteristic vector set for the concept user, the accuracy of the user's characteristic attribute vector is improved.

[0105] Figure 2 is a flow chart of an information processing method provided by the second embodiment of the present invention, such as Figure 2 As shown, the method includes:

[0106] Step 201: Determine multiple user sets and multiple conceptual users.

[0107] Step 202: for each user set: determine a member user from the user set; and determine a member concept user corresponding to the member user from a plurality of concept users.

[0108] Step 203: Determine the characteristic attribute vector of the member user corresponding to the member concept user.

[0109] Step 204: Determine the data source and processing method information corresponding to the user set; obtain the original information of the member user from the data source corresponding to the user set according to the user identifier of the member user.

[0110] The data source may be a database, a data acquisition address, etc. The processing method may be a calculation formula, a calculation model, etc. The data source and processing method information corresponding to different user sets. For example, the user sets include: Guangdong user set, Hong Kong user set, Macau user set, etc. The data source corresponding to the Guangdong user set may be the relevant data of Guangdong users in Guangdong. The data source corresponding to the Hong Kong user set may be the relevant data of Hong Kong users in Hong Kong.

[0111] The data source corresponding to the user set may be one or more. Different data sources correspond to different processing information. For example, the data source corresponding to the Guangdong user set may be the relevant data of Guangdong users in Guangdong, the relevant data of Guangdong users in Hong Kong, the relevant data of Guangdong users in Macau, etc.

[0112] Step 205: Using the processing method information, perform information processing on the original data of the member user to generate user data corresponding to the member user.

[0113] After obtaining the original information of the member users from the data source corresponding to the user set, the processing method information corresponding to the data source is determined, and the original data is processed according to the calculation formula or calculation model corresponding to the processing method information to generate user data corresponding to the member users.

[0114] If there are multiple data sources corresponding to the user set, for each data source: determine the processing method information corresponding to the data source, and process the original data of the member user in the data source according to the calculation formula or calculation model corresponding to the processing method information to generate the user data corresponding to the data source. Merge the user data corresponding to each data source to generate the user data corresponding to the member user.

[0115] For example, the data source corresponding to the Guangdong user set corresponds to the relevant data of Guangdong users in Guangdong, the relevant data of Guangdong users in Hong Kong, and the relevant data of Guangdong users in Macau. The first data and the first processing information in the relevant data of the member user in Guangdong, the second data and the second processing information in the relevant data of the member user in Hong Kong, and the third user data and the third processing information in the relevant data of the member user in Macau are obtained respectively. The first user data is generated based on the first data and the first processing information. The second user data is generated based on the second data and the second processing information. The third user data is generated based on the third data and the third processing information. Finally, the first user data, the second user data, and the third user data are merged to obtain the user data corresponding to the member user.

[0116] Step 206: Combine the user data and the characteristic attribute vector corresponding to the member user to generate a user sample corresponding to the member user.

[0117] Step 207: Using user samples corresponding to member users in each user set, train the initial model to obtain a normalized model.

[0118] Step 208: Determine the target user, input the user data of the target user into the normalization model, and obtain the characteristic attribute vector of the target user.

[0119] Step 209: Perform information processing on the target user according to the characteristic attribute vector of the target user.

[0120] In the solution of the embodiment of the present invention, data source and processing method information are set for each user set. After obtaining the original information of the member user from the data source corresponding to the user set, the original data of the member user is processed using the processing method information to generate user data corresponding to the member user. This solution can perform personalized processing on users from different user sets, so that the obtained user data is convenient for subsequent normalization or standardization processing.

[0121] Figure 3 is a flow chart of an information processing method provided by the third embodiment of the present invention, such as Figure 3 As shown, the method includes:

[0122] Step 301: Determine multiple user sets and multiple conceptual users.

[0123] Step 302: for each user set: determine a member user from the user set; and determine a member concept user corresponding to the member user from a plurality of concept users.

[0124] Step 303: Determine the characteristic attribute vector of the member concept user corresponding to the member user; combine the user data and the characteristic attribute vector corresponding to the member user to generate a user sample corresponding to the member user.

