Method and device for processing hotspot data, electronic equipment and storage medium

Abstract

The disclosure provides a hotspot data processing method and device, electronic equipment and storage medium, relates to the technical field of computers, in particular to the technical field of artificial intelligence such as data analysis, and a specific implementation scheme is as follows: acquiring multiple hotspot data from multiple news platforms, wherein each hotspot data includes a hotspot topic and a reference heat value corresponding to the hotspot topic; determining the semantic similarity between each hotspot topic; according to the semantic similarity between each hotspot topic, deduplicating each hotspot topic to determine a target topic; and generating a current comprehensive hotspot topic list according to the reference heat value corresponding to the target topic. Therefore, the hotspot topics of different news platforms are summarized and fused, and users can quickly and comprehensively understand the current popular topics.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, specifically to the fields of big data analysis, deep learning and other artificial intelligence technologies, and in particular to a method, apparatus, electronic device and storage medium for processing hot data. Background Technology

[0002] With the widespread adoption of the internet, an increasing number of news platforms are providing users with timely news content through mobile applications. Different platforms generate their own trending topics lists based on user browsing, commenting, and searching data. The content and order of these lists may differ between platforms. Users often find it difficult to quickly grasp the trending topics across different platforms. Therefore, researching how to enable users to comprehensively understand current trending topics is of great significance. Summary of the Invention

[0003] This disclosure provides a method, apparatus, device, and storage medium for processing hotspot data.

[0004] According to a first aspect of this disclosure, a method for processing hotspot data is provided, comprising:

[0005] Multiple hot topic data are obtained from multiple news platforms, wherein each hot topic data includes a hot topic and a reference popularity value corresponding to the hot topic;

[0006] Determine the semantic similarity among various trending topics;

[0007] Based on the semantic similarity between the aforementioned hot topics, duplicates of each hot topic are removed to determine the target topic;

[0008] Based on the reference popularity value corresponding to the target topic, a current comprehensive list of trending topics is generated.

[0009] According to a second aspect of this disclosure, a hotspot data processing apparatus is provided, comprising:

[0010] The acquisition module is used to acquire multiple hot topic data from multiple news platforms, wherein each hot topic data includes a hot topic and a reference popularity value corresponding to the hot topic;

[0011] The first determining module is used to determine the semantic similarity between various hot topics;

[0012] The second determining module is used to deduplicate each of the hot topics based on the semantic similarity between them, so as to determine the target topic;

[0013] The generation module is used to generate a current comprehensive list of trending topics based on the reference popularity value corresponding to the target topic.

[0014] According to a third aspect of this disclosure, an electronic device is provided, comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method as described in the first aspect.

[0018] According to a fourth aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions for causing the computer to perform the method as described in the first aspect.

[0019] According to a fifth aspect of this disclosure, a computer program product is provided, including computer instructions that, when executed by a processor, implement the method as described in the first aspect.

[0020] The hotspot data processing method, apparatus, equipment, and storage medium disclosed herein have at least the following beneficial effects:

[0021] First, multiple trending topics are collected from various news platforms. Each trending topic includes a trending topic and its corresponding reference popularity value. Then, the semantic similarity between these trending topics is determined. Next, based on this semantic similarity, duplicate trending topics are removed to identify target topics. Finally, based on the reference popularity value of each target topic, a comprehensive list of trending topics is generated. This process aggregates and integrates trending topics from different news platforms, allowing users to quickly and comprehensively understand current hot topics.

[0022] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0023] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0024] Figure 1 This is a flowchart illustrating a method for processing hotspot data according to an embodiment of this disclosure;

[0025] Figure 2 This is a flowchart illustrating a method for processing hotspot data according to another embodiment of this disclosure;

[0026] Figure 3 This is a flowchart illustrating a method for processing hotspot data according to another embodiment of this disclosure;

[0027] Figure 4 This is a schematic diagram of a hotspot data processing device according to an embodiment of the present disclosure;

[0028] Figure 5 This is a block diagram of an electronic device used to implement the hotspot data processing method of the embodiments of this disclosure. Detailed Implementation

[0029] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0030] To facilitate understanding of this disclosure, the technical field involved in this disclosure will be briefly explained below.

[0031] Artificial intelligence (AI) is the study of enabling computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, and planning). It involves both hardware and software technologies. AI hardware technologies generally include sensors, dedicated AI chips, cloud computing, distributed storage, and big data processing. AI software technologies mainly include computer vision, speech recognition, natural language processing, as well as machine learning, deep learning, big data processing, and knowledge graph technologies.

[0032] Deep learning learns the inherent patterns and hierarchical representations of sample data. The information gained during this learning process greatly aids in interpreting data such as text, images, and sound. Its ultimate goal is to enable machines to possess analytical and learning capabilities like humans, allowing them to recognize data such as text, images, and sound. Deep learning is a complex machine learning algorithm that has achieved results in speech and image recognition far exceeding those of previous related technologies.

