User Behavior Analysis Method and System Based on Big Data

Abstract

The present application provides a method and system for user behavior analysis based on big data. By obtaining the query logs of target users on an Internet search service platform; extracting topic tags and long-tail query data; determining multiple behavior interest degrees based on the long-tail query data, and determining multiple query interest sub-tags based on the query interest index and all the behavior interest degrees; performing query pointing association between the query interest sub-tags and the topic tags to obtain multiple pointing association vectors, and determining behavior trend characteristics based on all the pointing association vectors; obtaining the query phrase input by the target user, performing query matching between the query phrase and the behavior trend characteristics to obtain query behavior characteristics; and uploading the query behavior characteristics to the user behavior analysis center. The above solution can accurately capture the query phrases of users based on the query behavior characteristics, and make associated classification of the search interest directions of the query phrases, so as to realize the accurate analysis of the user search behavior pattern.

Description

Technical Field

[0001] This application relates to the field of big data analysis technology. More specifically, this application relates to a method and system for user behavior analysis based on big data. Background Art

[0002] With the explosive growth of data and the rapid improvement of computing power in the information age, big data analysis has gradually become a key technology in modern technological society. Traditional data processing methods are no longer able to handle the massive, fast, complex, and diverse data from various data sources. Among them, big data analysis mainly relies on distributed computing, cloud storage, and advanced algorithm processing architectures for efficient data storage and parallel processing. In addition, big data analysis also provides key impetus for promoting innovation fields such as personalized recommendation, business decision optimization, and intelligent prediction.

[0003] Existing big data analysis realizes the processing and analysis of massive data through various technical means. In query behavior analysis, natural language processing technology is used to understand and analyze the search terms input by users and their intentions, so as to accurately analyze users' interests and behavior patterns. By analyzing these data, the Internet search service platform can achieve personalized recommendation and user behavior prediction, improving user experience and business value. However, when users conduct search behaviors, they often express their query needs for the user behavior analysis system based on big data through simple and vague descriptive query phrases. It is difficult for the query system to accurately capture users' real concerns and interest preferences. Secondly, the interest preferences of users when using query phrases for queries are dynamically changing. For a key query topic, there will be multiple changes in interest query directions. Existing traditional query methods are difficult to adapt to these changes. Therefore, how to accurately capture users' query phrases and make associated categorizations of the search interest directions of query phrases, so as to achieve accurate analysis of users' search behavior patterns has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides a method and system for user behavior analysis based on big data, which can accurately capture users' query phrases and make associated categorizations of the search interest directions of query phrases, so as to achieve accurate analysis of users' search behavior patterns.

[0005] In a first aspect, this application provides a method for user behavior analysis based on big data, including the following steps:

[0006] Obtain the query log of the target user on the Internet search service platform from the big data center of the Internet search service platform;

[0007] Extract multiple topic tags when the target user conducts a query and the long-tail query data of each topic tag from the query log;

[0008] Select a topic tag as the selected topic tag, determine multiple behavioral interest degrees of the target user when performing a long-tail query under the selected topic tag according to the long-tail query data of the selected topic tag, and then determine multiple query interest sub-tags of the selected topic tag based on the query interest index of the Internet search service platform and all the behavioral interest degrees;

[0009] Associate each query interest sub-tag with the selected topic tag for query directivity, and then obtain multiple pointing association vectors corresponding to the selected topic tag. Determine the behavioral trend characteristics of the target user when performing a long-tail query under the selected topic tag according to all the pointing association vectors, and continue to determine the behavioral trend characteristics of the target user when performing a long-tail query under the remaining topic tags;

[0010] Obtain the query phrase input by the target user on the Internet search service platform at the current moment, match the query phrase with the behavioral trend characteristics under each topic tag, and obtain the query behavior characteristics of the target user;

[0011] Upload the query behavior characteristics of the target user to the user behavior analysis center.

[0012] In some embodiments, extracting multiple topic tags and the long-tail query data of each topic tag when the target user performs a query from the query log specifically includes:

[0013] Extract multiple query keywords from the query log;

[0014] Perform label clustering on all the query keywords to obtain multiple topic tags when the target user performs a query;

[0015] Select a topic tag as the selected topic tag, and combine the long-tail query records corresponding to each query keyword in the selected topic tag in the query log as the long-tail query data of the selected topic tag;

[0016] Continue to determine the long-tail query data of the remaining topic tags.

[0017] In some embodiments, performing label clustering on all the query keywords to obtain multiple topic tags when the target user performs a query specifically includes:

[0018] Determine the semantic similarity between each query keyword;

[0019] Use a clustering algorithm to perform similarity grouping on all the query keywords based on the semantic similarity between each query keyword to obtain multiple query similarity groups;

[0020] Determine the topic tag of each query similarity group, and then obtain multiple topic tags when the target user performs a query.

[0021] In some embodiments, determining multiple behavioral interest degrees of a target user during long-tail queries under a selected topic tag based on long-tail query data of the selected topic tag specifically includes:

[0022] Selecting a long-tail query term from the long-tail query data of the selected topic tag as the selected long-tail query term;

[0023] Determining the frequency of the behavioral pattern of the selected long-tail query term based on the long-tail query data;

[0024] Determining the interest weight of the selected long-tail query term in the long-tail query data;

[0025] Determining the behavioral interest degree of the target user when querying the selected long-tail query term under the selected topic tag according to the frequency of the behavioral pattern and the interest weight;

[0026] Continuing to determine the behavioral interest degrees of the target user when querying the remaining long-tail query terms under the selected topic tag.

[0027] In some embodiments, determining multiple query interest sub-tags of a selected topic tag based on the query interest index of an Internet search service platform and all the behavioral interest degrees specifically includes:

[0028] Obtaining the query interest index of the Internet search service platform;

[0029] Performing query behavior analysis on the selected topic tag based on the query interest index and each behavioral interest degree to obtain multiple query behavior viscosities of the selected topic tag;

[0030] Determining multiple query interest sub-tags of the selected topic tag according to all the query behavior viscosities.

