A product display interaction method and system based on virtual reality technology

Abstract

The present application provides a product display interaction method and system based on virtual reality technology, including: establishing a consumer portrait according to the identity information of the consumer, including the basic attributes of the consumer, determining AR content and interactive programs through attribute matching, and pushing them to the consumer's personal terminal; obtaining the consumer's current scene information, identifying the type and characteristics of the current scene, and adjusting the interactive program according to preset scene adaptation rules; when the consumer performs a sharing operation, obtaining the social relationship and tag attributes between the sharing object and the consumer, dividing the sharing object into different user types, and determining the corresponding AR content sharing method according to the different user types; obtaining the sharing location of the sharing operation, judging the correlation between the sharing location and the AR content through a geographic location matching algorithm, and dynamically adjusting the shared AR content; obtaining the time information of the sharing operation, and dynamically adjusting the shared AR content.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a product display interaction method and system based on virtual reality technology. Background Art

[0002] When consumers use AR interactive functions, how to reasonably restrict and personalize AR content according to different scenarios and users is a technical issue worthy of in-depth discussion. The generation and presentation of AR content needs to take into account the current usage scenario, such as the user's location, time and other factors, and dynamically adjust the AR content according to these factors to provide an AR experience that is more in line with the current scenario. The display of AR content should also be differentiated for different types of users. For users of different ages, genders, interests and hobbies, the display method and interactive form of AR content should be designed in a targeted manner to meet the personalized needs of different users. When displaying different products in AR scenes, it is also necessary to consider the type and characteristics of the products and reasonably restrict the display and interaction of products. When users share products in AR scenes, they also need to process and present AR content according to different sharing objects. In short, how to flexibly adjust and adapt AR content according to multiple factors such as scenarios, users, and products in AR interactions is a complex and interesting technical issue that requires continuous exploration and optimization in practice. Summary of the invention

[0003] The present invention provides a product display interaction method based on virtual reality technology, which mainly includes:

[0004] Based on the consumer's identity information, a consumer portrait is created, including the consumer's basic attributes. Through attribute matching, AR content and interactive programs are determined and pushed to the consumer's personal terminal;

[0005] Obtain the consumer's current scene information, identify the type and characteristics of the current scene, and adjust the interactive program according to the preset scene adaptation rules;

[0006] When a consumer performs a sharing operation, the social relationship and tag attributes between the sharing object and the consumer are obtained, the sharing object is divided into different user types, and the corresponding AR content sharing method is determined according to the different user types;

[0007] Get the sharing location of the sharing operation, determine the relevance of the sharing location and AR content through the geographic location matching algorithm, and dynamically adjust the shared AR content;

[0008] Get the time information of the sharing operation and dynamically adjust the shared AR content;

[0009] In AR scenarios, users’ interactive behavior data is obtained, and through user behavior analysis algorithms, users’ interaction preferences for different product types are determined. Based on the differences in interaction preferences, the display and interaction of AR products are dynamically adjusted.

[0010] Comprehensively analyze multi-dimensional data, including user attributes, scene information, sharing objects, location information, time information, and product types, and build an AR content recommendation model through machine learning algorithms to achieve intelligent AR content recommendation based on multi-dimensional data.

[0011] Further optionally, the process of establishing a consumer portrait based on the consumer's identity information, including the consumer's basic attributes, determining AR content and interactive programs through attribute matching, and pushing them to the consumer's personal terminal includes:

[0012] Obtain basic consumer attribute data, including age group, gender, occupation category and consumption level, and make preliminary classification of consumers; conduct in-depth mining of consumers' shopping history and browsing preferences through big data analysis, and extract personalized demand information, including brand preferences and product preferences; analyze consumers' mobility patterns and application preferences in combination with consumers' geographic location information and mobile device usage habits, and predict consumers' consumption scenarios; identify consumers' consumption characteristics based on preliminary classification, personalized demand information and consumption scenarios; through the content recommendation system, screen out AR content and interactive programs in inventory that match consumption characteristics; adjust the format and resolution of AR content and interactive programs according to the device compatibility and technical parameters of consumers' personal terminals; push the adjusted AR content and interactive programs to consumers' personal terminals; monitor consumers' reactions and interactions to pushed content through the user feedback collection module, and collect effect data; use data analysis tools to evaluate the collected effect data.