[0033] The following describes in detail, with reference to the accompanying drawings, the method, apparatus, computer equipment, and storage medium for processing hotspot data provided in this disclosure.

[0034] This disclosure provides a method for processing hotspot data. This method can be executed by a hotspot data processing device provided by this disclosure, or by an electronic device provided by this disclosure. The electronic device may include, but is not limited to, terminal devices such as mobile phones, desktop computers, and tablet computers, or servers. The following description uses the hotspot data processing device provided by this disclosure to execute the hotspot data processing method provided by this disclosure, but this is not intended to limit this disclosure. The device is referred to as "device".

[0035] Figure 1 This is a flowchart illustrating a method for processing hotspot data according to an embodiment of the present disclosure.

[0036] like Figure 1 As shown, the method for processing this hotspot data may include the following steps:

[0037] Step S101: Obtain multiple hot topic data from multiple news platforms, wherein each hot topic data includes a hot topic and a reference popularity value corresponding to the hot topic.

[0038] News platforms can be information platforms that provide any type of news and information. Examples include news websites and social networking platforms.

[0039] It should be noted that different news platforms can create their own trending topics lists based on user browsing, commenting, and searching data. Examples include Weibo's trending topics list and Zhihu's trending topics list.

[0040] Furthermore, since multiple trending topics typically exist within the same timeframe, news platforms usually assign a popularity score to each trending topic and rank them based on this score to differentiate their popularity.

[0041] It is understandable that, due to differences in the number of users, the accuracy of data, and the way trending topics are expressed on each news platform, the content and ranking of trending topics on each platform may be the same or different.

[0042] For example, at the same time, news platform A might have 30 trending topics on its trending topics list, while news platform B might have 10. Furthermore, news platform A and news platform B might share 5 trending topics.

[0043] In this embodiment of the disclosure, in order to collect current trending topics as comprehensively as possible, trending data can be obtained from multiple news platforms.

[0044] The number of news platforms can be determined according to actual needs. For example, it can be 3, 5 or 7, etc., and this disclosure does not limit it.

[0045] In this embodiment of the disclosure, the hot topic data obtained from the news platform may include hot topics on the hot topic list and the reference popularity value corresponding to the hot topics.

[0046] The trending topics can be texts of any length. For example, they can be a phrase, a sentence, or a paragraph, and this disclosure does not impose any restrictions on this. In addition, the reference popularity value is the popularity value of the trending topic on the hot topic list of the news platform to which it belongs.

[0047] Understandably, the popularity scores may differ across platforms. For example, if news platform A has tens of millions of users, its popularity score might be in the tens of millions, millions, or hundreds of thousands. Conversely, if news platform B has millions of users, its popularity score might be in the millions, hundreds of thousands, or tens of thousands.

[0048] It should be noted that the above examples are merely illustrative and should not be construed as limiting the hot topics and reference popularity values ​​in the embodiments of this disclosure.

[0049] Step S102: Determine the semantic similarity between each hot topic.

[0050] It should be noted that although different news platforms have different styles, and the content and order of their trending topics lists vary, many news platforms still share similar or identical content in terms of information sources and dissemination methods.

[0051] In this embodiment of the disclosure, in order to enable users to quickly understand different trending topics, the same or similar trending topics from different news platforms can be merged based on the semantic similarity between them.

[0052] Determining the semantic similarity between trending topics can be achieved in any possible way. For example, a machine learning model for calculating semantic similarity can be built, and any two trending topics can be input into the model to determine the semantic similarity between them.

[0053] Alternatively, we can first determine the text similarity between any two trending topics. When the text similarity is less than a certain fixed value, we determine that the semantic similarity between the two trending topics is 0. When the text similarity is greater than or equal to a certain fixed value, we can further use a machine learning model that calculates semantic similarity to determine the semantic similarity between the two trending topics.

[0054] It is understandable that each news platform can contain multiple trending topics, and multiple trending topics on the same news platform may also have similarities. Therefore, in this embodiment of the disclosure, all trending topics on all news platforms can be traversed to calculate the semantic similarity between any two trending topics.

[0055] It should be noted that the above examples are merely illustrative and should not be construed as limiting the determination of semantic similarity between various hot topics in the embodiments of this disclosure.

[0056] Step S103: Based on the semantic similarity between various hot topics, deduplication is performed on each hot topic to determine the target topic.

[0057] It should be noted that for a certain trending topic, there may not be any trending topics with similar meanings, or there may be one or more trending topics with similar meanings.

[0058] In this embodiment of the disclosure, the target topic is a hot topic selected from various hot topics that are semantically dissimilar to each other.

