Live broadcast content personalized recommendation method and device based on user portrait

Abstract

The invention provides a live broadcast content personalized recommendation method and device based on a user portrait. The method comprises the following steps: collecting real-time hot word data of each live broadcast content on a current live broadcast platform; constructing a live broadcast hot word structure tree based on the real-time hot word data of each live broadcast content; performing user portrait analysis based on the user portrait data to obtain user interest hot words; performing association mapping based on the live broadcast hot word structure tree of each live broadcast content and the user interest hot word to obtain a hot word association mapping result; and determining a matching degree value between each live broadcast content and the user interest hot word based on the hot word association mapping result of each live broadcast content, and generating a live broadcast content personalized recommendation list based on the matching degree value of each live broadcast content. According to the invention, the accuracy and diversity of live broadcast content recommendation are improved, and poor homogenization and timeliness are avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of computer, in particular to a live content personalized recommendation method based on user portrait and device thereof. BACKGROUND

[0002] With the booming development of the Internet live industry, the number of live content presents explosive growth, covering games, entertainment, education, e-commerce and other fields. Users in the vast amount of live content are difficult to quickly find the content that meets their own interests and needs, resulting in a decline in user experience, and the propagation efficiency of high-quality live content is also affected. In order to solve this problem, various live content recommendation methods have emerged, and the core purpose is to accurately push the live content that users may be interested in by analyzing user behavior data, content features and other information, improve user's viewing time and satisfaction, and promote the benign development of live platform.

[0003] However, the existing live content recommendation method has a major technical defect: in the recommendation process, the feature mining of live content is not deep enough, often only relying on single-dimensional keywords or simple content classification for matching, which cannot effectively capture the deep semantic association and dynamic change trend of live content. At the same time, when combining user information, the user's interest features and the complex features of live content cannot be accurately and dynamically associated, resulting in the problem of serious homogeneity and poor timeliness of the recommendation result, which is difficult to meet the user's personalized and diversified live content demand. SUMMARY

[0004] The present application provides a live content personalized recommendation method based on user portrait and device thereof, in order to improve the accuracy and diversity of live content recommendation, and avoid the problems of homogeneity and poor timeliness.

[0005] In the first aspect, the present application provides a live content personalized recommendation method based on user portrait, comprising: Collecting real-time hot word data of each live content being carried out on the current live platform; the real-time hot word data includes live hot word text and the occurrence frequency of each live hot word text; Building a live hot word structure tree based on the real-time hot word data of each live content; each node in the live hot word structure tree represents a live hot word text, the connection relationship between nodes represents the subordinate relationship between live hot word levels, and the attribute information of nodes represents the occurrence frequency; Performing user portrait analysis based on user portrait data to obtain user interest hot words; the user portrait data includes user's historical viewing records, historical interaction records and interest tags in registration records; mapping the live hot words structure tree of each live content and the user interest hot words to obtain a hot word association mapping result; the hot word association mapping result includes the number of nodes in which the user interest hot words appear in the live hot words structure tree, and the hierarchical information and the appearance frequency of each appearing node in the live hot words structure tree; determining the matching degree value between each live content and the user interest hot words based on the hot word association mapping result of each live content, and generating a live content personalized recommendation list based on the matching degree value of each live content.

[0006] In a second aspect, the present application further provides a live content personalized recommendation device based on user portrait, which is applied to the live content personalized recommendation method based on user portrait as described in the first aspect; the live content personalized recommendation device based on user portrait includes: A collection module is configured to collect real-time hot word data of each live content being performed on a current live platform; the real-time hot word data includes live hot word texts and the appearance frequency of each live hot word text. A structure tree construction module is configured to construct a live hot words structure tree based on the real-time hot word data of each live content; each node in the live hot words structure tree represents a live hot word text, the connection relationship between the nodes represents the subordinate relationship between the live hot word levels, and the attribute information of the nodes represents the appearance frequency. A user portrait analysis module is configured to perform user portrait analysis based on user portrait data to obtain user interest hot words; the user portrait data includes the interest tags in the historical viewing records, historical interaction records and registration records of the user. A hot word association mapping module is configured to perform association mapping based on the live hot words structure tree of each live content and the user interest hot words to obtain a hot word association mapping result; the hot word association mapping result includes the number of nodes in which the user interest hot words appear in the live hot words structure tree, and the hierarchical information and the appearance frequency of each appearing node in the live hot words structure tree. A live content recommendation module is configured to determine the matching degree value between each live content and the user interest hot words based on the hot word association mapping result of each live content, and generate a live content personalized recommendation list based on the matching degree value of each live content.

[0007] In a third aspect, the present application further provides an electronic device, which includes a memory for storing a computer software program, and a processor for reading and executing the computer software program to realize the live content personalized recommendation method based on user portrait as described above.

[0008] In a fourth aspect, the present application also provides a non-transitory computer readable storage medium, wherein the storage medium stores a computer software program, and the computer software program, when executed by a processor, implements the live content personalized recommendation method based on user portrait as described above.

[0009] In a fifth aspect, the present application also provides a computer program product comprising a computer program, and the computer program, when executed by a processor, implements the live content personalized recommendation method based on user portrait as described above.

[0010] The live content personalized recommendation method based on user portrait provided by the embodiments of the present application constructs a live hot word structure tree according to real-time hot word data of each live content, deeply mines deep semantic association and features of the live content by dividing hot word levels and occurrence frequencies, accurately captures user interest hot words by performing user portrait analysis on user portrait data, and then performs association mapping on the built live hot word structure tree and the user interest hot words, combines the number of occurrence nodes of the user interest hot words in the live hot word structure tree, and the level information and occurrence frequencies of each occurrence node in the live hot word structure tree, accurately associates live content features and user interest features, and finally generates a live content personalized recommendation list according to a matching degree value between live content and user interest hot words determined according to the hot word association mapping result, ensures that the recommendation result meets the personalized needs of the user, and dynamically captures changes in live content and user interest, improves the accuracy and diversity of the recommendation, and avoids the problems of homogeneity and poor timeliness. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 is a flowchart of the live content personalized recommendation method based on user portrait provided by the embodiments of the present application; Figure 2 is a structural diagram of the live content personalized recommendation device based on user portrait provided by the embodiments of the present application; Figure 3 is an embodiment diagram of an electronic device provided by the embodiments of the present application; Figure 4 is an embodiment diagram of a computer readable storage medium provided by the embodiments of the present application. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0013] In the description of the present invention, the terms "first" and "second" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of the said features. In the description of the present invention, "plural" means two or more, unless otherwise specifically defined.

