CN119089052B - An intelligent broadcasting ecosystem and method based on artificial intelligence multi-terminal application - Google Patents
An intelligent broadcasting ecosystem and method based on artificial intelligence multi-terminal application Download PDFInfo
- Publication number
- CN119089052B CN119089052B CN202411586715.XA CN202411586715A CN119089052B CN 119089052 B CN119089052 B CN 119089052B CN 202411586715 A CN202411586715 A CN 202411586715A CN 119089052 B CN119089052 B CN 119089052B
- Authority
- CN
- China
- Prior art keywords
- user
- portrait
- adjacent
- browsing
- interest
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9538—Presentation of query results
Landscapes
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to an intelligent broadcasting ecological system and method based on artificial intelligence multiport application, which relate to the field of audio and video broadcasting management and comprise the steps of obtaining a user interest tag matrix of a first online user and obtaining a user portrait of the first online user; and matching playing information according to the user interest tag update matrix, and pushing the matched playing information to multi-terminal applications such as a computer, a mobile phone, a sound box and the like for playing. The method and the device solve the technical problems that the periodic recommendation playing information in the prior art solves the defect of poor diversity of recommendation information based on interests, and the probability of matching with users is low, so that the browsing, playing and listening experience of the users is affected.
Description
Technical Field
The invention relates to the technical field of audio and video play management, in particular to an intelligent playing ecological system and method based on artificial intelligence multi-terminal application.
Background
The traditional audio playing mode is solidified, so that playing with higher flexibility degree cannot be realized, and various defects exist, such as poor fitting degree of audio playing content and users, and the playing time solidification of the audio playing content cannot be flexibly adjusted, such as flexible playing operation cannot be performed according to switching of multi-terminal application of the users.
Among the above drawbacks, the disadvantage that the audio playback content is poorly compatible with the user is difficult to solve, and in the conventional audio playback management system, the playback information of the user is often dependent on the user's own portraits, which are often constructed based on the user's long-term behavior patterns and preferences. Although this approach can provide a degree of personalized recommendation, over time, it can lead to the recommended content gradually tending toward unity, lacking in diversity.
At present, in order to solve the defect, some random contents are recommended periodically to realize the diversity of playing information, but the probability of matching with a user is low, and the browsing experience of the user is affected.
Disclosure of Invention
Aiming at the technical problems that in the prior art, periodical recommendation playing information is adopted to solve the defect of poor diversity of recommendation information based on interests and the probability of matching with users is low, so that the browsing experience of users is affected, the invention provides an intelligent broadcasting ecological system and method based on artificial intelligence multi-terminal application.
The technical scheme for solving the technical problems is as follows:
In a first aspect, the invention provides an artificial intelligence multi-terminal application-based smart method comprising obtaining a user interest tag matrix of a first online user, wherein the user interest tag matrix has a steady state recording duration which is a duration that the user interest tag matrix is not updated, obtaining a user representation of the first online user when the steady state recording duration is greater than or equal to a preset update period, wherein the user representation comprises a user representation and a user view content representation of a recording coverage time zone of a user base representation, the user representation and the user view content representation, conducting an adjacent interest search according to the user base representation, the user representation and the user view content representation to obtain an adjacent interest tag set, updating the user interest tag matrix according to the adjacent interest tag set, obtaining a user interest tag update matrix while resetting the steady state recording duration to 0 start timing, conducting a play information matching according to the user interest tag update matrix, conducting a play information matching of the first-terminal application, wherein the first-level representation is played according to the user base representation, the user representation and the user representation, the first-level-adjacent representation and the first-level-adjacent representation-adjacent-user representation, and the first-level-adjacent-consumer-representation is collected according to the first-level-adjacent-consumer-representation, and-adjacent-level-adjacent-user-representation, and-adjacent-user-level-adjacent-content-item-level-adjacent-item, collecting-adjacent-item, and-adjacent-level-adjacent-item-level-item, collecting, and-adjacent-user-adjacent-item-level-adjacent-item, collecting adjacent user behavior portraits of K-level adjacent user and browsing content portraits of K-level adjacent user to obtain basic portraits of K+1-level adjacent user, behavior portraits of K+1-level adjacent user and browsing content portraits of K+1-level adjacent user, wherein K+1 is more than or equal to 2 and less than or equal to 5; and performing adjacent interest frequency analysis according to the first-level adjacent user behavior portrayal, the first-level adjacent user browsing content portrayal, the second-level adjacent user behavior portrayal, the second-level adjacent user browsing content portrayal, and the K+1-level adjacent user behavior portrayal and the K+1-level adjacent user browsing content portrayal to obtain the adjacent interest tag set.
In a second aspect, the invention provides an artificial intelligence multi-port application-based intelligent broadcasting ecosystem, comprising an interest tag matrix invoking module, a user portrait invoking module, an intelligent broadcasting executing module and an intelligent broadcasting executing module, wherein the interest tag matrix invoking module is used for acquiring a user interest tag matrix of a first online user, wherein the user interest tag matrix is provided with a steady state record duration, the steady state record duration is a duration of time when the user interest tag matrix is not updated, the user portrait invoking module is used for acquiring a user portrait of the first online user when the steady state record duration is longer than or equal to a preset updating period, the user portrait comprises a user basic portrait, a user behavior portrait of the record coverage time zone of the steady state record duration and a user browsing content portrait, the adjacent interest retrieving module is used for conducting adjacent interest retrieval according to the user basic portrait, the user behavior portrait and the user browsing content portrait, and acquiring an adjacent interest tag set according to the adjacent interest tag matrix, the interest tag update module is used for updating the user interest tag matrix, and simultaneously resetting the steady state record to be 0 start timing, the intelligent broadcasting executing module is used for conducting broadcasting information according to the user portrait update matrix, and the adjacent interest tag label is used for acquiring the adjacent interest tag, the method comprises the steps of obtaining a primary adjacent user behavior portrait and a primary adjacent user browsing content portrait, collecting adjacent users according to the primary adjacent user basic portrait, the primary adjacent user behavior portrait and the primary adjacent user browsing content portrait to obtain a secondary adjacent user basic portrait, a secondary adjacent user behavior portrait and a secondary adjacent user browsing content portrait, collecting adjacent users according to a K-level adjacent user basic portrait, a K-level adjacent user behavior portrait and a K-level adjacent user browsing content portrait to obtain a K+1-level adjacent user basic portrait, a K+1-level adjacent user behavior portrait and a K+1-level adjacent user browsing content portrait, wherein K+1 is less than or equal to 2 and less than or equal to 5, and obtaining the adjacent interest tag set according to the primary adjacent user behavior portrait, the primary adjacent user browsing content portrait, the secondary adjacent user browsing content portrait, the K+1-level adjacent user behavior portrait and the K+1-level adjacent user browsing content portrait.
