Pushing method and device based on user characteristics, computer equipment and storage medium

Abstract

The invention discloses a pushing method and device based on user features, computer equipment and a storage medium. The method comprises the steps that user information of a user is acquired, and the user features are extracted from the user information; establishing a user portrait according to the user features, and adding the user portrait to a preset user portrait database; determining an information type of to-be-pushed information, and obtaining a target user corresponding to the information type from the user portrait database; and pushing the information to be pushed to the target user. According to the invention, personalized pushing can be carried out according to the user features.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and particularly to a push method, device, computer device and storage medium based on user characteristics. Background Art

[0002] In today's information age, message push technology is widely used in various applications and services, such as social networks, news applications, e-commerce, etc. However, there is a major technical problem with existing message push methods, that is, they cannot perform personalized push according to user characteristics. Generally, these methods can only perform general push, that is, send the same message to all users, and cannot perform adaptive push according to the characteristics of the push content and the personal and behavioral characteristics of users.

[0003] Taking financial information as an example, existing push methods can push the same financial news or fund advertisements to all users, but cannot perform personalized push according to factors such as user personal interests and behavioral habits. This not only reduces the efficiency and effect of the push, but also affects the user experience, and at the same time cannot guarantee the conversion rate.

[0004] Therefore, how to provide a message push method for personalized push according to user characteristics has become a technical problem that needs to be solved urgently by those skilled in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a push method, device, computer device and storage medium based on user characteristics, which can perform personalized push according to user characteristics.

[0006] According to one aspect of the present invention, a push method based on user characteristics is provided, and the method includes the following steps:

[0007] Obtain user information of a user and extract user characteristics from the user information;

[0008] Build a user portrait according to the user characteristics and add the user portrait to a preset user portrait database;

[0009] Determine the information type of the information to be pushed, and obtain the target users corresponding to the information type from the user portrait database;

[0010] Push the information to be pushed to the target users.

[0011] Optionally, the obtaining user information of a user and extracting user characteristics from the user information includes:

[0012] Determine user personal information and user behavior information from the user information;

[0013] Input the user's personal information and the user's behavior information into a feature recognition model for feature extraction to obtain the user's personal features and the user's behavior features;

[0014] Generate user tags corresponding to each of the user's personal features and the user's behavior features.

[0015] Optionally, establishing a user portrait based on the user features includes:

[0016] Encode the user's personal features and the user's behavior features to obtain an encoded feature vector;

[0017] Encode the user tags to obtain an encoded tag vector;

[0018] Generate a user portrait based on the encoded feature vector and the encoded tag vector.

[0019] Optionally, adding the user portrait to a preset user portrait database includes:

[0020] When the user's personal information changes within a preset update period, obtain the updated personal information after the change;

[0021] Obtain the newly added user behavior information within the preset update period;

[0022] Update the user portrait in the user portrait database according to the updated personal information and the newly added user behavior information to obtain an updated user portrait;

[0023] Replace the updated user portrait with the user portrait of the user in the user portrait database.

[0024] Optionally, determining the information type of the information to be pushed and obtaining the target users corresponding to the information type from the user portrait database includes:

[0025] Determine the information type of the information to be pushed;

[0026] When the information type is the first information type, use all users in the user portrait database as target users;

[0027] When the information type is the second information type, input the information to be pushed into a text analysis model to obtain content tags corresponding to the information to be pushed, and determine the target users matching the content tags from the user portrait database.

[0028] Optionally, determining the target users according to the content tags includes:

[0029] Obtain the content scores of each content tag of the information to be pushed; wherein, the content score is the degree of content association between the content tag and the content of the information to be pushed.

[0030] Calculate the similarity between the content tag and the encoded feature vector and the encoded tag vector of each user portrait.

[0031] Calculate the matching score between the information to be pushed and the user portrait according to the content score of each content tag and the similarity.

[0032] Take the users corresponding to the user portraits with matching scores greater than the preset threshold as the target users.

[0033] Optionally, pushing the information to be pushed to the target user includes:

[0034] When the information type of the information to be pushed is the first information type, push the information to be pushed to the target user in real time.