[0014] In the description of the present invention, the term "for example" is used to mean "serving as an example, illustration, or explanation". Any embodiment described as "for example" in the present invention is not necessarily construed as more preferred or more advantageous than other embodiments. The following description is given to enable any person skilled in the art to implement and use the present invention. In the following description, details are set forth for purposes of explanation. It should be understood that those of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other instances, well-known structures and processes are not elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed herein.

[0015] Refer to Figure 1 , Figure 1 is a schematic flowchart of the live content personalized recommendation method based on user portraits provided by the present invention. In the embodiments of the present invention, the execution subject of the live content personalized recommendation method based on user portraits is a live recommendation device. Therefore, the live content personalized recommendation method based on user portraits includes: Step 10, collect the real-time hot word data of each live content being broadcast on the current live platform. The real-time hot word data includes the live hot word text and the occurrence frequency of each live hot word text.

[0016] Optionally, the live recommendation device obtains in real time the text information in the audio stream and video stream of each live content being broadcast on the current live platforms. Among them, the audio stream needs to be converted into text through speech-to-text technology, and the video stream needs to extract text contents such as bullet screens and subtitles.

[0017] Furthermore, the live recommendation device preprocesses the collected text, including removing punctuation marks and stop words (such as meaningless words like "de" and "le"), and performing word segmentation. Further, the live recommendation device counts the occurrence frequency of each word after word segmentation, screens out the words with higher frequencies as the real-time hot words of the live content, and obtains the real-time hot word data including the live hot word text and the corresponding occurrence frequency.

[0018] In one embodiment, a live stream titled "XX Brand Makeup Tutorial" is underway on a live streaming platform. The audio stream of the live stream is acquired in real-time, and text such as "Today I'm recommending this foundation; the texture is very light and the coverage is good..." is obtained through speech-to-text technology. Simultaneously, the text displayed in the video's comments, such as "I've used this foundation, it's super good!" and "Please provide a link to the foundation," is extracted. These texts are preprocessed, removing punctuation and stop words such as "today" and "to everyone," and then segmented into words such as "foundation," "texture," "lightweight," "coverage effect," "good," and "link." Statistics show that "foundation" appeared 8 times, "good" appeared 5 times, and "coverage effect" appeared 3 times. Therefore, the real-time hot word data for this live stream is as follows: "foundation," frequency 8 times; "good," frequency 5 times; and "coverage effect," frequency 3 times.

[0019] Step 20: Construct a live stream hot word structure tree based on the real-time hot word data for each live stream content. Each node in the live stream hot word structure tree represents the text of a live stream hot word, the connection relationship between nodes represents the hierarchical relationship between live stream hot words, and the attribute information of the nodes represents the frequency of occurrence.

[0020] Furthermore, the live streaming recommendation device performs semantic analysis on the hot words to clarify the hierarchical relationship between them. Generally, broader hot words are used as upper-level nodes, and more specific hot words are used as lower-level nodes. The device then presents each live streaming hot word text as a node, with the hierarchical relationship between nodes reflected through connections. The frequency of hot words is also used as an attribute of each node, thus completing the construction of the live streaming hot word structure tree, as detailed in steps 201 to 204.

[0021] Step 30: Perform user profile analysis based on user profile data to obtain user interest hot keywords. User profile data includes user's historical viewing records, historical interaction records, and interest tags in registration records.

[0022] Furthermore, the live streaming recommendation device collects user profile data, which includes users' historical viewing records, historical interaction records, and interest tags in their registration records. Historical viewing records are analyzed to statistically analyze the types of live streaming content watched by users and related trending keywords; historical interaction records, such as likes, comments, shares, and purchases, are summarized to identify trending keywords related to live streaming content; and combined with interest tags from registration records, this information is analyzed to extract words that users frequently use and that have high user interest, identifying these as user interest keywords.

[0023] In one embodiment, user A's user profile data shows that their historical viewing records indicate they have watched multiple beauty-related live streams, especially tutorials on base makeup; their historical interaction records show they have repeatedly liked and commented on content related to "foundation" and "concealing effect" in beauty live streams, and they have previously purchased a certain brand of foundation; their registration records show interest tags for "beauty" and "base makeup." Analyzing this data, user A frequently uses terms such as "beauty," "base makeup," "foundation," and "concealing effect," and shows a high level of interest in these terms. Therefore, user A's top interest keywords are determined to be "beauty," "base makeup," "foundation," and "concealing effect."

[0024] Step 40: Based on the live stream hot word structure tree and user interest hot words for each live stream content, perform an association mapping to obtain the hot word association mapping result. The hot word association mapping result includes the number of nodes in the live stream hot word structure tree where user interest hot words appear, as well as the hierarchical information and frequency of each node in the live stream hot word structure tree.

[0025] Furthermore, the live streaming recommendation device associates and maps the live streaming hot word structure tree of each live stream content with user interest hot words. It checks one by one whether a user interest hot word has a corresponding node in the live streaming hot word structure tree; if so, it records the number of nodes. For each existing node, it also records its hierarchical information (i.e., the node's position) and frequency of occurrence in the live streaming hot word structure tree. This ultimately forms a hot word association mapping result that includes the number of nodes containing user interest hot words in the live streaming hot word structure tree, as well as the hierarchical information and frequency of each node in the structure tree.

[0026] Continuing with the above example, using the example of the keyword structure tree for user A's interest keywords "makeup," "base makeup," "foundation," "concealing effect," and the live stream "XX brand makeup tutorial," the live stream recommendation device performs association mapping. It finds that "makeup" corresponds to the root node (level 1) in the structure tree, appearing 10 times; "base makeup" corresponds to the "base makeup product" node (level 2), appearing 7 times; "foundation" corresponds to the "foundation" node (level 3), appearing 8 times; and "concealing effect" corresponds to the "concealing effect" node (level 4), appearing 3 times. The number of nodes for this user's interest keywords in the live stream keyword structure tree is 4. Therefore, the keyword association mapping result is: 4 nodes; "makeup" node level 1, frequency 10; "base makeup product" node level 2, frequency 7; "foundation" node level 3, frequency 8; and "concealing effect" node level 4, frequency 3.

[0027] Step 50: Determine the matching degree value between each live content and the user's interest hot words based on the hot word association mapping results of each live content, and generate a personalized recommendation list of live content based on the matching degree value of each live content.

