Live broadcast menu recommendation system and recommendation method based on different occupations

Abstract

The invention relates to the technical field of live broadcast menu recommendation, and discloses a live broadcast menu recommendation system and recommendation method based on different occupations, and the system comprises an intelligent recommendation module which is connected with a role recognition module, an interaction recognition module, a controller and a menu database; the role recognition module recognizes the occupational identity of a user and collects role information such as menu interaction habits and special menus of occupational groups, and the interaction recognition module captures and analyzes dynamic environment information including real-time user behaviors and scene features; and the intelligent recommendation module fuses occupational special menus and real-time scene features, screens target menu items from a menu database, and intelligently adjusts layout and outputs personalized recommendation menus according to user interaction habits and real-time behavior data. According to the method, the user experience of the live broadcast platform is remarkably improved, exclusive requirements of different occupational groups are met, a solid foundation is laid for diversified and professional development of the live broadcast platform, and the live broadcast technology is promoted to develop towards a more intelligent and more personalized direction.

Description

Technical Field

[0001] This invention relates to the field of live streaming menu recommendation technology, specifically to a live streaming menu recommendation system and method based on different professions. Background Technology

[0002] With the rapid development of internet technology, live streaming has moved from PCs to mobile devices, significantly improving convenience and interactivity, lowering barriers to entry, and becoming a popular communication tool. This shift has led to an increasingly close integration of live streaming with various professions. Educators, doctors, and other professionals from different industries have joined the ranks of live streamers, using live streaming platforms to showcase their professional skills, expand their career development paths, and meet the diverse needs of their audiences.

[0003] However, traditional live streaming platforms' menu recommendation systems have failed to keep pace, exhibiting significant technical shortcomings. Specifically, existing menu recommendation systems mostly employ static recommendation logic, relying excessively on historical click data while neglecting changes in real-time user interaction scenarios. For example, during a live stream, a user might suddenly need to connect via voice chat, but the current system cannot detect and recommend the corresponding function in a timely manner. Furthermore, the system ignores professional characteristics, failing to customize the functionalities specific to different professional groups. For instance, teachers might need a "classroom silence management" function during live lectures, while doctors might need "medical image annotation tools" during remote consultations, but these functions are often difficult to find in the existing menus.

[0004] This invention provides a live streaming menu recommendation system and method based on different professions to solve the above problems. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] To address the shortcomings of existing technologies, this invention provides a live streaming menu recommendation system and method based on different professions. It has the advantages of personalized and highly adaptable live streaming menu recommendations, and solves the problem that traditional live streaming platform menu recommendation systems mostly adopt static recommendation logic, rely too much on historical click data, ignore changes in real-time user operation scenarios, and neglect professional characteristics, failing to recommend live streaming menus according to the exclusive functional needs of different professional groups.

[0007] (II) Technical Solution

[0008] To achieve the aforementioned goals of personalized and highly adaptable live stream menu recommendations, this invention provides the following technical solution:

[0009] This invention provides a live streaming menu recommendation system based on different professions, comprising:

[0010] The intelligent recommendation module is connected to the role recognition module, the interaction recognition module, the controller, and the menu database.

[0011] The role recognition module is used to identify the user's professional identity and collect role information, which includes the menu interaction habits of the user's professional group and professional-specific menus.

[0012] The interaction recognition module is used to capture and analyze the user's dynamic environment information, which includes real-time user behavior data and real-time usage scenario characteristics.

[0013] The intelligent recommendation module is configured to perform the following: based on the occupational special menu and real-time usage scenario characteristics, filter target menu items from the menu database; combine the menu interaction habits and real-time user behavior data to adjust the layout of the target menu items and output them as recommended menu items;

[0014] The controller is used to respond to the user's selection command for the recommended menu item and execute the corresponding function operation.

[0015] Existing live streaming platforms' menu recommendation systems mainly rely on static historical data, neglecting changes in users' real-time operating scenarios and the specific functional needs of different professional groups, resulting in a discrepancy between recommended content and users' actual needs.