[0059] Specifically, when the semantic similarity between a trending topic and other trending topics does not meet the set conditions, it can be determined that the trending topic is unique, and therefore it is retained as the target topic.

[0060] When the semantic similarity of two or more trending topics meets the set conditions, it can be determined that these trending topics are duplicates. At this point, these trending topics can be deduplicated, and only one of them can be retained as the target topic.

[0061] Step S104: Generate a comprehensive list of trending topics based on the reference popularity value corresponding to the target topic.

[0062] Understandably, the target topics are selected from various trending topics. Therefore, the reference popularity scores for trending topics can also be used as reference popularity scores for the target topics.

[0063] The reference popularity value corresponding to the target topic represents its current popularity. Therefore, a comprehensive list of trending topics can be generated based on the reference popularity value of the target topic.

[0064] For example, all target topics can be matched with their reference popularity values ​​and sorted from highest to lowest popularity value to form a comprehensive list of trending topics.

[0065] It should be noted that the content and ranking of trending topics on various news platforms change in real time. To ensure consistency, a data collection period can be set, and trending data can be obtained from various news platforms at the same time in each period.

[0066] For example, the data collection cycle can be set to 5 minutes. Hot topic data is collected from various news platforms every 5 minutes, and a comprehensive list of trending topics for the current period is generated based on this data. This ensures both the timeliness of hot topics and records the changing trends in their popularity.

[0067] In this embodiment, multiple hot topic data are first obtained from multiple news platforms, where each hot topic data includes a hot topic and its corresponding reference popularity value. Then, the semantic similarity between each hot topic is determined. Next, based on the semantic similarity, duplicate hot topics are removed to determine the target topic. Finally, based on the reference popularity value corresponding to the target topic, a comprehensive list of current hot topics is generated. This achieves the aggregation and integration of hot topics from different news platforms, allowing users to quickly and comprehensively understand current trending topics.

[0068] Figure 2 This is a flowchart illustrating a method for processing hotspot data according to another embodiment of the present disclosure.

[0069] like Figure 2 As shown, the method for processing this hotspot data may include the following steps:

[0070] Step S201: Obtain multiple hot topic data from multiple news platforms, wherein each hot topic data includes a hot topic and a reference popularity value corresponding to the hot topic.

[0071] Step S202: Determine the semantic similarity between each hot topic.

[0072] It should be noted that the specific implementation of steps S201 and S202 can be found in the detailed description of other embodiments of this disclosure, and will not be repeated here.

[0073] Step S203: In response to the fact that the semantic similarity between any hot topic and other hot topics is less than the threshold, any hot topic is determined as the target topic.

[0074] When selecting a target topic from trending topics, the final target topic can be determined based on the semantic similarity between the trending topics.

[0075] In this embodiment of the disclosure, a threshold can be set for semantic similarity. The size of the threshold can be set as needed. For example, the threshold can be 0.8, 0.7, or 0.6, etc., and this disclosure does not limit it.

[0076] Furthermore, we can iterate through each trending topic, and when the semantic similarity between any trending topic and other trending topics is less than a threshold, we can determine that the trending topic is the target topic.

[0077] It should be noted that the number of target topics determined by the above method can be 0, 1 or more, and this disclosure does not limit this.

[0078] Step S204: In response to the semantic similarity between multiple hot topics being greater than or equal to a threshold, determine any one of the multiple hot topics as the target topic.

[0079] Specifically, when the semantic similarity of multiple trending topics is greater than or equal to a threshold, these trending topics can be identified as duplicates. In this case, one of the trending topics can be retained as the target topic.

[0080] It should be noted that within each trending topic, there may be multiple sets of overlapping topics. For example, two trending topics may belong to the same topic, and three trending topics may belong to another topic. In this embodiment of the disclosure, for each set of overlapping topics, a target topic can be identified.

[0081] In this embodiment of the disclosure, target topics are selected from the hot topics of various news platforms based on the semantic similarity between hot topics, ensuring that there are no topics with the same or similar content among the target topics, which facilitates users' browsing and use and saves users' time.

[0082] It should be noted that the credibility of data varies across news platforms due to differences in user numbers, data accuracy, and the methods used to generate trending topics. Platforms with a large user base, accurate data, and standardized expression have higher credibility, while platforms with a small user base, diverse data, and non-standard expression have lower credibility.

[0083] Therefore, priorities can be set for each news platform. For example, platforms with a large user base, accurate data, and standardized expression can be given higher priority, while platforms with a small user base, diverse data, and non-standard expression can be given lower priority.

[0084] For example, news platform A can be set to priority level 1, news platform B to priority level 2, and news platform C to priority level 3. The priority level can decrease or increase as the level increases; this disclosure does not limit this.

