A method and device for processing user information

Abstract

The present invention discloses a method and device for processing user information, and relates to the field of computer technology. A specific implementation of the method includes: obtaining first feature information of a first category of users; determining the predicted value corresponding to the first category of users according to the first feature information and a value prediction model; the value prediction model is obtained based on the second feature information and historical value of a second category of users; and processing the information of the first category of users according to the historical value and the predicted value of the first category of users. This implementation is conducive to accurate processing of user information and improving user stickiness.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a method and device for processing user information. Background Art

[0002] With the development of e-commerce, more and more users are active on e-commerce platforms. How to manage users accurately and efficiently is crucial to improving user stickiness and user experience.

[0003] At present, e-commerce platforms generally process user information based on user registration information or historical behavior, for example, processing user access rights information based on user registration information, or processing recommended item information received by users based on user historical behavior. The existing user information processing methods consider relatively single dimensions, which makes the processing of user information not accurate enough and is not conducive to improving user stickiness. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a method and device for processing user information, which can predict the predicted value of a first type of user based on the characteristic information and historical value of a second type of user who is different from the first type of user, and process the information of the first type of user in combination with the historical value and predicted value of the first type of user, thereby realizing more accurate processing of the information of the first type of user by combining different types of user values, which is conducive to improving user experience, improving user stickiness, and guiding users to convert types according to the values ​​corresponding to different types of users, thereby helping to further improve user stickiness.

[0005] To achieve the above objective, according to one aspect of an embodiment of the present invention, a method for processing user information is provided.

[0006] A method for processing user information according to an embodiment of the present invention includes:

[0007] Obtaining first characteristic information of a first category of users;

[0008] Determine the predicted value corresponding to the first category of users based on the first feature information and a value prediction model; the value prediction model is obtained based on the second feature information and historical value of the second category of users;

[0009] The information of the first category of users is processed according to the historical value of the first category of users and the predicted value.

[0010] Optionally,

[0011] In a preset first time period, the difference between the historical value of the second category of users and the historical value of the first category of users is less than a preset first threshold;

[0012] The value prediction model is obtained based on the second characteristic information of the second type of users in the first time period and the historical value.

[0013] Optionally,

[0014] The first characteristic information includes any one or more of the following: attribute information, historical behavior information, recommended item information, and environment information.

[0015] Optionally,

[0016] When the first feature information includes historical behavior information, within a preset second time period, the similarity between the historical behavior information of the second category of users and the historical behavior information of the first category of users is greater than a preset second threshold;

[0017] The value prediction model is obtained based on the second characteristic information of the second type of users in the second time period and the historical value.

[0018] Optionally,

[0019] The similarity is obtained based on the item information corresponding to the historical behavior information of the second category of users and the historical behavior information of the first category of users.

[0020] Optionally,

[0021] The value prediction model is a lightgbm model or a convolutional neural network model.

[0022] Optionally,

[0023] The processing of the information of the first category of users includes:

[0024] When the difference between the historical value and the predicted value of the first category of users is greater than a third threshold, the virtual resource information of the first category of users is processed according to the difference.

[0025] Optionally,

[0026] The processing of the information of the first category of users includes:

[0027] When the difference between the historical value of the first category of users and the predicted value is greater than a fourth threshold, recommendation information corresponding to the first category of users is generated and displayed according to the first feature information of the first category of users and the difference.

[0028] To achieve the above objective, according to another aspect of an embodiment of the present invention, a device for processing user information is provided.

[0029] A device for processing user information according to an embodiment of the present invention comprises: a feature acquisition module, a prediction module and a processing module; wherein:

[0030] The feature acquisition module is used to acquire first feature information of the first type of users;

[0031] The prediction module is used to determine the predicted value corresponding to the first type of user based on the first characteristic information and a value prediction model; the value prediction model is obtained based on the second characteristic information and historical value of the second type of user;

[0032] The processing module is used to process the information of the first category of users according to the historical value and the predicted value of the first category of users.

[0033] To achieve the above objective, according to another aspect of an embodiment of the present invention, an electronic device for processing user information is provided.

[0034] An electronic device for processing user information according to an embodiment of the present invention comprises: one or more processors; a storage device for storing one or more programs, and when the one or more programs are executed by the one or more processors, the one or more processors implement a method for processing user information according to an embodiment of the present invention.

[0035] To achieve the above objective, according to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided.

