Method and apparatus for pushing a topic, electronic device, storage medium, computer program

Abstract

Embodiments of the present disclosure relate to a method, apparatus, device, and medium for push processing of topics. The method includes, in response to obtaining a topic push request sent from a client, identifying a plurality of reference push topics that match the client feature information in the current push topic pool; identifying at least one target push topic to be currently pushed from the plurality of reference push topics based on the ranking scores corresponding to the respective reference push topics; sending the at least one target push topic to the client corresponding to the topic push request, and controlling the client corresponding to the topic push request to display a push page in which a link relationship has been pre-established between the clicked target push topic and the push page; and the push page includes relevant push information of the clicked target push topic. Thereby, the push success rate of the push topic is improved, the push topic link includes the push page of the corresponding relevant push information, and the effect of the push topic is improved.

Description

Technical Field

[0001] [Cross - reference to Related Applications] This application claims priority based on a Chinese patent application with application number 202211707037.9, titled "Topic Push Processing Method, Apparatus, Device and Medium", filed with the China National Intellectual Property Administration on December 29, 2022, and all the content described in the said application is incorporated into this application by reference.

[0002] [Technical Field] The present disclosure relates to the technical field of computer applications, and in particular, to a topic push processing method, apparatus, device and medium.

Background Art

[0003] With the development of computer technology, in order to provide better online services, topic push notifications have become a common service method, such as pushing consumption - hot topics in an online shopping form, etc., so that appropriate products can be purchased and aimless product browsing behavior can be avoided.

[0004] In related technologies, topics are manually set by practitioners. The practitioners set corresponding topics based on their subjective judgment of current consumption hotspots. When the corresponding topic is clicked, push information corresponding to the preset clicked topic is displayed. However, in such a topic determination form, the push accuracy rate and success rate of topics are low.

Summary of the Invention

[0005] In response to obtaining a topic push request sent from a client, embodiments of the present disclosure obtain client feature information corresponding to the client, identify a plurality of reference push topics that match the client feature information in the current push topic pool, obtain a ranking score corresponding to each reference push topic based on at least one ranking factor corresponding to each reference push topic, identify at least one target push topic to be currently pushed from the plurality of reference push topics based on the ranking score, and send the at least one target push topic to the client corresponding to the topic push request. When a click instruction for the at least one target push topic is detected, control is performed to cause the client corresponding to the topic push request to display a push page in which a link relationship has been pre-established between the clicked target push topic and the push page, and the push page includes related push information of the clicked target push topic, thereby providing a method for processing topic push.

[0006] An embodiment of the present disclosure further includes a first acquisition module for acquiring client feature information corresponding to the client in response to acquiring a topic push request sent from the client, a determination module for determining a plurality of reference push topics matching the client feature information in the current push topic pool, a second acquisition module for acquiring a ranking score corresponding to each reference push topic based on at least one ranking factor corresponding to each reference push topic, and determining at least one target push topic to be currently pushed from the plurality of reference push topics based on the ranking score, and sending the at least one target push topic to the client corresponding to the topic push request. When a click instruction for the at least one target push topic is detected, a transmission module for controlling the client corresponding to the topic push request to display a push page in which a link relationship is pre-established between the clicked target push topic and the push page, where the push page includes related push information of the clicked target push topic, to provide a topic push processing device.

[0007] An embodiment of the present disclosure further includes a processor and a memory for storing instructions executable by the processor. The processor reads the executable instructions from the memory and executes the instructions to provide an electronic device used to implement the topic push processing method according to the embodiment of the present disclosure.

[0008] An embodiment of the present disclosure further provides a computer-readable storage medium storing a computer program used to execute the topic push processing method according to the embodiment of the present disclosure.

Brief Description of the Drawings

[0009] The above and other features, advantages, and aspects of each embodiment of the present disclosure will become more apparent with reference to the following specific embodiments in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the accompanying drawings are schematic and that the original drawings and elements are not necessarily drawn to scale.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0010] Hereinafter, embodiments of the present invention will be described in more detail with reference to the drawings. The drawings show some examples of the present disclosure. However, the present disclosure can be implemented in various forms. The following embodiments are provided to understand the present disclosure more clearly and completely, and should not be construed as limiting the present invention. It should be understood that the drawings and embodiments of the present disclosure are merely illustrative and not used to limit the protection scope of the present disclosure.

[0011] It should be understood that the multiple steps described in the method embodiments of the present disclosure can be executed in a different order and / or executed in parallel. Furthermore, the method embodiments may include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited thereto.