In a third aspect, the invention provides an electronic device, comprising a memory for storing a computer software program, and a processor for reading and executing the computer software program, thereby implementing the intelligent multicast ecological method based on the artificial intelligence multi-terminal application of the first aspect.
In a fourth aspect, the present invention provides a non-transitory computer readable storage medium having stored therein a computer software program that when executed by a processor implements an artificial intelligence multi-terminal application-based smart seeding ecological method according to the first aspect.
The method has the beneficial effects that the user interest tag matrix of the first online user is obtained, and the steady-state time length of the first online user is recorded, namely the time length of the user interest tag matrix which is not updated. When the steady state recording duration reaches or exceeds a preset updating period, a user portrait of the user is obtained, wherein the user portrait comprises a user basic portrait, a user behavior portrait and a user browsing content portrait. And carrying out adjacent interest retrieval based on the user portrait to obtain an adjacent interest tag set. And updating the user interest tag matrix by using the adjacent interest tag set to form a user interest tag updating matrix, and resetting the steady state record duration. According to the technical scheme that the updated user interest tag matrix is matched with playing information and the matched playing information is pushed to the multi-terminal application to be played, the user basic portrait, the user behavior portrait and the user browsing content portrait are used as index bases of adjacent users, interest tags of other users with similar user basic portrait, behavior and browsing content are collected and used as indexes for enriching the user interest tag matrix, and compared with a traditional pushing mode, the method not only increases diversity, but also improves the probability of agreeing with the users, and achieves the technical effect of improving user experience.
Drawings
FIG. 1 is a schematic flow chart of an artificial intelligence multi-terminal application-based intelligent broadcasting ecological method;
FIG. 2 is a schematic diagram of an artificial intelligence multi-terminal application-based intelligent broadcasting ecosystem according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device according to the present invention;
FIG. 4 is a schematic diagram of a computer readable storage medium according to the present invention;
Fig. 5 is a schematic diagram of a possible structure of an audio playback management platform according to the present invention.
In the drawings, the list of components represented by the various numbers is as follows:
an electronic device 500, a memory 510, a processor 520, a computer program 511, a computer readable storage medium 600, a computer program 611.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include one or more of the described features. In the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
In the description of the present invention, the term "for example" is used to mean "serving as an example, instance, or illustration. Any embodiment described as "for example" in this disclosure is not necessarily to be construed as preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the invention. In the following description, details are set forth for purposes of explanation. It will be apparent to one of ordinary skill in the art that the present invention may be practiced without these specific details. In other instances, well-known structures and processes have not been described in detail so as not to obscure the description of the invention with unnecessary detail. Thus, 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.
Embodiment one:
as shown in fig. 1, the embodiment of the invention provides an intelligent broadcasting ecological method based on artificial intelligence multi-terminal application, which comprises the following steps:
Preferably, the intelligent broadcasting ecological method based on the artificial intelligence multi-terminal application disclosed by the embodiment of the application can be embedded into the audio playing management platform shown in fig. 5. The audio playing management platform comprises a system cloud platform, a scheme setting module, an application end, a playing end and a user end.
In one implementation mode, a user can manufacture phrase audio files through an audio AI synthesis technology provided by the platform, then the user can store the corresponding phrase audio files into an audio resource library of a system cloud platform after AI+manual verification is carried out, then the background can analyze each phrase audio file matched with each user by using the intelligent broadcasting ecological method based on the artificial intelligence multi-terminal application, the broadcasting sequence of each phrase audio file matched with each user is set by a background person, the broadcasting sequence is distributed to user broadcasting terminals, such as computers, mobile phones, large screens and the like, of organizations such as schools, communities, factories and enterprises through broadcasting terminals, when the user logs in through the application terminals including the computers, the mobile phones, the sound equipment and the like, the broadcasting is carried out according to the broadcasting sequence of the phrase audio files matched with each user, and meanwhile various broadcasting data are displayed on a visual large screen to a supervision layer.
In a further implementation manner, the audio playing management platform also provides an inter-cut function, when the information needing inter-cut is received, the system can be accessed through a mobile phone end or a computer end to broadcast emergency related audio files, and the emergency related audio files can also be played through a mouth-cast mode.
The audio playing management platform provided by the embodiment of the application can realize playing with higher flexibility through the temporary inserting function, can realize playing information selection with higher degree of fit with users through the intelligent playing ecological method based on the artificial intelligence multi-terminal application, can realize flexible switching of the multi-terminal application through distribution to the multi-terminal application, and realizes intelligent playing of units such as schools, communities, enterprises, factories and the like in a plurality of places of people.