[0031] In some embodiments, performing query directional association between each query interest sub-tag and the selected topic tag, and then obtaining multiple pointing association vectors corresponding to the selected topic tag specifically includes:

[0032] Selecting a query interest sub-tag as the selected query interest sub-tag;

[0033] Determining the tag co-occurrence rate of the selected query interest sub-tag and the selected topic tag in the historical search records of the target user;

[0034] Performing directional analysis on the selected query interest sub-tag to obtain the association directivity of the selected query interest sub-tag under the selected topic tag;

[0035] Obtaining the tag response degree of the target user to the selected query interest sub-tag;

[0036] Determine the pointing association vector of the selected query interest sub-tag to the selected topic tag based on the tag co-occurrence rate, the association directivity, and the tag responsiveness;

[0037] Continue to determine multiple pointing association vectors corresponding to the selected topic tag.

[0038] In some embodiments, determining the behavioral trend characteristics of the target user when performing a long-tail query under the selected topic tag according to all the pointing association vectors specifically includes:

[0039] Determine multiple association similarities of all the pointing association vectors;

[0040] Perform eigen-decomposition on all the association similarities to obtain multiple behavioral trend degrees and multiple behavioral characteristics under the selected topic tag;

[0041] Determine the behavioral trend characteristics of the target user when performing a long-tail query under the selected topic tag based on all the behavioral trend degrees and all the behavioral characteristics.

[0042] In a second aspect, the present application provides a user behavior analysis system based on big data, including:

[0043] An acquisition module, configured to acquire the query log of the target user on the Internet search service platform from the big data center of the Internet search service platform;

[0044] A processing module, configured to extract multiple topic tags when the target user performs a query and the long-tail query data of each topic tag from the query log;

[0045] The processing module is further configured to select a topic tag as the selected topic tag, determine multiple behavioral interest degrees of the target user when performing a long-tail query under the selected topic tag according to the long-tail query data of the selected topic tag, and further determine multiple query interest sub-tags of the selected topic tag based on the query interest index of the Internet search service platform and all the behavioral interest degrees;

[0046] The processing module is further configured to perform query pointing association between each query interest sub-tag and the selected topic tag, thereby obtaining multiple pointing association vectors corresponding to the selected topic tag, determine the behavioral trend characteristics of the target user when performing a long-tail query under the selected topic tag according to all the pointing association vectors, and continue to determine the behavioral trend characteristics of the target user when performing a long-tail query under the remaining topic tags;

[0047] The processing module is further configured to acquire the query phrase input by the target user on the Internet search service platform at the current moment, perform query matching between the query phrase and the behavioral trend characteristics under each topic tag to obtain the query behavioral characteristics of the target user;

[0048] An execution module, configured to upload the query behavior characteristics of the target user to a user behavior analysis center.

[0049] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned user behavior analysis method based on big data.

[0050] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned user behavior analysis method based on big data is implemented.

[0051] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects:

[0052] In the user behavior analysis method and system based on big data provided by the present application, first, query logs of the target user on the Internet search service platform are obtained from the big data center of the Internet search service platform; secondly, multiple topic tags when the target user makes a query and long-tail query data of each topic tag are extracted from the query logs; further, a topic tag is selected as the selected topic tag, and multiple behavior interest degrees when the target user makes a long-tail query under the selected topic tag are determined according to the long-tail query data of the selected topic tag. Multiple query interest sub-tags of the selected topic tag are determined based on the query interest index of the Internet search service platform and all the behavior interest degrees; then, each query interest sub-tag is associated with the selected topic tag in terms of query directivity, and then multiple pointing association vectors corresponding to the selected topic tag are obtained. The behavior trend characteristics when the target user makes a long-tail query under the selected topic tag are determined according to all the pointing association vectors, and the behavior trend characteristics when the target user makes a long-tail query under the remaining topic tags are continuously determined; in addition, a query phrase input by the target user on the Internet search service platform at the current moment is obtained, and the query phrase is matched with the behavior trend characteristics under each topic tag to obtain the query behavior characteristics of the target user; finally, the query behavior characteristics of the target user are uploaded to the user behavior analysis center.

[0053] It can be seen that this application can accurately capture the user's query phrase, and make an associated classification of the search interest direction of the query phrase, so as to realize an accurate analysis of the user's search behavior pattern. First, extract multiple topic tags when the target user makes a query to highly summarize and condense the main intention of the query keywords, which is conducive to the Internet search service platform better understanding the query request of the target user. Second, determine multiple behavior interest degrees when the target user makes a long-tail query under the selected topic tag according to the long-tail query data of the selected topic tag, so as to accurately capture the user's real concerns and interest preferences, and then optimize the association strength of the query results. Further, determine multiple query interest sub-tags of the selected topic tag to analyze the detailed query directions in which the target user shows a high degree of interest in other attributes of the topic tag when performing a search behavior under the topic tag, so as to effectively identify changes in the interest query direction. Then, make a query directional association between each query interest sub-tag and the selected topic tag to more clearly understand the association strength between the two tags, thus avoiding the problem of being unable to make an associated classification of the query interest. In addition, match the query phrase input by the target user with the behavior trend characteristics under each topic tag to obtain the query behavior characteristics of the target user, so as to reflect the search intention and information needs of the target user at the current moment, and then make an accurate analysis of the potential behavior trend of the target user, and further better capture the query dynamic changes of the user for the interest query phrase. Finally, upload the query behavior characteristics to the user behavior analysis center, so as to construct a more complete user portrait, and then realize the accurate identification of the interest preferences and behavior patterns of the target user. In summary, the technical solution provided by this application can accurately capture the user's query phrase, and make an associated classification of the search interest direction of the query phrase, so as to realize an accurate analysis of the user's search behavior pattern. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 is an exemplary flowchart of a method for analyzing user behavior based on big data according to some embodiments of the present application;

[0055] Figure 2 is an exemplary flowchart of determining multiple query interest sub-tags of a selected topic tag according to some embodiments of the present application;

[0056] Figure 3 is an exemplary flowchart of determining multiple pointing association vectors corresponding to a selected topic tag according to some embodiments of the present application;

[0057] Figure 4 is a schematic diagram of exemplary hardware and / or software of a system for analyzing user behavior based on big data according to some embodiments of the present application;

[0058] Figure 5It is a schematic structural diagram of a computer device for implementing a user behavior analysis method based on big data as shown in some embodiments of the present application. Detailed implementation manners

