Dynamic application intelligent pushing method and system based on credential terminal

Abstract

The invention discloses a dynamic application intelligent pushing method and system based on a credential terminal, and belongs to the technical field of information technology application innovation. Comprising the steps of obtaining current user information, extracting key features in the current user information, and generating a corresponding user portrait based on the key features; acquiring a real-time background process of the credential terminal, and determining a current scene identifier based on the real-time background process; screening in a preset application library based on the current scene identifier, and obtaining and pushing a plurality of matched applications by calculating the comprehensive scores of the applications; and obtaining a historical user portrait under the current scene identifier, performing user similarity calculation according to the user portrait and the historical user portrait, determining similar users, screening matched applications, and pushing the matched applications. The accuracy and timeliness of application matching can be improved, and user experience and stickiness are enhanced. The problem that an existing dynamic application pushing technology is insufficient in accuracy and timeliness when being applied to a credential terminal is solved.

Description

Technical Field

[0001] The present invention relates to the field of information technology application innovation technology, and in particular to a dynamic application intelligent push method and system based on an information innovation terminal. Background Art

[0002] The statements in this section merely mention background art related to the present invention and do not necessarily constitute prior art.

[0003] Dynamic application intelligent push is a technology that uses algorithm models to accurately push information or services that users may be interested in based on multi-dimensional data such as user behavior analysis, preference settings, and contextual environment.

[0004] Xinchuang terminals refer to products based on information technology application innovation (xinchuang). These products usually include computer hardware, software, network equipment, etc., and are designed to build an autonomous and controllable information technology system. With the continuous improvement of the xinchuang terminal ecosystem, the number of user computer applications continues to increase, and the decentralization of applications will inevitably lead to reduced user efficiency. The current dynamic application intelligent push technology applied to xinchuang terminals still has the following problems: 1. The types of pushed applications are simple. Most of them are information push. For example, they only push a list of applications that users need to install based on application ratings or installation volume, similar to must-haves and popular installations. They are not based on user application scenarios and have a single matching dimension. They may not accurately capture users' interests and needs, resulting in a mismatch between the pushed content and users' actual needs, resulting in a large amount of useless information push. This not only wastes users' time and energy, but may also reduce users' trust in the push system and their enthusiasm for use.

[0005] 2. The existing dynamic application intelligent push technology is only applicable to a specific scenario (such as WORD). The matching result is only the inherent content in the scenario. The scenario application is single and the matching content is fixed.

[0006] The patent document with publication number CN118467814A discloses an Internet-based network library content search and recommendation system. The method is based on user registration information and user behavior feature vectors. The cosine similarity calculation method is used to measure the similarity between several behavior feature vectors. Book recommendations are made through similarity scores, and the subsequent adaptive feedback mechanism realizes the continuous optimization of personalized recommendations. The method relies on the browser information management system to realize the information push function. It decides which content to push to the user by analyzing the user's browsing habits, preference settings, and other relevant information in the browser. The content pushed by this method is only text information, not recommended applications. Moreover, the scope of text information is limited, and only information matching the fixed types preset by the system can be recommended. Summary of the invention

[0007] In order to address the deficiencies in the prior art, the present invention provides a dynamic application intelligent push method, system, electronic device, computer storage medium and computer program product based on a trusted terminal. The method has wide applicability and flexibility, is not limited by specific scenarios, and can dynamically match the most suitable application in multiple interfaces such as the desktop, browser, file manager, taskbar, etc., effectively improving the user's daily office work efficiency.

[0008] In the first aspect, the present invention provides a method for intelligently pushing dynamic applications based on a trusted terminal; A dynamic application intelligent push method based on a trusted terminal, comprising: Acquire current user information, extract key features from the current user information, and generate a corresponding user portrait based on the key features; Obtain the real-time background process of the trusted terminal, and determine the current scene identifier based on the real-time background process; Based on the current scenario identifier, a preset application library is screened, and a plurality of matching applications are obtained and pushed by calculating the comprehensive scores of the applications; Obtain the historical user portrait under the current scenario identification, calculate the user similarity based on the user portrait and the historical user portrait, determine similar users, filter matching applications and push them.