[0036] A computer-readable storage medium according to an embodiment of the present invention stores a computer program, and when the program is executed by a processor, a method for processing user information according to an embodiment of the present invention is implemented.

[0037] An embodiment of the above invention has the following advantages or beneficial effects: the predicted value of the first category of users is determined based on the first characteristic information of the first category of users and the value prediction model, the value prediction model is obtained based on the second characteristic information and historical value of the second category of users, and then the first category of users is managed according to the real value and predicted value of the first category of users. The predicted value of the first category of users can be predicted based on the characteristic information and historical value of the second category of users who are different from the first category of users, and the information of the first category of users can be processed in combination with the historical value and predicted value of the first category of users, thereby realizing a more accurate processing of the information of the first category of users in combination with the values ​​of different types of users, which is conducive to improving user experience and user stickiness, and is conducive to guiding users to convert types according to the values ​​corresponding to different types of users, thereby further improving user stickiness.

[0038] 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

[0039] The accompanying drawings are used to better understand the present invention and do not constitute an improper limitation of the present invention.

[0040] Figure 1 is a schematic diagram of main steps of a method for processing user information according to an embodiment of the present invention;

[0041] Figure 2 is a schematic diagram of main steps of another method for processing user information according to an embodiment of the present invention;

[0042] Figure 3 is a schematic diagram of main steps of another method for processing user information according to an embodiment of the present invention;

[0043] Figure 4 is a schematic diagram of main steps of another method for processing user information according to an embodiment of the present invention;

[0044] Figure 5 is a schematic diagram of main modules of a device for processing user information according to an embodiment of the present invention;

[0045] Figure 6 is an exemplary system architecture diagram to which embodiments of the present invention may be applied;

[0046] Figure 7 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

[0047] 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.

[0048] It should be pointed out that the embodiments of the present invention and the technical features therein may be combined with each other without conflict.

[0049] Figure 1 4 is a schematic diagram of main steps of a method for processing user information according to an embodiment of the present invention.

[0050] like Figure 1 As shown, the method for processing user information in an embodiment of the present invention mainly includes the following steps:

[0051] Step S101: Obtain first characteristic information of a first type of user.

[0052] In an embodiment of the present invention, the first category of users and the second category of users are users of different types, for example, the first category of users are member users and the second category of users are non-member users, or the first category of users are non-member users and the second category of users are member users.

[0053] The first characteristic information includes any one or more of the following: attribute information, historical behavior information, recommended item information, and environment information.

[0054] The user's attribute information includes the user's gender, the user's age, the user's registration time, the city to which the user belongs, and the number of virtual resources of the user. Among them, the user's virtual resources are resources that can be used to exchange for various benefits such as physical items and coupons. For example, virtual resources can be account points or account virtual currency. The user's attribute information can also include the user's activity on the e-commerce platform. The user's activity can be determined based on the frequency of the user's generation of historical behavior information. For example, the user's activity can be reflected in the following aspects: the number of days the user places an order within a preset time period, the number of days the user places an order within a second time period not earlier than the current time (such as within the last 60 days), the number of days between the user's earliest order time and the current time, the number of days between the user's registration time and the current time, the user's cumulative browsing days, the frequency of users browsing the details pages of items of different categories, the number of times the user adds items to the shopping cart, and the number of comments on the items by the user, etc.

[0055] The user's historical behavior information includes the user's historical clicks, browsing, following, adding to carts, and placing orders. Recommended item information is the recommended item information that the user has received. The recommended item information is generally recommended by the e-commerce platform based on the user's interests or based on popular trends, such as the recommended item information is the same item used by celebrities. The user's environmental information is the weather in the user's area, the user's longitude and latitude, the user's network environment, etc. It is understandable that the user's environmental information is generally collected when the user generates historical behavior information, that is, the user's environmental information is generally collected when the user clicks, browses, follows, adds to carts, and places orders, including the weather in the user's area, the user's longitude and latitude, and the user's network environment.

[0056] The user's ordering behavior may include multiple aspects, such as the user's order volume within a preset first time period (such as within one year) and the total value of these orders, the user's total order volume within a second time period no earlier than the current time (such as within the last 90 days) and the total value of these orders, the item categories corresponding to the user's orders in the first time period and the user's category preference corresponding to the user portrait, the total number of items ordered by the user in the first time period, the number of orders with a value greater than a threshold, the order with the largest value among multiple orders, the total number of orders in which the user uses discount methods in the first time period, etc.

