Intelligent updating method and system for interactive content of cloud platform

Abstract

The invention relates to the technical field of interactive content updating, and discloses a cloud platform interactive content intelligent updating method and system, and the method comprises the steps: carrying out the analysis of a user operation behavior according to pre-obtained user operation data, calculating a thermodynamic value, and constructing a cloud platform click thermodynamic diagram; analyzing an operation intention of a user from the cloud platform click thermodynamic diagram through a preset intention analysis model, and constructing an intention feature vector; according to the intention feature vector, grading the user intention through a preset content optimization model, and according to the graded user intention, performing layered optimization on the interaction content of the cloud platform to obtain first interaction content; within a preset time period, updating the cloud platform click thermodynamic diagram, analyzing the interaction condition of the user to the first interaction content in combination with the updated cloud platform click thermodynamic diagram, and updating the first interaction content; according to the method, the interaction content of the cloud platform can be updated and optimized in time, and the interaction effect of the platform is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of interactive content updating, and in particular to a method and system for intelligently updating interactive content on a cloud platform. Background Art

[0002] Currently, cloud platforms serve as the core vehicle for information exchange and service provision. The quality of interactive content on live streaming platforms directly impacts user experience and platform competitiveness. With increasing user demand for personalized and intelligent services, live streaming platforms' interactive content needs to be dynamically updated and optimized based on user behavior and needs. Existing methods for updating interactive content on these platforms rely on manual experience or simple rule-based engines, lacking in-depth and comprehensive utilization of user activity data, resulting in poor interactive content updates.

[0003] The existing technology has the following problems: the analysis of user operation data is simple, and there is a lack of analysis of user operation behavior according to different areas of the cloud platform operation interface; the user operation intention analysis process is only based on user operation data, and the analyzed user intention is not accurate enough; when optimizing interactive content, a single optimization method is adopted, and it is impossible to provide differentiated content optimization solutions for different degrees of user intentions, resulting in poor optimization effect and difficulty in improving user interactive experience and participation; in order to solve at least one of the above problems, the present invention proposes a cloud platform interactive content intelligent update method and system. Summary of the Invention

[0004] In view of the shortcomings of the existing technology, the main purpose of the present invention is to provide a method and system for intelligently updating interactive content on a cloud platform, which can effectively solve the problems in the background technology. The specific technical solutions of the present invention are as follows:

[0005] A cloud platform interactive content intelligent updating method, comprising:

[0006] Based on the pre-acquired user operation data, analyze the user operation behavior and calculate the heat value to build the cloud platform click heat map;

[0007] Analyze the user's operation intention from the click heat map of the cloud platform through a preset intention analysis model and construct an intention feature vector;

[0008] According to the intention feature vector, the user intention is graded using a preset content optimization model, and the interactive content of the cloud platform is hierarchically optimized according to the graded user intention to obtain first interactive content;

[0009] Within a preset time period, the cloud platform click heat map is updated, and the user's interaction with the first interactive content is analyzed in combination with the updated cloud platform click heat map, and the first interactive content is updated to intelligently update the cloud platform interactive content.

[0010] Specifically, the method of analyzing user operation behaviors and calculating heat values ​​based on pre-acquired user operation data, and constructing a cloud platform click heat map, includes:

[0011] Based on the pre-acquired user operation data, analyze the user's click behavior on the interactive content of the cloud platform on different devices to obtain the click analysis results;

[0012] On the cloud platform operation interface, the heat values ​​of different positions of the interface are calculated according to the click analysis results, and a cloud platform click heat map is constructed.

[0013] Specifically, on the cloud platform operation interface, calculating the heat values ​​of different positions of the interface according to the click analysis results and constructing a cloud platform click heat map includes:

[0014] Divide the cloud platform operation interface into grids according to the preset grid size to obtain multiple grid areas;

[0015] For each grid area, the click analysis results are analyzed using a preset thermal analysis model to calculate the thermal value;

[0016] According to the thermal value of each grid area, a thermal value matrix is ​​constructed;

[0017] Based on the thermal value matrix, a cloud platform click heat map is constructed.

[0018] Specifically, the preset intention analysis model is used to analyze the user's operation intention from the cloud platform click heat map and construct an intention feature vector, including:

[0019] According to the cloud platform click heat map, the cloud platform operation interface is gradient-divided and the corresponding gradient value is calculated, and the first gradient area where the gradient value is greater than the preset gradient threshold is screened out;

[0020] The user's operation intention in the first gradient area is analyzed through a preset intention analysis model to construct an intention feature vector.

[0021] Specifically, the user's operation intention in the first gradient area is analyzed by a preset intention analysis model to construct an intention feature vector, including:

[0022] In the first gradient region, the user's operation intention is analyzed using a preset intention analysis model to obtain a first intention feature vector;

[0023] Mapping the first intention feature vector to the cloud platform operation interface according to a preset feature mapping rule to obtain a second intention feature vector;

[0024] The first intention feature vector and the second intention feature vector are combined to construct an intention feature vector.

[0025] Specifically, based on the intention feature vector, the user intention is graded using a preset content optimization model, and the interactive content of the cloud platform is hierarchically optimized based on the graded user intention to obtain the first interactive content, including:

[0026] According to the intention feature vector, the user's intention strength is analyzed through the preset content optimization model, and the user intention is graded to obtain multi-level user intention;

[0027] According to the multi-level user intentions, the interactive content of the cloud platform is hierarchically optimized to obtain first interactive content, wherein the multi-level user intentions include high-level user intentions, mid-level user intentions and low-level user intentions.

[0028] Specifically, according to the multi-level user intentions, the interactive content of the cloud platform is hierarchically optimized to obtain the first interactive content, including:

[0029] For high-level user intent, the first optimization instruction is generated by generating real-time interactive scenarios;

[0030] For intermediate user intent, the second optimization instruction is generated by dynamically reorganizing the interactive content and enhancing its effect;

[0031] For low-level user intent, generate third optimization instructions by adjusting the dynamic effects of interactive content;

[0032] In combination with the first optimization instruction, the second optimization instruction and the third optimization instruction, the interactive content of the cloud platform is optimized in layers to obtain first interactive content.