[0009] In some implementations, extracting key features from the current user information and generating a corresponding user portrait based on the key features specifically includes: extracting key features from user basic information, user behavior information, and user-related information, classifying users into groups based on the key features, and generating labels.

[0010] In some implementations, determining the current scene identifier based on the real-time background process includes: The process information and / or window information in the real-time background process is matched with a preset scene database to determine a current scene identifier.

[0011] In some implementations, the filtering in a preset application library based on the current scene identification information, obtaining a plurality of matching applications and pushing them by calculating a comprehensive score of the applications includes: Based on the current scenario identifier, a preset application library is screened to obtain preliminary matching applications; The comprehensive scores of the preliminary matching applications are calculated by the number of times the preliminary matching applications are used, the number of users, the application ratings and the application completeness. The preliminary matching applications are sorted in descending order according to the comprehensive scores to filter the matching applications.

[0012] In some implementations, calculating user similarity based on the user portrait and the historical user portrait, determining similar users and screening matching applications includes: Calculate the cosine similarity or Pearson correlation coefficient between the user profile and the historical user profile to determine the similarity score; Based on the similarity score, multiple similar users who are similar to the current user are screened, and matching application recommendations are made based on the application lists of similar users.

[0013] In some implementations, the method further includes: if the current scene is office software, determining a detailed scene based on mouse information and clipboard information.

[0014] In the second aspect, the present invention provides a dynamic application intelligent push system based on the trusted terminal; A dynamic application intelligent push system based on a trusted terminal, comprising: The user portrait generation module is configured to: obtain current user information, extract key features from the current user information, and generate a corresponding user portrait based on the key features; The scene monitoring module is configured to: obtain the real-time background process of the information innovation terminal, and determine the current scene identifier based on the real-time background process; The dynamic application push module is configured to: screen in a preset application library based on the current scenario identifier, obtain multiple matching applications and push them by calculating the comprehensive score of the application; obtain historical user portraits, calculate user similarity based on the user portraits and historical user portraits, determine similar users and screen matching applications and push them.

[0015] In a third aspect, the present invention provides an electronic device; An electronic device includes a memory, a processor and a computer program stored in the memory, wherein the processor executes the computer program to implement the steps of the above-mentioned dynamic application intelligent push method based on the trusted terminal.

[0016] In a fourth aspect, the present invention provides a computer-readable storage medium; A computer-readable storage medium having computer programs / instructions stored thereon, which, when executed by a processor, implement the steps of the above-mentioned dynamic application intelligent push method based on a trusted terminal.

[0017] In a fifth aspect, the present invention provides a computer program product; A computer program product includes a computer program / instructions, which, when executed by a processor, implement the steps of the above-mentioned dynamic application intelligent push method based on a trusted terminal.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. The technical solution provided by the present invention dynamically and accurately matches applications that can be directly clicked for use (including installed and recommended installation parts) according to the user's current application scenario, tag portrait and other information, thereby improving user office efficiency, improving the accuracy and timeliness of application matching, enhancing user experience and stickiness, and supporting diverse usage scenarios to promote the development of the information and innovation ecosystem.

[0019] 2. The technical solution provided by the present invention combines the characteristics of the ICT terminal and user needs to dynamically and intelligently match applications that meet user characteristics and interests in different application scenarios of the ICT terminal, thereby enhancing user convenience and improving work efficiency. For full-scenario applications, the matching push content is more diverse, which can significantly improve the user experience and satisfaction, while reducing the push of invalid information and improving the overall information processing efficiency.

[0020] 3. The technical solution provided by the present invention can provide users with application recommendations that better meet their needs by continuously learning and analyzing user behaviors and interests; this personalized recommendation method can enhance user experience and improve user stickiness and loyalty to the platform; through the dynamic application intelligent matching mechanism, it can support diverse usage scenarios and meet the personalized needs of different fields and users. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0022] Figure 1 A schematic diagram of the process of generating a user portrait provided by an embodiment of the present invention; Figure 2 A schematic diagram of a process of desktop scene monitoring provided by an embodiment of the present invention; Figure 3 A schematic diagram of a process for browser scene monitoring provided by an embodiment of the present invention; Figure 4 A flow chart of a method for intelligent push of dynamic applications based on a trusted terminal provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0023] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used in the present invention have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0024] It should be noted that the terms used herein are only for describing specific embodiments, and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "include" and "have" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0025] In the absence of conflict, the embodiments of the present invention and the features of the embodiments may be combined with each other.