[0028] Furthermore, the live streaming recommendation device calculates a matching degree value based on the hot word association mapping results of each live streaming content. Different weights can be set; generally, the shallower the node level (closer to the root node), the lower the weight, and the deeper the level, the higher the weight. Higher frequency of occurrence also results in higher weight. Optionally, in this embodiment of the invention, the matching degree value between the live streaming content and the user's interest hot words is obtained by multiplying the level weight and frequency weight of each matching node and then summing the results. Further, the live streaming recommendation device sorts the matching degree values ​​of all live streaming content and generates a personalized recommendation list of live streaming content in descending order.

[0029] In one embodiment, the weight of level 1 is set to 0.2, level 2 to 0.3, level 3 to 0.4, and level 4 to 0.5. The frequency weight is the frequency of occurrence divided by the highest frequency in the live stream keyword structure tree (in this example, the highest frequency is 10). For the live stream "XX Brand Makeup Tutorial", the "Makeup" node has a weight of 0.2*(10 / 10)=0.2; the "Base Makeup Products" node has a weight of 0.3*(7 / 10)=0.21; the "Foundation" node has a weight of 0.4*(8 / 10)=0.32; and the "Concealer Effect" node has a weight of 0.5*(3 / 10)=0.15. Therefore, the matching degree is 0.2+0.21+0.32+0.15=0.88.

[0030] Suppose there's another "YY Brand Skincare Livestream" on the platform, with a match score of 0.65 for user A's trending topics. Then, in the personalized recommendation list of user A's livestream content, sorted from highest to lowest match score, "XX Brand Makeup Tutorial" will appear before "YY Brand Skincare Livestream".

[0031] This invention constructs a live-stream hot word structure tree based on real-time hot word data for each live-stream content. By dividing hot words into levels and frequencies, it delves into the deep semantic relationships and features of the live-stream content. Through user profile analysis of user profile data, it accurately captures user interest hot words. Then, it uses the constructed live-stream hot word structure tree and user interest hot words for association mapping. Combining the number of nodes where user interest hot words appear in the live-stream hot word structure tree, as well as the level information and frequency of each node in the live-stream hot word structure tree, it achieves a precise association between live-stream content features and user interest features. Finally, based on the matching degree value between the live-stream content and user interest hot words determined by the hot word association mapping results, it generates a personalized recommendation list of live-stream content. This ensures that the recommendation results meet the personalized needs of users and can dynamically capture changes in live-stream content and user interests, improving the accuracy and diversity of recommendations and avoiding homogenization and poor timeliness.

[0032] In one embodiment, steps 201 to 204 include: Step 201: For any two first and second live stream hot word texts in the same live stream content, if the text similarity between the first and second live stream hot word texts is greater than or equal to the similarity threshold, then determine the text inclusion relationship between the first and second live stream hot word texts.

[0033] Optionally, the live streaming recommendation device selects any two hot word texts from the real-time hot word data within the same live streaming content, namely, the first live streaming hot word text and the second live streaming hot word text. A text similarity calculation algorithm is used to calculate the similarity between these two hot word texts. A similarity threshold is set; if the calculated similarity is greater than or equal to this threshold, it is determined that there is a text inclusion relationship between the first and second live streaming hot word texts. The text similarity calculation uses a cosine similarity algorithm.

[0034] In one embodiment, among the real-time trending keywords in the "XX Brand Makeup Tutorial" live stream, the first trending keyword text is selected as "base makeup products," and the second trending keyword text is selected as "foundation." The live stream recommendation device converts these two trending keyword texts into word vectors and calculates a similarity of 0.7 using the aforementioned cosine similarity formula. A similarity threshold of 0.6 is set. Since 0.7 > 0.6, it is determined that there is a textual inclusion relationship between "base makeup products" and "foundation."

[0035] Step 202: Determine the node relationship set based on text inclusion relationship, and construct the hot word structure tree and branch of the same live content based on hierarchical clustering combined with the node relationship set.

[0036] Furthermore, the live streaming recommendation device determines the node relationship set based on text inclusion relationships, as detailed in steps 2021 to 2024. The node relationship set includes parent-child node relationships and parent-node compatible sibling node relationships between hot word texts.

[0037] Furthermore, the live streaming recommendation device employs a hierarchical clustering method, combining a set of node relationships to construct a hot word structure tree with branches for the same live streaming content. Within each branch, the live streaming hot word text without a parent node is used as the root node. Based on the parent-child relationships of the root node in the node relationship set, all direct child nodes are connected to the root node. For each node designated as the first target child node, all direct child nodes are connected to it based on its parent-child relationships in the node relationship set. For any two nodes designated as second target nodes, parent-child connections and sibling connections are established respectively based on their parent-sibling relationships in the node relationship set.

[0038] Optionally, nodes within the same branch of each hot word structure tree form a complete hierarchical chain according to their subordinate relationships, denoted as the same branch of the hot word structure tree. ,in, This represents the number of branches in the hot word structure tree. Indicates the first Each hot word structure tree has a branch containing a hierarchical sequence of hot word texts.

[0039] Continuing with the above embodiments, in the "XX Brand Makeup Tutorial" live stream, the node relationship set includes relationships such as "Makeup Product" being the parent node of "Base Makeup Product," "Base Makeup Product" being the parent node of "Foundation," and "Foundation" being the parent node of "XX Brand Foundation," "Texture," "Lightweight," "Coverage Effect," and "Easy to Use." "Texture" and "Lightweight" are also parent nodes that are compatible with each other as sibling nodes. The live stream recommendation device uses "Makeup Product," which has no parent node, as the root node, and connects its direct child node "Base Makeup Product" to the root node. "Base Makeup Product" is the first target child node, and connects its direct child node "Foundation" to itself. "Foundation" is also the first target child node, and connects its direct child nodes "XX Brand Foundation," "Texture," "Lightweight," "Coverage Effect," and "Easy to Use" to itself. For the two second target nodes, "Texture" and "Lightweight," sibling node connections are established, and both are also connected to "Foundation" as parent-child nodes, forming a hot word structure tree with the same branch.

[0040] Step 203: Construct cross-branch relationships of the hot word structure tree based on the same branch of the hot word structure tree for different live streaming content.

[0041] Furthermore, the live streaming recommendation device analyzes the same branches of the hot word structure trees for different live streaming content to find the correlation between hot word texts in the same branches of different hot word structure trees. This correlation can be semantically similar, conceptually related, etc. Further, based on these correlations, the live streaming recommendation device constructs cross-branch relationships in the hot word structure trees, clarifying the connection methods and degree of correlation between the same branches of the hot word structure trees for different live streaming content, as detailed in steps 2301 to 2034.

[0042] Step 204: Construct a live-streaming hot word structure tree based on the same-branch and cross-branch relationships of the hot word structure tree.