[0012] As used herein, the term "comprising" and its variations are to include openly, that is, in the sense of "including, but not limited to...". The term "based on" means "at least partially based on". The term "one embodiment" means "at least one embodiment", the term "another embodiment" means "at least one another embodiment", and the term "some embodiments" means "at least some embodiments". Related definitions of other terms are given in the following description.

[0013] The concepts such as "first", "second", etc. mentioned in the present disclosure are only for distinguishing different devices, modules or units, and are not for limiting the order or interdependence relationship of the functions executed by these devices, modules or units.

[0014] The terms "one" and "a plurality" mentioned in the present disclosure are illustrative and not restrictive, and should be understood as "one or a plurality" unless otherwise clearly indicated in the context.

[0015] The names of the messages or information that interact between multiple devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of these messages or information.

[0016] To solve the above technical problems, or at least partially solve the above-mentioned technical problems, the present disclosure provides a method, apparatus, device, and medium for push processing of topics, improves the success rate of pushing topics, and the push topic link includes a push page of corresponding relevant push information, thereby improving the effect of pushing.

[0017] The technical solutions according to the embodiments of the present disclosure have the following advantages compared with the prior art: The push processing form of the topic according to the embodiment of the present disclosure, in response to obtaining a topic push request sent from a client, obtains client feature information corresponding to the client, identifies a plurality of reference push topics matching the client feature information in the current push topic pool, obtains a ranking score corresponding to each reference push topic based on at least one ranking factor corresponding to each reference push topic, identifies at least one target push topic to be currently pushed from the plurality of reference push topics based on the ranking score, and sends the at least one target push topic to the client corresponding to the topic push request. Thus, when a click instruction for at least one target push topic is detected, the client corresponding to the topic push request is controlled to display a push page in which a link relationship has been pre-established between the clicked target push topic and the push page, and the push page includes relevant push information of the clicked target push topic. Thereby, the success rate of pushing topics is improved, the push topic link includes a push page of corresponding relevant push information, and the effect of pushing is improved.

[0018] To solve the above-mentioned problems, the embodiments of the present disclosure provide a method for push processing of topics, and the method will be described below with reference to specific embodiments.

[0019] FIG. 1 is a schematic diagram of the process of a topic push processing method according to an embodiment of the present disclosure. The method is executable by a topic push processing device, and the device can be realized by software and / or hardware and can generally be integrated into an electronic device. As shown in FIG. 1, the method includes the following.

[0020] In step 101, in response to obtaining a topic push request sent from a client, client feature information corresponding to the client is obtained, and in the current push topic pool, a plurality of reference push topics matching the client feature information are identified.

[0021] Here, the client feature information includes, but is not limited to, the industrial type of topics of interest, etc. The industrial type of topics may be, for example, "food industry type", "cosmetic industry type", "jewelry art industry type", etc.

[0022] Regarding the fact that in different application scenarios, the forms of responding to obtaining a topic push request sent from a client are different, the following is an exemplary description.

[0023] In some preferred embodiments, when topic push is periodically executed on the client, the online time of the client topic push page is detected. When the online time reaches the topic push cycle time, a topic push request sent from the client is obtained.

[0024] For example, when the cycle time is 10 minutes, by obtaining a topic push request sent from the corresponding client every 10 minutes, the real-time nature of the topics pushed later is ensured.

[0025] In some exemplary embodiments, when it is detected that a preset topic update operation is performed on the client, a topic push request sent from the client is obtained. In this embodiment, the preset topic update operation may be performed by triggering a corresponding update control, or may be triggered by inputting voice information including a predetermined update keyword, etc.

[0026] It is understood that each push topic in the current push topic pool has a topic popularity, and the higher the topic popularity, the higher the hotness of the corresponding push topic. Here, the topic popularity of the corresponding topic is updated by the click-through rate (CTR) of the topic on the client.

[0027] Here, the current push topic pool is a real-time topic library that is maintained and updated in real time. The current push topic pool can include hot topics such as live streaming hot topics, industry hot topics, product hot topics, search hot topics, etc. in the corresponding push scene. For example, when the current push topic pool includes a live streaming hot topic, a playback video having a playback volume greater than a predetermined playback volume is obtained, and a video keyword corresponding to the playback video is obtained as a push topic. A topic popularity is set for each push topic.

[0028] For example, if the current push topic pool contains search topics determined based on search terms, after obtaining the search terms, the search terms obtained during the current analysis cycle are analyzed at a predetermined analysis frequency, and based on the search frequency of the search terms, popular search terms are determined, and the popular search terms are used as push topics. Alternatively, based on the popular search terms, a knowledge graph corresponding to the search scene may be searched. This knowledge graph includes a plurality of nodes, each node includes a corresponding search term, and nodes with a related relationship are connected to each other by edges. Therefore, after identifying the popular search terms, search the knowledge graph corresponding to the search scene to obtain related search terms, and use the related search terms and the popular search terms as search topics and the like.