[0026] Embodiment 1 The existing application push matching dimensions applied to trusted innovation terminals are single, the scenario applications are single, and the matching content is fixed, and the impact of application scenarios and user preferences on application push is not comprehensively considered; therefore, the present invention provides a dynamic application intelligent push method based on trusted innovation terminals, which performs dynamic application push based on the user's actual application scenarios and user characteristics, thereby improving the accuracy and timeliness of the push.

[0027] Next, combine Figure 1-Figure 4 , a dynamic application intelligent push method based on a trusted terminal disclosed in this embodiment is described in detail. The dynamic application intelligent push method based on a trusted terminal includes the following steps: S1. Obtain current user information, extract key features from the current user information, and generate a corresponding user portrait based on the key features.

[0028] Among them, the current user information includes user basic information, user behavior information and user related information, all of which are collected after the user's authorization and do not involve privacy information.

[0029] Specifically, basic user information is obtained by actively filling in information during user registration, such as through online forms, registration pages, questionnaires, etc. The main content collected is data such as gender, age, industry and profession. This method requires users to voluntarily provide personal information, so the quality of the data is higher, but it may also be limited because users are unwilling to disclose too much information.

[0030] User behavior information is collected through data analysis technology and machine learning algorithms, such as users' online behavior, application browsing records, search history, dwell events, click content, etc. User behavior information includes users' industry background and interests and hobbies.

[0031] Obtain user-related information through third-party data providers, partners, public data sources, etc. This method can supplement the deficiencies of internal enterprise data and provide more dimensional user information.

[0032] As an implementation method, S1 specifically includes: obtaining basic user information, user behavior information and user related information, extracting key features from the basic user information, user behavior information and user related information, and classifying users into groups based on the key features and generating labels. The specific process is as follows: S101. Obtain user basic information, user behavior information and user related information and perform data cleaning to remove abnormal and duplicate data to ensure quality.

[0033] S102: According to the preset dictionary data, the user basic information, user behavior information and user related information after data cleaning are converted into vector form through one-hot encoding, and key features are extracted according to expert experience and correlation analysis. For example, gender is converted into 0 and 1.

[0034] S103. The key features of multiple users are processed by the K-means clustering algorithm. The users are divided into K groups. The users in each group have similar behavioral features, that is, similar users; labels are generated for user portraits according to the categories of behavioral features (such as age, gender, profession, etc.).

[0035] S2. Obtain the real-time background process of the trusted computing terminal, and determine the current scene identifier based on the real-time background process.

[0036] Specifically, the process information and / or window information in the real-time background process is matched with a preset scene database to determine the current scene identifier.

[0037] For example, the specific process is as follows: S201, obtaining process information, if the process information is the handle of the current active window, executing S202; if the process information is a browser process, such as chrome, firefox, etc., executing S203; if the process information is an office software process, such as excel, word, executing S204; S202. Get the window title and window class name. If the window title is empty or the window class name is "xfdesktop" or "plasma-desktop", the current scene is the Xinchuang desktop.

[0038] S203, use xdotool, getactivewindow command to obtain the current active window, then use wmctrl, xprop command to obtain the specific information of the window, get the window title, and determine whether the current scene is a browser according to the window title. Specifically, if the window title is the browser name, the current scene is a browser.

[0039] Furthermore, if the current scene is a browser, in order to identify a more accurate browser application scene, it also includes: Use Python library and browser plug-in to crawl the web page content of the current browser window, extract key data such as title, metadata, keywords and links from the crawled web page content, and input it into a simple probability classifier based on Bayesian theorem to confirm the current website classification.

[0040] Specifically, the simple probability classifier based on Bayes' theorem is a Bayesian network trained by a training set. The training set consists of key data and annotations of corresponding website classification results. The input of the Bayesian network is the key data in numerical form, and the output is the website classification result.