[0057] It can be understood that the second characteristic information of the second category of users also includes: one or more of attribute information, historical behavior information, recommended item information and environment information.

[0058] Step S102: Determine the predicted value corresponding to the first category of users based on the first feature information and a value prediction model; the value prediction model is obtained based on the second feature information and historical value of the second category of users.

[0059] When constructing a value prediction model, a second type of user can be selected whose historical value generated within a preset first time period and the difference between the historical value of the first type of user is less than a preset first threshold, and a value prediction model can be constructed based on the second feature information of the selected second type of user and its historical value.

[0060] The historical value of the first category of users or the second category of users may be the corresponding gmv (Gross Merchandise Volume) of the user. For example, when the first time period is one year, the historical value of the first category of users in the first time period is the gmv of the first category of users in one year, and the gmv is the total amount corresponding to each order placed by the user in this year.

[0061] When building a value prediction model, you can first filter out the data of abnormal users, who are users with abnormal purchasing behavior (such as GMV exceeding 1 million in a year, total number of orders exceeding 100,000 in a year, etc.), users with abnormal orders, such as users whose order behavior does not match their attribute information (such as a member with a higher level who places less than 2 orders in a year), and high-risk users (such as purchasing agents filtered by risk control, etc.). In addition, user data can also be cleaned, such as cleaning order data where the number of purchases of the same item exceeds a threshold.

[0062] Then, a value prediction model can be constructed based on the cleaned data to improve the accuracy of the value prediction model. Taking the first time period from January 1, 2017 to December 31, 2017 as an example, when selecting the sample data for constructing the value prediction model, first, according to the historical value of the second type of users from January 1, 2017 to December 31, 2017, the data representing the second characteristic information and historical value of the second type of users is binned. For example, according to the difference between the maximum historical value n1 and the minimum historical value n2 of the second type of users, the data of the second type of users is divided into 20 bins. Then, the first bin of data is the data with a historical value of n1 to (n2 - n1) / 20, the second bin of data is the data with a historical value of (n2 - n1) / 20 to (n2 - n1) / 10, and so on. The 20th bin of data is the data with a historical value of 19(n2 - n1) / 20 to n2.

[0063] Then, according to the historical value of the first type of users, the data of the second type of users used to construct the value prediction model is selected. For example, when the historical value of the first type of users from January 1, 2017 to December 31, 2017 is m, where n1 < m < (n2 - n1) / 20, then m corresponds to the historical value of the first bin of data of the second type of users. That is to say, the first bin of data of the second type of users can be selected as the sample data for constructing the value prediction model.

[0064] Taking the first type of users as member users and the second type of users as non - member users as an example, the sample data for constructing the value prediction model is the data of non - member users' historical value in the first time period and the data of member users' historical value in the first time period that is less than the first threshold. This means that in the first time period, the purchasing power of non - member users is at the same level as that of member users. In other words, the ability of non - member users to generate value is at the same level as that of member users in the first time period. This makes the prediction of the predicted value of member users based on the value prediction model based on the same purchasing power as that of member users, thereby improving the prediction accuracy of the predicted value of member users.

[0065] In addition, when the first characteristic information of the first type of users includes historical behavior information, the sample data for constructing the value prediction model can be the data whose similarity of historical behavior information with that of the first type of users in the second time period is greater than the preset second threshold. This data represents the second characteristic information and historical value of the second type of users. That is to say, the value prediction model is obtained based on the second characteristic information and historical value of the second type of users in the second time period.

[0066] The second time period may be the same as the first time period or different from the first time period. The similarity between the historical behavior information of the first category of users and the historical behavior information of the second category of users may be obtained based on the item information corresponding to the historical behavior information of the second category of users and the historical behavior information of the first category of users, for example, the item information corresponding to the historical behavior information of the first category of users is item A and item B, and the item information corresponding to the historical behavior information of the second category of users is item B and item C. Then, the similarity between the historical behavior information of the first category of users and the historical behavior information of the second category of users may be calculated based on the item names corresponding to item A, item B, and item C, respectively.

[0067] Then, the data of the second category of users whose similarity with the historical behavior information of the first category of users is greater than a preset second threshold value is selected to construct a value prediction model. The data of the second category of users selected (sample data for constructing the value prediction model) has the same or similar item preferences as the first category of users in the second time period. This makes it possible to predict the predicted value of the first category of users according to the value prediction model based on the item preferences similar to those of the second category of users, thereby improving the prediction accuracy of the predicted value of member users.