[0033] Specifically, within a preset time period, updating the cloud platform click heat map, analyzing the user's interaction with the first interactive content in combination with the updated cloud platform click heat map, and updating the first interactive content to intelligently update the cloud platform interactive content include:

[0034] Within a preset time period, the cloud platform click heat map is updated according to real-time user operation data to obtain an updated cloud platform click heat map;

[0035] Analyzing the user's interaction with the first interactive content based on the click heat map of the updated cloud platform, and constructing an interaction effect vector;

[0036] The first interactive content is updated through the interactive effect vector to intelligently update the cloud platform interactive content.

[0037] Specifically, updating the first interactive content by using the interactive effect vector to intelligently update the interactive content on the cloud platform includes:

[0038] Decomposing the first interactive content according to the interactive effect vector to obtain first content, second content, and third content;

[0039] Using a preset content update model, corresponding contents in the first content, the second content, and the third content are updated respectively to construct an updated content sequence;

[0040] According to the update content sequence, the corresponding interface elements in the first interactive content are replaced and updated to intelligently update the cloud platform interactive content.

[0041] A cloud platform interactive content intelligent update system, used to implement a cloud platform interactive content intelligent update method, comprising:

[0042] The cloud platform click heat map construction module analyzes user operation behaviors and calculates heat values ​​based on pre-acquired user operation data to construct the cloud platform click heat map;

[0043] An intention feature vector construction module, which uses a preset intention analysis model to analyze the user's operation intention from the click heat map of the cloud platform and construct an intention feature vector;

[0044] An interactive content optimization module, which classifies user intentions according to the intention feature vector using a preset content optimization model, and performs hierarchical optimization on the interactive content of the cloud platform according to the classified user intentions to obtain first interactive content;

[0045] The interactive content update module updates the cloud platform click heat map within a preset time period, analyzes the user's interaction with the first interactive content in combination with the updated cloud platform click heat map, updates the first interactive content, and intelligently updates the cloud platform interactive content.

[0046] Compared with the prior art, this application has the following beneficial effects:

[0047] This application constructs a cloud platform click heat map based on user operation data and the cloud platform operation interface, analyzes user operation intentions in different areas based on the cloud platform click heat map, and adopts different interactive content optimization strategies for user operation intentions at different levels. The cloud platform click heat map is updated in combination with real-time user operation data, and the interactive content is optimized and updated. By constructing a cloud platform click heat map, the user's operation hotspots and distribution patterns on the interface can be reflected, the user's true intentions can be accurately grasped, and a clear direction for content optimization can be provided. Through layered optimization, the personalized needs of different users can be met, the user's interactive experience and participation can be improved, and the interactive content can be updated and optimized in a timely manner according to user feedback, thereby realizing intelligent updating of interactive content and improving the interactive content effect of the cloud platform. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a workflow diagram of a cloud platform interactive content intelligent updating method in Example 1 of the present invention;

[0049] Figure 2 This is a schematic diagram of a cloud platform click heat map in Example 1 of the present invention;

[0050] Figure 3 This is a workflow diagram for layered optimization of interactive content on a cloud platform in Example 1 of the present invention;

[0051] Figure 4 This is a structural diagram of a cloud platform interactive content intelligent update system in Example 2 of the present invention. DETAILED DESCRIPTION

[0052] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0053] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0054] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0055] Example 1:

[0056] This embodiment provides a cloud platform interactive content intelligent update method, such as Figure 1 As shown, a cloud platform interactive content intelligent update method includes:

[0057] S101. Analyze user operation behaviors based on pre-acquired user operation data, calculate heat values, and construct a cloud platform click heat map.

[0058] S102. Analyze the user's operation intention from the cloud platform click heat map using a preset intention analysis model and construct an intention feature vector.

[0059] S103: Classifying user intent using a preset content optimization model based on the intent feature vector, and performing layered optimization on the interactive content of the cloud platform based on the classified user intent to obtain first interactive content;

[0060] S104. Within a preset time period, update the cloud platform click heat map, analyze the user's interaction with the first interactive content in combination with the updated cloud platform click heat map, update the first interactive content, and intelligently update the cloud platform interactive content.

[0061] This embodiment analyzes user operation data, constructs a cloud platform click heat map, analyzes user operation intentions based on the cloud platform click heat map, grades user operation intentions and optimizes the interactive content of the cloud platform in layers, and finally updates the interactive content in real time based on user feedback on the interactive content; analyzing user operation intentions based on user operation data and optimizing the interactive content accordingly can meet the needs of different users, increase the frequency and depth of interaction between users and the platform, dynamically update the interactive content of the cloud platform, adapt to changes in user needs, and enhance the flexibility and adaptability of the cloud platform interactive content update process.

[0062] In this embodiment, based on the collected user operation data, various operation behaviors of users on the cloud platform are analyzed, including click, stay, slide and other behavior information. Different operation behaviors reflect the degree of user attention to different content areas. By analyzing the user operation data, the thermal values ​​of different areas of the cloud platform interface are calculated. The thermal values ​​reflect the user's clicks on different content areas, which can reflect the user's focus hotspots on the cloud platform; by analyzing the user operation data and constructing a heat map, the user's behavior hotspots on the cloud platform can be intuitively displayed, so as to quickly screen out the interactive content areas that users are interested in, and perform corresponding content updates for different areas.

[0063] Specifically, based on the constructed cloud platform click heat map, the user's operational behavior intentions are analyzed, including intentions to browse information, search for specific content, and make purchases. The cloud platform click heat map is analyzed through a preset intention analysis model, and features that can reflect user intentions are extracted to construct an intention feature vector. By constructing the intention feature vector, the true intention of the user's operational behavior can be analyzed, and the user's abstract needs can be converted into specific feature vectors, providing a clear direction for the optimization of interactive content and making content optimization more targeted.