[0085] Furthermore, when the semantic similarity of multiple trending topics is greater than or equal to a threshold, the target topic can be determined based on the priority of the platform to which each trending topic belongs.

[0086] In some embodiments of this disclosure, the hot topic data may further include the priority corresponding to the hot topic. The priority corresponding to the hot topic may be the priority of the news platform to which the hot topic belongs.

[0087] For example, if trending topics 1 to 30 originate from news platform A, trending topics 31 to 40 originate from news platform B, and trending topics 41 to 50 originate from news platform C, then the priority of trending topics 1 to 30 can be level 1, the priority of trending topics 31 to 40 can be level 2, and the priority of trending topics 41 to 50 can be level 3.

[0088] Furthermore, since multiple similar trending topics may exist on the same news platform, their priority can be determined by ranking them according to their popularity scores.

[0089] For example, 30 trending topics on news platform A can be sorted from highest to lowest popularity, with higher-ranked topics having higher priority.

[0090] In summary, the priority of trending topics can be divided into two levels: the first level is the priority of the news platform to which the trending topic belongs, and the second level is the priority of the trending topic in the ranking within the news platform.

[0091] Furthermore, when the semantic similarity of multiple trending topics is greater than or equal to a threshold, the trending topic with the highest priority can be identified as the target topic.

[0092] Specifically, you can first compare the priority of the platforms to which each trending topic belongs, and determine the trending topic with the highest platform priority as the candidate topic. When there is only one candidate topic, it can be determined as the target topic. When there are multiple candidate topics, determine the candidate topic with the highest ranking as the target topic based on their order.

[0093] In this embodiment of the disclosure, when selecting a target topic from various hot topics, a retrieval-supporting storage medium, such as the search engine Elasticsearch, can be initialized. Then, each hot topic is stored one by one. If the semantic similarity between the current hot topic to be stored and each of the already stored hot topics is less than a threshold, the hot topic can be stored as the target topic. If the semantic similarity between the current hot topic to be stored and the already stored hot topics is greater than or equal to the threshold, the priorities of the hot topic and the already stored hot topics can be compared. If the priority of the hot topic is higher than that of the already stored hot topics, the hot topic is used as the target topic, replacing the already stored hot topics. If the priority of the hot topic is lower than that of the already stored hot topics, the hot topic is discarded, and the next hot topic to be stored is processed.

[0094] In this embodiment of the disclosure, a target topic is selected from various hot topics according to their priority, which ensures the accuracy of the reference popularity value corresponding to the target topic and thus improves the credibility of the final comprehensive hot topic list.

[0095] Step S205: Determine the popularity value mapping relationship between the news platform corresponding to the news platform identifier and the search platform.

[0096] The news platform identifier can be any type of identifier that can represent each news platform. For example, it can be a number for each news platform, or it can be the name of each news platform. This disclosure does not limit this.

[0097] In this embodiment of the disclosure, when obtaining trending data from various news platforms, the trending data may further include the news platform identifier corresponding to the trending topic. Therefore, based on the news platform identifier, the news platform to which the trending topic belongs can be determined.

[0098] Understandably, the popularity scores of different news platforms may differ in magnitude. For example, if news platform A has tens of millions of users, its popularity score might be in the tens of millions, millions, or hundreds of thousands. If news platform B has millions of users, its popularity score might be in the millions, hundreds of thousands, or tens of thousands.

[0099] Therefore, when generating a comprehensive list of trending topics based on the reference popularity value corresponding to the target topic, the popularity values ​​of each target topic may differ significantly.

[0100] In this embodiment of the disclosure, the search frequency of trending topics on search platforms can be used as a benchmark to uniformly measure the popularity value of various news platforms.

[0101] For example, sample data can be used to discover the relationship between the popularity value of the same topic on news platforms and the click rate on search platforms, thereby determining the mapping relationship of popularity values ​​between news platforms and search platforms.

[0102] For example, for a trending topic S on news platform A, the popularity score is recorded every 5 minutes, and the average of the data for the day is taken as the average popularity score of trending topic S. At the same time, the search volume of trending topic S on the search platform on that day is recorded, and the average search volume over 5 minutes is calculated as the search frequency of trending topic S.

[0103] By analyzing sample data from each news platform, the mapping relationship between the popularity values ​​of each news platform and the search platform can be determined.

[0104] In this embodiment of the disclosure, once the target topic is determined, the popularity value mapping relationship between the corresponding news platform and the search platform can be determined based on the news platform identifier corresponding to the target topic.

[0105] The mapping relationship of heat values ​​can be expressed in any form. For example, it can be a linear function, or it can be a curvilinear function, etc. This disclosure does not limit it.

[0106] Step S206: Determine the target popularity value corresponding to the target topic based on the reference popularity value and popularity value mapping relationship corresponding to the target topic.