[0068] Of course, when determining the sample data for building the value prediction model, the historical value of the second category of users and the similarity between the historical behavior information of the second category of users and the historical behavior information of the first category of users can be combined at the same time. That is, the data of the second category of users whose difference between the historical value in the first time period and the historical value of the first category of users is less than the first threshold and whose historical behavior information in the first time period has a similarity with the historical behavior information of the first category of users greater than the second threshold can be selected as sample data, and the data represents the second characteristic information and historical value of the second category of users. Thus, if Figure 2 As shown, the method for processing user information provided by the embodiment of the present invention may include the following steps S201 to S205:

[0069] Step S201: Determine sample data of the second category of users, wherein the sample data represents second characteristic information of the second category of users and historical value of the second category of users within a first time period, wherein the difference between the historical value represented by the sample data and the historical value of the first category of users is less than a first threshold, and the similarity between the historical behavior information in the second characteristic information represented by the sample data and the historical behavior information of the first category of users is greater than a second threshold.

[0070] Step S202: constructing a value prediction model based on the second characteristic information and historical value of the second type of users represented by the sample data.

[0071] Step S203: Obtain first characteristic information of the first category of users.

[0072] Step S204: Determine the predicted value corresponding to the first type of users based on the first feature information and the value prediction model.

[0073] Step S205: Processing the information of the first category of users according to the historical value and the predicted value of the first category of users.

[0074] When constructing a value prediction model, it can be constructed based on the lightgbm model or the convolutional neural network model. During the model training process, the parameters are continuously adjusted to improve the model training efficiency and model accuracy. For example, the appropriate maxBin is adjusted to avoid slowing down the model training speed due to the pursuit of accuracy by using too large a maxBin, or reducing the accuracy of the model by using too small a maxBin to prevent overfitting; for example, the appropriate numLeaves is adjusted to avoid overfitting due to using too large a numLeaves, or too low an accuracy due to using too small a numLeaves. In short, when adjusting the model training parameters, it is based on higher model training efficiency and accuracy and the balance between the two. For example, for better accuracy, a larger maxBin can be used, a smaller learningRate and a larger numIterations can be used, a larger numLeaves can be used, and the training data set can also be increased. In order to avoid overfitting, a smaller maxBin, a smaller numLeaves, minSumHessianInLeaf can be used, and the training data set can also be increased.

[0075] After constructing the value prediction model, the accuracy of the value prediction model can be determined based on the mean square error between the historical value of the second category of users and the predicted value of the second category of users predicted by the value prediction model, or based on the actual gear corresponding to the data of the second category of users and the predicted gear of the data of the second category of users predicted by the value prediction model. When the accuracy of the value prediction model meets the requirements, the training of the value prediction model is stopped, and the value prediction model is used to predict the predicted value of the first category of users.

[0076] Step S103: Processing the information of the first category of users according to the historical value and the predicted value of the first category of users.

[0077] Taking the first category of users as member users and the second category of users as non-member users as an example, the predicted value of the first category of users represents the historical value corresponding to the non-member when the non-member has the second characteristic information that is the same as the first characteristic information. In other words, the predicted value of the first category of users represents the value corresponding to the first characteristic information if the member user has not activated the membership. Taking the user's value as gmv as an example, the difference between the historical value and the predicted value of the first category of users is the difference between the corresponding gmv when the member user and the non-member user have the same characteristic information. The difference here is the absolute value of the difference between the historical value and the predicted value of the first category of users. Generally speaking, when having the same characteristic information, the gmv corresponding to the member user is smaller than the gmv corresponding to the non-member. That is to say, for the user, activating a membership will make him spend less money under the same purchase conditions (buying the same items).

[0078] In one embodiment of the present invention, when the difference between the historical value and the predicted value of the first category of users is greater than a third threshold, the virtual resource information of the first category of users is processed according to the difference.