[0043] Furthermore, the live streaming recommendation device integrates the same-branch and cross-branch relationships of the hot word structure trees for each live streaming content. The same-branch hot word structure trees are arranged according to their internal hierarchical chains, and then the different hot word structure trees are connected through the cross-branch relationships to obtain the live streaming hot word structure tree, as shown in steps 2041 to 2044. The live streaming hot word structure tree can comprehensively reflect the hierarchical relationship between the hot words of each live streaming content and the cross-live streaming content relationship.

[0044] The live streaming hot word structure tree constructed in this embodiment of the invention can clearly present the hierarchical relationship between hot words in various live streaming content, including the detailed classification and subordinate connection of hot words within the same live streaming content. It can also reflect the correlation between hot words in different live streaming content, providing accurate hot word relationships for subsequent live streaming content recommendations based on user interest hot words. Therefore, it can more accurately find live streaming content that matches user interests and improve the accuracy and rationality of personalized live streaming content recommendations.

[0045] In one embodiment, steps 2021 to 2024 include: Step 2021: If the semantic inclusion relationship is that the first semantic range of the first live hot word text completely includes the second semantic range of the second live hot word text, then the first live hot word text is determined to be the first parent-child node relationship of the second live hot word text.

[0046] Optionally, the live streaming recommendation device further analyzes the semantic scope of a first and a second set of trending live streaming words that have a textual inclusion relationship within the same live streaming content. Through semantic analysis technology, the first semantic scope of the first set of trending live streaming words and the second semantic scope of the second set of trending live streaming words are determined. If the analysis determines that the first semantic scope completely encompasses the second semantic scope, then the first set of trending live streaming words is determined as the parent node of the second set of trending live streaming words, thus forming a first parent-child node relationship.

[0047] In one embodiment, during a live stream of "XX Brand Makeup Tutorial," the first trending keyword was "base makeup products," and the second was "foundation." The live stream recommendation device performed semantic analysis on both. The first semantic scope of "base makeup products" encompasses all makeup products used for facial base application, including foundation, cushion compacts, and BB creams. The second semantic scope of "foundation" refers only to liquid base makeup products that provide concealing and color correction. Clearly, the first semantic scope completely includes the second semantic scope; therefore, "base makeup products" is determined to be the first parent-child node of "foundation."

[0048] Step 2022: If the semantic inclusion relationship is that the second semantic range completely includes the first semantic range, then determine that the second live hot word text is the second parent-child node relationship of the first live hot word text.

[0049] Furthermore, the live streaming recommendation device also analyzes the semantic scope of the first and second live streaming trending words that have a textual inclusion relationship. When the analysis results show that the second semantic scope of the second live streaming trending word completely includes the first semantic scope of the first live streaming trending word, the second live streaming trending word is determined to be the parent node of the first live streaming trending word, forming a second parent-child node relationship.

[0050] Continuing with the live stream, the first trending keyword was "XX brand foundation," and the second was simply "foundation." The live stream recommendation algorithm determined that the first semantic scope of "XX brand foundation" refers only to foundation products from a specific brand; the second semantic scope of "foundation" encompasses foundation products from all brands. Since the second semantic scope completely includes the first, "foundation" is determined to be the second parent-child node of "XX brand foundation."

[0051] Step 2023: If the semantic inclusion relationship is that the first semantic range does not completely include the second semantic range, then determine that the first live hot word text and the second live hot word text are parent node compatible sibling nodes.

[0052] Furthermore, for the first and second live hot word texts that have a text inclusion relationship, after analyzing their semantic range, the live recommendation device finds that the first semantic range of the first live hot word text does not completely include the second semantic range of the second live hot word text, and the second semantic range does not completely include the first semantic range, that is, the semantic ranges of the two are partially related but do not completely include each other, then the first and second live hot word texts are determined to be parent node compatible sibling nodes.

[0053] Continuing with the trending keywords in live streaming, the first trending keyword was "texture," and the second was "lightweight." The live streaming recommendation system analyzed the semantic scope. The first semantic scope of "texture" refers to the properties and state of an object, including the fineness and consistency of a product; the second semantic scope of "lightweight" refers to the product's light and non-heavy texture. The first semantic scope does not completely encompass the second semantic scope; they are semantically related but not mutually exclusive. Therefore, "texture" and "lightweight" are determined to be parent nodes with compatible sibling relationships.

[0054] Step 2024: Determine the first parent-child node relationship, the second parent-child node relationship, and the parent node compatible sibling node relationship as a set of node relationships.

[0055] Furthermore, the live streaming recommendation device summarizes the first parent-child node relationship, the second parent-child node relationship, and the parent node compatible sibling node relationship, integrating different types of node relationships to obtain a node relationship set. The node relationship set covers various node relationships between hot word texts in the same live streaming content.

[0056] Continuing with the "XX Brand Makeup Tutorial" live stream, the previous steps established the first parent-child relationship between "base makeup products" and "foundation," the second parent-child relationship between "foundation" and "XX brand foundation," the parent-child sibling relationship between "texture" and "lightweight," and other parent-child relationships such as "foundation" and "texture," and "foundation" and "lightweight." The live stream recommendation device aggregated these relationships to form the node relationship set for the live stream.

[0057] The embodiments of the present invention can accurately determine the node relationships between various hot words in the same live broadcast content, forming a complete set of node relationships. This provides a clear basis for the subsequent construction of the hot word structure tree and its branches, ensuring the accuracy and logic of the node connections within the hot word structure tree and its branches. This allows the hot word structure tree to more accurately reflect the hierarchical subordination and association between hot words, laying a reliable relational foundation for the subsequent stages of personalized recommendation of live broadcast content.

[0058] In one embodiment, steps 2031 to 2034 include: Step 2031: For any two first target live stream content with the same branch of the first hot word structure tree and the second target live stream content with the same branch of the second hot word structure tree, determine the semantic similarity between the first target live stream hot word text and the second target live stream hot word text based on the first target live stream hot word text in the first hot word structure tree and the second target live stream hot word text in the second hot word structure tree.

[0059] Optionally, the live streaming recommendation device selects any two different live streaming contents, namely the first target live streaming content and the second target live streaming content, and extracts the same branch of their hot word structure tree, denoted as the first hot word structure tree branch and the second hot word structure tree branch. Hot word texts for the first target live streaming content are selected from the first hot word structure tree branch, and hot word texts for the second target live streaming content are selected from the second hot word structure tree branch. These two target live streaming hot word texts are analyzed using a semantic similarity calculation method to determine their semantic similarity. Semantic similarity is used to measure the degree of semantic connection between the two hot word texts.