[0064] Preferably, the strength of user intention is analyzed based on the intention feature vector. Different users have different operational intention strengths and different content needs. User intentions are graded through a preset content optimization model, and users are divided into different levels such as high intention, medium intention and low intention. The interactive content of the cloud platform is layered and optimized according to different levels of intention, and different optimization methods are used for different levels of intention. Personalized interactive content can be provided according to the operational needs of different users, so that the content can accurately meet the operational needs of different users, improve user satisfaction and participation in interactive content, and thus improve the platform's conversion rate and user retention rate.

[0065] At the same time, within a preset time period, the cloud platform click heat map is updated based on the user's real-time operation data, and the user's interaction with the first interactive content is analyzed in combination with the updated heat map. The user's feedback on the interactive content is analyzed through the user's interaction, and the cloud platform interactive content is updated in real time. Considering that the user's needs and behaviors are dynamically changing, the user's feedback on the content can be combined to promptly discover problems with the interactive content and make adjustments, to ensure that the interactive content of the cloud platform always remains attractive and practical, and to improve the user experience and the competitiveness of the platform.

[0066] This application constructs a cloud platform click heat map based on user operation data and the cloud platform operation interface, analyzes user operation intentions in different areas based on the cloud platform click heat map, and adopts different interactive content optimization strategies for user operation intentions at different levels. The cloud platform click heat map is updated in combination with real-time user operation data, and the interactive content is optimized and updated. By constructing a cloud platform click heat map, the user's operation hotspots and distribution patterns on the interface can be reflected, the user's true intentions can be accurately grasped, and a clear direction for content optimization can be provided. Through layered optimization, the personalized needs of different users can be met, the user's interactive experience and participation can be improved, and the interactive content can be updated and optimized in a timely manner according to user feedback, thereby realizing intelligent updating of interactive content and improving the interactive content effect of the cloud platform.

[0067] Furthermore, based on the pre-acquired user operation data, the user operation behavior is analyzed and the heat value is calculated to build a cloud platform click heat map, including:

[0068] S201. Analyze the user's click behavior on interactive content on the cloud platform on different devices based on pre-acquired user operation data to obtain click analysis results;

[0069] S202. On the cloud platform operation interface, calculate the thermal values ​​of different positions of the interface according to the click analysis results, and construct a cloud platform click heat map.

[0070] This embodiment is based on pre-acquired user operation data, analyzes the user's clicking behavior on different devices, grids the cloud platform operation interface, and constructs a cloud platform click heat map that can reflect user click hotspots by calculating the thermal values ​​of different positions on the cloud platform operation interface; the user's clicking behavior on different devices can be combined to analyze the interactive content areas that the user is interested in. The constructed cloud platform click heat map can intuitively display the user's click hot spots and cold spots on the cloud platform interface, so as to quickly locate the content areas and functional modules that need to be optimized, avoid blind optimization, and improve resource utilization efficiency and content optimization effects.

[0071] In this embodiment, based on the pre-acquired user operation data, the user's clicking behavior on different devices is analyzed. There are differences in screen size, operation method and interactive interface of different devices. The user's clicking behavior on the interactive content of the cloud platform on different devices is also different. The devices specifically include mobile phones, tablets, computers, etc. The user's content preferences and operating habits in different device environments are analyzed. The interactive content that the user is interested in can be analyzed in combination with the differences in the user's clicking behavior on different devices to avoid poor user interaction experience due to device differences.

[0072] Specifically, based on the pre-acquired user operation data, the key features of click behavior are extracted for the data set of each device type, including click location coordinates, click time, click frequency, click content type, etc. Among them, click content types include product images, text links, buttons, etc. The click behavior characteristics of users on different devices are superimposed to obtain the click analysis results.

[0073] Preferably, based on the click analysis results obtained by analysis, the user's click behavior on the cloud platform operation interface is quantified and the heat value is calculated. By analyzing the user's click behavior on different areas of the cloud platform interactive interface, the heat value of each area is calculated respectively, and the heat value is mapped to the cloud platform interface. Through different colors and depths, a cloud platform click heat map reflecting the user's click hotspots is constructed; by constructing a cloud platform click heat map, the distribution of users' click hotspots on the cloud platform can be intuitively displayed, thereby quickly distinguishing areas with high user attention and low user attention. When it is found that the heat value of an important functional area is low, the content layout can be adjusted or the functional design can be optimized in a timely manner to increase users' attention and usage rate in this area.

[0074] Furthermore, on the cloud platform operation interface, the heat values ​​of different positions on the interface are calculated based on the click analysis results, and a cloud platform click heat map is constructed, including:

[0075] S301, dividing the cloud platform operation interface into grids according to a preset grid size to obtain multiple grid areas;

[0076] S302: For each grid area, analyze the click analysis results using a preset thermal analysis model to calculate the thermal value;

[0077] S303, constructing a thermal value matrix according to the thermal value of each grid area;

[0078] S304. Based on the thermal value matrix, construct a cloud platform click heat map.

[0079] like Figure 2 As shown, this embodiment divides the cloud platform operation interface into grids, uses a preset thermal analysis model to calculate the thermal value of each grid area, constructs a thermal value matrix, and generates a cloud platform click heat map; Figure 2 The thickness of the line represents the depth of the heat map color. The thicker the line, the darker the color. The higher the heat value of the corresponding user, the more frequent the click operation on the area. Through grid division, heat value calculation and heat map construction, the user's click behavior can be combined to quantify the user's interest level, analyze the areas with high and low user attention, and provide data support for user intent analysis, content optimization strategy formulation, etc., thereby effectively improving the user experience and operational efficiency of the cloud platform.