The audio playing management platform provided by the embodiment of the application can be widely applied to a plurality of fields such as news information, online announcements, education, communities, factories, enterprises and the like. By providing personalized content recommendation, intelligent interaction experience and accurate data analysis service, user experience and satisfaction can be remarkably improved, and user viscosity and loyalty are enhanced. Meanwhile, the system has high expandability and flexibility, and can be subjected to customized development and optimized upgrading according to the requirements of different industries.
Because the AI auditing technology, the temporary inserting technology and the information distribution technology are relatively mature, the embodiment of the application is not repeated, and the implementation process of the intelligent broadcasting ecological method based on the artificial intelligence multi-terminal application provided by the embodiment of the application is mainly explained below:
S10, obtaining a user interest tag matrix of a first online user, wherein the user interest tag matrix has a steady-state recording duration, and the steady-state recording duration is a duration of time when the user interest tag matrix is not updated;
In the preferred embodiment of the invention, the first online user refers to the user currently logged on, the user interest tag matrix is a multi-dimensional data structure describing user preferences, each dimension representing the user's interest level in a particular topic or content, such as, for example, food, military, port wind clothing, preschool education, history, and the like. The steady state record duration refers to the time elapsed since the last update of the user interest tag matrix, and is used to measure the timeliness of the user interest tags.
Preferably, the process of the user interest tag matrix involves collecting behavior data of the user, such as browsing history, search records, purchasing behavior, etc., and then counting points of interest with longer user click frequency and browsing duration as user interest tags. The calculation of the steady state record duration is realized by recording the last update time of the user interest tag matrix and comparing the last update time with the current time.
The user interest tag matrix is constructed to provide a more personalized content recommendation by providing a deep understanding of the interests and preferences of the user. The monitoring of the steady state record duration ensures that the recommendation system can respond to the change of the user interests in time, avoids influencing the recommendation correlation and accuracy due to the outdated interest labels, and finally improves the user satisfaction degree and the overall efficiency of the recommendation system.
S20, when the steady state recording time is longer than or equal to a preset updating period, obtaining a user portrait of the first online user, wherein the user portrait comprises a user basic portrait, a user behavior portrait of a recording coverage time zone of the steady state recording time length and a user browsing content portrait;
In a preferred embodiment of the present invention, the preset update period refers to the shortest update period of the user interest tag matrix preset by the user, preferably 3 months. The user representation is a comprehensive user information model that is built by analyzing the user's behavior and preferences. The user base portrayal relates to basic information of the user, such as age, gender and occupation. The user behavior portrayal focuses on the behavior patterns of the user, such as browsing duration. The browsing of content portraits by a user is focused on the browsing habits of the user with respect to specific content, such as the type and frequency of content being browsed.
When the steady state record duration of the user reaches or exceeds the preset updating period of the system, the system triggers the updating process of the user portrait. This includes collecting and analyzing the user's up-to-date data such as user basic information updates, user behavior pattern changes in the overlay time zone, and user browsing habits of different content. Such data may be obtained through a user's online activity log, interaction records, and content consumption records.
The step of updating the user representation is critical to ensure that the recommender system is able to provide content that matches the current interests and behavior of the user. By periodically updating the user portraits, the system can capture dynamic changes in user interests, thereby improving the relevance and individuation of the recommended content. In addition, the updating of the user image is helpful for the system to more accurately predict the demands of the user, enhance the user experience and possibly improve the participation degree and satisfaction degree of the user on the recommended content.
S30, carrying out adjacent interest retrieval according to the user basic portrait, the user behavior portrait and the user browsing content portrait to obtain an adjacent interest tag set;
In the preferred embodiment of the invention, the contiguous interest search is a custom data statistics algorithm of the embodiment of the invention. The method comprises the steps of screening similar user samples by introducing a user basic portrait, the user behavior portrait and the user browsing content portrait as screening references, and then extracting interest points of the similar user samples to obtain an adjacent interest tag set.
Preferably, the implementation of contiguous interest retrieval generally involves the following steps, which will be elaborated upon later, here for purposes of summary:
The index is built by first building an index based on user base portraits (e.g., age, gender, occupation), user behavior portraits (e.g., duration of browsing), and user browsing content portraits (e.g., content type, frequency of browsing). Similarity calculation then identifies the adjacent users by calculating the similarity between the user portraits, resulting in adjacent user interests. Preferably, the method can be realized by a similarity measurement method such as cosine similarity, jaccard index and the like. And finally, extracting labels similar to or related to the current interest labels of the user according to the similarity calculation result to form an adjacent interest label set.
Generally, the interest points of adjacent users with similar behaviors, similar browsing contents and similar basic information are also likely to be interested by the first online user, so that the richness is stronger compared with the content recommended by the behavior data of the users, and the interest points are more personalized compared with the traditional richness mode and the information recommendation, thereby being beneficial to improving the experience of the users.
S40, updating the user interest tag matrix according to the adjacent interest tag set to obtain a user interest tag update matrix, and resetting the steady-state recording duration to 0 to start timing;
In the preferred embodiment of the invention, the user interest tag update matrix refers to a new matrix updated according to the adjacent interest tag set on the basis of the original user interest tag matrix, namely, the interest tags which are not present in the original user interest tag matrix in the adjacent interest tag set are added into the original user interest tag matrix, so that a richer user interest tag update matrix is obtained. At the same time, the steady state recording duration is reset to 0, and a new timing period is started so as to track the timing of the next update.
And S50, carrying out playing information matching according to the user interest tag update matrix, and pushing the matched playing information to the multi-terminal application for playing.