[0013] Further optionally, the acquiring of the current scene information of the consumer, identifying the type and characteristics of the current scene, and adjusting the interactive program according to a preset scene adaptation rule includes:

[0014] Through the consumer's personal terminal, obtain information about the consumer's environment, including light intensity, temperature and humidity, and noise level, and obtain scene information; identify the type of the current scene, and if the scene information indicates that the user is in a low-light and silent state, determine that the scene type is a night home environment; identify the characteristics of the current scene through the consumer's personal terminal, including: judging the user's mood and health status based on the personal terminal's front camera or the physiological sensors of the associated wearable device, including heart rate monitoring; if the user's mood and health status monitoring indicates that the user is tired or unhealthy, reduce the interactive content of the interactive program; test the quality of the network connection, obtain speed and stability indicators through network diagnostic tools, and adjust the content size of the interactive program; identify surrounding connectable smart devices, including smart bulbs and speakers, and obtain their status information through the Bluetooth or Wi-Fi scanning function of the personal terminal; when the status information of the smart device is available, add the connection interaction of the smart device to the interactive program; provide a configuration interface to obtain the adjustment parameters of the interactive program entered by the consumer, and adjust the interactive program based on the adjustment parameters.

[0015] Further optionally, when the consumer performs a sharing operation, the social relationship and tag attributes between the sharing object and the consumer are obtained, the sharing object is divided into different user types, and the corresponding AR content sharing method is determined according to the different user types, including:

[0016] Through social media analysis tools, the interaction records and personal information between consumers and sharing objects are captured; the obtained interaction records are analyzed to determine the intimacy and interaction frequency of the relationship, and the type of social relationship is identified, including family, close friends, acquaintances, colleagues or netizens; the user's personal information is processed, the interests, hobbies, age group, and gender are analyzed, and the user's label attributes are identified; according to social relationships and label attributes, decision trees or clustering algorithms are applied to divide sharing objects into different user types, including close users, social users, interest users, influential users, educational users, and work users; according to the user type and label attributes of the sharing object, the sharing method of AR content is generated, including generating stimulating AR content sharing for interest users and providing educational AR content sharing for educational users; through the historical sharing records between the sharing object and the consumer, the generation parameters of the AR content sharing method are optimized.

[0017] Further optionally, obtaining the sharing location of the sharing operation, determining the relevance between the sharing location and the AR content through a geographic location matching algorithm, and dynamically adjusting the shared AR content includes:

[0018] Obtain the sharing location of the sharing operation, including the geographic location information of the consumer and the sharing object, and obtain the sharing distance; through the environmental context perception system, search for POI information around the sharing object to obtain sharing environment feature data; determine the correlation between the AR content and the sharing location based on the sharing distance and sharing environment feature data; determine the movement speed and behavior pattern of the sharing object based on the distribution of the geographic location information of the sharing object in the time series, including walking or riding, and adjust the display method of the shared AR content.

[0019] Further optionally, the acquiring time information of the sharing operation and dynamically adjusting the shared AR content includes:

[0020] Obtain time information of the sharing operation, including the sharing time of the consumer's personal terminal and the predicted receiving time of the shared AR content by the sharing object; determine the time correlation between the sharing operation and the AR content based on the sharing time and the predicted receiving time; if the time correlation or the correlation between the sharing location and the AR content is lower than a threshold, optimize the shared AR content in a time-related or sharing location-related direction, including adding time-related or sharing location-related AR content.

[0021] Further optionally, in the AR scene, obtaining the user's interaction behavior data, judging the user's interaction preferences for different product types through a user behavior analysis algorithm, and dynamically adjusting the display and interaction of the AR product according to the difference in interaction preferences, includes:

[0022] Collect user interaction behavior data through the sensors and interfaces of AR applications, including touch, click, gesture and gaze tracking, and record the corresponding timestamps; use time series analysis methods to process user interaction data and timestamps to identify the interaction preferences of user interaction behaviors; count the number and duration of user interactions with each product in the AR scene to determine the user's interest in each type of product; adjust the display and interaction methods of AR products based on user interaction data and product type information, and use personalized algorithm parameters to achieve precise and personalized AR experience.

[0023] Further optionally, the multi-dimensional data, including user attributes, scene information, sharing objects, location information, time information, and product types, is comprehensively analyzed, and an AR content recommendation model is constructed through a machine learning algorithm to achieve intelligent recommendation of AR content based on multi-dimensional data, including:

[0024] Obtain user attribute data, including age, gender, occupation and hobbies, through user login information; identify the user's AR content interaction history based on the user's historical behavior records, and collect the user's explicit preference information through questionnaires and user feedback mechanisms; use environmental perception to capture the user's current scene information in real time, including indoor and outdoor environments, lighting conditions, surrounding objects and scenery features, and environmental noise levels; use location services to obtain the user's geographic location information, including latitude and longitude, place name and nearby points of interest (POI), to determine the type of geographical environment the user is in; record the time information of the user's interactive AR content through the device's time service function, including the current time, date, day of the week, as well as seasonal changes and special dates or events; analyze the social relationship between the user and the sharing object, and adjust the recommended content to adapt to different social scenarios and the user's social intentions according to the different sharing objects; use historical interaction data and user feedback to identify the user's preference for different AR content types based on the user's product type interests; collect parameter data of the user's device, including device type, processor speed, graphics processing capability and sensor type, to evaluate the compatibility of recommended AR content; analyze multi-dimensional data through machine learning algorithms, establish an AR content recommendation model, and predict and recommend personalized AR content.