[0080] In this embodiment, first, the cloud platform operation interface is divided into multiple grid areas according to a preset grid size. Different grid sizes are set according to the size, resolution and content optimization accuracy requirements of the cloud platform operation interface. For a computer interface with a resolution of 1920×1080, the grid size can be set to 20×20 pixels; according to the set grid size, the cloud platform operation interface is divided horizontally and vertically in sequence to divide it into multiple grid areas of the same size; through grid division, the statistics and analysis of click data are more standardized, avoiding differences in analysis results caused by inconsistent interface area sizes.

[0081] Secondly, after the cloud platform operation interface is grid-divided, the click analysis results are analyzed in each grid area using a preset thermal analysis model to calculate the thermal value of the area. The higher the thermal value, the higher the user attention in the grid area and the more frequent the user operations in the area. According to the user's operation behavior, the factors affecting the thermal value calculation and the corresponding weight of each factor are determined. By analyzing the user's operation behavior on the cloud platform, the factors affecting the thermal value calculation are set to include the number of clicks, click duration, user stay time, etc., and the weight of the number of clicks is set to 0.4, the weight of the click duration is set to 0.3, and the weight of the user stay time is set to 0.3. The thermal analysis model is specifically a weighted model, which calculates the corresponding thermal value by combining the factors affecting the thermal value calculation and the corresponding weights. The click analysis results are input into the thermal analysis model, the factors of thermal value calculation are analyzed, and weighted summation is performed to calculate the thermal value of each grid area. By calculating the thermal value, different user behavior factors can be comprehensively considered to comprehensively and accurately reflect the degree of user attention to different areas.

[0082] Preferably, the thermal values ​​calculated for each grid area are arranged in the order of rows and columns of the grid on the interface to construct a thermal value matrix. The thermal value matrix neatly arranges the thermal value information of each grid area of ​​the operation interface, provides standard data support for constructing a heat map, and improves the efficiency of heat map construction; according to the constructed thermal value matrix, the numerical values ​​in the thermal value matrix are mapped to image elements of different colors and depths according to the set color mapping rules to generate a cloud platform click heat map reflecting the distribution of user click hotspots, wherein the darker the color, the higher the thermal value, and the higher the corresponding user attention. The correspondence between thermal value and color is set, and the thermal value 0-10 is set to light blue, 11-20 to blue, 21-30 to dark blue, 31 and above to red, and the color depth deepens as the thermal value increases; by constructing a cloud platform click heat map, the distribution of user click hotspots on the cloud platform operation interface can be intuitively reflected. When updating interactive content, the interface area that needs to be optimized can be quickly located, thereby improving the efficiency of interactive content optimization.

[0083] Furthermore, through the preset intention analysis model, the user's operation intention is analyzed from the cloud platform click heat map, and the intention feature vector is constructed, including:

[0084] S401: Based on the cloud platform click heat map, the cloud platform operation interface is gradient-divided and the corresponding gradient values ​​are calculated, and a first gradient region with a gradient value greater than a preset gradient threshold is screened out;

[0085] S402: Analyze the user's operation intention in the first gradient area through a preset intention analysis model to construct an intention feature vector.

[0086] This embodiment performs gradient analysis on the cloud platform click heat map, locates the hot spots where users frequently operate based on the gradient of the pixel values ​​in the heat map, uses a preset intention analysis model to analyze the user operation intentions in the hot spots, and constructs an intention feature vector. Through gradient analysis and intention feature calculation, the user's operation intention on the cloud platform can be accurately identified, which improves the accuracy and reliability of the intention analysis. The intention feature vector provides direction for the optimization of the interactive content of the cloud platform, can realize personalized content updates, make the updated interactive content more in line with the user's intentions, and enhance the user experience and platform competitiveness.

[0087] In this embodiment, based on the constructed cloud platform click heat map, the pixel value gradient change in the cloud platform click heat map is analyzed. The gradient of the pixel value in the heat map reflects the severity of the heat value change. In the area where the user's operation intention is strong, the heat value will change more strongly, and the corresponding gradient value is higher, forming a high gradient area; the Sobel operator is used to perform a convolution operation on the cloud platform click heat map, and the gradient value of each pixel in the horizontal and vertical directions is calculated. The gradient values ​​in the horizontal and vertical directions are superimposed to obtain the gradient value of the grid area; by statistically analyzing the gradient value distribution of all pixel points, the gradient threshold is set to the mean plus 2 times the standard deviation. At this time, the screened area is the area with the most significant heat value change; the gradient value of each pixel point in the heat map is traversed, and the pixel points with gradient values ​​greater than the preset gradient threshold are screened out to form a first gradient area; through gradient analysis and threshold screening, the key areas of user operation can be screened out, thereby improving the pertinence and accuracy of intent analysis.

[0088] Specifically, within the filtered first gradient area, the user's operation intention is analyzed through a preset intention analysis model, the user's intention features are extracted, and an intention feature vector is constructed; the intention feature vector can convert the user's abstract operation intention into a specific feature vector. When optimizing the interactive content, targeted content optimization can be performed based on the intention feature vector to improve the effect of interactive content optimization.

[0089] Furthermore, the user's operation intention in the first gradient area is analyzed by a preset intention analysis model to construct an intention feature vector, including:

[0090] S501: Analyze the user's operation intention using a preset intention analysis model within a first gradient region to obtain a first intention feature vector;

[0091] S502: Map the first intention feature vector to the cloud platform operation interface according to a preset feature mapping rule to obtain a second intention feature vector;

[0092] S503: Construct an intention feature vector by combining the first intention feature vector and the second intention feature vector.

[0093] In this embodiment, within the first gradient area, the user's operation intention is analyzed by a preset intention analysis model to obtain a first intention feature vector; the first gradient area is an area where user operations are active and intentions are obvious, and the intention analysis model analyzes the user's click behavior data in this area. The user's click behavior data specifically includes the number of clicks, click duration, frequency, etc., analyzes the user's operation intention in this area, and converts the intention into a feature vector; first, the user operation data within the first gradient area is extracted, and the intention analysis model includes models such as support vector machine and random forest. The intention analysis model in this embodiment is a random forest model. The random forest model is trained using a large amount of historical user operation data and corresponding intention annotations to obtain a pre-trained random forest model. The user operation data in the first gradient area is input into the pre-trained intention analysis model. The model outputs the user operation intention category and the confidence of each intention category. The first intention feature vector is obtained by combining the confidence of each intention category.