[0107] In this process, the reference popularity value corresponding to the target topic can be used as input data, and the target popularity value corresponding to the target topic can be determined according to the corresponding popularity value mapping relationship.

[0108] Step S207: Generate a comprehensive list of trending topics based on the target popularity value corresponding to the target topic.

[0109] The target popularity value is a reference popularity value for each target topic, obtained after data standardization according to a unified scale. Based on the target popularity value corresponding to each target topic, a current comprehensive list of trending topics can be generated.

[0110] For example, all target topics can be matched one-to-one with their target popularity values, and sorted from highest to lowest popularity value to form a comprehensive list of trending topics.

[0111] In this embodiment of the disclosure, the reference popularity value of the target topic is converted according to the popularity value mapping relationship between various news platforms and search platforms to generate the target popularity value. This realizes the standardization of popularity values ​​of different news platforms according to a unified standard, and improves the accuracy of the final comprehensive list of hot topics.

[0112] It should be noted that when the same trending topic appears on multiple news platforms, it indicates that the topic is quite popular.

[0113] In some embodiments of this disclosure, the final target popularity value can be calculated by comprehensively considering the reference popularity values ​​of the target topic on various news platforms. Alternatively, different weights can be assigned to each news platform. Then, the final target popularity value can be obtained by weighted fusion based on the weights of each news platform and their corresponding reference popularity values.

[0114] Figure 3 This is a flowchart illustrating a method for processing hotspot data according to another embodiment of the present disclosure.

[0115] like Figure 3 As shown, the method for processing this hotspot data may include the following steps:

[0116] Step S301: Obtain multiple hot topic data from multiple news platforms, wherein each hot topic data includes a hot topic and a reference popularity value corresponding to the hot topic.

[0117] Step S302: Determine the semantic similarity between each hot topic.

[0118] Step S303: Based on the semantic similarity between various hot topics, deduplication is performed on each hot topic to determine the target topic.

[0119] It should be noted that the specific implementation process of steps S301, S302, and S303 can be referred to the detailed description of other embodiments of this disclosure, and will not be repeated here.

[0120] Step S304: Determine the initial popularity value mapping relationship between the news platform corresponding to the news platform identifier and the search platform.

[0121] The news platform identifier can be any type of identifier that can represent each news platform. For example, it can be a number for each news platform, or it can be the name of each news platform. This disclosure does not limit this.

[0122] In this embodiment of the disclosure, when obtaining trending data from various news platforms, the trending data may further include the news platform identifier corresponding to the trending topic. Therefore, based on the news platform identifier, the news platform to which the trending topic belongs can be determined.

[0123] Therefore, once the target topic is determined, the initial popularity value mapping relationship between the corresponding news platform and the search platform can be determined based on the news platform identifier corresponding to the target topic.

[0124] The initial heat value mapping relationship can be expressed in any form. For example, it can be a linear function, or it can be a curvilinear function, etc. This disclosure does not limit it in this way.

[0125] Step S305: Determine the mapping relationship between the topic type associated with the news platform identifier and the first parameter.

[0126] It should be noted that each news topic can be categorized based on its specific news content. For example, it can be divided into entertainment news, social news, or sports news.

[0127] Understandably, different news types can influence the popularity of news topics. For example, entertainment news tends to attract more attention from users than sports news.

[0128] Therefore, when determining the target popularity value of a topic, the first parameter can also be used to characterize the impact of the topic's classification on the news platform on the target popularity value. However, the mapping relationship between the topic type and the first parameter may differ across different news platforms.

[0129] For example, the first parameter for entertainment news on news platform A can be b1, while the first parameter for entertainment news on news platform B can be b2. The values ​​of b1 and b2 are different.

[0130] Step S306: Determine the first parameter corresponding to the target topic based on the first topic type corresponding to the target topic and the mapping relationship between the topic type and the first parameter.

[0131] In this embodiment of the disclosure, when obtaining trending data from various news platforms, the trending data may further include a first topic type corresponding to the trending topic. The first topic type is the topic type in which the trending topic is categorized on the news platform.

[0132] Specifically, the first parameter corresponding to the target topic can be determined based on the first topic type corresponding to the target topic and the mapping relationship between the topic type and the first parameter.

[0133] Step S307: Input the target topic into the classification model to obtain the second topic type of the target topic on the search platform.

[0134] It should be noted that the same news topic may be categorized differently on different platforms. For example, a news topic may be categorized as entertainment news on a news platform, but as social news on a search platform.

[0135] Different news types can affect the popularity of news topics. Therefore, when using the search frequency of trending topics on search platforms as a benchmark to uniformly measure the popularity value across various news platforms, a second parameter can be used to characterize the impact of the target topic's category on the target popularity value.