[0029] Here, the current topic library may include topics set according to the needs of the scene, for example, recommended topics set by relevant operators according to the needs of the scene.

[0030] In one embodiment of the present disclosure, before adding a topic to the push topic pool, it is also necessary to verify the topic, for example, filter out some new topics that overlap with the existing topics, or delete some topics containing preset characters. The preset topics may be set according to the needs of the scene. For example, the preset characters may be garbled characters, etc. The verification of the topic may be automatic or may be an online review, etc.

[0031] In one embodiment of the present disclosure, the topic popularity within the current push topic pool is maintained in real time. In one embodiment of the present disclosure, the topic popularity of the corresponding topic is updated by clicking on the qualified rate CTR.

[0032] In an embodiment of the present disclosure, after at least one target push topic is pushed to a corresponding client, in response to receiving a topic click instruction regarding a first push topic among at least one target push topic at the client, the current total push number and the current total click number of the first push topic are confirmed. The current total push number of the first push topic is obtained by adding 1 to the past total push number before the target push topic is pushed to the corresponding client. According to the calculation logic of the CTR, the ratio of the current total click number to the current total push number of the first push topic is calculated as the topic popularity of the first push topic.

[0033] In this embodiment, a second push topic that has not been clicked among at least one target push topic is identified. Since the second push topic has been pushed to the client but has not been clicked at the corresponding client, in order to maintain the topic hotness in real time, the current total push number and the past total click number of the second push topic are confirmed. The current total push number of the second push topic is obtained by adding 1 to the past total push number before the second push topic is pushed to the corresponding client. According to the calculation logic of the CTR, the ratio of the past total click number to the current total push number of the second push topic is calculated as the topic popularity of the second push topic.

[0034] Regarding the topic popularity of the push topics within the current push topic pool, based on click instructions of all clients corresponding to all push topic push requests that have been pushed, the topic popularity of the corresponding push topic is updated, thereby ensuring the real-time maintenance of the topic popularity of the push topic.

[0035] Accordingly, in the current push topic pool according to the embodiments of the present disclosure, while the included push topics can be updated in real time according to the current search term hotspots, industry hotspots, etc., in response to the click operation of the client corresponding to the topic push request, by maintaining the real-time popularity of the push topics, topics are pushed in the current push topic pool, and it is ensured that the trend of the hotspots such as the topic hotspots of the push topics and the industry hotspots in the actual scene coincide.

[0036] In one embodiment of the present disclosure, it can be understood that for each push topic, a client feature information label matching it is pre-constructed, and the matching client feature information label is obtained by collectively learning the client feature information of the client that clicked on the corresponding topic. A plurality of reference push topics matching the client feature information are identified in the current push topic pool based on the client feature information label.

[0037] In step 102, based on at least one ranking factor corresponding to each reference push topic, a ranking score corresponding to each reference push topic is obtained.

[0038] In step 103, based on the ranking score, at least one target push topic to be currently pushed is identified from the plurality of reference push topics, and the at least one target push topic is sent to the client corresponding to the topic push request. When a click instruction for the at least one target push topic is detected, the client corresponding to the topic push request is controlled to display a push page whose link relationship has been pre-constructed with the clicked target push topic, and the push page includes relevant push information of the clicked target push topic.

[0039] To ensure the push effect of the target push topic for the push, at least one target push topic to be currently pushed is identified from a plurality of reference push topics based on client characteristic information. Since at least one target push topic matches the client characteristic information, the push effect of the target push topic is ensured.

[0040] In one embodiment of the present disclosure, at least one ranking factor corresponding to each reference push topic is obtained. The ranking factor includes at least one of a topic type, a topic impression rate, and a topic popularity. The topic type may include hot topics summarized based on industry real-time hot spots, search term hot spots, etc., and recommended topics according to the needs of the scene (for example, when sudden current affairs news occurs, the keywords of the current affairs news are regarded as recommended topics, etc.). The topic impression rate is the initial impression rate of each push topic candidate in the target push topic set when each push topic in the previous push topic set was first pushed to the client corresponding to the topic request. It may also be the topic popularity of each push topic in the target push topic set when it was first pushed to the client corresponding to the topic request. It is understood that the set of relevant push information corresponding to each target push topic is obtained in advance, and the push page corresponding to each target push topic is generated according to the set of relevant push information. Here, the set of relevant push information includes a plurality of relevant push information belonging to any type of push information related to the corresponding target push topic. The relevant push information includes, but is not limited to, information of information types such as short videos, information of live streaming types such as live streaming videos, information of item types such as product push information, information of activity types such as discount activities, custom promotion information, etc.