[0059] The core of the present application is to obtain the query log of the target user on the Internet search service platform from the big data center; extract multiple topic tags when the target user makes a query and the long-tail query data of each topic tag from the query log; select one topic tag as the selected topic tag, determine multiple behavior interest degrees when the target user makes a long-tail query under the selected topic tag according to the long-tail query data of the selected topic tag, determine multiple query interest sub-tags of the selected topic tag based on the query interest index of the Internet search service platform and all the behavior interest degrees; perform query directional association between each query interest sub-tag and the selected topic tag, and then obtain multiple pointing association vectors corresponding to the selected topic tag, determine the behavior trend characteristics when the target user makes a long-tail query under the selected topic tag according to all the pointing association vectors, and continue to determine the behavior trend characteristics when the target user makes a long-tail query under the remaining topic tags; obtain the query phrase input by the target user on the Internet search service platform at the current moment, perform query matching between the query phrase and the behavior trend characteristics under each topic tag, and obtain the query behavior characteristics of the target user; upload the query behavior characteristics of the target user to the user behavior analysis center. The above solution can accurately capture the query phrases of users based on the query behavior characteristics, and make associated classification of the search interest directions of the query phrases, so as to realize the accurate analysis of the user search behavior pattern.

[0060] To better understand the above technical solution, the above technical solution will be described in detail below in combination with the accompanying drawings of the specification and specific implementation manners. Refer to Figure 1 , this figure is an exemplary flowchart of a user behavior analysis method based on big data as shown in some embodiments of the present application. The user behavior analysis method 100 based on big data mainly includes the following steps:

[0061] In step 101, obtain the query log of the target user on the Internet search service platform from the big data center of the Internet search service platform.

[0062] In specific implementation, obtain the query log of the target user on the Internet search service platform from the big data center of the Internet search service platform, that is: query the information of the target user in the big data center of the Internet search service platform, and then obtain the query log of the target user on the Internet search service platform. The Internet search platform is a platform that provides search services through a search engine. Usually, the big data center stores the original search data for analyzing and processing user search behaviors. Specifically, the big data center of the Internet search service platform in this application is an integrated system of various data entries and user query logs generated and collected in a big data environment. A large number of log records are stored on it, including big data such as the query logs of users. In this application, the query log records the data generated when the target user conducts information queries on the Internet search service platform. Among them, the query log includes query keywords, long-tail query records, etc. In other embodiments, the query log may also include other data contents, which are not limited here. By obtaining the query log, the search behavior of the target user can be analyzed, so as to optimize the search algorithm and further improve the search experience of the target user.

[0063] It should be noted that the query keyword represents the keyword phrase input by the target user, and the long-tail query record represents the phrase combination of long-tail query words. The long-tail query word represents a query phrase for content expansion and query supplement of the query keyword. One query keyword corresponds to one long-tail query record, and one long-tail query record contains multiple long-tail query words.

[0064] In step 102, extract multiple topic tags when the target user conducts a query and the long-tail query data of each topic tag from the query log.

[0065] In some embodiments, the method of extracting multiple topic tags when the target user conducts a query and the long-tail query data of each topic tag from the query log can be as follows:

[0066] Extract multiple query keywords from the query log;

[0067] Perform label clustering on all query keywords to obtain multiple topic tags when the target user conducts a query;

[0068] Select one topic tag as the selected topic tag, and combine the long-tail query records corresponding to each query keyword in the selected topic tag in the query log into the long-tail query data of the selected topic tag;

[0069] Continue to determine the long-tail query data of the remaining topic tags.

[0070] Among them, in some embodiments, the following method can be used to perform label clustering on all query keywords to obtain multiple topic labels when the target user makes a query, that is:

[0071] Determine the semantic similarity between each query keyword;

[0072] Based on the semantic similarity between each query keyword, use a clustering algorithm to group all query keywords by similarity to obtain multiple query similarity groups;

[0073] Determine the topic label of each query similarity group, and then obtain multiple topic labels when the target user makes a query.

[0074] In specific implementation, to determine the semantic similarity between each query keyword, a semantic similarity model can be used to capture the semantic similarity between each query keyword. Specifically, Word2Vec in the semantic similarity model can be used to capture the semantic similarity between each query keyword. In other embodiments, other semantic similarity models can also be used to capture the semantic similarity between each query keyword. For example, GloVe is not limited here.

[0075] In specific implementation, based on the semantic similarity between each query keyword, use a clustering algorithm to group all query keywords by similarity to obtain multiple query similarity groups, that is: the K-Means clustering algorithm in the clustering algorithm can be used to group all query keywords by similarity, and each grouping result is used as a query similarity group, and then multiple query similarity groups are obtained. In addition, in other embodiments, other clustering algorithms can also be used to group all query keywords by similarity. For example, the Hierarchical Clustering algorithm is not limited here.

[0076] It should be noted that in this embodiment, a query similarity group represents a set of multiple query keywords with a relatively high degree of association in semantic similarity. By determining the query similarity group, the query topics of the target user can be better classified and sorted, which is beneficial to analyzing their behavior patterns.

[0077] In specific implementation, the topic modeling method can be used to determine the topic label of each query similarity group, and then obtain multiple topic labels when the target user makes a query. In addition, in other embodiments, other methods can also be used to determine the topic label of each query similarity group. For example, the word frequency analysis method, the co-occurrence matrix method, etc. are not limited here.

[0078] It should be noted that in this embodiment, the semantic similarity model is used to capture the semantic similarity between query keywords. The semantic similarity represents the degree of similarity in meaning or concept between query keywords. The similarity grouping represents the process of grouping all query keywords according to the semantic similarity metric. In addition, in this embodiment, label clustering represents the process of extracting and calibrating the core themes highly relevant to the query behavior of the target user, which will not be elaborated here.

[0079] It should also be noted that in this application, the topic label represents the label of the core theme highly relevant to the query behavior of the target user. A topic label contains multiple query keywords. By determining the topic label, the main intention of the query keywords can be highly condensed, which is beneficial for the Internet search service platform to better understand the query requests of the target user.

[0080] In addition, it should be noted that in this application, the long-tail query data represents a set of long-tail query records. A long-tail query data contains multiple long-tail query records. By determining the long-tail query data, the special needs of the target user can be more completely reflected, so as to optimize the query of the search service.

[0081] In step 103, select a topic label as the selected topic label. Determine multiple behavior interest degrees of the target user when performing long-tail queries under the selected topic label according to the long-tail query data of the selected topic label. Furthermore, determine multiple query interest sub-labels of the selected topic label based on the query interest index of the Internet search service platform and all behavior interest degrees.