[0025] The present invention provides a product display interactive system based on virtual reality technology, which mainly includes:

[0026] User portrait building module, used to analyze consumers’ basic attributes and preferences to customize personalized AR content;

[0027] A scene adaptation adjustment module, which is used to adjust the interactive program and AR display according to the consumer's current environment;

[0028] Social relationship analysis module, used to personalize shared content based on the social tags and relationships of sharers;

[0029] Location information matching module, used to adjust the shared AR content and relevance based on geographic location;

[0030] Time information analysis module, used to dynamically adjust the pushed AR content according to the time of sharing;

[0031] AR content recommendation engine, used to comprehensively analyze multi-dimensional data and intelligently recommend personalized AR experiences.

[0032] The technical solution provided by the embodiment of the present invention may have the following beneficial effects:

[0033] The present invention discloses a product display interaction method based on virtual reality technology. The unique business scenario problem is how to provide an augmented reality experience that is both personalized and highly relevant to the user's current environment under the condition of variable influencing factors such as different identity information of users, scene characteristics, time periods and product attributes. The present invention constructs an intelligent recommendation model through multi-dimensional data analysis and machine learning algorithms in complex environments, which can provide users with an augmented reality experience that is highly personalized and closely related to their actual environment. This not only improves the user's interactive experience and satisfaction, but also provides brands and enterprises with precise marketing tools to achieve higher user engagement and brand loyalty. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 The present invention is a flowchart of a product display interaction method based on virtual reality technology.

[0035] Figure 2 It is a schematic diagram of a product display interaction method and system based on virtual reality technology of the present invention.

[0036] Figure 3 This is another schematic diagram of a product display interaction method and system based on virtual reality technology of the present invention. DETAILED DESCRIPTION

[0037] The following will describe the technical solutions in the embodiments of the present invention in detail in conjunction with the accompanying drawings in the embodiments of the present invention. The described embodiments are only part of the embodiments of the present invention.

[0038] like Figure 1-3 In this embodiment, a product display interaction method and system based on virtual reality technology may specifically include:

[0039] S101. Create a consumer portrait based on the consumer's identity information, including the consumer's basic attributes. Through attribute matching, determine the AR content and interactive program, and push them to the consumer's personal terminal.

[0040] Obtain basic consumer attribute data, including age group, gender, occupation category and consumption level, and make preliminary classification of consumers. Through big data analysis, conduct in-depth mining of consumers' shopping history and browsing preferences, and extract personalized demand information, including brand preferences and product preferences. Combine consumers' geographic location information and mobile device usage habits to analyze consumers' mobility patterns and application preferences, and predict consumers' consumption scenarios. Based on preliminary classification, personalized demand information and consumption scenarios, identify consumers' consumption characteristics. Through the content recommendation system, screen out AR content and interactive programs in inventory that match consumption characteristics. Adjust the format and resolution of AR content and interactive programs according to the device compatibility and technical parameters of consumers' personal terminals. Push the adjusted AR content and interactive programs to consumers' personal terminals. Through the user feedback collection module, monitor consumers' reactions and interactions to the pushed content and collect effect data. Use data analysis tools to evaluate the collected effect data.

[0041] For example, a basic attribute data set of user A is being processed. User A is a male aged 25-34, a software engineer, with a monthly consumption level of US$2,000-3,000, and is initially classified as a high-spending group. Further, through big data analysis of user A's shopping history and browsing data, user A's brand preference is Apple, product preference is electronic products, and there is a high purchase frequency in the electronic product category, especially preferring smartphones and smart watches. Combined with user A's geographic location information, such as user A often moves in Manhattan, New York, and user A's mobile device usage habits, such as user A uses the phone for a total of 4 hours during non-working hours on weekdays, it can be analyzed that user A consumes on the way to commute or in restaurants. Using machine learning algorithms, such as decision trees or clustering algorithms, user A's consumption characteristics can be identified. For example, it is identified that user A has an 80% probability of shopping online during lunch breaks on weekdays. Through the content recommendation system, AR content and interactive programs that match user A's consumption characteristics can be screened out. The recommendation system can select an interactive AR game related to smart watches from the inventory because this meets user A's preference for smart wearable devices. Assuming that user A's device is the latest iPhone, which supports high resolution and advanced AR functions, the format and resolution of AR content and interactive programs will be adjusted to ensure the best experience. AR games need to run at 1080p resolution and 60fps to avoid delays. After pushing the adjusted AR content and interactive programs to user A's personal terminal, monitor user A's reaction through the user feedback collection module. The average interaction time of user A in the game is 10 minutes, which reflects the level of interest of user A in this content. Finally, use data analysis tools to evaluate the effect data. By analyzing user A's click-through rate on the pushed content, it is specifically 30%, which is 10 percentage points higher than the average level, indicating that the content recommendation is very successful.