[0136] Specifically, a classification model can be used to determine the second topic type that the target topic is categorized into on the search platform. This classification model can be trained using a large amount of labeled sample data.

[0137] Step S308: Determine the second parameter corresponding to the target topic based on the second topic type and the mapping relationship between the topic type associated with the search platform and the second parameter.

[0138] Specifically, based on the mapping relationship between the topic types associated with the search platform and the second parameter, the second parameter corresponding to each type of topic on the search platform can be determined.

[0139] Step S309: Determine the heat value mapping relationship based on the initial heat value mapping relationship, the first parameter, and the second parameter.

[0140] Specifically, the initial heat value mapping relationship can be merged with the first parameter and the second parameter to form a heat value mapping relationship.

[0141] For example, when the initial heat value mapping relationship is a function of the reference heat value, this function can be added to the first parameter and the second parameter to form the heat value mapping function.

[0142] It should be noted that the mapping relationship of popularity values ​​across various news platforms can be determined through data fitting.

[0143] For example, a linear function y = p + a * x + b(xc) + c(xq) can be used to represent the popularity value mapping relationship. Here, y = p + a * x is the initial popularity value mapping function, the parameters p and a are related to the news platform to which the target topic belongs, and x is the reference popularity value of the target topic. b(xc) is the first parameter, representing the first topic type of the target topic on the news platform. c(xq) is the second parameter, representing the second topic type of the target topic on the search platform.

[0144] When determining the parameters p, a, b(xc), c(xq) in a linear function through data fitting, a large amount of sample data can be obtained first.

[0145] For example, for a trending topic S on news platform A, the popularity value is recorded every 5 minutes, and the average value of the data for the day is taken as the reference popularity value x. Simultaneously, the search volume of trending topic S on the search platform on that day is recorded, and the average search volume over 5 minutes is calculated as the target popularity value y. Furthermore, the first topic type xc of the trending topic on news platform A and the second topic type xq of the trending topic on the search platform can also be recorded.

[0146] The above method allows us to obtain sample data from different news platforms. Then, based on the sample data from each news platform, we can determine the parameters p, a, b(xc), and c(xq) for each platform through linear fitting.

[0147] Step S310: Determine the target popularity value corresponding to the target topic based on the reference popularity value and popularity value mapping relationship corresponding to the target topic.

[0148] Step S311: Generate a comprehensive list of trending topics based on the target popularity value corresponding to the target topic.

[0149] It should be noted that the specific implementation process of steps S310 and S311 can be referred to the detailed description of other embodiments of this disclosure, and will not be repeated here.

[0150] In this embodiment of the disclosure, the mapping relationship of popularity values ​​between various news platforms and search platforms is determined based on the type of news platform, the topic type of the target topic on the news platform, and the topic type of the target topic on the search platform. This further improves the accuracy of the target popularity value corresponding to the target topic and the credibility of the final comprehensive hot topic list.

[0151] According to embodiments of this disclosure, this disclosure also provides a hotspot data processing apparatus.

[0152] Figure 4 This is a schematic diagram of a hotspot data processing apparatus according to an embodiment of the present disclosure. Figure 4 As shown, the hotspot data processing device 400 may include: an acquisition module 410, a first determination module 420, a second determination module 430, and a generation module 440.

[0153] The acquisition module 410 is used to acquire multiple hot topic data from multiple news platforms. Each hot topic data includes a hot topic and a reference popularity value corresponding to the hot topic.

[0154] The first determining module 420 is used to determine the semantic similarity between various hot topics;

[0155] The second determining module 430 is used to deduplicatize each hot topic based on the semantic similarity between them in order to determine the target topic.

[0156] The generation module 440 is used to generate a current comprehensive list of trending topics based on the reference popularity value corresponding to the target topic.

[0157] It should be noted that the explanation of the above-described embodiments of the hot data processing method also applies to the hot data processing device of this embodiment, and the implementation principle is similar, so it will not be repeated here.

[0158] In this embodiment, multiple hot topic data are first obtained from multiple news platforms, where each hot topic data includes a hot topic and its corresponding reference popularity value. Then, the semantic similarity between each hot topic is determined. Next, based on the semantic similarity, duplicate hot topics are removed to determine the target topic. Finally, based on the reference popularity value corresponding to the target topic, a comprehensive list of current hot topics is generated. This achieves the aggregation and integration of hot topics from different news platforms, allowing users to quickly and comprehensively understand current trending topics.

[0159] In one possible implementation of this disclosure, the second determining module may include:

[0160] The first determining unit is used to determine any hot topic as the target topic in response to the fact that the semantic similarity between any hot topic and other hot topics is less than a threshold.