In a preferred embodiment of the present invention, the matching of playing information refers to searching for matching content according to the interest tag matrix of the user. Preferably, when the current playing information is uploaded, various labels are configured based on the content of the current playing information, the labels are consistent with the user interest labels, and the playing information of the user interest labels with the user interest label updating matrix is used as matched playing information. The multi-terminal application refers to an information pushing terminal, a knowledge question and answer interaction terminal, an audio phrase playing terminal, a PC management terminal, a mobile operation terminal and the like, and is exemplified by a PC terminal, a mobile phone terminal, a display terminal, a hardware playing terminal, a sound and the like, and a manager can be configured in a self-defined manner. After the matched playing information is matched, the matched playing information is distributed to the multi-terminal application logged in by the first online user, and is preferably pushed to the mobile phone terminal, wherein the pushing mode can be an audio and video message or text message lamp mode, so that the intelligent performance of pushing the playing information is improved, and the technical effects of balancing richness and individuation are achieved.
Further, when the steady state recording time is longer than or equal to a preset update period, a user portrait of the first online user is obtained, and step S20 includes the steps of:
s21, the user basic portrait comprises age information, user gender and user occupation;
S22, the user behavior portrait comprises user browsing time information;
s23, the user browsing content portrait comprises user browsing content type and user browsing frequency information;
And S24, wherein the user browsing duration information, the user browsing content type and the user browsing frequency information are in one-to-one correspondence.
In the preferred embodiment of the present invention, the user base portraits need only include age information, user gender and user occupation, and other user base information such as birth area, academy, nationality, etc. need not be considered, because if the base portraits add too many tags, there will be restrictions on the adjacent users collected, resulting in the adjacent users being too similar to the first online user, which will result in a possible close overlap of the adjacent interest tags with the original interest tags. The user base portrayal need only include age information, user gender, and user occupation. User behavior portraits primarily refer to a plurality of durations during which a user is recording various types of viewed content in an overlaid time zone. User browsing content portraits refers to the type of user browsing content in the recording overlay time zone, and the browsing frequency of each type. And using the user browsing duration information, the user browsing content type and the user browsing frequency information as important reference data of the adjacent users.
The method has the advantages that the user can be prevented from deviating from the first online user too much by collecting a small amount of user basic information, the user browsing duration information, the user browsing content type and the user browsing frequency information are used as main screening conditions, and adjacent users with the same behavior portraits can be selected, so that target sample users are selected as adjacent users, interest tags of the target sample users are regarded as adjacent interest tags, interest tag matrixes of the first online user are enriched, the richness of recommended playing information of the first online user is improved, meanwhile, the probability of agreeing with the first online user is improved, and the user browsing experience is improved.
Further, based on the user basic portrait, the user behavior portrait and the user browsing content portrait, performing adjacent interest search, obtaining a contiguous interest tag set, step S30 comprising the steps of:
S31, collecting adjacent users according to the user basic portraits, the user behavior portraits and the user browsing content portraits to obtain a first-level adjacent user basic portraits, a first-level adjacent user behavior portraits and a first-level adjacent user browsing content portraits;
S32, collecting adjacent users according to the primary adjacent user basic portraits, the primary adjacent user behavior portraits and the primary adjacent user browsing content portraits to obtain secondary adjacent user basic portraits, secondary adjacent user behavior portraits and secondary adjacent user browsing content portraits;
S33, until adjacent user collection is carried out according to K-level adjacent user basic portraits, K-level adjacent user behavior portraits and K-level adjacent user browsing content portraits, K+1-level adjacent user basic portraits, K+1-level adjacent user behavior portraits and K+1-level adjacent user browsing content portraits are obtained, and K+1 is more than or equal to 2 and less than or equal to 5;
S34, performing adjacent interest frequency analysis according to the first-level adjacent user behavior portrayal, the first-level adjacent user browsing content portrayal, the second-level adjacent user behavior portrayal, the second-level adjacent user browsing content portrayal, and the K+1-level adjacent user behavior portrayal and the K+1-level adjacent user browsing content portrayal to obtain the adjacent interest tag set.
In a preferred embodiment of the present invention, contiguous interest retrieval refers to a custom user-based portrait data mining technique for finding other points of interest that are similar or related to the user's current interest. The adjacent user collection refers to finding other users with similar characteristics to the target user through portrait information of the users. The first class of contiguous users are directly similar to the target user's user population. Secondary adjacency users refer to a group of users similar to the primary adjacency users, with a direct relationship to the target user being far away. K-level adjacent users, namely expanding the obtained user group through K-level similar user relations. And (3) adjacent interest tag sets, namely tag sets which are obtained based on adjacent user portrait analysis and are possibly interested by the target user.
The detailed process is that firstly, a first-level adjacent user group which is most similar to the user is determined through basic information (age, sex and occupation), behavior data (browsing duration) and content preference (browsing content type and frequency) of the user, then the images of the first-level adjacent users are subjected to the same analysis to find second-level adjacent users which are similar to the first-level adjacent users, the process can be expanded to K-level adjacent users until a sufficient data volume is obtained or a preset upper limit (2.ltoreq.K+1.ltoreq.5) of the adjacent levels is reached, finally, interest frequency analysis is carried out on the images of all the adjacent users, the frequency of which interest labels appear in the users is highest, and the labels are used as an adjacent interest label set.
Through the steps, a comprehensive adjacent interest tag set can be constructed. This approach not only considers the direct interests of the user, but also extends the interests of other user groups similar to the user, thereby providing a richer and diversified interest tag set. This helps the recommender system to find new content that the user may not have directly expressed but is potentially interested in, thereby improving the novelty and user satisfaction of the recommendation. In addition, through multistage adjacent user acquisition, the system can capture the diversity and the complexity of user interests more carefully, and further improve the performance and the user experience of the recommendation system.