[0041] S204: Further refine the application scenario by combining the mouse information and the clipboard information.

[0042] For example, if the current scene is confirmed to be office software based on the process information and window information, further scene refinement is performed based on the mouse information and clipboard information. If the left mouse button is pressed and dragged, it is a text selection scene; if there is content on the clipboard, it can be identified as a paste and copy scene.

[0043] It can greatly improve the accuracy and practicality of matching, and better meet the needs of users working on trusted computing terminals.

[0044] Furthermore, you can set system events through the terminal software, select Settings in the main interface and select "Event Monitoring" in the settings, add system events that need to be monitored, such as window activation, file opening, etc., and bind hot keys to specific workflows so that the corresponding scenes can be triggered when the hot keys are pressed.

[0045] Furthermore, special scenes, such as the taskbar, are identified based on the mouse coordinate position and keyboard shortcut keys. The taskbar itself belongs to the desktop window scene, but since the taskbar has special functions, the scene of the taskbar must be determined based on the mouse and keyboard.

[0046] S3: Filter the preset application library based on the current scene identification information, obtain multiple matching applications and push them by calculating the comprehensive scores of the applications. Specifically, it includes: S301. Filter applications that match the current scene type in a preset application library based on the current scene identification information as preliminary matching applications.

[0047] S302, calculating the comprehensive score of the preliminary matching applications by the number of times the preliminary matching applications are used, the number of users, the application rating and the application completeness, and sorting the preliminary matching applications in descending order according to the comprehensive score to filter the matching applications. The comprehensive score is expressed as: ; ; ; ; ; In the formula, represents the weight of the number of times used, represents the weight of the number of users, represents the weight of the rating, represents the weight of the completeness details, Indicates the number of times application i is used. represents the number of users of application i, represents the rating of application i, Indicates the completeness details of application i (a value between 0 and 1, 1 being complete).

[0048] S4. Obtain the historical user portrait of the preliminary matching application, calculate the user similarity based on the user portrait and the historical user portrait, determine similar users, filter the matching applications, and push them.

[0049] Specifically, the cosine similarity or Pearson correlation coefficient between the user portrait and the historical user portrait is calculated to determine the similarity score; based on the similarity score, multiple similar users similar to the current user are screened, and matching application recommendations are made based on the application lists of the similar users.

[0050] Exemplary: Suppose there is a user-application rating matrix as follows:

[0051] Calculate user similarity: Use cosine similarity to calculate the similarity between user 1 and other users: Similarity between user 1 and user 2: cosine_sim(user 1, user 2) = (54 + 43) / (sqrt(5^2+ 4^2) * sqrt(4^2 + 3^2 + 5^2)) ≈ 0.94 Similarity between user 1 and user 3: cosine_sim(user 1, user 3) = 0 Similarity between user 1 and user 4: cosine_sim(user 1, user 4) = (55 + 45) / (sqrt(5^2+ 4^2) * sqrt(5^2 + 5^2)) ≈ 0.98 Find similar users: According to the similarity score, user 4 is the most similar, followed by user 2.

[0052] Generate a recommendation list: User 4 likes App D, and User 2 likes App C, so App C and App D are recommended to User 1.

[0053] Embodiment 2 This embodiment discloses a dynamic application intelligent push system based on a trusted terminal, including: The user portrait generation module is configured to: obtain current user information, extract key features from the current user information, and generate a corresponding user portrait based on the key features; The scene monitoring module is configured to: obtain the real-time background process of the information innovation terminal, and determine the current scene identifier based on the real-time background process; The dynamic application push module is configured to: screen in a preset application library based on the current scenario identifier, obtain multiple matching applications and push them by calculating the comprehensive score of the application; obtain historical user portraits, calculate user similarity based on the user portrait and historical user portraits, determine similar users and screen matching applications and push them.

[0054] It should be noted that the user portrait generation module, scenario monitoring module and dynamic application push module correspond to the steps in Embodiment 1, and the examples and application scenarios implemented by the modules and the corresponding steps are the same, but are not limited to the contents disclosed in Embodiment 1. It should be noted that the modules as part of the system can be executed in a computer system such as a set of computer executable instructions.