[0016] This invention significantly improves upon the shortcomings of existing live streaming platform menu recommendation systems by constructing a live streaming menu recommendation system based on different professions. The system intelligently identifies the user's profession and, by integrating profession-specific menus with real-time scene characteristics, achieves personalized recommendations by filtering target menu items from a menu database. Furthermore, it dynamically adjusts the menu layout by combining user menu interaction habits and real-time behavioral data to ensure that the recommended content highly matches the user's actual needs.

[0017] Preferably, the role recognition module performs occupational identity verification through biometric recognition technology or user account login information.

[0018] Preferably, the occupational special menu is a configurable menu set customized according to the work needs of different occupational groups, supporting users to add or delete menu options in a personalized manner.

[0019] Preferably, the interaction recognition module analyzes real-time usage scenario characteristics in the following ways: monitoring user operation behavior data on the live streaming platform, and determining the current usage scenario type through behavior pattern analysis; behavior patterns include function button click records, form filling content, video viewing records, etc.

[0020] Preferably, the intelligent recommendation module performs the following when filtering target menu items:

[0021] The matching degree between the functional description of each menu item in the menu database and the current usage scenario type is calculated as the scenario relevance; the similarity between the functional description of each menu item in the menu database and the functional description set of the configurable menu set is compared as the occupational relevance; based on the occupational relevance and scenario relevance, a weighted calculation is performed to select target menu items whose comprehensive score reaches the threshold.

[0022] Preferably, the menu interaction habits include the user's past frequency of using the menu and the user's past habitual positions on the menu.

[0023] Preferably, the interaction recognition module analyzes real-time user behavior data by: capturing real-time user gestures using sensor technology, including swiping direction, touch trajectory, or click location; and capturing user voice commands using microphone and speech recognition technology.

[0024] Preferably, the layout adjustment of the target menu item by the intelligent recommendation module includes: sorting each menu item in the target menu item according to the dynamic usage frequency, wherein the dynamic usage frequency includes past usage frequency and real-time usage frequency, and wherein the real-time usage frequency is dynamically counted by the click position, touch trajectory and number of triggers of voice commands captured by the interaction recognition module in real time.

[0025] The display position of the target menu item is based on the user's previously used position of the menu, and is subsequently adjusted based on real-time user behavior. The subsequent adjustment is to dynamically adjust the position of the menu item in the interface based on real-time gestures and voice commands captured by the interaction recognition module.

[0026] Another aspect of the present invention provides a menu recommendation method, comprising the following steps:

[0027] S1: Users securely access the system through the role recognition module using biometric technology or user account login. The system collects and analyzes the user's role information, which includes the menu interaction habits of the user's professional group and professional-specific menus.

[0028] S2: The interaction recognition module captures and analyzes the user's dynamic environment information, including capturing the user's real-time gestures and voice commands to obtain real-time user behavior data, monitoring the user's operation behavior data on the live streaming platform to determine the current usage scenario type, thereby obtaining real-time usage scenario characteristics.

[0029] S3: The intelligent recommendation module uses the user's occupation-specific menu and real-time usage scenario characteristics to calculate and compare the matching degree of each menu item with the current scenario and the similarity of the occupation-specific menu, and selects highly relevant menu items from the menu database as target menu items.

[0030] S4: The intelligent recommendation module further combines users' menu interaction habits and real-time user behavior data, dynamically sorts the positions of each menu item in the recommended menu based on real-time usage frequency, and then adjusts the menu display position based on users' past habitual positions of the menu and real-time user behavior data.

[0031] S5: The controller responds to the user's selection command for the recommended menu items, executes the corresponding function operation, and provides the user with a smooth live menu recommendation experience.

[0032] (III) Beneficial Effects

[0033] Compared with existing technologies, this invention provides a live streaming menu recommendation system and method based on different professions, which has the following beneficial effects:

[0034] This live streaming menu recommendation system, based on different professions, achieves personalized recommendations for live streaming menus based on user professional identity and real-time operation scenarios through the close cooperation of intelligent recommendation modules with role recognition and interaction recognition modules. This not only improves the user experience but also meets the exclusive functional needs of different professional groups, bringing a revolutionary change to the menu recommendation system of live streaming platforms.