[0060] In one embodiment, the first target live stream content is "XX brand beauty tutorial," and the first target live stream hot word text in the same branch of its first hot word structure tree is "beauty products"; the second target live stream content is "ZZ brand makeup recommendation," and the second target live stream hot word text in the same branch of its second hot word structure tree is "makeup products." The live stream recommendation device calculates semantic similarity and finds that the semantic similarity between "beauty products" and "makeup products" is 0.8.

[0061] Step 2032: Based on semantic similarity and the first occurrence frequency of the first target live stream hot word text and the second occurrence frequency of the second target live stream hot word text, determine the semantic association strength between the first target live stream hot word text and the second target live stream hot word text.

[0062] Furthermore, the live streaming recommendation device calculates the semantic association strength between the first target live streaming hot word text and the second target live streaming hot word text based on the semantic similarity between them, combined with the first occurrence frequency of the first target live streaming hot word text and the second occurrence frequency of the second target live streaming hot word text, according to a preset calculation formula.

[0063] The formula for calculating semantic association strength is: r(a,b)=s(a,b)*log[f(a)+f(b)+1].

[0064] Where r(a,b) represents the semantic association strength between the first target live stream hot word text h(a) and the second target live stream hot word text h(b), s(a,b) represents the semantic similarity between the first target live stream hot word text h(a) and the second target live stream hot word text h(b), f(a) represents the first occurrence frequency of the first target live stream hot word text h(a), f(b) represents the second occurrence frequency of the second target live stream hot word text h(b), and log() represents the logarithmic function.

[0065] Continuing with the above example, the first occurrence frequency of "beauty product" f(a) = 10, the second occurrence frequency of "makeup product" f(b) = 8, and the semantic similarity s(a,b) = 0.8. The semantic association strength is calculated according to the formula: r(a,b) = 0.8 * log(10 + 8 + 1) = 0.8 * log(19) ≈ 0.8 * 1.2788 = 1.023.

[0066] Step 2033: The maximum semantic association strength among the live hot word texts is determined as the branch association strength between the same branch of the first hot word structure tree and the same branch of the second hot word structure tree.

[0067] Furthermore, the live streaming recommendation device pairs all hot word texts in the same branch of the first hot word structure tree with all hot word texts in the same branch of the second hot word structure tree, and calculates the semantic association strength between each pair of hot word texts according to the method in step 2032. Further, among all the calculated semantic association strengths, the live streaming recommendation device selects the largest value and determines it as the branch association strength between the same branch of the first hot word structure tree and the same branch of the second hot word structure tree.

[0068] In one embodiment, within the same branch of the first hot word structure tree for "XX Brand Makeup Tutorial" and the same branch of the second hot word structure tree for "ZZ Brand Makeup Recommendation," besides "makeup products" and "makeup products," there are also multiple pairs of hot word texts such as "foundation products" and "eyeshadow," and "foundation" and "makeup tools." The semantic association strength between "makeup products" and "makeup products" is calculated to be 1.023, while the semantic association strengths of the other pairs of hot word texts are all less than this value. Therefore, the branch association strength between the two branches is determined to be 1.023.

[0069] Step 2034: If the branch association strength is greater than or equal to the preset association strength threshold, and the root nodes of the same branch of the first hot word structure tree and the same branch of the second hot word structure tree have a semantic inclusion relationship, then it is determined that there is a cross-branch subordinate relationship between the same branch of the first hot word structure tree and the same branch of the second hot word structure tree. Based on the cross-branch subordinate relationships between the same branches of all hot word structure trees, the cross-branch relationship of the hot word structure tree is determined.

[0070] Furthermore, a preset association strength threshold is set. If the branch association strength between the same branch of the first hot word structure tree and the same branch of the second hot word structure tree is greater than or equal to this threshold, and further analysis reveals that the root nodes of these two branches have a semantic inclusion relationship, the live streaming recommendation device determines that there is a cross-branch subordinate relationship between them. Further, the live streaming recommendation device summarizes the cross-branch subordinate relationships between the same branches of all hot word structure trees to determine the cross-branch relationships of the hot word structure trees.

[0071] In one embodiment, a preset association strength threshold of 0.8 is set. The root node of the first hot word tree structure for "XX Brand Makeup Tutorial" is "Makeup Products," and the root node of the second hot word tree structure for "ZZ Brand Makeup Recommendation" is "Makeup Products." It is known that the branch association strength between the two is 1.023 > 0.8, and the semantic scope of "Makeup Products" completely encompasses the semantic scope of "Makeup Products," meaning there is a semantic inclusion relationship between the root nodes. Therefore, a cross-branch subordinate relationship is determined between these two branches, and this relationship is included in the cross-branch relationship of the hot word tree structure.

[0072] The embodiments of this invention can accurately construct the cross-branch relationships between the same branches of the hot word structure tree of different live streaming content, clearly reflecting the degree of correlation and subordinate relationship between the hot word systems of different live streaming content. This makes the constructed live streaming hot word structure tree not only include the hierarchical relationship of hot words within a single live streaming content, but also reflect the relationship between hot words of different live streaming content. This provides a comprehensive basis for the accurate matching and personalized recommendation of cross-live streaming content based on user interest hot words, improving the richness and accuracy of the recommendations.

[0073] In one embodiment, steps 2041 to 2044 include: Step 2041: Based on the cross-branch subordination relationship in the hot word structure tree, construct a cross-live content hierarchical structure. The hot word structure tree within the same live content maintains the original hierarchical subordination relationship with the same branch. Add the corresponding occurrence frequency as attribute information to each node to obtain the initial structure tree.

[0074] Optionally, the live streaming recommendation device connects the same branches of the hot word structure trees of different live streaming content based on the cross-branch subordination relationships in the hot word structure tree, forming a hierarchical structure across live streaming content. For the same branch of the hot word structure tree within the same live streaming content, its original hierarchical subordination relationship remains unchanged. At the same time, the corresponding occurrence frequency is added as attribute information to each node in the initial structure tree, resulting in the initial structure tree. The connection relationships between nodes in the tree fully represent the subordination relationships between all hot word levels.