[0035] When the information type of the information to be pushed is the second information type, obtain the optimal browsing time range of the target user from the user behavior information of the target user, and push the information to be pushed to the target user within the optimal browsing time range.

[0036] To achieve the above object, the present invention also provides a device for a push method based on user characteristics, and the device specifically includes the following components:

[0037] An acquisition module, configured to acquire user information of a user and extract user characteristics from the user information.

[0038] A portrait module, configured to establish a user portrait according to the user characteristics and add the user portrait to a preset user portrait database.

[0039] A determination module, configured to determine the information type of the information to be pushed and obtain the target user corresponding to the information type from the user portrait database.

[0040] A push module, configured to push the information to be pushed to the target user.

[0041] To achieve the above object, the present invention also provides a computer device, which specifically includes: a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the computer program, the steps of the push method based on user characteristics introduced above are implemented.

[0042] To achieve the above object, the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-described push method based on user characteristics are implemented.

[0043] The push method, device, computer device and storage medium based on user characteristics provided by the present invention analyze the user characteristics in user information, extract corresponding user characteristics from both personal information and behavioral information to establish a user portrait, so as to construct a user portrait database and realize the unified management of user portraits, making the understanding of user characteristics more comprehensive and accurate. At the same time, according to the information type of the information to be pushed, the target users to be pushed are determined from the user portrait database, and the information to be pushed is specifically pushed to the target users. This push method can improve the accuracy and efficiency of information push, realize the personalization and high efficiency of information push. This push method can better meet the needs of users, improve the user experience, enhance user loyalty, and at the same time can also improve the efficiency and effect of information push, bringing more commercial value to related applications and services. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] By reading the following detailed description of the preferred embodiments, various other advantages and benefits will become clear to those of ordinary skill in the art. The drawings are only for the purpose of showing the preferred embodiments and are not considered to be a limitation of the present invention. Moreover, throughout the drawings, the same reference numerals are used to represent the same components. In the drawings:

[0045] Figure 1 An optional flowchart of the push method based on user characteristics provided for Example 1;

[0046] Figure 2 An optional structural diagram of the push device based on user characteristics provided for Example 2;

[0047] Figure 3 An optional hardware architecture diagram of the computer device provided for Example 3. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] In order to make the object, technical solution and advantages of the present invention more clear, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0049] Example 1

[0050] The embodiment of the present invention provides a push method based on user characteristics, asFigure 1 As shown in the figure, the method specifically includes the following steps:

[0051] Step S101: Obtain the user information of the user and extract user characteristics from the user information.

[0052] Among them, when the user performs personalized behaviors such as content consumption, content production, viewing targets, product trading, and position viewing in the financial community, the community management party needs to push various types of information to the user to improve the user's browsing interest and trading interest. Therefore, it is necessary to conduct targeted analysis based on the user's characteristics and behaviors and perform personalized push of messages in order to increase the user's interest value in the information and improve the trading willingness.

[0053] Therefore, when analyzing the user characteristics of the user, it is possible to start from two aspects: user personal information and user behavior information, and create a user portrait for each user, so that the community management party can push information and trading products with higher adaptability to the user according to the user portrait.

[0054] Step S102: Establish a user portrait based on the user characteristics and add the user portrait to a preset user portrait database.

[0055] Among them, the user portrait is a unique user portrait generated in all aspects based on the user personal characteristics and user behavior characteristics extracted from the user personal information and user behavior information, as well as the user tags corresponding to the user personal characteristics and user behavior characteristics, and the user portrait is updated in a timely manner according to the time period to achieve personalized observation of each community user. To increase the user's interest value and purchase willingness for the community products.

[0056] Step S103: Determine the information type of the information to be pushed and obtain the target users corresponding to the information type from the user portrait database.

[0057] Among them, first classify the information to be pushed to determine the category of the information to be pushed, such as posts, news, announcements, links, etc. If it is a general information to be pushed such as news and announcements, the information to be pushed will be pushed to each user in a timely manner. If it is a message of types such as posts and links, the content of this type of information to be pushed will be analyzed again, and it will be pushed to the appropriate users according to the content tags to achieve personalized push and improve the click-through rate and conversion rate of the pushed messages.