[0035] The menu recommendation method provided by this invention, based on user role information and combined with dynamic environmental information, uses an intelligent recommendation module to filter recommended menu items and dynamically adjust the layout of recommended menu items, achieving highly adaptable recommendations for live streaming menus. This not only improves user satisfaction but also provides strong support for the professional development of live streaming platforms. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the system principle of the present invention;

[0037] Figure 2 This is a system data flow diagram of the present invention;

[0038] Figure 3 This is a schematic diagram of the method steps of the present invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] In the description of this invention, it should be understood that the terms "center", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0041] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal communication between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0042] Please see Figure 1 and Figure 2 One embodiment of the present invention provides a live streaming menu recommendation system based on different professions, including: an intelligent recommendation module connected to a role recognition module, an interaction recognition module, a controller, and a menu database; the role recognition module is used to identify the user's professional identity and collect role information, including the menu interaction habits of the user's professional group and professional-specific menus; the interaction recognition module is used to capture and analyze the user's dynamic environment information, including real-time user behavior data and real-time usage scenario characteristics; the intelligent recommendation module is configured to perform: filtering target menu items from the menu database based on professional-specific menus and real-time usage scenario characteristics; adjusting the layout of the target menu items based on menu interaction habits and real-time user behavior data, and outputting them as recommended menu items; the controller is used to respond to the user's selection command for recommended menu items and execute the corresponding functional operation.

[0043] In this embodiment, professional identity verification and role information are collected through biometric recognition technology of the role recognition module or user account login information.

[0044] In the above embodiments, biometric identification technologies, including but not limited to fingerprint and facial recognition, are used. The user account contains elements for professional identity verification, such as confirming the user's professional identity through the professional information filled in during user registration or account information associated with enterprises and institutions. This not only improves the accuracy and security of user identity verification, but also effectively prevents unauthorized user access and protects the system's data security and user privacy.

[0045] In this embodiment, the occupational special menu is a set of configurable menus customized according to the work needs of different occupational groups, and supports users to add or delete menu options in a personalized way.

[0046] In the above embodiments, the design of the occupational special menu fully considers the work needs and operating habits of different occupational groups, and provides a configurable menu set, allowing users to make personalized additions and deletions according to actual needs. This flexibility not only improves the applicability of the system, but also enhances the user experience satisfaction.

[0047] In this embodiment, the interaction recognition module analyzes the characteristics of the real-time usage scenario in the following ways:

[0048] Monitor user behavior data on live streaming platforms and determine the current usage scenario type through behavior pattern analysis;

[0049] Behavioral patterns include function button click records, form filling records, and video viewing records.

[0050] In the above embodiments, the interaction recognition module monitors user behavior data on the live streaming platform in real time and uses behavioral pattern analysis technology to determine the current usage scenario type. This behavioral analysis method can accurately capture the user's usage intent and needs, providing the intelligent recommendation module with real-time and accurate scenario feature information, thereby optimizing the recommendation effect.

[0051] When filtering target menu items, the intelligent recommendation module calculates a comprehensive score by assessing the matching degree (scenario relevance) between each menu item in the menu database and the current usage scenario type, as well as the similarity (occupational relevance) with the functional descriptions of various occupational special menus. This process is feasible because modern recommendation systems widely employ content-based recommendation algorithms and collaborative filtering algorithms, which can effectively calculate the similarity or matching degree between items (menu items in this example) and user interests or needs. By setting reasonable feature vectors and similarity calculation rules for different scenario types and occupational special menus, the intelligent recommendation module can accurately filter menu items that are highly relevant to the user's current needs.