[0094] For example, the intent analysis model outputs a purchase intention confidence of 0.7, a view details intention confidence of 0.2, and a sharing intention confidence of 0.1. Then the first intention feature vector is [0.7, 0.2, 0.1]. By analyzing user intention in the first gradient area, intent analysis can be performed based on the core area of ​​user behavior, reducing data interference, improving the accuracy and efficiency of intent recognition, and quickly obtaining the user's preliminary intention information in key areas.

[0095] Specifically, according to the preset feature mapping rules, the first intention feature vector is mapped to the overall operation interface of the cloud platform to obtain the second intention feature vector. Different cloud platform operation interface layouts and functional module distributions will affect the user's operation intention. The first intention feature vector is associated with the location, function and other information of the operation interface through vector mapping, and the intention feature is mapped to the specific interface scene. The actual operation scene information is added to the intention feature to supplement the interface dimension information missing from the first intention feature vector; according to the layout and function of the cloud platform operation interface, the feature mapping rules are set. The feature mapping rules set in this embodiment include: when the first gradient area is located in the navigation bar at the top of the interface and the search intent confidence in the first intention feature vector is high, the value of the feature dimension related to the navigation bar search function in the second intention feature vector is increased; when the first gradient area is located in the product display area, the feature dimension values ​​of functions such as viewing product details and adding to the shopping cart are adjusted according to the first intention feature vector; the specific position of the first gradient area in the cloud platform operation interface and the functional module to which it belongs are determined, and the first intention feature vector is adjusted and expanded according to the feature mapping rules.

[0096] For example, the first intention feature vector is [0.7, 0.2, 0.1], indicating a purchase intention confidence of 0.7, a view details intention confidence of 0.2, and a sharing intention confidence of 0.1. The first gradient region is located in the product display area. According to the feature mapping rules, the values ​​of dimensions related to functions such as adding to a shopping cart and viewing product details are weighted according to the original intention confidence. The second intention feature vector is obtained by adding new dimensions to represent the intention features related to the product display area function. By combining intent features with cloud platform operation interface scenarios, more interface dimension information can be added to the intent feature vector, making the intent analysis results more consistent with the user's true intentions in actual interface operations, thereby improving the accuracy and optimization effect of interactive content recommendations and interface optimization.

[0097] Preferably, the first intention feature vector reflects the user's operating intention within the first gradient area, and the second intention feature vector supplements the platform interface scene information. Combining the first intention feature vector and the second intention feature vector by directly splicing the elements of the vector can integrate the multi-dimensional information of the user's operating intention, avoid the limitations of a single vector, improve the integrity and accuracy of the intention feature vector, and provide rich data support for the optimization of interactive content on the cloud platform.

[0098] Furthermore, based on the intention feature vector, the user intention is graded using a preset content optimization model, and the interactive content of the cloud platform is hierarchically optimized based on the graded user intention to obtain first interactive content, including:

[0099] S601: Analyze the user's intention strength based on the intention feature vector using a preset content optimization model, classify the user's intention, and obtain multi-level user intention;

[0100] S602: Perform hierarchical optimization on the interactive content of the cloud platform according to the multi-level user intention to obtain first interactive content, wherein the multi-level user intention includes high-level user intention, mid-level user intention, and low-level user intention.

[0101] This embodiment analyzes the intent feature vector based on the content optimization model, classifies user intent by intensity, and optimizes the display format and recommendation strategy of interactive content for different levels of user intent, thereby achieving accurate matching of content and user needs. Users can obtain content that meets their needs more quickly, thereby improving user experience and platform operation efficiency.

[0102] In this embodiment, based on the intention feature vector, the user's intention strength is analyzed through a preset content optimization model, and the user intention is graded to obtain multi-level user intentions; the intention feature vector includes multi-dimensional information of the user's operation intention. First, the intention feature vector is standardized using the Z-score standardization method to eliminate the influence of dimensional differences in different dimensions. The content optimization model includes models such as logistic regression, decision tree, and neural network. The content optimization model of this embodiment uses a decision tree model. A large number of historical intention feature vectors and their corresponding labeled intention levels are used to train the decision tree model to obtain a pre-trained decision tree model. The preprocessed intent feature vector is input into the pre-trained decision tree model. The model outputs the predicted probability of each intent level. The standard for grading user intent is: when the intent probability is greater than or equal to 0.7, it is classified as high-level user intent; when the intent probability is greater than 0.3 and less than 0.7, it is classified as intermediate user intent; when the intent probability is less than or equal to 0.3, it is classified as low-level user intent; by grading user intent, different content optimization strategies can be formulated for different levels of intent, so that the platform can perform different degrees of content updates for different intent levels, while reducing resource waste while achieving content update optimization.

[0103] Specifically, according to the different levels of user intentions after division, the interactive content of the cloud platform is layered and optimized to obtain the first interactive content; different levels of user intentions correspond to different degrees of content optimization needs, and the interactive content of the cloud platform is layered, and different interactive content display and interaction methods are set for users with different intention levels. This can improve the matching degree between content and user needs, avoid the waste of resources caused by adopting a single fixed content optimization method, achieve accurate matching of interactive content and user intentions, improve content conversion rate and user satisfaction, and improve resource utilization.

[0104] Further, such as Figure 3 As shown, according to the multi-level user intention, the interactive content of the cloud platform is hierarchically optimized to obtain the first interactive content, including:

[0105] S701: For the advanced user intention, generate a first optimization instruction by generating a real-time interactive scenario;

[0106] S702: For the intermediate user intention, generate a second optimization instruction by dynamically reorganizing the interactive content and enhancing the effect;

[0107] S703: For low-level user intentions, generate a third optimization instruction by adjusting the dynamic effect of the interactive content;

[0108] S704: Combine the first optimization instruction, the second optimization instruction, and the third optimization instruction to perform layered optimization on the interactive content of the cloud platform to obtain first interactive content.