[0161] The second determining unit is used to determine any one of the multiple hot topics as the target topic in response to the semantic similarity between multiple hot topics being greater than or equal to a threshold.

[0162] In one possible implementation of this disclosure, the hotspot data further includes the priority corresponding to the hot topics, and the second determining unit is specifically used for:

[0163] Identify the highest priority trending topic among multiple trending topics as the target topic.

[0164] In one possible implementation of this disclosure, the hot topic data further includes the news platform identifier corresponding to the hot topic, and the generation module may include:

[0165] The third determining unit is used to determine the popularity value mapping relationship between the news platform corresponding to the news platform identifier and the search platform.

[0166] The fourth determining unit is used to determine the target popularity value corresponding to the target topic based on the reference popularity value and popularity value mapping relationship corresponding to the target topic;

[0167] The generation unit is used to generate a comprehensive list of trending topics based on the target popularity value corresponding to the target topic.

[0168] In one possible implementation of this disclosure, the hotspot data further includes a first topic type corresponding to the hotspot topic, and the third determining unit is specifically used for:

[0169] Determine the initial popularity value mapping relationship between the news platform corresponding to the news platform identifier and the search platform;

[0170] Determine the mapping relationship between the topic type associated with the news platform identifier and the first parameter;

[0171] Based on the first topic type corresponding to the target topic and the mapping relationship between the topic type and the first parameter, determine the first parameter corresponding to the target topic;

[0172] Input the target topic into the classification model to obtain the second topic type of the target topic on the search platform;

[0173] Based on the second topic type and the mapping relationship between the topic types associated with the search platform and the second parameter, determine the second parameter corresponding to the target topic;

[0174] The mapping relationship of heat values ​​is determined based on the initial heat value mapping relationship, the first parameter, and the second parameter.

[0175] It should be noted that the explanation of the above-described embodiments of the hot data processing method also applies to the hot data processing device of this embodiment, and the implementation principle is similar, so it will not be repeated here.

[0176] In this embodiment of the disclosure, the mapping relationship of popularity values ​​between various news platforms and search platforms is determined based on the type of news platform, the topic type of the target topic on the news platform, and the topic type of the target topic on the search platform. This further improves the accuracy of the target popularity value corresponding to the target topic and the credibility of the final comprehensive hot topic list.

[0177] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, and a computer program product.

[0178] Figure 5 A schematic block diagram of an example electronic device 500 that can be used to implement embodiments of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0179] like Figure 5 As shown, device 500 includes a computing unit 501, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 502 or a computer program loaded from storage unit 508 into random access memory (RAM) 503. RAM 503 may also store various programs and data required for the operation of device 500. The computing unit 501, ROM 502, and RAM 503 are interconnected via bus 504. Input / output (I / O) interface 505 is also connected to bus 504.

[0180] Multiple components in device 500 are connected to I / O interface 505, including: input unit 506, such as keyboard, mouse, etc.; output unit 507, such as various types of monitors, speakers, etc.; storage unit 508, such as disk, optical disk, etc.; and communication unit 509, such as network card, modem, wireless transceiver, etc. Communication unit 509 allows device 500 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0181] The computing unit 501 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 501 performs the various methods and processes described above, such as the hot data processing method. For example, in some embodiments, the hot data processing method may be implemented as a computer software program tangibly contained in a machine-readable medium, such as storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on device 500 via ROM 502 and / or communication unit 509. When the computer program is loaded into RAM 503 and executed by the computing unit 501, one or more steps of the hot data processing method described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to perform the hot data processing method by any other suitable means (e.g., by means of firmware).

[0182] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0183] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0184] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable media can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0185] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0186] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), the Internet, and blockchain networks.

[0187] Computer systems can include clients and servers. Clients and servers are generally geographically separated and typically interact via communication networks. The client-server relationship is established by computer programs running on the respective computers and having a client-server relationship with each other. A server can be a cloud server, also known as a cloud computing server or cloud host, a hosting product within the cloud computing service system that addresses the shortcomings of traditional physical hosts and VPS (Virtual Private Server) services, such as high management difficulty and weak business scalability. Servers can also be servers for distributed systems or servers incorporating blockchain technology.

[0188] In this embodiment, multiple hot topic data are first obtained from multiple news platforms, where each hot topic data includes a hot topic and its corresponding reference popularity value. Then, the semantic similarity between each hot topic is determined. Next, based on the semantic similarity, duplicate hot topics are removed to determine the target topic. Finally, based on the reference popularity value corresponding to the target topic, a comprehensive list of current hot topics is generated. This achieves the aggregation and integration of hot topics from different news platforms, allowing users to quickly and comprehensively understand current trending topics.