Preferably, the specific steps of determining the adjacent users are as follows, and the determination flow of the first-level adjacent user is described as an example, and the determination manners of other adjacent users are the same:
Further, the adjacent user collection is performed based on the user base portrayal, the user behavior portrayal, and the user browsing content portrayal, to obtain a first-level adjacent user base portrayal, a first-level adjacent user behavior portrayal, and a first-level adjacent user browsing content portrayal, S31 comprising the steps of:
S311, constructing a user basic portrait adjacent condition according to the user basic portrait;
further, the step S311 of constructing a user basic portrait adjacent condition based on the user basic portrait includes the steps of:
s3111, the user basic portrait includes type basic portrait attribute and quantization basic portrait attribute;
S3112, when any of the type base portrayal attributes is different, not satisfying the user base portrayal adjacency condition;
s3113, traversing the quantized basic portrait attribute and configuring an attribute deviation threshold;
S3113 when any quantized base portrayal attribute deviation is greater than or equal to the attribute deviation threshold, failing to satisfy the user base portrayal adjacency condition.
S312, constructing a user behavior portrait adjacent condition according to the user behavior portrait;
s313, constructing a user browsing content portrait adjacent condition according to the user browsing content portrait;
s314, adding a next-level adjacent user when the first user simultaneously meets the user basic portrait adjacent condition, the user behavior portrait adjacent condition and the user browsing content portrait adjacent condition;
S315, when the first-level adjacent users meet the number of N users, obtaining the first-level adjacent user basic portraits, the first-level adjacent user behavior portraits and the first-level adjacent user browsing content portraits, wherein N is more than or equal to 5.
In the preferred embodiment of the present invention, the configuration rules of the user basic portrait adjacency condition, the user behavior portrait adjacency condition and the user browsing content portrait adjacency condition are the same, and the configuration flow of the user basic portrait adjacency condition is exemplified as the following description:
The user base portrayal includes a type base portrayal attribute, which refers to a tag that cannot be quantified using numbers, such as gender and occupation, and a quantified base portrayal attribute, which refers to a quantifiable base portrayal attribute, such as age.
And traversing the quantized basic portrait attributes through a management end aiming at the quantized basic portrait attributes, configuring attribute deviation thresholds, wherein the attribute deviation thresholds are in one-to-one correspondence with the quantized basic portrait attributes, and if any quantized basic portrait attribute deviation of a sample user is greater than or equal to the attribute deviation thresholds, the user basic portrait adjacency condition is not satisfied. The user base portrait adjacency condition is satisfied when the type base portrait attributes are all the same and when each quantized base portrait attribute deviation is less than the attribute deviation threshold.
Similarly, a user behavior portrait adjacency condition and a user browsing content portrait adjacency condition are constructed, when a first user simultaneously meets the user basic portrait adjacency condition, the user behavior portrait adjacency condition and the user browsing content portrait adjacency condition, a first-stage adjacency user is added, and when the first-stage adjacency user meets the number of N users, the first-stage adjacency user basic portrait, the first-stage adjacency user behavior portrait and the first-stage adjacency user browsing content portrait are obtained, wherein N is more than or equal to 5. At least 5 are needed, and in fact, at most 7 are not needed, so that too many interest tags are avoided, and the interest tags of the first online user are submerged, namely, 7 is larger than or equal to N is larger than or equal to 5.
Further, the step S34 of obtaining the contiguous interest tag set by performing contiguous interest frequency analysis based on the first-level contiguous user behavior portrayal, the first-level contiguous user browsing content portrayal, the second-level contiguous user behavior portrayal, the second-level contiguous user browsing content portrayal, up to k+1-level contiguous user behavior portrayal and k+1-level contiguous user browsing content portrayal, includes the steps of:
s341, extracting a first browsing content type, a first browsing duration sum and a first browsing frequency sum according to the first-level adjacent user behavior portraits, the first-level adjacent user browsing content portraits, the second-level adjacent user behavior portraits, the second-level adjacent user browsing content portraits, the K+1-level adjacent user behavior portraits and the K+1-level adjacent user browsing content portraits, and the M browsing content type, the M browsing duration sum and the M browsing frequency sum;
s342, performing interest analysis on the first browsing content type according to the first browsing duration summation and the first browsing frequency summation to obtain a first interest index;
S343, until interest analysis is carried out on the type of the M browsing content according to the sum of the M browsing duration and the sum of the M browsing frequency, and an M interest index is obtained;
And S344, extracting the first interest index until the browsing content type portrait tag which is larger than or equal to the interest index threshold value in the Mth interest index is set as the adjacent interest tag set.
In a preferred embodiment of the present invention, the browsing content types up to k+1 level of the adjacent user behavior portraits and k+1 level of the adjacent user browsing content portraits are collated according to the first level of the adjacent user behavior portraits, the first level of the adjacent user browsing content portraits, the second level of the adjacent user behavior portraits, the second level of the adjacent user browsing content portraits, up to the mth browsing content type. Further, counting the sum of the browsing time durations of the first browsing content type to obtain a first browsing time duration sum, counting the sum of the browsing time durations of the second browsing content type to obtain a second browsing time duration sum, and counting the sum of the browsing time durations of the Mth browsing content type until the sum of the browsing time durations of the Mth browsing content type is counted to obtain an Mth browsing time duration sum. Further, the sum of the frequencies of the first browsing content types is counted to obtain a first browsing frequency sum, and the sum of the browsing frequencies of the Mth browsing content type is counted until the sum of the browsing frequencies of the Mth browsing content type is counted to obtain an Mth browsing frequency sum. The first interest index refers to the interest degree of the first browsing content type calculated according to the first browsing duration summation and the first browsing frequency summation and the set rule, and the greater the value is, the greater the interest degree is. And until interest analysis is carried out on the type of the M browsing content according to the summation of the M browsing duration and the summation of the M browsing frequency, and an M interest index is obtained. And extracting the first interest index until the browsing content type portrait tag which is larger than or equal to the interest index threshold value in the Mth interest index is set as the adjacent interest tag set. The interest index threshold refers to a sorting threshold preset by a user, each browse content type has a corresponding interest tag, the interest tags are set to be adjacent to an interest tag set, preferably M is an integer, M is more than or equal to 1, and M represents the total number of the browse content types.