[0058] Step S104: Push the information to be pushed to the target users.

[0059] Among them, the push messages can be classified and pushed according to the information categories of the messages, and the user click-through rate can be maximized by two push methods: real-time push and scheduled push. In addition, it is necessary to analyze the push data within a preset period to adjust the push content and push strategy and optimize the push plan.

[0060] Further, the obtaining of the user information of the user and extracting user characteristics from the user information includes:

[0061] Step A1: Determine the user's personal information and user behavior information from the user information.

[0062] Among them, the personal information entered by the user when registering in this financial community is obtained, such as age, gender, occupation, region, license, language target, etc. In addition, the behavior information generated by the user when using the financial community is also collected, such as the types of posts browsed, browsing duration, favorites, transaction data, browsing path, etc. of behavior information, in order to generate a user portrait of the user.

[0063] Step A2: Input the user's personal information and the user's behavior information into a feature recognition model for feature extraction to obtain user personal characteristics and user behavior characteristics.

[0064] Among them, after obtaining the user's personal information and user behavior information, the acquired data is preprocessed, including information cleaning and information sorting, removing irrelevant or incorrect information, processing missing values, and standardizing the information. A feature recognition model is used to extract meaningful features from the user information. The purpose of feature extraction is to transform the original data into feature vectors that can reflect the user's characteristics.

[0065] Step A3: Generate user tags corresponding to each of the user's personal characteristics and the user's behavior characteristics.

[0066] Among them, before generating the tags, a user tag system is first defined, including two clear tag systems: personal characteristic tags (such as age, gender, region, etc.) and behavior characteristic tags (such as purchase behavior, browsing behavior, social behavior, etc.). According to the user's personal characteristics, personal characteristic tags are assigned to the user, such as personal characteristic tags like "youth", "middle-aged", "programmer", etc.; according to the user's behavior characteristics, behavior characteristic tags are assigned to the user, such as behavior characteristic tags like "high-frequency purchaser", "price-sensitive user" or "conservative investor", etc. The user's personal characteristics and user behavior characteristics are mapped to the matching preset tags.

[0067] Specifically, the establishing of the user portrait according to the user characteristics includes:

[0068] Step B1: Encode the user's personal characteristics and the user's behavioral characteristics to obtain an encoded feature vector.

[0069] Step B2: Encode the user tags to obtain an encoded tag vector.

[0070] Step B3: Generate a user profile based on the encoded feature vector and the encoded tag vector.

[0071] Further, adding the user profile to a preset user profile database includes:

[0072] Step C1: When the user's personal information changes within a preset update period, obtain the updated personal information after the change.

[0073] Step C2: Obtain the newly added user behavioral information within the preset update period.

[0074] Step C3: Update the user profile in the user profile database according to the updated personal information and the newly added user behavioral information to obtain an updated user profile.

[0075] Step C4: Replace the updated user profile with the user profile of the user in the user profile database.

[0076] In this embodiment, to ensure the accuracy of the user profiles in the user profile database, after a preset update period, obtain the changed or newly added user information within this period, and regularly update and adjust the user profiles in the user profile database to obtain more accurate user profiles, so as to timely push suitable high-interest push content for users.

[0077] Even further, determining the information type of the information to be pushed and obtaining the target users corresponding to the information type from the user profile database includes:

[0078] Step D1: Determine the information type of the information to be pushed.

[0079] Among them, the information to be pushed is divided into a first information type and a second information type. The first information type is information with strong timeliness and universality, such as news, announcements, etc.; the second information type is information with relatively single content and strong pertinence, such as posts, links, etc.; according to different information types, respectively determine the target users to be pushed for targeted pushing.

[0080] Step D2: When the information type is the first information type, use all users in the user profile database as target users.

[0081] Step D3: When the information type is the second information type, input the information to be pushed into the text analysis model to obtain content tags corresponding to the message to be pushed, and determine the target users matching the content tags from the user portrait database.

[0082] Among them, determining the target users according to the content tags includes:

[0083] Step E1: Obtain the content scores of each content tag of the information to be pushed; wherein, the content score is the degree of content association between the content tag and the message to be pushed.