[0125] Step 304: Use user samples corresponding to member users in each user set to train the initial model to obtain a normalized model.

[0126] Step 305: Determine the target user, input the user data of the target user into the normalization model, and obtain the characteristic attribute vector of the target user.

[0127] Step 306: Obtain user information of the target user; generate a user profile of the target user based on the user information and feature attribute vector of the target user.

[0128] User information is the relevant information of the target user. User information can be set according to business needs, i.e., the needs of information processing. User information can be region, relevant area, habit information, etc.

[0129] Step 307: Perform information processing on the target user according to the user portrait of the target user.

[0130] Specifically, the target user's strategy information, prompt information, optimization process, user clustering, etc. can be determined based on the target user's user portrait, and information processing can be performed on the target user based on the target user's strategy information, prompt information, optimization process, user clustering, etc.

[0131] In one embodiment of the present invention, information processing is performed on the target user based on the characteristic attribute vector of the target user, including: inputting the characteristic attribute vector of the target user into a user analysis model; determining policy information corresponding to the target user based on output information of the user analysis model; and performing information processing on the target user based on the policy information.

[0132] Policy information can be set according to business needs. Policy information may include: marketing strategy, reminder strategy, delivery channel, delivery frequency, etc. Information processing can be performed on target users according to marketing strategy. Reminder information can also be sent to target users through delivery channels and delivery frequencies. Delivery channels may include: phone, email, SMS, etc.

[0133] In the solution of the embodiment of the present invention, after obtaining the characteristic attribute vector of the target user by using the normalized model, a user profile of the target user is generated according to the user information and the characteristic attribute vector of the target user. The user profile is independent of the user set. The user profile of each user can be used to perform unified information processing on the users of each user set.

[0134] To make the solution of the embodiment of the present invention easier to understand, the following is an example of credit card analysis and processing of users in the Greater Bay Area. Existing credit card marketing user portraits are either only for Guangdong residents, or only for Hong Kong residents or Macau residents, and are not applicable to credit card products in the Greater Bay Area. For people who frequently travel between the three places and make purchases, the existing user portrait solutions cannot capture the characteristics of this type of people.

[0135] The core goal of user portrait construction is to transform professional knowledge such as algorithms and big data into actionable user portrait construction projects based on a deep understanding of business needs and constraints. Compared with traditional credit card marketing, the customer base of credit cards in the Greater Bay Area has different characteristics, so targeted data sources and data processing methods are needed.

[0136] The data used for user profiling can be divided into two categories: local data and foreign data. For people living in Hong Kong, the data related to Hong Kong is local data, and the data related to Guangdong and Macau is foreign data.

[0137] A normalization model is established to normalize the data of users in the three regions, so that users in different regions can be placed on the same dimension to measure whether they are the target of credit card marketing in the Greater Bay Area. Concept users are established to compare the normalized user data of the three regions, which can flexibly adapt to changes in exchange rates without the need for frequent model training.

[0138] First, according to the region, the following user sets are established: Guangdong user set, Hong Kong user set, and Macau user set. Define the consumption attributes of each user set. Due to the differences between each region, the factors that affect the user portrait of credit card marketing are also inconsistent. For example, the consumption attributes of the Hong Kong user set are commercial insurance, MTR usage times, horse racing frequency, etc. The consumption attributes of the Macau user set are cyber amount, etc. The consumption attributes of the Guangdong user set are Alipay credit, WeChat flow, etc.

[0139] Next, we build a normalization model to make the user data of the three places comparable. We can pre-define several distinguishing concept users, such as "high consumption, love of luxury goods", "low consumption, prefer cash life", "high income and high investment awareness", etc.

[0140] Taking the concept user of "high consumption, love of luxury goods" as an example, find the user groups that meet the concept mapping information from the above user set, assuming that they are the Guangdong user group, the Hong Kong user group, and the Macau user group. Guangdong users correspond to consumption information in three places, namely Guangdong users' Guangdong consumption data, Guangdong users' Hong Kong consumption data, and Guangdong users' Macau consumption data. Similarly, Hong Kong users, that is, Macau users, can also obtain similar consumption data.