[0042] S102: Obtain the consumer's current scene information, identify the type and characteristics of the current scene, and adjust the interactive program according to preset scene adaptation rules.

[0043] Through the consumer's personal terminal, obtain information about the consumer's environment, including light intensity, temperature and humidity, and noise level, and obtain scene information. Identify the type of the current scene. If the scene information indicates that the user is in a low-light and silent state, the scene type is determined to be a night home environment. Identify the characteristics of the current scene through the consumer's personal terminal, including: judging the user's mood and health status based on the personal terminal's front camera or the physiological sensors of the associated wearable device, including heart rate monitoring; if the user's mood and health status monitoring indicates that the user is tired or the user is unhealthy, reduce the interactive content of the interactive program. Test the quality of the network connection, obtain speed and stability indicators through the network diagnostic tool, and adjust the content size of the interactive program; identify the surrounding connectable smart devices, including smart bulbs and speakers, and obtain their status information through the Bluetooth or Wi-Fi scanning function of the personal terminal; when the status information of the smart device is available, add the connection interaction of the smart device to the interactive program. Provide a configuration interface to obtain the adjustment parameters of the interactive program entered by the consumer, and adjust the interactive program based on the adjustment parameters.

[0044] For example, suppose a consumer is using a smartphone or tablet computer, which has multiple sensors built in to obtain a variety of environmental information. The light sensor of the personal terminal shows that the current light intensity is 150 lux (lx), which is a relatively low light intensity, usually indicating that the environment is at night or the indoor lighting is dim. The temperature and humidity sensor of the terminal shows that the current room temperature is 22°C and the relative humidity is 60%, which is a comfortable living environment for most people. The microphone of the terminal measures the ambient noise level as 30 decibels (dB), which usually means a very quiet environment. With the help of the wearable device, the user's heart rate is monitored as 80 beats per minute, which to some extent indicates that the user is in a relaxed state, but if the user's average heart rate is usually 60 beats / minute, it means that the user feels a little tired or has slight stress. Through the network diagnostic tool, the test results show that the current network download speed is 5Mbps, the upload speed is 1Mbps, and the packet loss rate is 2%, which indicates that the network connection quality is average and the data transmission volume of the interactive program needs to be reduced to ensure a smooth experience. After Bluetooth scanning, a smart light bulb is found to be connectable and its status is available. The smart speaker is also identified as available and the current volume is set to 30%. Add the connection operation of smart bulbs and smart speakers to the interactive program, and add the output operation of outputting AR content through smart bulbs and smart speakers. Consumers set the brightness mode of the interactive program to the eye-pleasing mode through the configuration interface to reduce eye pressure.

[0045] S103: When a consumer performs a sharing operation, the social relationship and tag attributes between the sharing object and the consumer are obtained, the sharing object is divided into different user types, and corresponding AR content sharing methods are determined according to the different user types.

[0046] Through social media analysis tools, capture the interaction records and personal information between consumers and sharing objects. Analyze the obtained interaction records to determine the intimacy and interaction frequency of the relationship, and identify the type of social relationship, including family, close friends, acquaintances, colleagues or netizens. Process the user's personal information, analyze interests, hobbies, age groups, and gender, and identify the user's tag attributes. According to social relationships and tag attributes, apply decision trees or clustering algorithms to divide sharing objects into different user types, including close users, social users, interest users, influential users, educational users, and work users. Generate AR content sharing methods based on the user type and tag attributes of the sharing object, including generating stimulating AR content sharing for interest users and providing educational AR content sharing for educational users. Optimize the generation parameters of AR content sharing methods through historical sharing records between sharing objects and consumers.