[0084] Specifically, perform text analysis on the information to be pushed, determine the main content of the information to be pushed, add several content tags to each information to be pushed, and include content scores, for example: "stock" (60%), "new energy" (55%), "upward trend" (50%).

[0085] Step E2: Calculate the similarity between the content tag and the encoded feature vector and the encoded tag vector of each user portrait.

[0086] Step E3: Calculate the matching score between the information to be pushed and the user portrait according to the content score of each content tag and the similarity.

[0087] Step E4: Use the users corresponding to the user portraits with matching scores greater than the preset threshold as the target users.

[0088] Among them, according to the user portrait, it can be known which category of financial consultation the user is more interested in, and pushing the information to be pushed with a higher matching degree to the user can improve the click-through rate and conversion rate.

[0089] Furthermore, pushing the information to be pushed to the target users includes:

[0090] Step F1: When the information type of the information to be pushed is the first information type, push the information to be pushed to the target users in real time.

[0091] Step F2: When the information type of the information to be pushed is the second information type, obtain the optimal browsing time range of the target users from the user behavior information of the target users, and push the information to be pushed to the target users within the optimal browsing time range.

[0092] Among them, in order to further improve the click-through rate of the target users to receive the information to be pushed, set the information to be pushed of the second information type to be pushed at a fixed time, and push it within the time period when the users browse this financial community most frequently, which can effectively increase the probability of users browsing the information to be pushed, and then improve the conversion rate.

[0093] Further, the method further includes: counting the information push data within a set period, and adjusting the push strategy and push content according to the information push data.

[0094] Among them, the information push data includes the number of sends, the number of clicks, and the conversion rate within a preset time period. By calculating the first ratio of the number of sends to the number of clicks, and the second ratio of the number of clicks to the conversion rate, and analyzing the first ratio and the second ratio, the push content and push strategy are adjusted. When the number of sends is much higher than the number of clicks, there may be problems such as the email being marked as spam or the title not being attractive enough, and it is necessary to improve the attractiveness of the push content or adjust the form of the push content; the number of clicks reflects the degree of interest of users in the push content, while the conversion rate reflects the ratio of users from clicking to conversion. If the number of clicks is high but the conversion rate is not high, it is necessary to adjust the cost performance or preferential degree of the push product to improve the willingness of users to purchase the product.

[0095] In this embodiment, by analyzing the user characteristics in the user information, the corresponding user characteristics are extracted from both personal information and behavioral information to establish a user portrait, so as to construct a user portrait database and realize the unified management of the user portrait, making the mastery of user characteristics more comprehensive and accurate. At the same time, according to the information type of the information to be pushed, the target users to be pushed are determined from the user portrait database, and the information to be pushed is specifically pushed to the target users. This push method can improve the accuracy and efficiency of information push, realize the personalization and high efficiency of information push, which can better meet the needs of users, improve the user experience, enhance user loyalty, and at the same time can also improve the efficiency and effect of information push, bringing more commercial value to related applications and services.

[0096] Embodiment 2

[0097] Based on the push method based on user characteristics provided in the above Embodiment 1, a push device based on user characteristics is provided in this embodiment. Specifically, Figure 2 The optional structural block diagram of the push device based on user characteristics is shown. The push device based on user characteristics is divided into one or more program modules. One or more program modules are stored in a storage medium and executed by one or more processors to complete the present invention. The program modules referred to in the present invention refer to a series of computer program instruction segments that can complete specific functions, which are more suitable for describing the execution process of the push device based on user characteristics in the storage medium. The following description will specifically introduce the functions of each program module in this embodiment.

[0098] As Figure 2 shown, the push device based on user characteristics specifically includes the following components:

[0099] An acquisition module 201, configured to acquire user information of a user and extract user features from the user information;

[0100] A portrait module 202, configured to establish a user portrait according to the user features and add the user portrait to a preset user portrait database;

[0101] A determination module 203, configured to determine the information type of the information to be pushed and acquire target users corresponding to the information type from the user portrait database;

[0102] A push module 204, configured to push the information to be pushed to the target users.