By sorting the interest labels with higher interest indexes of adjacent users, the interest labels matched with the first online user are improved as much as possible while the interest labels are enriched, and useless pushing is avoided, so that the browsing experience of the users is affected.
Further, according to the first browsing duration sum and the first browsing frequency sum, interest analysis is performed on the first browsing content type to obtain a first interest index, and step S342 includes the steps of:
S3421, adding the first browsing duration with a first weight, adding the first browsing frequency with a second weight;
S3422, carrying out weighted summation on the first normalized parameter added by the first browsing duration and the second normalized parameter added by the first browsing frequency, and obtaining the first interest index.
In a preferred embodiment of the present invention, the interest analysis preferably proceeds as follows:
and (3) configuring a first weight for the browsing duration in advance through the management terminal, and configuring a second weight for the browsing frequency, wherein the sum of the second weight and the first weight is equal to 1. Further, a first normalization parameter added by the first browsing duration and a second normalization parameter added by the first browsing frequency are weighted and added by the first weight and the second weight, so that the first interest index is obtained.
The intelligent broadcasting ecological method based on the artificial intelligence multi-terminal application provided by the embodiment of the invention has at least the following technical effects:
And acquiring a user interest tag matrix of the first online user, and recording the steady-state time length of the first online user, namely the time length of the user interest tag matrix which is not updated. When the steady state recording duration reaches or exceeds a preset updating period, a user portrait of the user is obtained, wherein the user portrait comprises a user basic portrait, a user behavior portrait and a user browsing content portrait. And carrying out adjacent interest retrieval based on the user portrait to obtain an adjacent interest tag set. And updating the user interest tag matrix by using the adjacent interest tag set to form a user interest tag updating matrix, and resetting the steady state record duration. According to the technical scheme that the updated user interest tag matrix is matched with playing information and the matched playing information is pushed to the multi-terminal application to be played, the user basic portrait, the user behavior portrait and the user browsing content portrait are used as index bases of adjacent users, interest tags of other users with similar user basic portrait, behavior and browsing content are collected and used as indexes for enriching the user interest tag matrix, and compared with a traditional pushing mode, the method not only increases diversity, but also improves the probability of agreeing with the users, and achieves the technical effect of improving user experience.
Embodiment two:
As shown in fig. 2, based on the same inventive concept as the intelligent broadcasting ecological method based on the artificial intelligence multi-terminal application provided in the first embodiment, the embodiment of the present invention further provides an intelligent broadcasting ecological system based on the artificial intelligence multi-terminal application, including:
The interest tag matrix invoking module is used for acquiring a user interest tag matrix of a first online user, wherein the user interest tag matrix has a steady-state recording duration, and the steady-state recording duration is a duration of time when the user interest tag matrix is not updated;
The user portrait calling module is used for obtaining a user portrait of the first online user when the steady state recording time is longer than or equal to a preset updating period, wherein the user portrait comprises a user basic portrait, a user behavior portrait of a recording coverage time zone of the steady state recording time length and a user browsing content portrait;
The contiguous interest retrieval module is used for conducting contiguous interest retrieval according to the user basic portrait, the user behavior portrait and the user browsing content portrait to obtain a contiguous interest tag set;
The interest tag updating module is used for updating the user interest tag matrix according to the adjacent interest tag set to obtain a user interest tag updating matrix, and resetting the steady-state record duration to 0 to start timing;
and the intelligent broadcasting execution module is used for matching the broadcasting information according to the user interest tag updating matrix and pushing the matched broadcasting information to the multi-terminal application for broadcasting.
Further, the user portrait retrieval module executing steps include:
The user basic portrait comprises age information, user gender and user occupation;
the user behavior portrait comprises user browsing duration information;
the user browsing content portrait comprises user browsing content type and user browsing frequency information;
The user browsing duration information, the user browsing content type and the user browsing frequency information are in one-to-one correspondence.
Further, the contiguous interest retrieval module performs operations including:
collecting adjacent users according to the user basic portraits, the user behavior portraits and the user browsing content portraits to obtain a first-level adjacent user basic portraits, a first-level adjacent user behavior portraits and a first-level adjacent user browsing content portraits;
Performing adjacent user collection according to the primary adjacent user basic portraits, the primary adjacent user behavior portraits and the primary adjacent user browsing content portraits to obtain secondary adjacent user basic portraits, secondary adjacent user behavior portraits and secondary adjacent user browsing content portraits;
Until the adjacent user collection is carried out according to the K-level adjacent user basic portraits, the K-level adjacent user behavior portraits and the K-level adjacent user browsing content portraits, K+1-level adjacent user basic portraits, K+1-level adjacent user behavior portraits and K+1-level adjacent user browsing content portraits are obtained, and K+1 is more than or equal to 2 and less than or equal to 5;
And performing adjacent interest frequency analysis according to the first-level adjacent user behavior portrayal, the first-level adjacent user browsing content portrayal, the second-level adjacent user behavior portrayal, the second-level adjacent user browsing content portrayal, and the K+1-level adjacent user behavior portrayal and the K+1-level adjacent user browsing content portrayal to obtain the adjacent interest tag set.
Further, the step of executing the contiguous interest search module includes:
constructing a user basic portrait adjacent condition according to the user basic portrait;
Constructing a user behavior portrait adjacency condition according to the user behavior portrait;
Constructing a user browsing content portrait adjacent condition according to the user browsing content portrait;
adding a next-level neighbor user when the first user satisfies the user basic portrayal neighbor condition, the user behavior portrayal neighbor condition, the user browsing content portrayal neighbor condition simultaneously;
When the first-level adjacent users meet the number of N users, the first-level adjacent user basic portraits, the first-level adjacent user behavior portraits and the first-level adjacent user browsing content portraits are obtained, wherein N is more than or equal to 5.