[0082] In some embodiments, the following method can be used to determine multiple behavior interest degrees of the target user when performing long-tail queries under the selected topic label according to the long-tail query data of the selected topic label, that is:

[0083] Select a long-tail query term from the long-tail query data of the selected topic label as the selected long-tail query term;

[0084] Determine the behavior pattern frequency of the selected long-tail query term based on the long-tail query data;

[0085] Determine the interest weight of the selected long-tail query term in the long-tail query data;

[0086] Determine the behavior interest degree of the target user when performing the selected long-tail query term query under the selected topic label according to the behavior pattern frequency and the interest weight;

[0087] Continue to determine the behavior interest degrees of the target user when performing the remaining long-tail query term queries under the selected topic label.

[0088] In specific implementation, the behavior pattern frequency of the selected long-tail query term is determined based on the long-tail query data, that is: the total vocabulary of the long-tail query data and the occurrence frequency of the selected long-tail query term in the long-tail query data are respectively obtained, and the ratio of the occurrence frequency to the total vocabulary is used as the behavior pattern frequency of the selected long-tail query term. In addition, in other embodiments, other calculation methods can also be used to calculate the behavior pattern frequency, which is not limited here.

[0089] It should be noted that the behavior pattern frequency in this embodiment represents a statistical index used to describe the query frequency of the target user for the long-tail query term. By determining the behavior pattern frequency, it is beneficial to analyze the interest preferences of the target user, so as to optimize the user's search experience.

[0090] In specific implementation, the interest weight of the selected long-tail query term in the long-tail query data is determined, that is: the total number of long-tail query records in the long-tail query data is obtained, and the ratio of the total number of records to the number of long-tail query records containing the selected long-tail query term is used as the weight factor, and the logarithm of the weight factor is used as the interest weight of the selected long-tail query term in the long-tail query data. In addition, in other embodiments, other calculation methods can also be used to calculate the interest weight, which is not limited here.

[0091] It should be noted that the interest weight in this embodiment represents the query importance used to measure the target user's query for the long-tail query term. By determining the interest weight, the interest direction of the target user during the query can be grasped, so as to make a more reasonable query retrieval. In addition, the weight factor in this embodiment represents a calculation intermediate variable and has no practical significance, so it will not be elaborated here.

[0092] In specific implementation, the behavior interest degree of the target user for querying the selected long-tail query term under the selected theme label is determined based on the behavior pattern frequency and the interest weight, that is: the product of the behavior pattern frequency and the interest weight is used as the behavior interest degree of the target user for querying the selected long-tail query term under the selected theme label. In addition, in other embodiments, other calculation methods can also be used to calculate the behavior interest degree, which is not limited here.

[0093] It should be noted that in this application, the behavioral interest degree represents the preference tendency of the target user for the interest direction represented by the long-tail query term under the topic label when sending a query request. The greater the behavioral interest degree, the more prominent the preference tendency of the target user for the interest direction represented by the long-tail query term under the topic label when sending a query request; the smaller the behavioral interest degree, the weaker the preference tendency of the target user for the interest direction represented by the long-tail query term under the topic label when sending a query request. One behavioral interest degree corresponds to one long-tail query term. By determining the behavioral interest degree, the behavioral motivation of the target user can be better understood, so as to optimize the association strength of the query results.

[0094] In some embodiments, with reference to Figure 2 As shown, this figure is an exemplary flowchart for determining multiple query interest sub-labels of a selected topic label according to some embodiments of this application. In this embodiment, determining multiple query interest sub-labels of a selected topic label based on the query interest index of the Internet search service platform and all behavioral interest degrees can be implemented by the following steps:

[0095] First, in step 1031, obtain the query interest index of the Internet search service platform;

[0096] Then, in step 1032, perform query behavior analysis on the selected topic label based on the query interest index and each behavioral interest degree to obtain multiple query behavior viscosities of the selected topic label;

[0097] Finally, in step 1033, determine multiple query interest sub-labels of the selected topic label according to all query behavior viscosities.

[0098] Specifically, when implementing, the query interest index of the Internet search service platform can be obtained in the search server of the Internet search platform. The query interest index represents an adaptive coefficient generated by the Internet search service platform according to the historical search data of the target user. The query interest index reflects the potential interest of the target user, which will not be elaborated here.

[0099] Specifically, when implementing, perform query behavior analysis on the selected topic label based on the query interest index and each behavioral interest degree to obtain multiple query behavior viscosities of the selected topic label, that is: multiply the query interest index by each behavioral interest degree respectively, and use each product result as the query behavior viscosity of the selected topic label, so as to obtain multiple query behavior viscosities of the selected topic label. In addition, in other embodiments, other calculation methods can also be used to calculate the query behavior viscosity, which is not limited here.

[0100] It should be noted that in this embodiment, the query behavior viscosity represents the dependence of the target user on a specific query interest direction during the search behavior. The greater the query behavior viscosity, the greater the dependence of the target user on the specific query interest direction during the search behavior; the smaller the query behavior viscosity, the smaller the dependence of the target user on the specific query interest direction during the search behavior. One query behavior viscosity corresponds to one long-tail query term. By determining the query behavior viscosity, the specific query interest direction of the target user can be effectively analyzed. In addition, in this embodiment, the query behavior analysis represents the process of analyzing the specific query interest direction of the target user, which will not be elaborated here.

[0101] Among them, in some embodiments, the following method can be used to determine multiple query interest sub-labels of the selected theme label based on all the query behavior viscosities, that is:

[0102] Compare each query behavior viscosity with a preset behavior viscosity respectively, extract all the query behavior viscosities greater than the preset behavior viscosity, and use the long-tail query terms corresponding to the extracted query behavior viscosities as interest theme terms, and do not process the others;

[0103] Determine multiple query interest sub-labels of the selected theme label based on all the interest theme terms.

[0104] Specifically, when implementing, determine multiple query interest sub-labels of the selected theme label based on all the interest theme terms, that is: select one interest theme term as the selected interest theme term, capture the semantic similarity between the remaining long-tail query terms under the selected theme label and the selected interest theme term, group the remaining long-tail query terms under the selected theme label based on all the semantic similarities, and determine a query interest sub-label with the selected interest theme term as the core, and then obtain multiple query interest sub-labels of the selected theme label.