[0079] Still taking the example that the first type of users are member users and the second type of users are non-members, when the difference between the historical value of the first type of users and their predicted value is greater than the third threshold, it means that the membership value of the first type of users is higher, that is, opening a membership saves the user a higher transaction amount, making the user spend less. In order to encourage users to maintain the type of first type of users, that is, to encourage users to maintain the membership type and improve user stickiness, the virtual resource information of the first type of users can be processed in the form of increasing virtual resources, that is, adding virtual resources to the first type of users, and the number of virtual resources can be determined according to the difference between the historical value of the first type of users and their predicted value. For example, the larger the difference, the more virtual resources there are.

[0080] Therefore, if Figure 3 As shown, the method for processing user information provided by the embodiment of the present invention may include the following steps:

[0081] Step S301: Obtain first characteristic information of a first type of user.

[0082] Step S302: Determine the predicted value corresponding to the first category of users based on the first characteristic information and a value prediction model; the value prediction model is obtained based on the second characteristic information and historical value of the second category of users.

[0083] Step S303: When the difference between the historical value and the predicted value of the first category of users is greater than a third threshold, the virtual resource information of the first category of users is processed according to the difference.

[0084] It can be understood that when the first category of users are non-member users and the second category of users are member users, the predicted value of the first category of users represents the value corresponding to the first characteristic information when the non-member users activate membership. Taking the user's value as gmv as an example, the difference between the historical value and the predicted value of the first category of users is the difference between the corresponding gmv when the non-member users and the member users have the same characteristic information. The difference here is the absolute value of the difference between the historical value and the predicted value of the first category of users.

[0085] In order to encourage non-member users to become members and improve user stickiness, when the difference between the historical value and the predicted value of the first category of users is greater than a fourth threshold, recommendation information corresponding to the first category of users can be generated and displayed based on the first feature information of the first category of users and the difference.

[0086] According to the above embodiments, Figure 4 As shown, the user information processing method provided by the embodiment of the present invention may include the following steps:

[0087] Step S401: Obtain first characteristic information of a first type of user.

[0088] Step S402: Determine the predicted value corresponding to the first category of users based on the first characteristic information and a value prediction model; the value prediction model is obtained based on the second characteristic information and historical value of the second category of users.

[0089] Step S403: When the difference between the historical value and the predicted value of the first category of users is greater than a fourth threshold, recommendation information corresponding to the first category of users is generated and displayed according to the first feature information of the first category of users and the difference.

[0090] The generated recommendation information may be as follows: "If you become a member, you can save Y1 yuan by purchasing K item" or "If you become a member, you can save at least Y2 yuan within a year", where K item can be an item that the user has purchased, and Y1 and Y2 are determined based on the difference between the historical value and the predicted value of the first category of users. When the user uses a device that processes user information, the recommendation information can be displayed on the homepage of the device that processes user information (such as a terminal used by the user) or the user's personal homepage, or when the user views the item information, the recommendation information can be displayed in the form of a pop-up window. This encourages users to convert types based on the recommendation information, such as converting from a non-member type to a member type, thereby improving user stickiness.

[0091] It can be seen from the method for processing user information according to the embodiment of the present invention that the predicted value of the first category of users is determined based on the first characteristic information of the first category of users and the value prediction model, the value prediction model is obtained based on the second characteristic information and historical value of the second category of users, and then the first category of users is managed according to the real value and predicted value of the first category of users. As a result, the predicted value of the first category of users can be predicted based on the characteristic information and historical value of the second category of users who are different from the first category of users, and the information of the first category of users can be processed in combination with the historical value and predicted value of the first category of users, thereby realizing a more accurate processing of the information of the first category of users in combination with the values ​​of different types of users, which is conducive to improving user experience, improving user stickiness, and guiding users to perform type conversion according to the values ​​corresponding to different types of users, thereby further improving user stickiness.

[0092] Figure 5 4 is a schematic diagram of main modules of an apparatus for processing user information according to an embodiment of the present invention.

[0093] like Figure 5 As shown, the device 500 for processing user information according to the embodiment of the present invention includes: a feature acquisition module 501, a prediction module 502 and a processing module 503; wherein,

[0094] The feature acquisition module 501 is used to acquire first feature information of a first type of user;

[0095] The prediction module 502 is used to determine the predicted value corresponding to the first type of user based on the first characteristic information and the value prediction model; the value prediction model is obtained based on the second characteristic information and historical value of the second type of user;

[0096] The processing module 503 is used to process the information of the first category of users according to the historical value and the predicted value of the first category of users.

[0097] In one embodiment of the present invention, within a preset first time period, the difference between the historical value of the second category of users and the historical value of the first category of users is less than a preset first threshold; the value prediction model is obtained based on the second feature information and the historical value of the second category of users within the first time period.