[0041] In one embodiment of the present disclosure, according to the relevant push information set, a push page corresponding to each target push topic is generated, and the push page includes push information related to the corresponding target push topic. A link relationship is constructed between each target push topic and the corresponding push page, and at least one target push topic is sent to a client corresponding to a topic push request. Further, when a click instruction for at least one target push topic is detected, the client corresponding to the topic push request is controlled to display the push page of the clicked target push topic. While the push effect of the pushed target push topic is guaranteed by the consistency between the at least one pushed topic and the client characteristic information, the target push topic constructs a link relationship with the push page including the relevant push information related to the corresponding topic, and by triggering the corresponding target push topic, it is guaranteed to obtain the relevant push information, improving the interactive experience.

[0042] For example, as shown in FIG. 2, when the client characteristic information corresponding to the client is "interested in topics of the food industry type", the target push topics of the video industry type identified in the current push topic pool are a, b, and c. When a is clicked, as shown in FIG. 3, the push page A corresponding to a is displayed, and this push page A includes cooking push videos related to a, etc.

[0043] To sum up, the method for pushing topic in the embodiment of the present disclosure is to, in response to obtaining a topic push request sent from a client, obtain client feature information corresponding to the client, identify a plurality of reference push topics matching the client feature information in the current push topic pool, obtain a ranking score corresponding to each reference push topic based on at least one ranking factor corresponding to each reference push topic, identify at least one target push topic to be currently pushed from the plurality of reference push topics based on the ranking score, send the at least one target push topic to the client corresponding to the topic push request, and when a click instruction for the at least one target push topic is detected, control the client corresponding to the topic push request to display a push page with a pre-constructed link relationship with the clicked target push topic, where the push page includes relevant push information of the clicked target push topic. Thereby, the success rate of pushing topics is improved, and the push topic link includes the push page of the corresponding relevant push information, improving the effect of the push.

[0044] Note that, as illustrated below, in different application scenarios, identifying at least one target push topic from a plurality of reference push topics may have other optional embodiments.

[0045] In one embodiment of the present disclosure, according to the time added to the current push topic pool, the first predetermined number of push topics are identified from the plurality of reference push topics as at least one target push topic.

[0046] In one embodiment of the present disclosure, since new topics may be added to the current push topic pool at any time, in order to identify the topic popularity of the newly added topics, it can be easily understood that a target push topic is identified from the new topics by random determination.

[0047] In an embodiment of the present disclosure, when there is at least one first candidate push topic that meets a predetermined random push condition among a plurality of reference push topics, at least one target push topic is randomly identified from the at least one first candidate push topic, and the number of topics of the first push topic can be set according to the needs of the scene. Here, the first candidate push topic that meets the predetermined random push condition is a new topic for which it is necessary to identify topic popularity.

[0048] In the actual execution process, the above-mentioned predetermined random push conditions vary in different application scenarios. In some possible embodiments, the total number of pushes of the reference push topic is less than a first predetermined push count threshold. For example, the predetermined push count threshold is 10,000 or the like. In this case, the corresponding reference push topic is considered to meet the predetermined random push condition. Here, the total number of pushes of the reference push topic is the total number of pushes since the reference push topic was added to the current push topic pool.

[0049] In this embodiment, when there is at least one second candidate push topic that does not meet the predetermined random push condition among a plurality of reference push topics, at least one target push topic is identified by the topic popularity of the at least one second candidate push topic. For example, at least one second candidate push topic is ranked in descending order of topic popularity, and a predetermined number of second push topics from the beginning of the ranking result are selected as the target push topics. Here, the number of second candidate push topics can be set according to the needs of the scene.

[0050] In this embodiment, when a plurality of reference push topics include both first candidate push topics and second candidate push topics, the number of first candidate push topics and second candidate push topics can be determined according to the needs of the scene. For example, if the number of target push topics sent to the client corresponding to the topic request is 5 each time, 2 first candidate push topics and 3 second candidate push topics can be identified as the target push topics.