[0047] For example, in the social media analysis tool, a consumer and a sharing object have 30 interaction records in the past month, including 15 likes, 10 comments, and 5 direct message exchanges. Personal information collection shows that the sharing object mentioned family activities and work experience. Through the analysis of data mining technology, it is judged that the intimacy of this relationship is high and the interaction frequency is relatively frequent, so this social relationship is classified as a colleague relationship. Further, using natural language processing and classification algorithms, a series of label attributes are extracted from the personal information of the sharing object. The user's personal information mentioned football, movies, and travel many times, so the user is labeled as "football lover", "movie fan" and "travel lover". Through the analysis of the birthday information provided by the user, it is judged that the user is in the age group of 25-34 years old, and the gender is inferred to be male based on the avatar and name. When the decision tree algorithm is used to divide the sharing objects into different user types, based on the interaction frequency and intimacy, this colleague belongs to the "close user" type. At the same time, according to the hobby tags, it can also be classified as an "interest user". Then, according to the type of this user, the generated AR content sharing method will be personalized. For example, a virtual football scene is designed for this user who is interested in "football lover" and "travel lover", allowing users to conduct virtual tours and interactions in world-famous football stadiums, thereby creating a stimulating AR content sharing experience. By analyzing the historical sharing records between this consumer and the sharing object, when the shared AR content is combined with football elements, the number of interactions increases by 20%. Based on this, the generation parameters of the AR content sharing method are adjusted to add football-related elements in future sharing methods.

[0048] S104: Obtain a sharing location of the sharing operation, determine the relevance of the sharing location to the AR content through a geographic location matching algorithm, and dynamically adjust the shared AR content.

[0049] Get the sharing location of the sharing operation, including the geographic location information of the consumer and the sharing object, and get the sharing distance. Through the environmental context perception system, search for POI information around the sharing object to obtain the sharing environment feature data. Determine the relevance of the AR content to the sharing location based on the sharing distance and sharing environment feature data. According to the distribution of the geographic location information of the sharing object in the time series, judge the movement speed and behavior pattern of the sharing object, including walking or riding, and adjust the display mode of the shared AR content.

[0050] For example, consumer A is located at longitude and latitude (30522°N, 112437°W), and sharing object B is located at longitude and latitude (30522°N, 112430°W). Using the Haversine formula to calculate the distance between two points on the earth, it can be concluded that the straight-line distance between consumer A and sharing object B is about 77 meters. The POI search around sharing object B shows that there is a cafe 20 meters away, a bookstore 50 meters away, and a park 100 meters away. By analyzing these POI data, it can be evaluated that the environmental characteristics of sharing object B are a leisure and entertainment area. If the AR content is associated with historical masterpieces, and there is a bookstore within 50 meters around the location of sharing object B, then the correlation between this AR content and the sharing location can be rated as high. By analyzing the distribution of the geographic location information of sharing object B in the past 5 minutes, it can be observed that its location has changed from (30522°N, 112437°W) to (30490°N, 112500°W), with a total distance of about 900 meters. If it is assumed that the movement is uniform, the average walking speed can be calculated to be about 180 meters / minute, which can be identified as riding in a car through statistical analysis. Therefore, the AR system can adjust the stability and follow-up speed of the content display to ensure that the occupants can easily view the AR content while moving, such as reducing the movement speed of the AR object, increasing the display time of the AR content, or simplifying the content to avoid distraction.

[0051] S105: Obtain time information of the sharing operation, and dynamically adjust the shared AR content.

[0052] Obtain the time information of the sharing operation, including the sharing time of the consumer's personal terminal and the predicted receiving time of the shared AR content received by the sharing object. Determine the time correlation between the sharing operation and the AR content based on the sharing time and the predicted receiving time. If the time correlation or the correlation between the sharing location and the AR content is lower than the threshold, optimize the shared AR content in the direction of time correlation or sharing location correlation, including adding time-related or sharing location-related AR content.

[0053] For example, in a sharing operation scenario, user A uses his smartphone to share an AR display of a New Year's countdown clock in Times Square, New York at 3 p.m. (15:00). 15:00, April 1, 2023 (recorded by user A's terminal device) Then, the application predicts that user B will receive the shared AR content at 3:10 p.m. (15:10), which is the predicted reception time calculated based on factors such as user B's current online status and network latency. Predicted reception time information: 15:10, April 1, 2023 (prediction based on network conditions) In order to determine the time relevance of the sharing operation and the AR content, the difference between the two time points is analyzed, which is 10 minutes in this example. Because the New Year's countdown is more than 6 months away from user B's reception time (15:10, April 1, 2023), the time relevance of the AR content of this sharing operation is determined to be low. Low time relevance Because the time relevance is lower than the threshold, the system will automatically optimize the shared AR content to improve the time relevance. For example, the system can add a real-time countdown to show how many days and hours are left until the New Year, specifically, the real-time countdown "X days, Y hours, and Z minutes left until the New Year 2024". In addition, if it is found that the correlation between the shared location and the AR content is also below the set threshold, the system will also optimize in this direction. If user B is actually in Los Angeles instead of New York, consider the time zone difference and adjust the countdown in the AR content to reflect the local time in Los Angeles.