[0052] When the intelligent recommendation module filters target menu items, it executes the following:

[0053] The matching degree between the functional description of each menu item in the menu database and the current usage scenario type is used as the scenario relevance; the formula for calculating the scenario relevance is:

[0054]

[0055] in, For menu item function descriptions, Keywords for the scene These are the weighting coefficients.

[0056] The similarity between the functional descriptions of each menu item in the menu database and the functional description set of the configurable menu set is used as the occupational relevance. This occupational relevance is evaluated based on a semantic similarity model (such as BERT) to assess the degree of matching between the functional descriptions and occupational templates. The formula for occupational relevance is:

[0057]

[0058] The target menu items are selected based on a weighted calculation of occupational relevance and scenario relevance, with the overall score reaching a threshold.

[0059] In the above embodiments, the intelligent recommendation module considers both scenario relevance and occupational relevance when filtering target menu items. By calculating the matching degree of each menu item with the current usage scenario type and its similarity with the configurable menu set, and combining this with a weighted calculation method, it can accurately filter menu items that are highly relevant to the user's current needs. This filtering method not only improves the accuracy of recommendations but also enhances the system's intelligence level.

[0060] For example, suppose there's a live streaming platform whose menu database contains various types of menu items, such as "game streaming," "educational lectures," and "entertainment shows." When a user is identified as a teacher, the profession-specific menu might include options like "online classes" and "educational information." Furthermore, if the current usage scenario involves the user logging into the platform between 8 PM and 10 PM (a common timeframe for online education), the intelligent recommendation module can calculate the high degree of match between the "online classes" menu item and the current scenario, and include it as one of the target menu items.

[0061] In this embodiment, menu interaction habits include the user's past frequency of using the menu and the user's past habitual location of the menu.

[0062] In the above embodiments, the analysis of menu interaction habits takes into account the user's past frequency of menu use and preferred locations. This information reflects the user's usage preferences and habits. The intelligent recommendation module fully considers these habits when adjusting the layout, and can provide users with recommended menu items that better match their usage habits, thereby improving user satisfaction and loyalty.

[0063] In this embodiment, the interaction recognition module's analysis of real-time user behavior data includes:

[0064] The system uses sensor technology to capture users' real-time gestures, including swipe direction, touch trajectory, or click location.

[0065] Capture user voice commands through microphones and speech recognition technology.

[0066] In the above embodiments, the interaction recognition module captures the user's gestures and voice commands in real time using sensor and voice recognition technologies. This information provides rich material for the analysis of user behavior data. By analyzing this data, the system can more accurately understand the user's operational intentions and needs, thereby providing more tailored recommended content.

[0067] The intelligent recommendation module considers users' past frequency of menu usage, preferred locations, and current usage frequency when adjusting the layout. This is feasible because modern user interface design widely employs dynamic layout and adaptive adjustment technologies, which can optimize the interface layout and display based on user behavior and preferences. By recording and analyzing user interactions such as clicks and swipes on menu items, the intelligent recommendation module learns user habits and dynamically adjusts the order and display position of menu items in subsequent recommendations.

[0068] In this embodiment, the intelligent recommendation module adjusts the layout of the target menu items, including:

[0069] The menu items within the target menu are sorted by dynamic usage frequency, which includes past usage frequency and real-time usage frequency. The real-time usage frequency is dynamically counted by the click position, touch trajectory, and number of voice command triggers captured by the interaction recognition module.

[0070] The display position of the target menu item is based on the user's past habitual position of the menu, and is subsequently adjusted based on real-time user behavior. The subsequent adjustment is to dynamically adjust the position of the menu item in the interface based on real-time gestures and voice commands captured by the interaction recognition module.

[0071] In the above embodiments, the intelligent recommendation module, when adjusting the layout, not only considers the user's past frequency of use and preferred positions for the menu items, but also dynamically sorts them based on real-time usage frequency. This adjustment method makes the order of recommended menu items more in line with the user's current usage needs and behavioral habits. Furthermore, by adjusting the display positions based on real-time user behavior, the personalization and applicability of the recommendations can be further improved.