[0141] Users in the Guangdong user set, Hong Kong user set, and Macau user set that correspond to the same concept user will be normalized into similar feature attribute vectors representing the user. For example, all users in the three user sets that correspond to the concept user "high consumption, love of luxury goods" have different consumption attributes in the three places, but after being processed by the normalization model, the final output is a similar feature attribute vector representing the user.

[0142] Figure 4 FIG. 1 is a schematic diagram of a construction process of a normalization model provided by the present invention. Figure 4 As shown, the entire process of building a normalized model is as follows:

[0143] Step S01: Collect user data and consumption attribute data in Guangdong, Hong Kong and Macao.

[0144] Step S02: Define concept users and concept mapping information. Define multiple concept users with differentiation, such as "high consumption, love of luxury goods", "low consumption, prefer cash life", "high income and high investment awareness", etc.

[0145] Step S03: define the normalized user's characteristic attribute vector. The characteristic attribute may have physical meaning or may not have physical meaning.

[0146] Step S04: For each conceptual user, define a vector set corresponding to the conceptual user. The vector set is used to store possible values ​​of the normalized characteristic attribute vector of the user.

[0147] Step S05: Divide the users in each user set based on the concept mapping information of the concept users.

[0148] Step S06: Introduce variables such as exchange rate and gold price in different regions to train the model and obtain a normalized model. After the model is trained, the data of users in the three regions can be used as input to obtain a normalized feature attribute vector. The feature attribute vector can be used to construct a user profile for credit cards in the Greater Bay Area.

[0149] Compared with existing credit card marketing user portrait solutions, the solution of the embodiment of the present invention fully considers the characteristics of the Greater Bay Area credit cards, strengthens the influence of users' local data in the three places and cross-regional consumption attribute data, and makes the user data in the three places comparable through a normalized model, thereby constructing a user portrait that meets business needs.

[0150] Figure 5 is a schematic diagram of the structure of an information processing device provided by an embodiment of the present invention, such as Figure 5 As shown, the device comprises:

[0151] A user determination module 501, used to determine multiple user sets and multiple conceptual users;

[0152] The sample generation module 502 is used for each user set to: determine a member user from the user set; determine a member concept user corresponding to the member user from multiple concept users; determine a feature attribute vector of the member concept user corresponding to the member user; combine user data and feature attribute vector corresponding to the member user to generate a user sample corresponding to the member user;

[0153] The model training module 503 is used to train the initial model using user samples corresponding to member users in each user set to obtain a normalized model;

[0154] A vector generation module 504 is used to determine a target user, input the user data of the target user into a normalized model, and obtain a characteristic attribute vector of the target user;

[0155] The information processing module 505 is used to perform information processing on the target user according to the characteristic attribute vector of the target user.

[0156] Optionally, the sample generation module 502 is specifically configured to:

[0157] Determine concept mapping information corresponding to the user set;

[0158] Determine the attribute information corresponding to the member user;

[0159] According to the concept mapping information and the attribute information corresponding to the member user, a member concept user corresponding to the member user is determined from multiple concept users.

[0160] Optionally, the sample generation module 502 is further configured to:

[0161] Determine the data source and processing method information corresponding to the user set;

[0162] According to the user ID of the member user, the original information of the member user is obtained from the data source corresponding to the user set;

[0163] The processing method information is used to process the original data of the member users to generate user data corresponding to the member users.

[0164] Optionally, the vector generation module 504 is further used for:

[0165] Determine a target user set corresponding to the target user;

[0166] Determine the data source and processing method information corresponding to the target user set;

[0167] According to the user ID of the target user, the original information of the target user is obtained from the data source corresponding to the target user set;

[0168] The processing method information is used to process the original data of the target user to generate user data corresponding to the target user.

[0169] Optionally, the vector generation module 504 is further used for:

[0170] Determine a target concept user corresponding to a target user from among multiple concept users;

[0171] Determine the vector set corresponding to the target concept user;

[0172] In response to the characteristic attribute vector of the target user not being present in the vector set, warning information for the target user is generated.