[0054] S106. In an AR scenario, obtain the user's interaction behavior data, determine the user's interaction preferences for different product types through a user behavior analysis algorithm, and dynamically adjust the display and interaction of AR products based on the differences in interaction preferences.

[0055] Collect user interaction behavior data through the sensors and interfaces of the AR application, including touch, click, gesture and gaze tracking, and record the corresponding timestamps. Use time series analysis methods to process user interaction data and timestamps to identify the interaction preferences of user interaction behaviors. Count the number and duration of user interactions with each product in the AR scene to determine the user's interest in each type of product. Adjust the display and interaction methods of AR products based on user interaction data and product type information, and use personalized algorithm parameters to achieve precise and personalized AR experience.

[0056] For example, the number of times a user clicks on a specific product can be counted through the touch and interface sensors integrated into the AR application. For example, when viewing a shoe displayed in AR, the user clicks on different color options 5 times, trying to see different color combinations. By integrating eye tracking technology, the area where users spend the most time in the AR environment is evaluated. Eye tracking data shows that users gazed at a particular watch for 20 seconds in a 30-second session, indicating a high interest in this product. Analysis of the collected time series interaction data can identify users' interaction preferences. Users usually stay on each product for about 10 seconds when browsing products, but when users encounter high-interest products, the stay time increases to more than 30 seconds. Count the number and duration of user interactions with each product in the AR scene. The average number of interactions between users and furniture products is 15 times, with an average duration of 2 minutes, while the average number of interactions with electronic products is 30 times, with an average duration of 3 minutes, indicating that users have a higher level of interest in electronic products. Use classification algorithms to analyze user interaction data with product types. Through the decision tree classification algorithm, it can be found that users are usually more willing to interact with entertainment AR products in their spare time in the afternoon. Use user preferences to adjust the display and interaction methods of AR products. For example, if the user's interaction preference is eye tracking, increase the contrast of AR content and increase the proportion of bright colors to achieve a personalized user experience.

[0057] S107. Comprehensively analyze multi-dimensional data, including user attributes, scene information, sharing objects, location information, time information, and product types, and build an AR content recommendation model through a machine learning algorithm to achieve intelligent recommendation of AR content based on multi-dimensional data.

[0058] Obtain user attribute data, including age, gender, occupation, and hobbies, through user login information. Identify the user's AR content interaction history based on the user's historical behavior records, and collect the user's explicit preference information through questionnaires and user feedback mechanisms. Use environmental perception to capture the user's current scene information in real time, including indoor and outdoor environments, lighting conditions, surrounding objects and scenery features, and environmental noise levels. Use location services to obtain the user's geographic location information, including latitude and longitude, place name, and nearby points of interest (POI) to determine the type of geographical environment the user is in. Record the time information of the user's interactive AR content through the device's time service function, including the current time, date, day of the week, as well as seasonal changes and special dates or events. Analyze the social relationship between the user and the sharing object, and adjust the recommended content to adapt to different social scenarios and the user's social intentions based on the different sharing objects. Based on the user's product type interests, use historical interaction data and user feedback to identify the user's preferences for different AR content types. Collect parameter data of the user's device, including device type, processor speed, graphics processing capabilities, and sensor type, to evaluate the compatibility of recommended AR content. Through machine learning algorithms, multi-dimensional data is analyzed to establish an AR content recommendation model to predict and recommend personalized AR content.

[0059] For example, when obtaining user attribute data, it is found that a user is a 35-year-old female, a software engineer, and her hobbies include travel and photography. In terms of identifying the user's AR content interaction history, it is observed that the user interacted with AR games three times a week on average in the past month, with an average interaction time of 25 minutes each time. Through the user feedback mechanism, for example, a user expressed a high interest in historical AR content in the questionnaire, scoring 7 (out of 5). The user is currently in an indoor environment captured in real time using environmental perception technology, with medium lighting conditions (about 500 lux) and low ambient noise levels (about 30 decibels). The geographic location information obtained using location services indicates that the user is located in the center of New York City, with longitude and latitude of 47128°N, 70060°W, and nearby points of interest include Times Square and Central Park. According to the information recorded by the device's time service function, for example, the user interacted with AR at 3 pm on the weekend, which was in spring and close to the Easter holiday. Users share AR content about the latest technology with colleagues on weekdays, while on weekends they are more inclined to share AR experiences about travel destinations with their families. Through historical interaction data, it was found that users have a clear preference for shopping AR content, including virtual fitting, and the average browsing time is 15 minutes. The collected technical parameter data includes that the user's smartphone is the latest model of iPhone, with an A14 bionic chip, advanced graphics processing, and equipped with a variety of sensors such as gyroscopes and accelerometers. Based on the user's behavior and attribute data, the algorithm predicts that the user is 85% likely to be interested in the upcoming travel AR game. Therefore, the AR content recommendation model will recommend this game to the user to enhance the interactive experience.