[0075] In one embodiment, the keyword structure tree for the "XX Brand Makeup Tutorial" live stream has a hierarchical relationship of "Makeup Products - Base Makeup Products - Foundation - Sub-nodes" within the same branch, while the keyword structure tree for the "ZZ Brand Makeup Recommendation" live stream has a hierarchical relationship of "Makeup Products - Eyeshadow - Eyeshadow Texture" within the same branch, and the two have a cross-branch subordinate relationship. The live stream recommendation device constructs a cross-live stream content hierarchical structure based on this cross-branch subordinate relationship, placing the "Makeup Products" branch under the "Makeup Products" branch. Branches within the same live stream content maintain their original hierarchy; for example, "Base Makeup Products" still belongs to "Makeup Products," and "Foundation" still belongs to "Base Makeup Products," etc. A frequency attribute is added to each node, such as an attribute of 10 for the "Makeup Products" node and 8 for the "Makeup Products" node, resulting in the initial structure tree.

[0076] Step 2042: Based on the sum of the frequencies of all nodes in each branch of the initial tree structure, and combined with the level depth of each branch in the initial tree structure, determine the importance index of each branch. The level depth of the root node is 1, and the depth increases by 1 for each level downward.

[0077] Furthermore, the live streaming recommendation device first calculates the sum of the occurrence frequencies of all nodes within each branch of the initial tree structure, and then determines the level depth of each branch in the initial tree structure, with the level depth of the root node being 1, and the depth increasing by 1 for each subsequent level. Further, the live streaming recommendation device combines these two data points to determine the importance index of each branch. Optionally, in this embodiment of the invention, the importance index is calculated using the formula: I = S / D, where I represents the branch importance index, S represents the sum of the occurrence frequencies of all nodes within the branch, and D represents the level depth of the branch.

[0078] In one embodiment, in the initial tree structure, the "Beauty Products" branch includes nodes "Beauty Products" (frequency 10), "Base Makeup Products" (frequency 7), "Foundation" (frequency 8), etc., with the sum of the frequencies of all nodes S = 10 + 7 + 8 + 6 + 2 + 4 + 3 + 5 = 45. The branch's level depth D = 1, and its importance index I = 45 / 1 = 45. The "Makeup Products" branch includes nodes "Makeup Products" (frequency 8), "Eyeshadow" (frequency 6), and "Eyeshadow Texture" (frequency 4), with the sum of the frequencies S = 8 + 6 + 4 = 18, level depth D = 2, and importance index I = 18 / 2 = 9.

[0079] Step 2043: The branches with importance indices greater than or equal to the preset index threshold are identified as core branches, and dynamic association paths are constructed based on the semantic similarity and semantic association strength of nodes in any two core branches.

[0080] Furthermore, a preset index threshold is set, and the live streaming recommendation device identifies branches with an importance index greater than or equal to this threshold as core branches. Further, the live streaming recommendation device performs pairwise analysis on nodes in any two core branches, calculating the semantic similarity and semantic association strength between the nodes (the semantic association strength calculation is the same as in step 2032), and connects nodes with semantic similarity greater than or equal to a preset similarity threshold and semantic association strength greater than or equal to a preset association strength threshold to construct dynamic association paths. These dynamic association paths are used to connect closely related nodes in different core branches.

[0081] In one embodiment, a preset index threshold of 10, a preset association strength threshold of 0.25, and a preset association strength threshold of 0.35 are set. The "beauty products" branch has an importance index of 45 > 10, and is therefore identified as a core branch. It is also assumed that the "skincare products" branch has an importance index of 15 > 10, and is also a core branch. The semantic similarity between the node "foundation" in the "beauty products" branch and the node "moisturizing essence" in the "skincare products" branch is 0.3. The frequency of "foundation" is 8, and the frequency of "moisturizing essence" is 10. The semantic association strength r = 0.3 * log(8 + 10 + 1) ≈ 0.3 * 1.2788 = 0.3836. Based on this, a dynamic association path of "foundation - moisturizing essence" is constructed.

[0082] Step 2044: The dynamic association path with the lowest path strength is identified as the target association path, and the target association path is added to the initial structure tree to obtain the live hot word structure tree. The path strength is the sum of the semantic association strengths between nodes in the dynamic association path.

[0083] Furthermore, the live streaming recommendation device calculates the path strength of each dynamic association path, which is the sum of the semantic association strengths between nodes in the dynamic association path. Among all dynamic association paths, the path with the lowest path strength is selected as the target association path and added to the initial structure tree, ultimately forming a complete live streaming hot word structure tree.

[0084] In one embodiment, there are two dynamic association paths: path one, "foundation liquid - moisturizing essence," has a path strength of 0.3836, and path two, "base makeup product - facial cleanser," has a path strength of 0.521. Path one has the lowest path strength, so it is identified as the target association path and added to the initial structure tree, resulting in a live streaming hot word structure tree that includes the original hierarchical relationship and the "foundation liquid - moisturizing essence" association path.

[0085] The live streaming hot word structure tree constructed in this embodiment of the invention not only retains the hierarchical relationship of hot words within a single live streaming content, but also realizes the association of hot words in different live streaming content through cross-branch relationships. By identifying the core branches, important content is highlighted, and the addition of dynamic association paths enhances the relevance and dynamism of the structure tree. This makes the live streaming hot word structure tree comprehensively and accurately reflect the overall relationship network of live streaming hot words on the platform, providing an efficient hot word structure foundation for subsequent user interest hot word matching and personalized live streaming recommendations, thereby improving the accuracy of recommendations and user experience.

[0086] Furthermore, the personalized live streaming content recommendation device based on user profiles provided by the present invention will be described below. The personalized live streaming content recommendation device based on user profiles described below can be referred to in correspondence with the personalized live streaming content recommendation method based on user profiles described above.

[0087] Optional, refer to Figure 2 , Figure 2 This is a schematic diagram of the structure of the live streaming content personalized recommendation device based on user profiles provided by the present invention. The live streaming content personalized recommendation device based on user profiles includes...

[0088] The data acquisition module 210 is used to collect real-time hot word data for each live stream currently running on the live streaming platform. The real-time hot word data includes the text of the live stream hot words and the frequency of occurrence of each text. The structure tree construction module 220 is used to construct a live hot word structure tree based on the real-time hot word data of each live content; each node in the live hot word structure tree represents the live hot word text, the connection relationship between nodes represents the hierarchical relationship between live hot words, and the attribute information of the nodes represents the frequency of occurrence. User profile analysis module 230 is used to perform user profile analysis based on user profile data to obtain user interest hot words; user profile data includes user's historical viewing records, historical interaction records and interest tags in registration records; The hot word association mapping module 240 is used to perform association mapping based on the hot word structure tree of each live content and the hot words of user interest to obtain the hot word association mapping result. The hot word association mapping result includes the number of nodes in the hot word structure tree of user interest, as well as the hierarchical information and frequency of each node in the hot word structure tree. The live streaming content recommendation module 250 is used to determine the matching degree value between each live streaming content and the user's interest hot words based on the hot word association mapping results of each live streaming content, and to generate a personalized recommendation list of live streaming content based on the matching degree value of each live streaming content.