[0189] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0190] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A method for processing hotspot data, comprising: Multiple trending data points are obtained from multiple news platforms, wherein each trending data point includes a trending topic and a reference popularity value corresponding to the trending topic; Determine the semantic similarity among various trending topics; Based on the semantic similarity between the aforementioned hot topics, duplicates of each hot topic are removed to determine the target topic; Based on the reference popularity value corresponding to the target topic, a current comprehensive list of trending topics is generated; The hot topic data also includes the news platform identifier corresponding to the hot topic. Generating a current comprehensive list of hot topics based on the reference popularity value corresponding to the target topic includes: Determine the popularity value mapping relationship between the news platform corresponding to the news platform identifier and the search platform; The target popularity value corresponding to the target topic is determined based on the reference popularity value and the popularity value mapping relationship. The comprehensive list of trending topics is generated based on the target popularity value corresponding to the target topic. The hot topic data also includes the first topic type corresponding to the hot topic, and determining the mapping relationship of popularity values ​​between the news platform corresponding to the news platform identifier and the search platform includes: Determine the initial popularity value mapping relationship between the news platform corresponding to the news platform identifier and the search platform; Determine the mapping relationship between the topic type associated with the news platform identifier and the first parameter; Based on the first topic type corresponding to the target topic and the mapping relationship between the topic type and the first parameter, the first parameter corresponding to the target topic is determined; The target topic is input into a classification model to obtain the second topic type of the target topic on the search platform; Based on the second topic type and the mapping relationship between the topic types associated with the search platform and the second parameter, the second parameter corresponding to the target topic is determined; The heat value mapping relationship is determined based on the initial heat value mapping relationship, the first parameter, and the second parameter; The step of determining the heat value mapping relationship based on the initial heat value mapping relationship, the first parameter, and the second parameter includes: The initial heat value mapping relationship is fused with the first parameter and the second parameter to form the heat value mapping relationship.

2. The method as described in claim 1, wherein, The step of deduplicating the hot topics based on their semantic similarity to determine the target topic includes: If the semantic similarity between any hot topic and other hot topics is less than a threshold, then the hot topic is determined to be the target topic. In response to the semantic similarity among multiple trending topics being greater than or equal to the threshold, any one of the multiple trending topics is determined as the target topic.

3. The method as described in claim 2, wherein, The hot topic data also includes the priority of the hot topics, and determining any one of the multiple hot topics as the target topic includes: The hot topic with the highest priority among the multiple hot topics is identified as the target topic.

4. A device for processing hotspot data, comprising: The acquisition module is used to acquire multiple hot topic data from multiple news platforms, wherein each hot topic data includes a hot topic and a reference popularity value corresponding to the hot topic; The first determining module is used to determine the semantic similarity between various hot topics; The second determining module is used to deduplicate each of the hot topics based on the semantic similarity between them, so as to determine the target topic; The generation module is used to generate a current comprehensive list of trending topics based on the reference popularity value corresponding to the target topic. The hot topic data also includes the news platform identifier corresponding to the hot topic, and the generation module includes: The third determining unit is used to determine the popularity value mapping relationship between the news platform corresponding to the news platform identifier and the search platform. The fourth determining unit is used to determine the target popularity value corresponding to the target topic based on the reference popularity value corresponding to the target topic and the popularity value mapping relationship; The generation unit is used to generate the comprehensive hot topic list based on the target popularity value corresponding to the target topic; The hot topic data also includes a first topic type corresponding to the hot topic, and the third determining unit is used for: Determine the initial popularity value mapping relationship between the news platform corresponding to the news platform identifier and the search platform; Determine the mapping relationship between the topic type associated with the news platform identifier and the first parameter; Based on the first topic type corresponding to the target topic and the mapping relationship between the topic type and the first parameter, the first parameter corresponding to the target topic is determined; The target topic is input into a classification model to obtain the second topic type of the target topic on the search platform; Based on the second topic type and the mapping relationship between the topic types associated with the search platform and the second parameter, the second parameter corresponding to the target topic is determined; The heat value mapping relationship is determined based on the initial heat value mapping relationship, the first parameter, and the second parameter; The third determining unit is specifically used to fuse the initial heat value mapping relationship with the first parameter and the second parameter to form the heat value mapping relationship.

5. The apparatus of claim 4, wherein, The second determining module includes: The first determining unit is configured to determine any hot topic as the target topic in response to the fact that the semantic similarity between any hot topic and other hot topics is less than a threshold. The second determining unit is used to determine any one of the multiple hot topics as the target topic in response to the semantic similarity between multiple hot topics being greater than or equal to the threshold.

6. The apparatus of claim 5, wherein, The hotspot data also includes the priority corresponding to the hot topics, and the second determining unit is used for: The hot topic with the highest priority among the multiple hot topics is identified as the target topic.

7. An electronic device, comprising: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.

8. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1-3.

9. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1-3.

Images