[0072] For example, if a user frequently clicks on the "Online Classroom" and "Educational Information" menu items and habitually places them at the top of the screen, the intelligent recommendation module can place these two menu items in a more prominent position when generating recommended menus, thereby improving user access efficiency and satisfaction. Simultaneously, if real-time user behavior data shows that the user is frequently swiping the screen to find the "Interactive Q&A" menu item, the intelligent recommendation module can dynamically adjust "Interactive Q&A" to a position closer to the user's current focus.

[0073] Please see Figure 3 Another embodiment of the present invention provides a menu recommendation method, applied to a live streaming menu recommendation system based on different professions as described in the above-mentioned embodiment. For ease of understanding, an application scenario and corresponding method steps of the relevant method are described below:

[0074] S1: Users securely access the system through the role recognition module using biometric technology or user account login. The system collects and analyzes the user's role information, which includes the menu interaction habits of the user's professional group and professional-specific menus.

[0075] For example, if user A is a teacher, after logging into the system using facial recognition technology, the role recognition module identifies his profession as a teacher and collects the teacher's menu interaction habits (such as frequent use of the "upload courseware" and "classroom management" functions) as well as profession-specific menus (such as "classroom interaction tools" and "homework correction").

[0076] S2: The interaction recognition module captures and analyzes the user's dynamic environment information, including capturing the user's real-time gestures and voice commands to obtain real-time user behavior data, monitoring the user's operation behavior data on the live streaming platform to determine the current usage scenario type, thereby obtaining real-time usage scenario characteristics.

[0077] For example, user A frequently clicks the "Upload Courseware" button on the live streaming platform and uses the voice command "Open Classroom Interaction Tool". The interaction recognition module analyzes that the current usage scenario is "online teaching".

[0078] S3: The intelligent recommendation module uses the user's occupation-specific menu and real-time usage scenario characteristics to calculate and compare the matching degree of each menu item with the current scenario and the similarity of the occupation-specific menu, and selects highly relevant menu items from the menu database as target menu items.

[0079] For example, the intelligent recommendation module calculates the matching degree between "Courseware Upload" and "Classroom Interaction Tools" and the "Online Teaching" scenario, and selects highly relevant menu items such as "Courseware Upload", "Classroom Interaction Tools", and "Homework Grading" as target menu items.

[0080] S4: The intelligent recommendation module further combines users' menu interaction habits and real-time user behavior data, dynamically sorts the positions of each menu item in the recommended menu based on real-time usage frequency, and then adjusts the menu display position based on users' past habitual positions of the menu and real-time user behavior data.

[0081] For example, if user A frequently uses the "Courseware Upload" function in the past, and real-time gestures show that they frequently click the "Courseware Upload" button, the intelligent recommendation module will place the "Courseware Upload" function at the top of the menu and adjust the positions of "Classroom Interaction Tools" and "Homework Grading" based on real-time gestures to make them more in line with the user's operating habits.

[0082] Step 5: The controller responds to the user's selection command for the recommended menu items, executes the corresponding function operation, and provides the user with a smooth live menu recommendation experience.

[0083] For example, when user A clicks the "Upload Courseware" button, the controller executes the courseware upload function, thereby achieving accurate recommendations for the live broadcast menu.

[0084] It is evident that the entire menu recommendation process, including menu selection and layout, is highly convenient. Furthermore, it can dynamically recommend menus based on user A's real-time and historical operations, achieving personalized live stream menu recommendations based on user's professional identity and real-time operation scenarios. This not only enhances the user experience but also meets the exclusive functional needs of different professional groups, improves user satisfaction, and provides strong support for the professional development of live streaming platforms.