[0098] In one embodiment of the present invention, the first feature information includes any one or more of the following: attribute information, historical behavior information, recommended item information, and environment information.

[0099] In one embodiment of the present invention, when the first characteristic information includes historical behavior information, within a preset second time period, the similarity between the historical behavior information of the second category of users and the historical behavior information of the first category of users is greater than a preset second threshold; the value prediction model is based on the second characteristic information of the second category of users within the second time period and the historical value.

[0100] In one embodiment of the present invention, the similarity is obtained based on the item information corresponding to the historical behavior information of the second category of users and the historical behavior information of the first category of users.

[0101] In one embodiment of the present invention, the value prediction model is a lightgbm model or a convolutional neural network model.

[0102] In one embodiment of the present invention, the processing module 503 is used to process the virtual resource information of the first category of users according to the difference between the historical value and the predicted value of the first category of users when the difference between the historical value and the predicted value is greater than a third threshold.

[0103] In one embodiment of the present invention, the processing module 503 is used to generate and display recommendation information corresponding to the first category of users based on the first feature information of the first category of users and the difference when the difference between the historical value of the first category of users and the predicted value is greater than a fourth threshold.

[0104] It can be seen from the device for processing user information according to the embodiment of the present invention that the predicted value of the first category of users is determined based on the first characteristic information of the first category of users and the value prediction model, the value prediction model is obtained based on the second characteristic information and historical value of the second category of users, and then the first category of users is managed according to the real value and predicted value of the first category of users. As a result, the predicted value of the first category of users can be predicted based on the characteristic information and historical value of the second category of users who are different from the first category of users, and the information of the first category of users can be processed in combination with the historical value and predicted value of the first category of users, thereby realizing a more accurate processing of the information of the first category of users in combination with the values ​​of different types of users, which is conducive to improving user experience, improving user stickiness, and guiding users to convert types according to the values ​​corresponding to different types of users, thereby further improving user stickiness.

[0105] Figure 6 An exemplary system architecture 600 is shown to which the method for processing user information or the apparatus for processing user information according to the embodiments of the present invention can be applied.

[0106] like Figure 6As shown, system architecture 600 may include terminal devices 601, 602, 603, network 604 and server 605. Network 604 is used to provide a medium for communication links between terminal devices 601, 602, 603 and server 605. Network 604 may include various connection types, such as wired, wireless communication links or optical fiber cables, etc.

[0107] The user can use the terminal devices 601, 602, 603 to interact with the server 605 through the network 604 to receive or send messages, etc. Various communication client applications can be installed on the terminal devices 601, 602, 603, such as shopping applications, web browser applications, search applications, instant messaging tools, email clients, social platform software, etc.

[0108] The terminal devices 601 , 602 , and 603 may be various electronic devices having a display screen and supporting web browsing, including but not limited to smart phones, tablet computers, laptop computers, and desktop computers, etc.

[0109] The server 605 may be a server that provides various services, such as a backend management server that provides support for shopping websites browsed by users using the terminal devices 601, 602, and 603. The backend management server may analyze and process the received data such as product information query requests, and feed back the processing results (such as target push information and product information) to the terminal device.

[0110] It should be noted that the method for processing user information provided in the embodiment of the present invention is generally executed by the server 605 , and accordingly, the device for processing user information is generally set in the server 605 .

[0111] It should be understood that Figure 6 The number of terminal devices, networks and servers in the embodiment is only for illustration. Any number of terminal devices, networks and servers may be provided according to implementation requirements.

[0112] Reference below Figure 7 , which shows a schematic diagram of the structure of a computer system 700 of a terminal device suitable for implementing an embodiment of the present invention. Figure 7 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.

[0113] like Figure 7As shown, the computer system 700 includes a central processing unit (CPU) 701, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 702 or a program loaded from a storage part 708 into a random access memory (RAM) 703. In the RAM 703, various programs and data required for the operation of the system 700 are also stored. The CPU 701, the ROM 702, and the RAM 703 are connected to each other via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0114] The following components are connected to the I / O interface 705: an input section 706 including a keyboard, a mouse, etc.; an output section 707 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 708 including a hard disk, etc.; and a communication section 709 including a network interface card such as a LAN card, a modem, etc. The communication section 709 performs communication processing via a network such as the Internet. A drive 710 is also connected to the I / O interface 705 as needed. A removable medium 711, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 710 as needed, so that a computer program read therefrom is installed into the storage section 708 as needed.