[0103] Specifically, the acquisition module 201 is configured to:

[0104] Determine user personal information and user behavior information from the user information;

[0105] Input the user personal information and the user behavior information into a feature recognition model for feature extraction to obtain user personal features and user behavior features;

[0106] Generate user tags corresponding to each of the user personal features and the user behavior features of the user.

[0107] Wherein, the portrait module 202 is configured to:

[0108] Encode the user personal features and the user behavior features to obtain encoded feature vectors;

[0109] Encode the user tags to obtain encoded tag vectors;

[0110] Generate a user portrait according to the encoded feature vectors and the encoded tag vectors.

[0111] Further, the portrait module 202 is further configured to:

[0112] When the user personal information changes within a preset update period, acquire the updated personal information after the change;

[0113] Acquire the newly added user behavior information within the preset update period;

[0114] Update the user portrait in the user portrait database according to the updated personal information and the newly added user behavior information to obtain an updated user portrait;

[0115] Replace the updated user portrait with the user portrait of the user in the user portrait database.

[0116] Furthermore, the determining module 203 is configured to:

[0117] Determine the information type of the information to be pushed;

[0118] When the information type is the first information type, all users in the user portrait database are used as target users;

[0119] When the information type is the second information type, the information to be pushed is input into a text analysis model to obtain content tags corresponding to the information to be pushed, and the target users matching the content tags are determined from the user portrait database.

[0120] In addition, the determining module 203 is further configured to:

[0121] Obtain the content score of each content tag of the information to be pushed; wherein, the content score is the degree of content association between the content tag and the information to be pushed;

[0122] Calculate the similarity between the content tag and the encoded feature vector and the encoded tag vector of each user portrait;

[0123] Calculate the matching score between the information to be pushed and the user portrait according to the content score of each content tag and the similarity;

[0124] Use the users corresponding to the user portraits with matching scores greater than a preset threshold as the target users.

[0125] Further, the pushing module 204 is configured to:

[0126] When the information type of the information to be pushed is the first information type, push the information to be pushed to the target users in real time;

[0127] When the information type of the information to be pushed is the second information type, obtain the optimal browsing time range of the target users from the user behavior information of the target users, and push the information to be pushed to the target users within the optimal browsing time range.

[0128] Embodiment III

[0129] This embodiment further provides a computer device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server or a cabinet server (including an independent server, or a server cluster composed of multiple servers) that can execute programs. For example Figure 3As shown in the figure, the computer device 30 of this embodiment at least includes, but is not limited to, a memory 301 and a processor 302 that can communicate with each other through a system bus. It should be noted that, Figure 3 Only the computer device 30 with components 301-302 is shown, but it should be understood that it is not required to implement all the shown components, and more or fewer components can be alternatively implemented.

[0130] In this embodiment, the memory 301 (i.e., the readable storage medium) includes flash memory, hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 301 can be an internal storage unit of the computer device 30, such as the hard disk or memory of the computer device 30. In other embodiments, the memory 301 can also be an external storage device of the computer device 30, such as a plug-in hard disk equipped on the computer device 30, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, etc. Of course, the memory 301 can also include both the internal storage unit and the external storage device of the computer device 30. In this embodiment, the memory 301 is generally used to store the operating system and various application software installed on the computer device 30. In addition, the memory 301 can also be used to temporarily store various data that have been output or will be output.

[0131] In some embodiments, the processor 302 can be a Central Processing Unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips. The processor 302 is generally used to control the overall operation of the computer device 30.

[0132] Specifically, in this embodiment, the processor 302 is used to execute the program of the push method based on user characteristics stored in the memory 301. When the program of the push method based on user characteristics is executed, the following steps are implemented:

[0133] Obtain the user information of the user and extract the user characteristics from the user information;

[0134] Establish a user portrait according to the user characteristics and add the user portrait to a preset user portrait database;

[0135] Determine the information type of the information to be pushed, and obtain the target users corresponding to the information type from the user portrait database;

[0136] Push the information to be pushed to the target user.

[0137] For the specific implementation process of the above method steps, refer to Embodiment 1, and this embodiment will not be repeated here.