[0055] Embodiment 3 Embodiment 3 of the present invention provides an electronic device, including a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps of the above-mentioned dynamic application intelligent push method based on the trusted terminal are completed.

[0056] Embodiment 4 Embodiment 4 of the present invention provides a computer-readable storage medium for storing computer instructions. When the computer instructions are executed by a processor, the steps of the above-mentioned dynamic application intelligent push method based on the trusted terminal are completed.

[0057] Embodiment 5 Embodiment 5 of the present invention provides a computer program product, including a computer program / instruction, which, when executed by a processor, implements the steps of the above-mentioned dynamic application intelligent push method based on the trusted terminal.

[0058] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0059] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device, and a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0061] The description of each embodiment in the above embodiments has different emphases. For parts not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0062] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A dynamic application intelligent push method based on a trusted terminal, characterized in that: include: Acquire current user information, extract key features from the current user information, and generate a corresponding user portrait based on the key features; Obtain the real-time background process of the trusted terminal, and determine the current scene identifier based on the real-time background process; Based on the current scenario identifier, a preset application library is screened, and a plurality of matching applications are obtained and pushed by calculating the comprehensive scores of the applications; Obtain the historical user portrait under the current scenario identification, calculate the user similarity based on the user portrait and the historical user portrait, determine similar users, filter and match applications, and push them.

2. The method for intelligently pushing dynamic applications based on a trusted terminal as claimed in claim 1, characterized in that: The extracting of key features from the current user information and generating a corresponding user portrait based on the key features specifically includes: extracting key features from user basic information, user behavior information and user related information, classifying users into groups based on the key features and generating labels.

3. The method for intelligently pushing dynamic applications based on a trusted terminal as claimed in claim 1 is characterized in that: The determining of the current scene identification information based on the real-time background process specifically includes: The process information and / or window information in the real-time background process is matched with a preset scene database to determine a current scene identifier.

4. The method for intelligently pushing dynamic applications based on a trusted terminal as claimed in claim 1, characterized in that: The screening in a preset application library based on the current scene identification information, obtaining multiple matching applications and pushing them by calculating the comprehensive scores of the applications includes: Based on the current scenario identifier, a preset application library is screened to obtain preliminary matching applications; The comprehensive scores of the preliminary matching applications are calculated by the number of times the preliminary matching applications are used, the number of users, the application ratings and the application completeness. The preliminary matching applications are sorted in descending order according to the comprehensive scores to filter the matching applications.

5. The method for intelligently pushing dynamic applications based on a trusted terminal as claimed in claim 1, characterized in that: Calculating user similarity based on user portraits and historical user portraits, determining similar users and screening matching applications includes: Calculate the cosine similarity or Pearson correlation coefficient between the user profile and the historical user profile to determine the similarity score; Based on the similarity score, multiple similar users who are similar to the current user are screened, and matching application recommendations are made based on the application lists of similar users.

6. The method for intelligently pushing dynamic applications based on a trusted terminal as claimed in claim 1, characterized in that: Also includes: If the current scene is office software, the detailed scene is determined according to the mouse information and clipboard information.

7. The dynamic application intelligent push system based on the trusted terminal is characterized by: include: The user portrait generation module is configured to: obtain current user information, extract key features from the current user information, and generate a corresponding user portrait based on the key features; The scene monitoring module is configured to: obtain the real-time background process of the information innovation terminal, and determine the current scene identifier based on the real-time background process; The dynamic application push module is configured to: screen in a preset application library based on the current scenario identifier, obtain multiple matching applications and push them by calculating the comprehensive score of the application; obtain historical user portraits and historical scenario identification information, calculate user similarity based on user portraits and historical user portraits, determine similar users, screen matching applications and push them.

8. An electronic device comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the steps of the dynamic application intelligent push method based on the trusted terminal as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program / instruction stored thereon, characterized in that: When the computer program / instructions are executed by the processor, the steps of the dynamic application intelligent push method based on the trusted terminal as described in any one of claims 1-6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by the processor, the steps of the dynamic application intelligent push method based on the trusted terminal as described in any one of claims 1-6 are implemented.

Images