[0109] In this embodiment, for advanced user intentions, a first optimization instruction is generated by generating a real-time interactive scenario; the advanced user intention is strong and clear, and by generating a real-time interactive scenario, its needs can be quickly met, and the real-time interactive scenario can simulate a real interactive environment; according to the cloud platform business type and the direction of the advanced user's intention, the type of real-time interactive scenario is determined, and according to the determined scenario type, corresponding interface interactive elements are set, including interactive interface layout, prompt information, operation buttons, etc., and the designed real-time interactive scenario is converted into a first optimization instruction, which includes specific parameters of the scene elements, display rules, interaction logic and other information.

[0110] For example, in an e-commerce live streaming platform, a first optimization instruction is set: a limited-time sale countdown module is displayed in the upper right corner of the product details page, and the module is hidden after the countdown ends; the purchase button is clicked to jump to the payment page; the remaining inventory prompt information is refreshed every 10 seconds; for advanced user intentions, an efficient operation path is provided to users through real-time interactive scenarios, shortening the conversion process, improving the conversion rate, and enhancing the user experience and satisfaction on the platform.

[0111] For intermediate user intentions, a second optimization instruction is generated by dynamically reorganizing the interactive content and enhancing its effects. Intermediate users have a certain interest in content but their needs are not clear. By dynamically reorganizing the interactive content and enhancing its effects, the interactive content is reorganized, key information is highlighted, and the effects of the interactive content are optimized. Existing interactive content is analyzed to extract information related to the intermediate user intentions, and the interactive content is rearranged and combined according to the relevance and importance of the information. Visual design, copywriting optimization and other means can be used to enhance the content display effect, specifically including adjusting visual elements such as text layout, color matching, image size and clarity to make the content more attractive. The content reorganization and effect enhancement plan generates a second optimization instruction, including the specific method of content reorganization, parameter setting for effect enhancement, etc. Content reorganization and effect enhancement can provide more attractive content display for intermediate user intentions, thereby increasing user residence time and engagement on the platform.

[0112] For low-level user intentions, a third optimization instruction is generated by adjusting the dynamic effects of the interactive content; low-level user intentions are weak and they lack interest in the platform content, so by adjusting the dynamic effects of the interactive content, specifically including adding animations, special effects, sound effects, etc., user attention can be attracted and users can be guided to pay attention to and explore the platform content; according to the style of the cloud platform and the elements that users are interested in, corresponding dynamic effects are selected, including flashing, bouncing, explosion and other animation effects; relevant parameters of the dynamic effects are designed, including animation speed, duration, frequency of occurrence, sound effect volume, etc., and the selected dynamic effects and parameter settings are used to generate a third optimization instruction. By generating dynamic effects, users can be attracted, the initial cognitive threshold of users for the platform content can be lowered, the user's curiosity and desire to explore can be stimulated, and the user is encouraged to further browse and use the platform.

[0113] Preferably, the interactive content of the cloud platform is optimized in layers by combining the first optimization instruction, the second optimization instruction and the third optimization instruction to obtain the first interactive content; the optimization instructions generated for different user intention levels are integrated, layered according to user intentions, and applied to the corresponding interactive content of the cloud platform to achieve personalized content display and services for users with different intentions, so that the platform content can match the needs of users at different levels to achieve the best optimization effect.

[0114] Furthermore, within a preset time period, the cloud platform click heat map is updated, and the user's interaction with the first interactive content is analyzed in combination with the updated cloud platform click heat map, and the first interactive content is updated to intelligently update the cloud platform interactive content, including:

[0115] S801. Update the cloud platform click heat map based on real-time user operation data within a preset time period to obtain an updated cloud platform click heat map;

[0116] S802: Analyze the user's interaction with the first interactive content based on the updated cloud platform click heat map, and construct an interaction effect vector;

[0117] S803: Update the first interactive content through the interactive effect vector to intelligently update the cloud platform interactive content.

[0118] This embodiment updates the cloud platform click heat map within a preset time period, analyzes the user's changing behavioral trends and needs, analyzes the user's interaction with the first interactive content based on the updated cloud platform click heat map, constructs an interaction effect vector, and updates the first interactive content based on the interaction effect vector, thereby realizing real-time intelligent updating of the cloud platform interactive content, so that the platform interactive content continues to match user needs and is dynamically optimized.

[0119] In this embodiment, within a preset time period, the cloud platform click heat map is updated based on real-time user operation data to obtain an updated cloud platform click heat map; the user's operation behavior and interest preference changes are analyzed within the time period, and the cloud platform click heat map is updated based on real-time user operation data, and the distribution range and color changes of hot spots in the heat map are updated. By updating the heat map, the user's latest click hot spots and behavior trends can be reflected in a timely manner, providing accurate data support for the optimization of the first interactive content.

[0120] Specifically, based on the click heat map of the updated cloud platform, the user's interaction with the first interactive content is analyzed, and an interaction effect vector is constructed; the click heat map of the updated cloud platform includes the distribution of users' clicks on the first interactive content, and by analyzing the heat values ​​and click behavior patterns of different areas in the heat map, key features are extracted, and according to the business goals and content characteristics of the cloud platform, indicators for analyzing the interaction are set, including the number of clicks, click-through rate, average stay time, and regional heat value ratio; the data corresponding to each indicator is extracted from the click heat map of the updated cloud platform and real-time user operation data; the numerical values ​​corresponding to each indicator are arranged in order to obtain an interaction effect vector; by constructing the interaction effect vector, the effect of the first interactive content can be quickly evaluated, and the problems existing in the interactive content and the corresponding optimization directions can be analyzed.