[0138] Embodiment 4

[0139] This embodiment also provides a computer-readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a random access memory (RAM), a static random access memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disc, a server, an App application store, etc. There is a computer program stored thereon, and when the computer program is executed by a processor, the following method steps are implemented:

[0140] Obtain the user information of the user and extract user features from the user information;

[0141] Establish a user portrait according to the user features and add the user portrait to a preset user portrait database;

[0142] Determine the information type of the information to be pushed, and obtain the target user corresponding to the information type from the user portrait database;

[0143] Push the information to be pushed to the target user.

[0144] For the specific implementation process of the above method steps, refer to Embodiment 1, and this embodiment will not be repeated here.

[0145] It should be noted that in this article, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitations, an element defined by the statement "including one..." does not exclude the existence of additional identical elements in the process, method, article or device including that element.

[0146] The serial numbers of the above embodiments of the present invention are only for description and do not represent the superiority or inferiority of the embodiments.

[0147] Through the description of the above embodiments, those skilled in the art can clearly understand that the above method of the embodiment can be implemented by means of software plus a necessary general hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method.

[0148] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A push method based on user characteristics, characterized in that, The method includes: Obtain the user information of the user and extract user features from the user information; Build a user portrait based on the user features and add the user portrait to a preset user portrait database; Determine the information type of the information to be pushed, and obtain the target users corresponding to the information type from the user portrait database; Push the information to be pushed to the target users.

2. The push method based on user characteristics according to claim 1, wherein The obtaining the user information of the user and extracting user features from the user information includes: Determine the user personal information and user behavior information from the user information; Input the user personal information and the user behavior information into a feature recognition model for feature extraction to obtain user personal features and user behavior features; Generate user tags corresponding to each of the user personal features and the user behavior features of the user.

3. The push method based on user characteristics according to claim 2, wherein The building the user portrait based on the user features includes: Encode the user personal features and the user behavior features to obtain encoded feature vectors; Encode the user tags to obtain encoded tag vectors; Generate a user portrait according to the encoded feature vectors and the encoded tag vectors.

4. The push method based on user characteristics according to claim 3, wherein, The adding the user portrait to a preset user portrait database includes: When the user personal information changes within a preset update period, obtain the updated personal information after the change; Obtain the new user behavior information within the preset update period; Update the user portrait in the user portrait database according to the updated personal information and the new user behavior information to obtain an updated user portrait; Replace the updated user portrait with the user portrait of the user in the user portrait database.

5. The push method based on user characteristics according to claim 3, wherein The determining the information type of the information to be pushed and obtaining the target users corresponding to the information type from the user portrait database includes: Determine the information type of the information to be pushed; When the information type is the first information type, use all users in the user portrait database as target users; When the information type is the second information type, input the information to be pushed into a text analysis model to obtain content tags corresponding to the information to be pushed, and determine the target users matching the content tags from the user portrait database.

6. The push method based on user characteristics according to claim 5, wherein The determining the target users according to the content tags includes: Obtain the content scores of each content tag of the information to be pushed; wherein, the content score is the degree of content association between the content tag and the information to be pushed; Calculate the similarity between the content tags and the encoded feature vectors and the encoded tag vectors of each user portrait; Calculate the matching score between the information to be pushed and the user portrait according to the content scores of each content tag and the similarity; Use the users corresponding to the user portraits with matching scores greater than a preset threshold as the target users.

7. The push method based on user characteristics according to claim 5, wherein The pushing the information to be pushed to the target users includes: When the information type of the information to be pushed is the first information type, push the information to be pushed to the target users in real time; When the information type of the information to be pushed is the second information type, obtain the optimal browsing time range of the target user from the user behavior information of the target user, and push the information to be pushed to the target user within the optimal browsing time range.

8. A push device based on user characteristics, characterized in that, The device includes: An acquisition module, configured to acquire user information of a user and extract user characteristics from the user information; A profiling module, configured to establish a user profile according to the user characteristics and add the user profile to a preset user profile database; A determination module, configured to determine the information type of the information to be pushed and obtain a target user corresponding to the information type from the user profile database; A push module, configured to push the information to be pushed to the target user.

9. A computer device, the computer device comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program implements the steps of the method according to any one of claims 1 to 7 when executed by the processor.

Images