[0089] This invention constructs a live-stream hot word structure tree based on real-time hot word data for each live-stream content. By dividing hot words into levels and frequencies, it delves into the deep semantic relationships and features of the live-stream content. Through user profile analysis of user profile data, it accurately captures user interest hot words. Then, it uses the constructed live-stream hot word structure tree and user interest hot words for association mapping. Combining the number of nodes where user interest hot words appear in the live-stream hot word structure tree, as well as the level information and frequency of each node in the live-stream hot word structure tree, it achieves a precise association between live-stream content features and user interest features. Finally, based on the matching degree value between the live-stream content and user interest hot words determined by the hot word association mapping results, it generates a personalized recommendation list of live-stream content. This ensures that the recommendation results meet the personalized needs of users and can dynamically capture changes in live-stream content and user interests, improving the accuracy and diversity of recommendations and avoiding homogenization and poor timeliness.

[0090] Please see Figure 3 , Figure 3 An embodiment diagram of an electronic device provided in accordance with the present invention. For example... Figure 3 As shown, this embodiment of the invention provides an electronic device 300, including a memory 310, a processor 320, and a computer program 311 stored in the memory 310 and executable on the processor 320. When the processor 320 executes the computer program 311, it performs the following steps: Collect real-time hot word data for each live stream currently running on the live streaming platform; real-time hot word data includes the text of the live stream hot words and the frequency of occurrence of each live stream hot word text; A live stream hot word structure tree is constructed based on the real-time hot word data of each live stream content; each node in the live stream hot word structure tree represents the text of the live stream hot word, the connection relationship between nodes represents the hierarchical relationship between the live stream hot words, and the attribute information of the nodes represents the frequency of occurrence. User profile analysis is performed based on user profile data to obtain user interest hot words; user profile data includes user's historical viewing records, historical interaction records, and interest tags in registration records. Based on the hot word structure tree of each live content and the hot words of user interest, the hot word association mapping result is obtained. The hot word association mapping result includes the number of nodes in the hot word structure tree of user interest, as well as the hierarchical information and frequency of each node in the hot word structure tree. Based on the hot word association mapping results of each live stream content, the matching degree value between each live stream content and the user's interest hot words is determined, and a personalized recommendation list of live stream content is generated based on the matching degree value of each live stream content.

[0091] Please see Figure 4 , Figure 4 An embodiment diagram of a computer-readable storage medium provided in accordance with an embodiment of the present invention is shown. Figure 4 As shown, this embodiment provides a computer-readable storage medium 400 on which a computer program 311 is stored. When the computer program 311 is executed by a processor, it performs the following steps: Collect real-time hot word data for each live stream currently running on the live streaming platform; real-time hot word data includes the text of the live stream hot words and the frequency of occurrence of each live stream hot word text; A live stream hot word structure tree is constructed based on the real-time hot word data of each live stream content; each node in the live stream hot word structure tree represents the text of the live stream hot word, the connection relationship between nodes represents the hierarchical relationship between the live stream hot words, and the attribute information of the nodes represents the frequency of occurrence. User profile analysis is performed based on user profile data to obtain user interest hot words; user profile data includes user's historical viewing records, historical interaction records, and interest tags in registration records. Based on the hot word structure tree of each live content and the hot words of user interest, the hot word association mapping result is obtained. The hot word association mapping result includes the number of nodes in the hot word structure tree of user interest, as well as the hierarchical information and frequency of each node in the hot word structure tree. Based on the hot word association mapping results of each live stream content, the matching degree value between each live stream content and the user's interest hot words is determined, and a personalized recommendation list of live stream content is generated based on the matching degree value of each live stream content.

[0092] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer is able to execute the personalized live content recommendation method based on user profiles provided by the above methods, the method including: Collect real-time hot word data for each live stream currently running on the live streaming platform; real-time hot word data includes the text of the live stream hot words and the frequency of occurrence of each live stream hot word text; A live stream hot word structure tree is constructed based on the real-time hot word data of each live stream content; each node in the live stream hot word structure tree represents the text of the live stream hot word, the connection relationship between nodes represents the hierarchical relationship between the live stream hot words, and the attribute information of the nodes represents the frequency of occurrence. User profile analysis is performed based on user profile data to obtain user interest hot words; user profile data includes user's historical viewing records, historical interaction records, and interest tags in registration records. Based on the hot word structure tree of each live content and the hot words of user interest, the hot word association mapping result is obtained. The hot word association mapping result includes the number of nodes in the hot word structure tree of user interest, as well as the hierarchical information and frequency of each node in the hot word structure tree. Based on the hot word association mapping results of each live stream content, the matching degree value between each live stream content and the user's interest hot words is determined, and a personalized recommendation list of live stream content is generated based on the matching degree value of each live stream content.

[0093] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0094] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0095] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for personalized recommendation of live streaming content based on user profiles, characterized in that, include: Collect real-time hot word data for each live stream currently in progress on the live streaming platform; The real-time hot word data includes the text of live hot words and the frequency of occurrence of each text of live hot words; A live stream hot word structure tree is constructed based on real-time hot word data for each live stream content; In the live streaming hot word structure tree, each node represents the text of the live streaming hot word, the connection relationship between nodes represents the hierarchical relationship between the live streaming hot words, and the attribute information of the nodes represents the frequency of occurrence. User profile analysis is performed based on user profile data to obtain user interest hot words; the user profile data includes user's historical viewing records, historical interaction records, and interest tags in registration records. Based on the hot word structure tree of each live content and the hot words of user interest, an association mapping is performed to obtain the hot word association mapping result; The hot word association mapping results include the number of nodes in the live hot word structure tree where user interest hot words appear, as well as the hierarchical information and frequency of each node in the live hot word structure tree; Based on the hot word association mapping results of each live stream content, the matching degree value between each live stream content and the user's interest hot words is determined, and a personalized recommendation list of live stream content is generated based on the matching degree value of each live stream content.

2. The method for personalized recommendation of live streaming content based on user profiles according to claim 1, characterized in that, The construction of a live stream hot word structure tree based on real-time hot word data for each live stream content includes: For any two first and second live stream hot word texts in the same live stream content, if the text similarity between the first and second live stream hot word texts is greater than or equal to the similarity threshold, then the text inclusion relationship between the first and second live stream hot word texts is determined. Based on the text inclusion relationship, a set of node relationships is determined, and based on hierarchical clustering combined with the set of node relationships, a hot word structure tree with the same branch for the same live content is constructed. Based on the hot word structure tree of different live streaming content, construct cross-branch relationships of the hot word structure tree within the same branch; The live streaming hot word structure tree is constructed based on the same branch and cross branch relationships of the hot word structure tree.