[0105] It should be noted that the process of capturing semantic similarity and the process of similarity grouping in this embodiment have been described in detail in step 102, and will not be elaborated here. In addition, the preset behavior viscosity in this embodiment is a threshold of the query behavior viscosity set in advance, and the specific value can be set according to actual application requirements, and will not be limited here.

[0106] It should also be noted that in this embodiment, the interest theme term represents the detailed query direction with high interest shown by the target user during the search process. In this application, the query interest sub-label represents the detailed query direction with high interest shown by the target user for other attributes of the theme label during the search behavior under the theme label. One query interest sub-label contains multiple long-tail query terms. By determining the query interest sub-label, the special needs of the target user can be better understood, which is beneficial to the search engine to conduct behavior analysis on the search habits of the target user.

[0107] In step 104, each query interest sub-tag is associated with the selected topic tag in a query-directed manner, thereby obtaining multiple pointing association vectors corresponding to the selected topic tag. Based on all the pointing association vectors, the behavioral trend characteristics of the target user when performing long-tail queries under the selected topic tag are determined, and then the behavioral trend characteristics of the target user when performing long-tail queries under the remaining topic tags are determined.

[0108] In some embodiments, referring to Figure 3 As shown, this figure is an exemplary flowchart for determining multiple pointing association vectors corresponding to the selected topic tag according to some embodiments of the present application. In this embodiment, each query interest sub-tag is associated with the selected topic tag in a query-directed manner, and then multiple pointing association vectors corresponding to the selected topic tag can be implemented by the following steps:

[0109] First, in step 1041, a query interest sub-tag is selected as the selected query interest sub-tag;

[0110] Secondly, in step 1042, the tag co-occurrence rate of the selected query interest sub-tag and the selected topic tag in the historical search records of the target user is determined;

[0111] Furthermore, in step 1043, a pointing analysis is performed on the selected query interest sub-tag to obtain the association pointing of the selected query interest sub-tag under the selected topic tag;

[0112] Then, in step 1044, the tag response degree of the target user to the selected query interest sub-tag is obtained;

[0113] In addition, in step 1045, a pointing association vector of the selected query interest sub-tag for the selected topic tag is determined based on the tag co-occurrence rate, the association pointing, and the tag response degree;

[0114] Finally, in step 1046, multiple pointing association vectors corresponding to the selected topic tag are continuously determined.

[0115] Among them, in some embodiments, the tag co-occurrence rate of the selected query interest sub-tag and the selected topic tag in the historical search records of the target user can be determined in the following manner, that is:

[0116] Extract all query keywords and all long-tail query words in the query log of the target user;

[0117] Map all query keywords and all long-tail query terms to respective topic labels and respective query interest sub-labels, obtain the number of matches for the mapped query keywords and the number of matches for the mapped long-tail query terms, add the number of matches for the mapped query keywords and the number of matches for the mapped long-tail query terms, and use the added result as the total number of times the label appears in the historical search records of the target user;

[0118] Obtain the number of co-occurrences of the selected query interest sub-label and the selected topic label in the historical search records of the target user, and use the ratio of the number of co-occurrences of the label to the total number of times the label appears as the co-occurrence rate of the selected query interest sub-label and the selected topic label in the historical search records of the target user.

[0119] In specific implementation, map all query keywords and all long-tail query terms to respective topic labels and respective query interest sub-labels, that is: determine whether each query keyword belongs to one of the respective topic labels, if it belongs, the mapped match is successful, otherwise the mapped match is unsuccessful; determine whether each long-tail query term belongs to one of the respective query interest sub-labels, if it belongs, the mapped match is successful, otherwise the mapped match is unsuccessful, which will not be elaborated here. In addition, in this embodiment, the number of matches represents the number of successful mapped matches.

[0120] It should be noted that in this embodiment, the co-occurrence rate of the label is used to measure the degree of association between the query interest sub-label and the topic label. A high co-occurrence rate indicates a good association between the query interest sub-label and the topic label, and a low co-occurrence rate indicates a poor association between the query interest sub-label and the topic label.

[0121] In specific implementation, perform a directional analysis on the selected query interest sub-label to obtain the association directionality of the selected query interest sub-label under the selected topic label, that is: the TF-IDF algorithm can be used to perform a directional analysis on the selected query interest sub-label to obtain the association directionality of the selected query interest sub-label under the selected topic label. The specific directional analysis process will not be elaborated here. In addition, in other embodiments, other methods can also be used to perform a directional analysis on the selected query interest sub-label, for example, the cosine similarity algorithm, etc., which is not limited here.

[0122] It should be noted that in this embodiment, the directional analysis represents an analysis method for calculating the text relevance between the query interest sub-label and the topic label, which will not be elaborated here.

[0123] It should also be noted that in this embodiment, the association directionality represents the relevance between the query interest sub-label and the topic label. By determining the association directionality, it is beneficial to analyze the association strength between the two labels, thereby effectively improving the accuracy of the search service platform for user behavior analysis.

[0124] In specific implementation, the tag response degree of the target user to the selected query interest sub-tag can be obtained through the search server of the Internet search platform. The tag response degree represents the interest degree of the target user when the Internet search platform pushes relevant search results according to the selected query interest sub-tag after receiving the search request. Obtaining the tag response degree is beneficial to more specifically analyze the specific demand direction of the target user.

[0125] In specific implementation, based on the tag co-occurrence rate, the association directivity, and the tag response degree, determine the pointing association vector of the selected query interest sub-tag to the selected topic tag, that is: perform vector conversion on the tag co-occurrence rate, the association directivity, and the tag response degree to obtain the pointing association vector of the selected query interest sub-tag to the selected topic tag. Specifically, the vector conversion can be implemented through the numpy component in Python. The specific conversion process is not elaborated here. In addition, other vector conversion methods can also be used for conversion, which is not limited here.

[0126] It should be noted that in this application, the pointing association vector represents the vectorized representation of the association pointing index of the query interest sub-tag to the selected topic tag. Each query interest sub-tag corresponds to a pointing association vector. By determining the pointing association vector, the association strength between the two tags can be more clearly understood, so as to more accurately analyze the user's search behavior.