[0085] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A live streaming menu recommendation system based on different professions, characterized in that, include: The intelligent recommendation module is connected to the role recognition module, the interaction recognition module, the controller, and the menu database, respectively. The role recognition module is used to identify the user's professional identity and collect role information, which includes the menu interaction habits of the user's professional group and professional-specific menus. The interaction recognition module is used to capture and analyze the user's dynamic environment information, which includes real-time user behavior data and real-time usage scenario characteristics. The intelligent recommendation module is configured to execute: Based on the specific menu for the profession and the characteristics of real-time usage scenarios, target menu items are filtered from the menu database; Based on the menu interaction habits and real-time user behavior data, the layout of the target menu items is adjusted and output as recommended menu items; The controller is used to respond to the user's selection command for the recommended menu item and execute the corresponding function operation.

2. The live streaming menu recommendation system based on different professions according to claim 1, characterized in that: The role recognition module verifies professional identity through biometric recognition technology or user account login information.

3. The live streaming menu recommendation system based on different professions according to claim 1, characterized in that: The occupational special menu is a set of configurable menus customized according to the work needs of different occupational groups, and supports users to add or delete menu options in a personalized way.

4. The live streaming menu recommendation system based on different professions according to claim 3, characterized in that: The interaction recognition module analyzes real-time usage scenario characteristics in the following ways: Monitor user behavior data on live streaming platforms and determine the current usage scenario type through behavior pattern analysis; Behavioral patterns include function button click records, form filling records, and video viewing records.

5. A live streaming menu recommendation system based on different professions according to claim 4, characterized in that: The intelligent recommendation module performs the following when filtering target menu items: The matching degree between the functional description of each menu item in the menu database and the current usage scenario type is used as the scenario relevance. The similarity between the functional descriptions of each menu item in the menu database and the functional description set of the configurable menu set is used as the occupational relevance. Based on the weighted calculation of occupational relevance and scenario relevance, target menu items that reach the threshold of comprehensive score are selected.

6. The live streaming menu recommendation system based on different professions according to claim 1, characterized in that: The menu interaction habits include the user's past frequency of using the menu and the user's past habitual positions on the menu.

7. A live streaming menu recommendation system based on different professions according to claim 6, characterized in that: The interaction recognition module analyzes real-time user behavior data including: The system uses sensor technology to capture users' real-time gestures, including swipe direction, touch trajectory, or click location. Capture user voice commands through microphones and speech recognition technology.

8. A live streaming menu recommendation system based on different professions according to claim 7, characterized in that: The intelligent recommendation module adjusts the layout of the target menu items, including: The menu items within the target menu are sorted by dynamic usage frequency, which includes past usage frequency and real-time usage frequency. The real-time usage frequency is dynamically counted by the click position, touch trajectory, and number of voice command triggers captured by the interaction recognition module. The display position of the target menu item is based on the user's previously used position of the menu, and is subsequently adjusted based on real-time user behavior. The subsequent adjustment is to dynamically adjust the position of the menu item in the interface based on real-time gestures and voice commands captured by the interaction recognition module.

9. A menu recommendation method, applied to a live-streaming menu recommendation system based on different professions as described in any one of claims 1 to 8, characterized in that, Includes the following steps: Step 1: Users securely access the system through the role recognition module using biometric technology or user account login. The system collects and analyzes the user's role information, which includes the menu interaction habits of the user's professional group and professional-specific menus. Step 2: The interaction recognition module captures and analyzes the user's dynamic environment information, including capturing the user's real-time gestures and voice commands to obtain real-time user behavior data, monitoring the user's operation behavior data on the live streaming platform to determine the current usage scenario type, thereby obtaining real-time usage scenario characteristics. Step 3: The intelligent recommendation module, based on the user's occupation-specific menu and real-time usage scenario characteristics, calculates and compares the matching degree of each menu item with the current scenario and the similarity of the occupation-specific menu, and selects highly relevant menu items from the menu database as target menu items. Step 4: The intelligent recommendation module further combines users' menu interaction habits and real-time user behavior data, dynamically sorts the positions of each menu item in the recommended menu based on real-time usage frequency, and then adjusts the menu display position based on users' past habitual positions of the menu and real-time user behavior data. Step 5: The controller responds to the user's selection command for the recommended menu items, executes the corresponding function operation, and provides the user with a smooth live menu recommendation experience.

Images