3. The personalized recommendation method for live streaming content based on user profiles according to claim 2, characterized in that, The construction of the live-streaming hot word structure tree based on the same-branch relationship and cross-branch relationship of the hot word structure tree includes: Based on the cross-branch subordination relationship in the hot word structure tree, a cross-live content hierarchical structure is constructed. The hot word structure tree within the same live content maintains the original hierarchical subordination relationship with the same branch. The frequency of occurrence of each node is added as attribute information to obtain the initial structure tree. Based on the sum of the occurrence frequencies of all nodes in each branch of the initial structure tree, and combined with the level depth of each branch in the initial structure tree, the importance index of each branch is determined; the level depth of the root node is 1, and the depth increases by 1 for each level downward. Branches with an importance index greater than or equal to a preset index threshold are identified as core branches, and dynamic association paths are constructed based on the semantic similarity and semantic association strength of nodes in any two core branches. The dynamic association path with the lowest path strength is identified as the target association path, and the target association path is added to the initial structure tree to obtain the live hot word structure tree; the path strength is the sum of the semantic association strengths between nodes in the dynamic association path.

4. The method for personalized recommendation of live streaming content based on user profiles according to claim 2, characterized in that, The construction of cross-branch relationships in the hot word structure tree based on different live streaming content includes: For any two first target live stream content with the same branch of the first hot word structure tree and the second target live stream content with the same branch of the second hot word structure tree, determine the semantic similarity between the first target live stream hot word text and the second target live stream hot word text based on the first target live stream hot word text in the first hot word structure tree and the second target live stream hot word text in the second hot word structure tree. Based on the semantic similarity combined with the first occurrence frequency of the first target live stream hot word text and the second occurrence frequency of the second target live stream hot word text, the semantic association strength between the first target live stream hot word text and the second target live stream hot word text is determined; The maximum semantic association strength among the texts of live streaming hot words is determined as the branch association strength between the same branch of the first hot word tree structure and the same branch of the second hot word tree structure. If the branch association strength is greater than or equal to the preset association strength threshold, and the root nodes of the same branch of the first hot word structure tree and the same branch of the second hot word structure tree have a semantic inclusion relationship, then it is determined that there is a cross-branch subordinate relationship between the same branch of the first hot word structure tree and the same branch of the second hot word structure tree. Based on the cross-branch subordinate relationships between the same branches of all hot word structure trees, the cross-branch relationship of the hot word structure tree is determined.

5. The method for personalized recommendation of live streaming content based on user profiles according to claim 4, characterized in that, The formula for calculating the semantic association strength is: r(a,b)=s(a,b)*log[f(a)+f(b)+1]. Where r(a,b) represents the semantic association strength between the first target live stream hot word text h(a) and the second target live stream hot word text h(b), s(a,b) represents the semantic similarity between the first target live stream hot word text h(a) and the second target live stream hot word text h(b), f(a) represents the first occurrence frequency of the first target live stream hot word text h(a), f(b) represents the second occurrence frequency of the second target live stream hot word text h(b), and log() represents the logarithmic function.

6. The personalized recommendation method for live streaming content based on user profiles according to claim 2, characterized in that, The step of determining the node relationship set based on the text inclusion relationship includes: If the semantic inclusion relationship is such that the first semantic range of the first live hot word text completely includes the second semantic range of the second live hot word text, then the first live hot word text is determined to be the first parent-child node relationship of the second live hot word text. If the semantic inclusion relationship is that the second semantic range completely includes the first semantic range, then the second live hot word text is determined to be the second parent-child node relationship of the first live hot word text; If the semantic inclusion relationship is that the first semantic range does not completely include the second semantic range, then the first live hot word text and the second live hot word text are determined to be parent node compatible sibling nodes. The first parent-child node relationship, the second parent-child node relationship, and the parent node compatible sibling node relationship are determined as a set of node relationships.

7. The method for personalized recommendation of live streaming content based on user profiles according to any one of claims 2 to 6, characterized in that, In each hot word structure tree, the live hot word text without a parent node is taken as the root node in the same branch. All direct child nodes are connected to the root node according to the parent-child node relationship in the node relationship set. For each first target child node, all direct child nodes are connected to the first target child node according to the parent-child node relationship in the node relationship set. For any two second target nodes, parent-child node connections and sibling node connections are established according to the parent-sibling node relationship in the node relationship set. The nodes in the same branch of each hot word structure tree form a hierarchical chain according to the subordinate relationship.

8. A personalized recommendation device for live streaming content based on user profiles, characterized in that, Applied to the personalized recommendation method for live streaming content based on user profiles as described in any one of claims 1 to 7; The personalized live streaming content recommendation device based on user profiles includes: The data acquisition module is used to collect real-time hot word data for each live stream currently in progress on the live streaming platform; the real-time hot word data includes the text of the live stream hot words and the frequency of occurrence of each text of the live stream hot words. The structure tree construction module is used to construct a live hot word structure tree based on the real-time hot word data of each live content. Each node in the live hot word structure tree represents the text of the live hot word, the connection relationship between nodes represents the hierarchical relationship between the live hot words, and the attribute information of the nodes represents the frequency of occurrence. The user profile analysis module is used to perform user profile analysis based on user profile data to obtain user interest hot words; the user profile data includes the user's historical viewing records, historical interaction records, and interest tags in the registration records. The hot word association mapping module is used to perform association mapping based on the hot word structure tree of each live content and the hot words of user interest to obtain the hot word association mapping result; the hot word association mapping result includes the number of nodes in the hot word structure tree of user interest, as well as the hierarchical information and frequency of each node in the hot word structure tree of live content. The live streaming content recommendation module is used to determine the matching degree between each live streaming content and the user's interest hot words based on the hot word association mapping results of each live streaming content, and to generate a personalized recommendation list of live streaming content based on the matching degree value of each live streaming content.

9. An electronic device, comprising: Memory, used to store computer software programs; A processor for reading and executing the computer software program, characterized in that, when the processor executes the computer software program, it implements the personalized recommendation method for live streaming content based on user profiles as described in any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium, wherein a computer software program is stored therein, characterized in that, When the computer software program is executed by the processor, it implements the personalized recommendation method for live streaming content based on user profiles as described in any one of claims 1 to 7.

Images