[0127] It should also be noted that in this application, the query pointing association represents the analysis process of the pointing association of the query interest sub-tag to the selected topic tag. Among them, perform query pointing association on each query interest sub-tag and the selected topic tag, that is: select a query interest sub-tag as the selected query interest sub-tag; determine the tag co-occurrence rate of the selected query interest sub-tag and the selected topic tag in the historical search record of the target user; perform directivity analysis on the selected query interest sub-tag to obtain the association directivity of the selected query interest sub-tag under the selected topic tag; obtain the tag response degree of the target user to the selected query interest sub-tag; based on the tag co-occurrence rate, the association directivity, and the tag response degree, determine the pointing association vector of the selected query interest sub-tag to the selected topic tag; continue to determine multiple pointing association vectors corresponding to the selected topic tag, that is, complete the query pointing association of each query interest sub-tag and the selected topic tag.

[0128] In some embodiments, the following method can be adopted to determine the behavior trend characteristics of the target user when performing long-tail queries under the selected topic tag according to all the pointing association vectors, that is:

[0129] Determine multiple association similarities of all the pointing association vectors;

[0130] Perform eigen decomposition on all association similarities to obtain multiple behavior trend degrees and multiple behavior characteristics under the selected topic label;

[0131] Determine the behavior trend characteristics of the target user when performing long-tail queries under the selected topic label based on all behavior trend degrees and all behavior characteristics.

[0132] In specific implementation, determine multiple association similarities of all vectors pointing to the association vector, that is: take the Euclidean distance between every two vectors pointing to the association vector as the association similarity between every two vectors pointing to the association vector, and then obtain multiple association similarities of all vectors pointing to the association vector. In addition, in other embodiments, other calculation methods can also be used to obtain the association similarity, which is not limited here.

[0133] It should be noted that in this embodiment, the association similarity represents the degree of association similarity between two query interest sub-labels. The higher the association similarity, the higher the degree of association similarity between the two query interest sub-labels; the lower the association similarity, the lower the degree of association similarity between the two query interest sub-labels.

[0134] Among them, in some embodiments, the eigen decomposition of all association similarities to obtain multiple behavior trend degrees and multiple behavior characteristics under the selected topic label can be carried out in the following manner, that is:

[0135] Construct a similarity matrix through all association similarities;

[0136] Determine multiple behavior trend degrees and multiple behavior characteristics under the selected topic label from the similarity matrix.

[0137] In specific implementation, construct a similarity matrix through all association similarities, that is: preset a matrix dimension. Based on the matrix dimension, each query interest sub-label is correspondingly used as the row and column of the matrix, and the association similarity between every two query interest sub-labels is correspondingly filled as the matrix element, so as to obtain the similarity matrix. Among them, a matrix dimension can be preset according to the total number of query interest sub-labels. For example, if the total number of query interest sub-labels is 3, the matrix dimension is set to 3*3. When specifically setting, it can be set according to actual needs, which is not limited here.

[0138] In specific implementation, multiple behavior trend degrees and multiple behavior characteristics under the selected topic label are determined from the similarity matrix, that is: multiple matrix eigenvalues of the similarity matrix and the matrix eigenvectors corresponding to each matrix eigenvalue are obtained through eigen - decomposition calculation. Each matrix eigenvalue is respectively used as a behavior trend degree under the selected topic label, and the matrix eigenvector corresponding to each behavior trend degree is respectively used as a behavior characteristic under the selected topic label, thereby obtaining multiple behavior trend degrees and multiple behavior characteristics under the selected topic label.

[0139] It should be noted that in this embodiment, the behavior characteristic represents the typical behavior model and search preference of the target user when using the search service platform for searching. The behavior trend degree represents the likelihood of the corresponding behavior characteristic occurring when the target user conducts a search under the selected topic label. By determining the behavior trend degree and behavior characteristic, it is beneficial to understand the search preferences of the target user, so as to make a more accurate analysis of the search behavior pattern of the target user, and further improve the user experience.

[0140] In specific implementation, based on all the behavior trend degrees and all the behavior characteristics, the behavior trend characteristic of the target user when conducting a long - tail query under the selected topic label is determined, that is: the maximum behavior trend degree among all the behavior trend degrees is extracted, and the behavior characteristic corresponding to this behavior trend degree is used as the behavior trend characteristic of the target user when conducting a long - tail query under the selected topic label.

[0141] It should be noted that in this application, the behavior trend characteristic represents the change pattern of the search behavior and search interest shown by the target user within a period of time. Through the behavior trend characteristic, the transfer process of the target user's search from broad - based search to detailed search can be reflected, so as to more accurately analyze the behavior pattern of the target user and optimize the search engine, and further enable the search service platform to better adapt to the demand changes of the target user.

[0142] In specific implementation, through the above - mentioned implementation steps of determining the behavior trend characteristic of the target user when conducting a long - tail query under the selected topic label according to all the pointing association vectors, the behavior trend characteristic of the target user when conducting a long - tail query under the remaining topic labels can be continuously determined, which will not be elaborated here.

[0143] In step 105, the query phrase input by the target user on the Internet search service platform at the current moment is obtained, and the query phrase is query - matched with the behavior trend characteristics under each topic label to obtain the query behavior characteristic of the target user.

[0144] In specific implementation, the query phrase input by the target user on the Internet search service platform at the current moment can be obtained by embedding a front - end capture code. In other embodiments, other methods can also be used to obtain the query phrase, which is not limited here.

[0145] In some embodiments, to query and match the query phrase with the behavioral trend features under each topic label to obtain the query behavior features of the target user, the following method can be adopted, that is:

[0146] Perform semantic analysis on the query phrase to obtain the key topic words and auxiliary long-tail words when querying the query phrase;

[0147] Determine the semantic association features between the key topic words and the auxiliary long-tail words;

[0148] Match the semantic association features with the behavioral trend features under each topic label to obtain the query behavior features of the target user.

[0149] Specifically, when implementing, perform semantic analysis on the query phrase to obtain the key topic words and auxiliary long-tail words when querying the query phrase, that is: use the word embedding analysis method in natural language processing technology to perform semantic analysis on the query phrase to obtain the key topic words and auxiliary long-tail words when querying the query phrase. The specific analysis process will not be elaborated here. In addition, in other embodiments, other processing technologies can also be used to perform semantic analysis on the query phrase, for example, topic modeling method, text similarity calculation method, etc., which are not limited here.