[0121] Preferably, the first interactive content is updated according to the calculated interactive effect vector to intelligently update the interactive content of the cloud platform; the interactive effect vector includes the user's interactive feedback information on the first interactive content, and analysis of each indicator value in the vector can determine the advantages and disadvantages of the interactive content, formulate corresponding optimization strategies, adjust and update the first interactive content, make the content more in line with user needs, optimize the content based on real-time user feedback, and enable the interactive content of the cloud platform to dynamically adapt to changes in user needs, improve the quality of interactive content and user experience, enhance the platform's attractiveness and stickiness to users, and improve the platform's operating results.

[0122] Furthermore, the first interactive content is updated through the interactive effect vector to intelligently update the interactive content on the cloud platform, including:

[0123] S901: Decompose the first interactive content according to the interactive effect vector to obtain first content, second content, and third content;

[0124] S902: Update corresponding contents in the first content, the second content, and the third content respectively using a preset content update model to construct an updated content sequence;

[0125] S903: Replace and update corresponding interface elements in the first interactive content according to the update content sequence, so as to intelligently update the interactive content on the cloud platform.

[0126] In this embodiment, the first interactive content is decomposed according to the interaction effect vector to obtain the first content, the second content and the third content; according to the structure and functional characteristics of the interactive content of the cloud platform, the content decomposition rules are set, and the interactive content of the e-commerce product details page is divided into the product display area, the user evaluation area, and the purchase operation area according to the function; according to the decomposition standard, the first interactive content is decomposed into the first content, the second content and the third content; through content decomposition, each part of the content can be analyzed and optimized separately, avoiding direct optimization of the content as a whole, and improving the accuracy and efficiency of interactive content optimization.

[0127] Specifically, for the decomposed first content, second content and third content, the contents are updated respectively through a preset content update model, and the updated contents are combined to construct an updated content sequence; the content update model includes models such as decision trees and neural networks. The content update model in this embodiment is a neural network model. A large amount of historical content data and corresponding user feedback data are used to train the neural network model to obtain a pre-trained neural network model. Each part of the content is input into the trained content update model respectively. The model analyzes each part of the content and the user feedback data and outputs a corresponding update strategy and updated content; according to the display order or logical relationship of the content in the interface, the updated first content, second content and third content are arranged in sequence to obtain an updated content sequence; by updating different contents separately, corresponding optimization solutions can be provided for each part of the content, so that the updated content is more in line with user needs and behavioral habits.

[0128] Preferably, the original interface elements in the cloud platform interface are replaced with the updated content based on the updated content sequence. After the interface element replacement is complete, the interface functionality is tested to check whether the updated content displays normally and whether the functions are usable, thereby achieving real-time updates of interactive content. The optimized content is quickly replaced in the cloud platform operation interface, enabling the platform to respond promptly to user needs and behavioral changes, improving user experience and satisfaction on the platform. Content testing can ensure that the updated content is stable and reliable, avoiding functional failures and user churn caused by updates.

[0129] Example 2:

[0130] In this embodiment, if Figure 4 , provides a cloud platform interactive content intelligent update system for implementing a cloud platform interactive content intelligent update method, including:

[0131] The cloud platform click heat map construction module analyzes user operation behaviors and calculates heat values ​​based on pre-acquired user operation data to construct the cloud platform click heat map;

[0132] The intent feature vector construction module uses a preset intent analysis model to analyze the user's operation intention from the cloud platform's click heat map and construct an intent feature vector;

[0133] The interactive content optimization module classifies user intentions according to the intention feature vector using a preset content optimization model, and optimizes the interactive content of the cloud platform in layers according to the classified user intentions to obtain the first interactive content;

[0134] The interactive content update module updates the cloud platform click heat map within a preset time period, analyzes the user's interaction with the first interactive content based on the updated cloud platform click heat map, updates the first interactive content, and intelligently updates the cloud platform interactive content.

[0135] In this embodiment, the cloud platform click heat map construction module collects user operation data, specifically including user behavior information such as click location, dwell time, and operation frequency on the cloud platform, divides the cloud platform operation interface into a grid, and calculates the heat value of each area based on the user operation data. The higher the heat value, the higher the user's attention to the interactive content in the area. The cloud platform click heat map is constructed based on the heat value; by constructing the cloud platform click heat map, the user's operation behavior is visualized, and the key areas of user attention and neglected areas can be quickly located, providing data support for analyzing user intentions and optimizing the platform interface layout and content display; the intention feature vector construction module analyzes the user's operation intention based on the cloud platform click heat map, screens out the first gradient area with strong user operation intention, uses a preset intention analysis model to extract the characteristics of the user's operation behavior in the first gradient area, including the number of clicks, click location distribution, etc., analyzes the user's operation intention through the intention analysis model, and constructs the intention feature vector; combining the cloud platform click heat map to analyze the user's operation intention and construct the intention feature vector, it can convert the user's intention into a computable and processable feature vector, and provide a basis for optimizing the platform interactive content according to the user's intention.

[0136] Specifically, the interactive content optimization module analyzes user intent strength based on intent feature vectors using a preset content optimization model, categorizing user intent into multiple levels: high, medium, and low. Differentiated content optimization strategies are developed for different levels of user intent, such as generating real-time interactive scenarios for high-level user intent, dynamically reorganizing and enhancing content for medium-level user intent, and adjusting content dynamics for low-level user intent. This results in a layered optimization of the cloud platform's interactive content, resulting in the first interactive content. This layered optimization allows for varying degrees of optimization based on the strength of user intent, improving the optimization efficiency of the platform's interactive content and boosting user engagement and satisfaction. The interactive content update module updates the cloud platform's click heat map based on real-time user action data within a preset time period. By analyzing the updated heat map and user feedback on the first interactive content, the module uses a preset content update model to update each component separately, constructing an updated content sequence, and replacing and updating the cloud platform's interactive content. By updating interactive content in real time, it can adapt to users' evolving needs and behavioral habits, preventing outdated interactive content and enhancing user experience.