[0115] 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 709, and / or installed from the removable medium 711. When the computer program is executed by the central processing unit (CPU) 701, the above-mentioned functions defined in the system of the present invention are executed.

[0116] 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.

[0117] 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 the 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.

[0118] The modules involved in the embodiments of the present invention may be implemented by software or hardware. The modules described may also be set in a processor. For example, they may be described as: a processor includes a feature acquisition module, a prediction module, and a processing module. The names of these modules do not, in some cases, constitute limitations on the modules themselves. For example, the feature acquisition module may also be described as a "module for acquiring first feature information of a first type of user."

[0119] As another aspect, the present invention also provides a computer-readable medium, which may be included in the device described in the above embodiment; or it 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: obtaining first feature information of a first category of users; determining the predicted value corresponding to the first category of users based on the first feature information and a value prediction model; the value prediction model is obtained based on the second feature information and historical value of the second category of users; and processing the information of the first category of users based on the historical value of the first category of users and the predicted value.

[0120] According to the technical solution of the embodiment of the present invention, the predicted value of the first category of users is determined based on the first characteristic information of the first category of users and the value prediction model, the value prediction model is obtained based on the second characteristic information and historical value of the second category of users, and then the first category of users is managed according to the real value and predicted value of the first category of users. As a result, the predicted value of the first category of users can be predicted based on the characteristic information and historical value of the second category of users who are different from the first category of users, and the information of the first category of users can be processed in combination with the historical value and predicted value of the first category of users, thereby realizing a more accurate processing of the information of the first category of users in combination with the values ​​of different types of users, which is conducive to improving user experience, improving user stickiness, and guiding users to convert types according to the values ​​corresponding to different types of users, thereby further improving user stickiness.

[0121] 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. A method for processing user information, characterized in that: include: Obtaining first characteristic information of a first category of users; Determining the predicted value corresponding to the first type of user according to the first feature information and the value prediction model; The value prediction model is obtained based on the second characteristic information and historical value of the second category of users; the first category of users and the second category of users are users of different types; Processing information of the first category of users according to the historical value of the first category of users and the predicted value; The processing of the information of the first type of users includes: when the difference between the historical value of the first type of users and the predicted value is greater than a third threshold, processing the virtual resource information of the first type of users in the form of adding virtual resources according to the difference, so as to urge the users to remain the type of the first type of users; The first feature information includes historical behavior information. When the first feature information includes historical behavior information, within a preset second time period, the similarity between the historical behavior information of the second category of users and the historical behavior information of the first category of users is greater than a preset second threshold.

2. The method according to claim 1, characterized in that: In a preset first time period, the difference between the historical value of the second category of users and the historical value of the first category of users is less than a preset first threshold; The value prediction model is obtained based on the second characteristic information of the second type of users in the first time period and the historical value.

3. The method according to claim 1, characterized in that The first characteristic information also includes any one or more of the following: attribute information, recommended item information, and environment information.

4. The method according to claim 1, characterized in that: When the first feature information includes historical behavior information, The value prediction model is obtained based on the second characteristic information of the second type of users in the second time period and the historical value.

5. The method according to claim 4, characterized in that The similarity is obtained based on the item information corresponding to the historical behavior information of the second category of users and the historical behavior information of the first category of users.

6. The method according to claim 1, characterized in that The value prediction model is a lightgbm model or a convolutional neural network model.

7. A device for processing user information, characterized in that: The device applies the method described in any one of claims 1 to 6, including: a feature acquisition module, a prediction module and a processing module; wherein: The feature acquisition module is used to acquire first feature information of the first type of users; The prediction module is used to determine the predicted value corresponding to the first category of users according to the first feature information and a value prediction model; the value prediction model is obtained based on the second feature information and historical value of the second category of users; the first category of users and the second category of users are users of different types; The processing module is used to process the information of the first type of users in the form of adding virtual resources according to the historical value of the first type of users and the predicted value, so as to encourage the users to remain the type of the first type of users; The processing module is used to process the virtual resource information of the first category of users according to the difference between the historical value and the predicted value when the difference between the first category of users is greater than a third threshold.

8. An electronic device for processing user information, 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 6.

9. A computer readable medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images