[0060] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

[0061] This disclosure includes but is not limited to personal or private information and user data. Before collecting and processing personal or private information and user data, the application of this disclosure has clearly informed the personal information processing rules, and obtained the individual's voluntary consent to authorize data collection and processing, and at the same time met the "explicit consent" requirements, and at the same time, the collection and processing are within the scope of laws and regulations.

Claims

1. A product display interaction method based on virtual reality technology, characterized in that: The method comprises: Based on the consumer's identity information, a consumer portrait is created, including the consumer's basic attributes. Through attribute matching, AR content and interactive programs are determined and pushed to the consumer's personal terminal; Obtain the consumer's current scene information, identify the type and characteristics of the current scene, and adjust the interactive program according to the preset scene adaptation rules; When a consumer performs a sharing operation, the social relationship and tag attributes between the sharing object and the consumer are obtained, the sharing object is divided into different user types, and the corresponding AR content sharing method is determined according to the different user types; the user types include interest users and educational users; Get the sharing location of the sharing operation, determine the relevance of the sharing location and AR content through the geographic location matching algorithm, and dynamically adjust the shared AR content; Get the time information of the sharing operation and dynamically adjust the shared AR content; In AR scenarios, users’ interactive behavior data is obtained, and through user behavior analysis algorithms, users’ interaction preferences for different product types are determined. Based on the differences in interaction preferences, the display and interaction of AR products are dynamically adjusted. Comprehensively analyze multi-dimensional data, including user attributes, scene information, sharing objects, location information, time information, and product types, and build an AR content recommendation model through machine learning algorithms to achieve intelligent AR content recommendation based on multi-dimensional data; When the consumer performs a sharing operation, the social relationship and tag attributes between the sharing object and the consumer are obtained, the sharing object is divided into different user types, and the corresponding AR content sharing methods are determined according to the different user types, including: generating stimulating AR content sharing for interested users and providing educational AR content sharing for educational users; The obtaining of the sharing location of the sharing operation, determining the relevance between the sharing location and the AR content through a geographic location matching algorithm, and dynamically adjusting the shared AR content includes: Get the sharing location of the sharing operation, including the geographic location information of the consumer and the sharing object, and get the sharing distance; Through the environmental context perception system, POI information is searched around the sharing object to obtain the sharing environment feature data; Determine the relevance of the AR content to the sharing location based on the sharing distance and sharing environment feature data; According to the distribution of the shared object's geographic location information in the time series, the moving speed and behavior pattern of the shared object, including walking or riding, are judged, and the display mode of the shared AR content is adjusted; The obtaining of time information of the sharing operation and dynamically adjusting the shared AR content includes: Obtaining the time information of the sharing operation, including the sharing time of the consumer's personal terminal and the predicted receiving time of the shared AR content by the sharing object; Determine the time correlation between the sharing operation and the AR content based on the sharing time and the predicted receiving time; If the time correlation or the correlation between the sharing location and the AR content is lower than a threshold, the shared AR content is optimized in a direction related to the time correlation or the sharing location, including adding AR content related to the time correlation or the sharing location.

2. The method according to claim 1, wherein: The consumer portrait is established based on the consumer's identity information, including the consumer's basic attributes, and the AR content and interactive program are determined through attribute matching and pushed to the consumer's personal terminal, including: Obtain basic consumer attribute data, including age, gender, occupational category and consumption level, and make preliminary classifications of consumers; Through big data analysis, we can deeply explore consumers’ shopping history and browsing preferences and extract personalized demand information, including brand preferences and product preferences; Analyze consumers’ mobility patterns and application preferences by combining their geographic location information and mobile device usage habits, and predict their consumption scenarios; Identify consumers’ consumption characteristics based on preliminary classification, personalized demand information and consumption scenarios; Through the content recommendation system, AR content and interactive programs that match consumption characteristics are screened out from the inventory; Adjust the format and resolution of AR content and interactive programs according to the device compatibility and technical parameters of the consumer's personal terminal; Push the adjusted AR content and interactive programs to consumers’ personal terminals; Through the user feedback collection module, monitor consumers' reactions and interactions to pushed content and collect effect data; Use data analysis tools to evaluate the collected effect data.