[0173] Optionally, the information processing module 505 is specifically used for:

[0174] Input the target user’s characteristic attribute vector into the user analysis model;

[0175] Determine the policy information corresponding to the target user based on the output information of the user analysis model;

[0176] According to the policy information, information processing is performed on the target user.

[0177] Optionally, the information processing module 505 is specifically used for:

[0178] Get the user information of the target user;

[0179] Generate a user profile of the target user based on the user's user information and feature attribute vector;

[0180] Perform information processing on target users based on their user portraits.

[0181] An embodiment of the present invention provides an electronic device, including:

[0182] one or more processors;

[0183] The storage device is used to store one or more programs. When the one or more programs are executed by one or more processors, the one or more processors implement the method of any of the above embodiments.

[0184] An embodiment of the present invention provides a computer program product, including a computer program. When the computer program is executed by a processor, the information processing method in the embodiment of the present invention is implemented.

[0185] Reference below Figure 6 , which shows a schematic diagram of the structure of a computer system 600 of a terminal device suitable for implementing an embodiment of the present invention. Figure 6 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0186] like Figure 6 As shown, the computer system 600 includes a central processing unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 602 or a program loaded from a storage part 608 into a random access memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, the ROM 602, and the RAM 603 are connected to each other via a bus 604. An input / output (I / O) interface 605 is also connected to the bus 604.

[0187] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed, so that a computer program read therefrom is installed into the storage section 608 as needed.

[0188] In particular, according to the embodiments disclosed in the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present invention include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-mentioned functions defined in the system of the present invention are executed.

[0189] It should be noted that the computer-readable medium shown in the present invention may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present invention, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0190] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, functions and operations of the system, method and computer program product according to various embodiments of the present invention. In this regard, each box in the flow chart or block diagram can represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flow chart, and the combination of the boxes in the block diagram or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0191] The modules involved in the embodiments of the present invention may be implemented in software or hardware. The modules described may also be arranged in a processor, for example, they may be described as: a user determination module, a sample generation module, a model training module, a vector generation module, and an information processing module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the user determination module may also be described as a "module for determining multiple user sets and multiple conceptual users".

[0192] As another aspect, the present invention further provides a computer-readable medium, which may be included in the device described in the above embodiment; or may exist independently without being assembled into the device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by a device, the device includes:

[0193] Determine multiple user sets and multiple conceptual users;

[0194] For each user set: determining a member user from the user set; determining a member concept user corresponding to the member user from a plurality of concept users; determining a feature attribute vector of the member user corresponding to the member concept user; combining user data and feature attribute vector corresponding to the member user to generate a user sample corresponding to the member user;

[0195] Using user samples corresponding to member users in each of the user sets, an initial model is trained to obtain a normalized model;

[0196] Determine a target user, input user data of the target user into the normalization model, and obtain a feature attribute vector of the target user;

[0197] Information processing is performed on the target user according to the characteristic attribute vector of the target user.

[0198] According to the technical solution of the embodiment of the present invention, the conceptual user is obtained by ignoring different user sets and dividing the users using the dimensions corresponding to the user processing. The initial model is trained using the user samples corresponding to the member users in each user set to obtain a normalized model. The user sample includes: the user data corresponding to the member user and the characteristic attribute vector of the conceptual user corresponding to the member user. The user data of the target user is input into the normalized model to obtain the characteristic attribute vector of the target user, and information processing is performed on the target user based on the characteristic attribute vector of the target user. Therefore, the solution of the embodiment of the present application can perform normalization processing on users from different user sets, and perform unified information processing on users from different user sets using the characteristic attribute vector of the user, making the user processing process simple and efficient.

[0199] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may occur depending on design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An information processing method, characterized in that: include: Determine multiple user sets and multiple conceptual users; For each user set: determining a member user from the user set; determining a member concept user corresponding to the member user from a plurality of concept users; determining a feature attribute vector of the member user corresponding to the member concept user; combining user data and feature attribute vector corresponding to the member user to generate a user sample corresponding to the member user; Using user samples corresponding to member users in each of the user sets, an initial model is trained to obtain a normalized model; Determine a target user, input user data of the target user into the normalization model, and obtain a feature attribute vector of the target user; Information processing is performed on the target user according to the characteristic attribute vector of the target user.