[0150] It should be noted that in this embodiment, the key topic words represent the search topics when the target user conducts a search, and the auxiliary long-tail words represent the auxiliary words for content supplementation and direction expansion of the search topic when the target user conducts a search.

[0151] Specifically, when implementing, determine the semantic association features between the key topic words and the auxiliary long-tail words, that is: input the key topic words and the auxiliary long-tail words into a pre-trained semantic association model to obtain the semantic association features between the key topic words and the auxiliary long-tail words.

[0152] It should be noted that the pre-trained semantic association model in this embodiment is a model obtained by performing semantic association training using a large number of query keyword samples and long-tail query word samples. This application uses a word embedding model. In addition, in other embodiments, other models can also be used, for example, context embedding model, etc., which will not be elaborated here.

[0153] It should also be noted that in this embodiment, the semantic association features represent the association between the search behavior pattern of the target user and the key topic words and auxiliary long-tail words. By determining the semantic association features, the search interest direction and search behavior trend of the target user can be analyzed.

[0154] Among them, in some embodiments, the semantic association features are feature-matched with the behavioral trend features under each topic label to obtain the query behavior features of the target user, which can be implemented in the following manner, that is:

[0155] Determine the similarity matching degree between the semantic association features and the behavioral trend features under each topic label;

[0156] Extract the maximum similarity matching degree from all the similarity matching degrees, and use the behavioral trend feature corresponding to this similarity matching degree as the query behavior feature of the target user.

[0157] Specifically, the Bayesian classification method can be used to determine the similarity matching degree between the semantic association features and the behavioral trend features under each topic label. In addition, in other embodiments, other calculation methods can also be used to calculate the similarity matching degree. For example, the Jaccard similarity method, the Pearson correlation coefficient method, etc. are not limited here.

[0158] It should be noted that in this embodiment, the similarity matching degree represents the degree of association between the semantic association features and the behavioral trend features. One similarity matching degree corresponds to one behavioral trend feature. By determining the similarity matching degree, the behavioral similarity between the query phrase of the target user and each topic label can be reflected, so as to accurately infer and analyze the search behavior of the target user.

[0159] It should also be noted that the query behavior features in this application represent the specific search behavior patterns and search direction preferences shown by the target user when using the search service platform for information query. By determining the query behavior features, the search intention and information needs of the target user can be reflected, so as to accurately analyze the potential behavioral trends of the target user.

[0160] In step 106, upload the query behavior features of the target user to the user behavior analysis center.

[0161] In some embodiments, uploading the query behavior features of the target user to the user behavior analysis center can be implemented in the following manner, that is:

[0162] Process the transmission format of the query behavior features of the target user, and send the query behavior features after the transmission format processing to the user behavior analysis center through the standard transmission protocol, and the user behavior analysis center outputs the query behavior of the user.

[0163] In specific implementation, the query behavior characteristics of the target user can be processed in terms of transmission format by the format conversion tool Apache NiFi according to the interface format of the user behavior analysis center. In addition, in other embodiments, other format conversion tools can also be used to process the query behavior characteristics in terms of transmission format. For example, Talend, etc. are not limited here.

[0164] In specific implementation, the query behavior characteristics after transmission format processing are sent to the user behavior analysis center through a standard transmission protocol, and the user behavior analysis center outputs the query behavior of the user, that is: the user management center further processes and analyzes the query behavior characteristics, so as to construct a more complete user behavior portrait and output the query behavior of the user.

[0165] It should be noted that in this embodiment, the user behavior analysis center represents an integrated system platform for collecting, storing, analyzing, and managing user behavior data. Through the user behavior analysis center, the behavior patterns, interest preferences, and interaction histories of users can be deeply understood, so as to optimize the user experience.

[0166] In addition, on the other hand of this application, in some embodiments, this application provides a user behavior analysis system based on big data. Refer to Figure 4 , this figure is a schematic diagram of exemplary hardware and / or software of a user behavior analysis system based on big data according to some embodiments of this application. The user behavior analysis system 200 based on big data includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described as follows:

[0167] The acquisition module 201 is mainly used in this application to obtain the query logs of the target user on the Internet search service platform from the big data center of the Internet search service platform.

[0168] The processing module 202 is mainly used in this application to extract multiple topic tags and the long-tail query data of each topic tag when the target user makes a query from the query logs.

[0169] The processing module 202 is further used to select a topic tag as the selected topic tag, determine multiple behavior interest degrees when the target user makes a long-tail query under the selected topic tag according to the long-tail query data of the selected topic tag, and then determine multiple query interest sub-tags of the selected topic tag based on the query interest index of the Internet search service platform and all the behavior interest degrees.

[0170] In addition, the processing module 202 is further configured to perform query directional association between each query interest sub-tag and the selected topic tag, so as to obtain multiple pointing association vectors corresponding to the selected topic tag, determine the behavior trend characteristics of the target user when performing long-tail queries under the selected topic tag according to all the pointing association vectors, and continue to determine the behavior trend characteristics of the target user when performing long-tail queries under the remaining topic tags;

[0171] In addition, the processing module 202 is further configured to obtain the query phrase input by the target user on the Internet search service platform at the current moment, perform query matching between the query phrase and the behavior trend characteristics under each topic tag, and obtain the query behavior characteristics of the target user;

[0172] The execution module 203 is mainly configured to upload the query behavior characteristics of the target user to the user behavior analysis center in this application.

[0173] In addition, this application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned user behavior analysis method based on big data.

[0174] In some embodiments, refer to Figure 5 , this figure is a schematic structural diagram of a computer device for implementing the user behavior analysis method based on big data according to some embodiments of this application. The user behavior analysis method based on big data in the above embodiments can be implemented by Figure 5 The shown computer device, this computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0175] The processor 301 can be a general-purpose central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the user behavior analysis method based on big data in this application.

[0176] The communication bus 302 can be used to transmit information between the above components.

[0177] The memory 303 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), a magnetic disk or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 303 can exist independently and be connected to the processor 301 through the communication bus 302. The memory 303 can also be integrated with the processor 301.

[0178] Among them, the memory 303 is used to store the program code for executing the solution of this application and is controlled by the processor 301 to execute. The processor 301 is used to execute the program code stored in the memory 303. The program code can include one or more software modules. The determination of the user behavior analysis method based on big data in the above embodiments can be implemented by one or more software modules in the processor 301 and the program code in the memory 303.