Further, the step of executing the contiguous interest search module includes:
The user basic portrait comprises type basic portrait attributes and quantization basic portrait attributes;
When any one of the type basic portrait attributes is different, the user basic portrait adjacency condition is not satisfied;
Traversing the quantized basic portrait attributes and configuring attribute deviation thresholds;
When any one of the quantized base portrayal attribute deviations is greater than or equal to the attribute deviation threshold, the user base portrayal adjacency condition is not satisfied.
Further, the step of executing the contiguous interest search module includes:
Extracting a first browsing content type, a first browsing duration sum and a first browsing frequency sum according to the first-level adjacent user behavior portraits, the first-level adjacent user browsing content portraits, the second-level adjacent user behavior portraits, the second-level adjacent user browsing content portraits, the K+1-level adjacent user behavior portraits and the K+1-level adjacent user browsing content portraits, and the first browsing content type, the first browsing duration sum and the first browsing frequency sum until the Mth browsing content type, the Mth browsing duration sum and the Mth browsing frequency sum;
According to the first browsing duration summation and the first browsing frequency summation, interest analysis is carried out on the first browsing content type, and a first interest index is obtained;
Until interest analysis is carried out on the type of the M browsing content according to the summation of the M browsing duration and the summation of the M browsing frequency, and an M interest index is obtained;
And extracting the first interest index until the browsing content type portrait tag which is larger than or equal to the interest index threshold value in the Mth interest index is set as the adjacent interest tag set.
Further, the step of executing the contiguous interest search module includes:
the first browsing duration sum has a first weight, and the first browsing frequency sum has a second weight;
and carrying out weighted summation on the first normalization parameter added by the first browsing duration and the second normalization parameter added by the first browsing frequency, and obtaining the first interest index.
Embodiment III:
referring to fig. 3, fig. 3 is a schematic diagram of an embodiment of an electronic device according to an embodiment of the invention. As shown in fig. 3, an embodiment of the present invention provides an electronic device 500, including a memory 510, a processor 520, and a computer program 511 stored in the memory 510 and executable on the processor 520, wherein the processor 520 executes the computer program 511 to implement the following steps:
Obtaining a user interest tag matrix of a first online user, wherein the user interest tag matrix has a steady-state recording duration, and the steady-state recording duration is a duration of time when the user interest tag matrix is not updated;
when the steady state recording time length is greater than or equal to a preset updating period, obtaining a user portrait of the first online user, wherein the user portrait comprises a user basic portrait, a user behavior portrait of a recording coverage time zone of the steady state recording time length and a user browsing content portrait;
Performing adjacent interest retrieval according to the user basic portrait, the user behavior portrait and the user browsing content portrait to obtain an adjacent interest tag set;
Updating the user interest tag matrix according to the adjacent interest tag set to obtain a user interest tag update matrix, and resetting the steady-state recording duration to 0 to start timing;
According to the user interest tag update matrix, performing play information matching, pushing the matched play information to a multi-terminal application for play;
Wherein performing contiguous interest retrieval based on the user base portrayal, the user behavior portrayal, and the user browsing content portrayal, obtaining a contiguous interest tag set comprises:
collecting adjacent users according to the user basic portraits, the user behavior portraits and the user browsing content portraits to obtain a first-level adjacent user basic portraits, a first-level adjacent user behavior portraits and a first-level adjacent user browsing content portraits;
Performing adjacent user collection according to the primary adjacent user basic portraits, the primary adjacent user behavior portraits and the primary adjacent user browsing content portraits to obtain secondary adjacent user basic portraits, secondary adjacent user behavior portraits and secondary adjacent user browsing content portraits;
Until the adjacent user collection is carried out according to the K-level adjacent user basic portraits, the K-level adjacent user behavior portraits and the K-level adjacent user browsing content portraits, K+1-level adjacent user basic portraits, K+1-level adjacent user behavior portraits and K+1-level adjacent user browsing content portraits are obtained, and K+1 is more than or equal to 2 and less than or equal to 5;
And performing adjacent interest frequency analysis according to the first-level adjacent user behavior portrayal, the first-level adjacent user browsing content portrayal, the second-level adjacent user behavior portrayal, the second-level adjacent user browsing content portrayal, and the K+1-level adjacent user behavior portrayal and the K+1-level adjacent user browsing content portrayal to obtain the adjacent interest tag set.
Embodiment four:
Referring to fig. 4, fig. 4 is a schematic diagram of an embodiment of a computer readable storage medium according to an embodiment of the invention. As shown in fig. 4, the present embodiment provides a computer-readable storage medium 600 having stored thereon a computer program 611, which computer program 611 when executed by a processor implements the steps of:
Obtaining a user interest tag matrix of a first online user, wherein the user interest tag matrix has a steady-state recording duration, and the steady-state recording duration is a duration of time when the user interest tag matrix is not updated;
when the steady state recording time length is greater than or equal to a preset updating period, obtaining a user portrait of the first online user, wherein the user portrait comprises a user basic portrait, a user behavior portrait of a recording coverage time zone of the steady state recording time length and a user browsing content portrait;
Performing adjacent interest retrieval according to the user basic portrait, the user behavior portrait and the user browsing content portrait to obtain an adjacent interest tag set;
Updating the user interest tag matrix according to the adjacent interest tag set to obtain a user interest tag update matrix, and resetting the steady-state recording duration to 0 to start timing;
According to the user interest tag update matrix, performing play information matching, pushing the matched play information to a multi-terminal application for play;
Wherein performing contiguous interest retrieval based on the user base portrayal, the user behavior portrayal, and the user browsing content portrayal, obtaining a contiguous interest tag set comprises:
collecting adjacent users according to the user basic portraits, the user behavior portraits and the user browsing content portraits to obtain a first-level adjacent user basic portraits, a first-level adjacent user behavior portraits and a first-level adjacent user browsing content portraits;
Performing adjacent user collection according to the primary adjacent user basic portraits, the primary adjacent user behavior portraits and the primary adjacent user browsing content portraits to obtain secondary adjacent user basic portraits, secondary adjacent user behavior portraits and secondary adjacent user browsing content portraits;
Until the adjacent user collection is carried out according to the K-level adjacent user basic portraits, the K-level adjacent user behavior portraits and the K-level adjacent user browsing content portraits, K+1-level adjacent user basic portraits, K+1-level adjacent user behavior portraits and K+1-level adjacent user browsing content portraits are obtained, and K+1 is more than or equal to 2 and less than or equal to 5;
And performing adjacent interest frequency analysis according to the first-level adjacent user behavior portrayal, the first-level adjacent user browsing content portrayal, the second-level adjacent user behavior portrayal, the second-level adjacent user browsing content portrayal, and the K+1-level adjacent user behavior portrayal and the K+1-level adjacent user browsing content portrayal to obtain the adjacent interest tag set.