2. The method according to claim 1, characterized in that The step of determining, from among the plurality of concept users, a member concept user corresponding to the member user comprises: Determining concept mapping information corresponding to the user set; Determine attribute information corresponding to the member user; A member concept user corresponding to the member user is determined from the multiple concept users according to the concept mapping information and the attribute information corresponding to the member user.

3. The method according to claim 1, characterized in that Before combining the user data and the characteristic attribute vector corresponding to the member user to generate the user sample corresponding to the member user, the method further includes: Determine the data source and processing method information corresponding to the user set; According to the user identifier of the member user, obtaining the original information of the member user from the data source corresponding to the user set; The processing method information is used to process the original data of the member user to generate user data corresponding to the member user.

4. The method according to claim 1, characterized in that: Before inputting the user data of the target user into the normalization model to obtain the characteristic attribute vector of the target user, the method further includes: Determine a target user set corresponding to the target user; Determine the data source and processing method information corresponding to the target user set; Acquire original information of the target user from a data source corresponding to the target user set according to the user identifier of the target user; The original data of the target user is processed by using the processing mode information to generate user data corresponding to the target user.

5. The method according to claim 1, characterized in that After inputting the user data of the target user into the normalization model to obtain the characteristic attribute vector of the target user, the method further includes: Determining a target concept user corresponding to the target user from the plurality of concept users; Determine a vector set corresponding to the target concept user; In response to the characteristic attribute vector of the target user not being in the vector set, generating warning information for the target user.

6. The method according to claim 1, characterized in that The performing information processing on the target user according to the characteristic attribute vector of the target user includes: Inputting the characteristic attribute vector of the target user into the user analysis model; Determining the policy information corresponding to the target user according to the output information of the user analysis model; Information processing is performed on the target user according to the policy information.

7. The method according to claim 1, characterized in that The performing information processing on the target user according to the characteristic attribute vector of the target user includes: Obtaining user information of the target user; Generate a user profile of the target user according to the user information and feature attribute vector of the target user; Information processing is performed on the target user according to the user portrait of the target user.

8. An information processing device, characterized in that: include: A user determination module, used to determine multiple user sets and multiple conceptual users; The sample generation module is used for: for each user set: determining a member user from the user set; determining a member concept user corresponding to the member user from a plurality of concept users; determining a feature attribute vector corresponding to the member concept user; combining user data and feature attribute vector corresponding to the member user to generate a user sample corresponding to the member user; A model training module, used to train an initial model using user samples corresponding to member users in each of the user sets to obtain a normalized model; A vector generation module, used to determine a target user, input the user data of the target user into the normalization model, and obtain a characteristic attribute vector of the target user; The information processing module is used to perform information processing on the target user according to the characteristic attribute vector of the target user.

9. The device according to claim 8, characterized in that The sample generation module is specifically used for: Determining concept mapping information corresponding to the user set; Determine attribute information corresponding to the member user; A member concept user corresponding to the member user is determined from the multiple concept users according to the concept mapping information and the attribute information corresponding to the member user.

10. The device according to claim 8, characterized in that The sample generation module is also used for: Determine the data source and processing method information corresponding to the user set; According to the user identifier of the member user, obtaining the original information of the member user from the data source corresponding to the user set; The processing method information is used to process the original data of the member user to generate user data corresponding to the member user.

11. The device according to claim 8, characterized in that The vector generation module is also used for: Determine a target user set corresponding to the target user; Determine the data source and processing method information corresponding to the target user set; Acquire original information of the target user from a data source corresponding to the target user set according to the user identifier of the target user; The original data of the target user is processed by using the processing mode information to generate user data corresponding to the target user.

12. The device according to claim 8, characterized in that The vector generation module is also used for: Determining a target concept user corresponding to the target user from the plurality of concept users; Determine a vector set corresponding to the target concept user; In response to the characteristic attribute vector of the target user not being in the vector set, generating warning information for the target user.

13. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

14. A computer readable medium having a computer program stored thereon, characterized in that When the program is executed by a processor, the method described in any one of claims 1 to 7 is implemented.

15. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images