[0179] The communication interface 304 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0180] In a specific implementation, as an embodiment, the computer device can include multiple processors, and each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, the processor can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0181] The computer device described above can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0182] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above-described user behavior analysis method based on big data is implemented.

[0183] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0184] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application is also intended to include these modifications and variations.

Claims

1. A user behavior analysis method based on big data, characterized in that: The steps include: Obtaining the query log of the target user on the Internet search service platform from the big data center of the Internet search service platform; Extracting multiple topic tags when the target user performs a query and long-tail query data of each topic tag from the query log; A topic tag is selected as the selected topic tag, and multiple behavioral interests of the target user when performing long-tail queries under the selected topic tag are determined based on the long-tail query data of the selected topic tag, and then multiple query interest subtags of the selected topic tag are determined based on the query interest index of the Internet search service platform and all the behavioral interests; Associating each query interest sub-tag with the selected topic tag for query directionality, thereby obtaining multiple directionality association vectors corresponding to the selected topic tag, determining the behavior trend characteristics of the target user when performing long-tail queries under the selected topic tag based on all directionality association vectors, and continuing to determine the behavior trend characteristics of the target user when performing long-tail queries under the remaining topic tags; Obtaining the query phrase entered by the target user on the Internet search service platform at the current moment, performing query matching on the query phrase and the behavior trend characteristics under each topic tag, and obtaining the query behavior characteristics of the target user; Uploading the query behavior characteristics of the target user to a user behavior analysis center; The behavioral interest level indicates the preference tendency of the target user for the interest direction represented by the long-tail query word under the topic tag when issuing a query request. The multiple behavioral interest levels of the target user when performing a long-tail query under the selected topic tag are determined based on the long-tail query data of the selected topic tag, specifically including: Select a long-tail query term from the long-tail query data of the selected topic tag as the selected long-tail query term; Determining the behavior pattern frequency of the selected long-tail query term based on the long-tail query data; Determining an interest weight of a selected long-tail query term in the long-tail query data; Determining the behavioral interest of the target user when searching for the selected long-tail query term under the selected topic tag according to the behavioral pattern frequency and the interest weight; Continue to determine the target users' behavioral interest in the remaining long-tail search terms under the selected topic tag.

2. The method according to claim 1, characterized in that Extracting multiple topic tags when a target user performs a query and long-tail query data of each topic tag from the query log specifically includes: Extracting multiple query keywords from the query log; All query keywords are clustered to obtain multiple topic tags when the target user performs a query; Selecting a topic tag as a selected topic tag, and combining long-tail query records corresponding to each query keyword in the selected topic tag in the query log into long-tail query data of the selected topic tag; Continue to identify long-tail query data for the remaining hashtags.

3. The method according to claim 2, characterized in that All query keywords are clustered by tags to obtain multiple topic tags when the target user performs a query, including: Determine the semantic similarity between each query keyword; Based on the semantic similarity between each query keyword, a clustering algorithm is used to group all query keywords by similarity to obtain multiple query similarity groups; The topic labels of each query similarity group are determined, thereby obtaining multiple topic labels when the target user performs a query.

4. The method according to claim 1, characterized in that The multiple query interest sub-tags of the selected topic tag are determined based on the query interest index and all behavioral interest of the Internet search service platform, including: Obtaining the query interest index of the Internet search service platform; Performing query behavior analysis on the selected topic tag based on the query interest index and each behavior interest degree to obtain multiple query behavior viscosities of the selected topic tag; Multiple query interest sub-tags of the selected topic tag are determined according to the viscosity of all query behaviors.

5. The method according to claim 1, characterized in that The query directionality association of each query interest sub-tag with the selected topic tag is performed, and then multiple directionality association vectors corresponding to the selected topic tag are obtained, specifically including: Selecting a query interest sub-tag as a selected query interest sub-tag; Determine the tag co-occurrence rate between the selected query interest subtag and the selected topic tag in the historical search records of the target user; Performing a directivity analysis on the selected query interest subtag to obtain the associated directivity of the selected query interest subtag under the selected topic tag; Obtain the tag responsiveness of the target user to the selected query interest subtag; Determine a directional association vector of the selected query interest sub-tag to the selected topic tag based on the tag co-occurrence rate, the association directivity and the tag responsiveness; Continue to determine a plurality of pointing association vectors corresponding to the selected topic label.

6. The method according to claim 1, characterized in that The behavioral trend characteristics of the target user when performing long-tail queries under the selected topic tags are determined based on all pointing association vectors, including: determining multiple association similarities of all pointing association vectors; Perform feature decomposition on all associated similarities to obtain multiple behavioral trends and multiple behavioral features under the selected topic tags; Based on all behavioral trends and all behavioral features, the behavioral trend features of the target user when performing long-tail queries under the selected topic tags are determined.

7. A user behavior analysis system based on big data, which uses the method described in any one of claims 1 to 6 to perform user behavior analysis, characterized in that: The system includes: An acquisition module is used to acquire the query log of the target user on the Internet search service platform from the big data center of the Internet search service platform; A processing module, used to extract multiple topic tags when a target user performs a query and long-tail query data of each topic tag from the query log; The processing module is further used to select a topic tag as a selected topic tag, determine multiple behavioral interest levels of the target user when performing a long-tail query under the selected topic tag based on the long-tail query data of the selected topic tag, and then determine multiple query interest sub-tags of the selected topic tag based on the query interest index of the Internet search service platform and all the behavioral interest levels; The processing module is further used to associate each query interest sub-tag with the selected topic tag for query directionality, thereby obtaining multiple directionality association vectors corresponding to the selected topic tag, determining the behavior trend characteristics of the target user when performing long-tail queries under the selected topic tag based on all the directionality association vectors, and continuing to determine the behavior trend characteristics of the target user when performing long-tail queries under the remaining topic tags; The processing module is further used to obtain the query phrase input by the target user on the Internet search service platform at the current moment, and perform query matching on the query phrase with the behavior trend characteristics under each topic tag to obtain the query behavior characteristics of the target user; The execution module is used to upload the query behavior characteristics of the target user to the user behavior analysis center.

8. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores codes, and the processor is configured to obtain the codes and execute the user behavior analysis method based on big data as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the user behavior analysis method based on big data as described in any one of claims 1 to 6 is implemented.

Images