In the foregoing embodiments, the descriptions of the embodiments are focused on, and for those portions of one embodiment that are not described in detail, reference may be made to the related descriptions of other embodiments.
It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present invention without departing from the spirit or scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the present invention and the equivalent techniques thereof, the present invention is also intended to include such modifications and variations.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411586715.XA CN119089052B (en) | 2024-11-08 | 2024-11-08 | An intelligent broadcasting ecosystem and method based on artificial intelligence multi-terminal application |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411586715.XA CN119089052B (en) | 2024-11-08 | 2024-11-08 | An intelligent broadcasting ecosystem and method based on artificial intelligence multi-terminal application |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN119089052A CN119089052A (en) | 2024-12-06 |
| CN119089052B true CN119089052B (en) | 2025-01-03 |
Family
ID=93663153
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411586715.XA Active CN119089052B (en) | 2024-11-08 | 2024-11-08 | An intelligent broadcasting ecosystem and method based on artificial intelligence multi-terminal application |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119089052B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN120471672A (en) * | 2025-05-13 | 2025-08-12 | 赣州发展征信有限责任公司 | User portrayal method and system based on big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399197A (en) * | 2018-01-30 | 2018-08-14 | 重庆邮电大学 | Collaborative filtering recommending method based on user's confidence level and time context |
| CN109345348A (en) * | 2018-09-30 | 2019-02-15 | 重庆誉存大数据科技有限公司 | The recommended method of multidimensional information portrait based on travel agency user |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6345274B1 (en) * | 1998-06-29 | 2002-02-05 | Eastman Kodak Company | Method and computer program product for subjective image content similarity-based retrieval |
| CN109697629B (en) * | 2018-11-15 | 2023-02-24 | 平安科技（深圳）有限公司 | Product data pushing method and device, storage medium and computer equipment |
-
2024
- 2024-11-08 CN CN202411586715.XA patent/CN119089052B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108399197A (en) * | 2018-01-30 | 2018-08-14 | 重庆邮电大学 | Collaborative filtering recommending method based on user's confidence level and time context |
| CN109345348A (en) * | 2018-09-30 | 2019-02-15 | 重庆誉存大数据科技有限公司 | The recommended method of multidimensional information portrait based on travel agency user |
Also Published As
| Publication number | Publication date |
|---|---|
| CN119089052A (en) | 2024-12-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107832437B (en) | Audio/video pushing method, device, equipment and storage medium | |
| CN110781321B (en) | Multimedia content recommendation method and device | |
| WO2021042826A1 (en) | Video playback completeness prediction method and apparatus | |
| CN109511015B (en) | Multimedia resource recommendation method, device, storage medium and equipment | |
| US11849160B2 (en) | Image analysis system | |
| CN106126524B (en) | Information pushing method and device | |
| US10747802B1 (en) | Image recommendations for thumbnails for online media items based on user activity | |
| CN119089052B (en) | An intelligent broadcasting ecosystem and method based on artificial intelligence multi-terminal application | |
| CN113268589B (en) | Key user identification method, key user identification device, readable storage medium and computer equipment | |
| CN108595526B (en) | Resource recommendation method and device | |
| US20140074828A1 (en) | Systems and methods for cataloging consumer preferences in creative content | |
| Simmie et al. | Ranking twitter influence by combining network centrality and influence observables in an evolutionary model | |
| CN113742580A (en) | Target type data recall method and device, electronic equipment and storage medium | |
| JP2013246683A (en) | Information processing apparatus, information processing method, and program | |
| CN119691221B (en) | Student personalized education management method based on artificial intelligence | |
| CN106844724B (en) | Method and device for recommending applications based on applications installed by user | |
| CN119316389A (en) | A dialogue method, device, equipment and medium | |
| CN113254757B (en) | Data recommendation method, device, equipment and storage medium | |
| CN114119078A (en) | Target resource determination method, device, electronic equipment and medium | |
| CN110569447B (en) | Network resource recommendation method and device and storage medium | |
| CN114025176A (en) | Anchor recommendation method and device, electronic equipment and storage medium | |
| CN111639199A (en) | Multimedia file recommendation method, device, server and storage medium | |
| CN117033610A (en) | Method, device, client, server and storage medium for acquiring topics | |
| Wang et al. | Adaptive identification of hashtags for real-time event data collection | |
| Richier et al. | Predicting popularity dynamics of online contents using data filtering methods |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Chen Xiaojie Inventor after: Zhan Libin Inventor after: Zhang Wenjing Inventor before: Chen Xiaojie Inventor before: Zhan Libin Inventor before: Zhang Wen |