[0137] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A cloud platform interactive content intelligent update method, characterized in that: include: Based on the pre-acquired user operation data, analyze the user operation behavior and calculate the heat value to build the cloud platform click heat map; Analyze the user's operation intention from the click heat map of the cloud platform through a preset intention analysis model and construct an intention feature vector; According to the intention feature vector, the user intention is graded using a preset content optimization model, and the interactive content of the cloud platform is hierarchically optimized according to the graded user intention to obtain first interactive content; Within a preset time period, the cloud platform click heat map is updated, and the user's interaction with the first interactive content is analyzed in combination with the updated cloud platform click heat map, and the first interactive content is updated to intelligently update the cloud platform interactive content.

2. A cloud platform interactive content intelligent updating method according to claim 1, characterized in that: The method of analyzing user operation behaviors and calculating heat values ​​based on pre-acquired user operation data and constructing a cloud platform click heat map includes: Based on the pre-acquired user operation data, analyze the user's click behavior on the interactive content of the cloud platform on different devices to obtain the click analysis results; On the cloud platform operation interface, the heat values ​​of different positions of the interface are calculated according to the click analysis results, and a cloud platform click heat map is constructed.

3. A cloud platform interactive content intelligent updating method according to claim 2, characterized in that: On the cloud platform operation interface, the heat values ​​of different positions of the interface are calculated according to the click analysis results, and a cloud platform click heat map is constructed, including: Divide the cloud platform operation interface into grids according to the preset grid size to obtain multiple grid areas; For each grid area, the click analysis results are analyzed using a preset thermal analysis model to calculate the thermal value; According to the thermal value of each grid area, a thermal value matrix is ​​constructed; Based on the thermal value matrix, a cloud platform click heat map is constructed.

4. A cloud platform interactive content intelligent update method according to claim 1, characterized in that: The method of analyzing the user's operation intention from the cloud platform click heat map using a preset intention analysis model and constructing an intention feature vector includes: According to the cloud platform click heat map, the cloud platform operation interface is gradient-divided and the corresponding gradient value is calculated, and the first gradient area where the gradient value is greater than the preset gradient threshold is screened out; The user's operation intention in the first gradient area is analyzed through a preset intention analysis model to construct an intention feature vector.

5. A cloud platform interactive content intelligent update method according to claim 4, characterized in that: The method of analyzing the user's operation intention in the first gradient area by using a preset intention analysis model and constructing an intention feature vector includes: In the first gradient region, the user's operation intention is analyzed using a preset intention analysis model to obtain a first intention feature vector; Mapping the first intention feature vector to the cloud platform operation interface according to a preset feature mapping rule to obtain a second intention feature vector; The first intention feature vector and the second intention feature vector are combined to construct an intention feature vector.

6. A cloud platform interactive content intelligent updating method according to claim 1, characterized in that: According to the intention feature vector, the user intention is graded using a preset content optimization model, and the interactive content of the cloud platform is hierarchically optimized according to the graded user intention to obtain first interactive content, including: According to the intention feature vector, the user's intention strength is analyzed through the preset content optimization model, and the user intention is graded to obtain multi-level user intention; According to the multi-level user intentions, the interactive content of the cloud platform is hierarchically optimized to obtain first interactive content, wherein the multi-level user intentions include high-level user intentions, mid-level user intentions and low-level user intentions.

7. A cloud platform interactive content intelligent update method according to claim 6, characterized in that: According to the multi-level user intentions, the interactive content of the cloud platform is hierarchically optimized to obtain first interactive content, including: For high-level user intent, the first optimization instruction is generated by generating real-time interactive scenarios; For intermediate user intent, the second optimization instruction is generated by dynamically reorganizing the interactive content and enhancing its effect; For low-level user intent, generate third optimization instructions by adjusting the dynamic effects of interactive content; In combination with the first optimization instruction, the second optimization instruction and the third optimization instruction, the interactive content of the cloud platform is optimized in layers to obtain first interactive content.

8. A cloud platform interactive content intelligent updating method according to claim 1, characterized in that: The step of updating the cloud platform click heat map within a preset time period, analyzing the user's interaction with the first interactive content in combination with the updated cloud platform click heat map, and updating the first interactive content to intelligently update the cloud platform interactive content includes: Within a preset time period, the cloud platform click heat map is updated according to real-time user operation data to obtain an updated cloud platform click heat map; Analyzing the user's interaction with the first interactive content based on the click heat map of the updated cloud platform, and constructing an interaction effect vector; The first interactive content is updated through the interactive effect vector to intelligently update the cloud platform interactive content.

9. A cloud platform interactive content intelligent updating method according to claim 8, characterized in that: Updating the first interactive content by using the interactive effect vector to intelligently update the interactive content on the cloud platform includes: Decomposing the first interactive content according to the interactive effect vector to obtain first content, second content, and third content; Using a preset content update model, corresponding contents in the first content, the second content, and the third content are updated respectively to construct an updated content sequence; According to the update content sequence, the corresponding interface elements in the first interactive content are replaced and updated to intelligently update the cloud platform interactive content.

10. A cloud platform interactive content intelligent update system, characterized in that: A method for intelligently updating interactive content on a cloud platform according to any one of claims 1 to 9, comprising: The cloud platform click heat map construction module analyzes user operation behaviors and calculates heat values ​​based on pre-acquired user operation data to construct the cloud platform click heat map; An intention feature vector construction module, which uses a preset intention analysis model to analyze the user's operation intention from the click heat map of the cloud platform and construct an intention feature vector; An interactive content optimization module, which classifies user intentions according to the intention feature vector using a preset content optimization model, and performs hierarchical optimization on the interactive content of the cloud platform according to the classified user intentions to obtain first interactive content; The interactive content update module updates the cloud platform click heat map within a preset time period, analyzes the user's interaction with the first interactive content in combination with the updated cloud platform click heat map, updates the first interactive content, and intelligently updates the cloud platform interactive content.

Images