3. The method according to claim 1, wherein: The obtaining of the current scene information of the consumer, identifying the type and characteristics of the current scene, and adjusting the interactive program according to the preset scene adaptation rules include: Through the consumer's personal terminal, obtain information about the consumer's environment, including light intensity, temperature, humidity and noise level, and obtain scene information; Identify the type of the current scene. If the scene information indicates that the user is in a low-light and silent state, the scene type is determined to be a night home environment. Identify the characteristics of the current scene through the consumer's personal terminal, including: judging the user's emotions and health status based on the front camera of the personal terminal or the physiological sensors of the associated wearable device, including heart rate monitoring; If the user's mood and health status monitoring indicates that the user is tired or unhealthy, reduce the interactive content of the interactive program; Test the quality of your network connection, get speed and stability indicators with network diagnostic tools, and adjust the content size of interactive programs; Through the Bluetooth or Wi-Fi scanning function of the personal terminal, the connected smart devices in the surrounding area, including smart light bulbs and speakers, are identified and their status information is obtained; When the status information of the smart device is available, adding a connection interaction of the smart device to the interactive program; A configuration interface is provided to obtain adjustment parameters of the interactive program input by the consumer, and the interactive program is adjusted based on the adjustment parameters.

4. The method according to claim 1, wherein: When the consumer performs a sharing operation, the social relationship and tag attributes between the sharing object and the consumer are obtained, the sharing object is divided into different user types, and the corresponding AR content sharing method is determined according to the different user types, including: Use social media analysis tools to capture interaction records and personal information between consumers and sharing objects; Analyze the interaction records obtained to determine the closeness of the relationship and the frequency of interaction, and identify the types of social relationships, including family, close friends, acquaintances, and colleagues or netizens; Process the user's personal information, analyze interests, hobbies, age group and gender, and identify the user's tag attributes; Based on social relationships and tag attributes, decision trees or clustering algorithms are used to divide sharing objects into different user types, including intimate users, social users, interest users, influential users, educational users, and work users. Generate a sharing method for AR content based on the user type and tag attributes of the sharing object; Through the historical sharing records between the sharing objects and consumers, the generation parameters of the AR content sharing method are optimized.

5. The method according to claim 1, wherein: In the AR scene, the user's interaction behavior data is obtained, and the user's interaction preferences for different product types are determined through a user behavior analysis algorithm. According to the difference in interaction preferences, the display and interaction of AR products are dynamically adjusted, including: Collecting user interaction behavior data through the AR application's sensors and interfaces, including touch, click, gesture, and gaze tracking, and recording corresponding timestamps; Use time series analysis methods to process user interaction data and timestamps to identify the interaction preferences of user interaction behaviors; Count the number and duration of user interactions with each product in the AR scene to determine the user's interest in each type of product; Adjust the display and interaction methods of AR products based on user interaction data and product type information, and use personalized algorithm parameters to achieve precise and personalized AR experience.

6. The method according to claim 1, wherein: The multi-dimensional data, including user attributes, scene information, sharing objects, location information, time information, and product types, is comprehensively analyzed, and an AR content recommendation model is constructed through a machine learning algorithm to realize intelligent recommendation of AR content based on multi-dimensional data, including: Obtain user attribute data through user login information, including age, gender, occupation and hobbies; Identify the user’s AR content interaction history based on historical user behavior records, and collect the user’s explicit preference information through questionnaires and user feedback mechanisms; Use environmental perception to capture the user's current scene information in real time, including indoor and outdoor environments, lighting conditions, surrounding objects and scenery features, and ambient noise levels; Use location services to obtain the user's geographic location information, including latitude and longitude, place name and nearby points of interest (POI), to determine the type of geographical environment the user is in; The device's time service function records the time information of the user's interactive AR content, including the current time, date and day of the week, as well as seasonal changes and special dates or events; Analyze the social relationship between users and sharing objects, and adjust the recommended content to suit different social scenarios and users' social intentions according to the different sharing objects; Based on the user's product type interests, historical interaction data and user feedback are used to identify the user's preferences for different AR content types; Collecting user device parameter data, including device type, processor speed, graphics processing capabilities, and sensor type, to assess compatibility of recommended AR content; Through machine learning algorithms, multi-dimensional data is analyzed to establish an AR content recommendation model to predict and recommend personalized AR content.

7. A product display interaction system based on virtual reality technology, applied to the product display interaction method according to any one of claims 1 to 6, characterized in that: The system comprises: User portrait building module, used to analyze consumers’ basic attributes and preferences to customize personalized AR content; A scene adaptation adjustment module, which is used to adjust the interactive program and AR display according to the consumer's current environment; Social relationship analysis module, used to personalize shared content based on the social tags and relationships of sharers; Location information matching module, used to adjust the shared AR content and relevance based on geographic location; Time information analysis module, used to dynamically adjust the pushed AR content according to the time of sharing; AR content recommendation engine, used to comprehensively analyze multi-dimensional data and intelligently recommend personalized AR experiences.

Images