[0051] In one embodiment of the present disclosure, after identifying at least one target push topic from the target push topic set, the topic impression rate of the target push topic is further updated. In some possible embodiments, for each target push topic, the difference between the first predetermined push count threshold corresponding to the topic push request and the current total push count can be calculated. The first predetermined push count threshold can be determined according to the scene and is usually the maximum number of times that can be pushed to the client. For example, the first predetermined push count threshold may be 10. The current total push count of each target push topic is the total number of times pushed to the client corresponding to the current topic push request, and a reference ratio of the difference to the first predetermined push count threshold is calculated.

[0052] After obtaining the reference ratio, the product value of the reference ratio and the topic impression rate is calculated, and by updating the topic impression rate of each target push topic based on the product value corresponding to each target push topic, the larger the current total push count, the smaller the obtained difference, and the smaller the obtained reference ratio, the smaller the corresponding updated topic impression rate.

[0053] For example, if the past impression rate of target push topic 1 before being pushed to client Q this time is 0.5, the first predetermined push threshold is 10, and the current total push count after this push is 2 (that is, this is the second time of pushing to client Q), the updated past impression rate is determined to be 0.5×(10 - 2) / 10 = 0.4, and the past impression rate of target push topic 1 decreases from 0.5 to 0.4 after this push.

[0054] The more times a topic is pushed to the client corresponding to the topic push request, the more likely it is an old topic for the client, so the corresponding topic impression rate decreases. When identifying target push topics by combining the topic impression rates, the probability of being pushed to the client multiple times decreases.

[0055] In some possible embodiments, several target push topics are pushed to clients corresponding to the same topic requirement relatively frequently. However, since the client has clicked on the target push topic at the client side, in order to avoid a low topic impression rate based only on the number of pushes, the target push topics that the client is interested in are identified as old topics, resulting in a lower probability of being pushed to the corresponding clients. In this embodiment, when the client corresponding to the topic push request responds to the command to click on at least one target push topic, the current total number of pushes of the clicked target push topic is cleared to zero, and the count resumes. That is, after the target push topic is clicked, when it is pushed to the same client next, the current total number of pushes of the target push topic becomes 1, and the count starts again.

[0056] Here, what ranking factors are included in the at least one ranking factor to be identified can be selected according to the needs of the scenario. For example, only the topic popularity can be used as the ranking factor, or for example, only the topic impression rate can be used as the ranking factor, etc.

[0057] After at least one ranking factor for each reference push topic is identified, a normalization value corresponding to each ranking factor is determined. The form of the normalization value corresponding to each ranking factor may be determined according to the needs of the scenario and is not enumerated in this specification.

[0058] In the actual execution process, when the topic type is included in the ranking factor, in order to be able to push to the client corresponding to the recommended topic, the normalization value corresponding to the recommended topic is increased. Also, for example, when the topic type is included in the ranking factor, in order to be able to push to the client corresponding to the new topic, the current number of times the new topic has been pushed is identified, and the corresponding normalization value is determined based on the number of times it has been pushed. The normalization value can be inversely proportional to the number of times it has been pushed. A new topic with a small number of times pushed can match a higher normalization value, and the probability that a new topic with a small number of times pushed is pushed to the client corresponding to the topic requirement is improved.

[0059] In this embodiment, by adding all the normalization values corresponding to each reference push topic to obtain the ranking score of each reference push topic, the plurality of reference push topics are ranked in descending order of the ranking score to obtain a reference push topic ranking list, and the first predetermined number of reference push topics are specified as at least one target push topic from the reference push topic ranking list.

[0060] That is, in the embodiments of the present disclosure, referring to FIG. 4, when at least one of the ranking factors includes a topic type, a topic impression rate, and a topic popularity, the current push topic pool includes hot topics obtained by summarizing real-time hot spots in the industry, hot spots in search terms, etc. (when a hot topic meets a predetermined random push condition, the hot topic is regarded as a new topic, etc.), and recommended topics set according to the needs of the scene (for example, when a current news suddenly occurs, the keyword of the current news is used as a recommended topic, or in order to promote a certain special sale, the recommended topic obtained for the keyword of the special sale). After identifying a plurality of reference push topics that match the characteristic information of the client in the current push topic pool, obtain the topic type, topic impression rate, topic popularity, etc. of each reference push topic (when there is no corresponding ranking factor, directly determine the normalization value of the corresponding ranking factor to be 0. For example, if reference push topic E is a new topic that has just been added, the topic popularity of E is normalized to 0). After normalizing at least one ranking factor corresponding to each reference push topic, a normalization value corresponding to each reference push topic is obtained. Add up all the normalization values corresponding to each reference push topic to obtain the ranking score of each reference push topic, and obtain a finally ranked reference push topic ranking list for the reference push topics. Determine at least one target push topic from the reference push topic ranking list starting from the beginning. Here, the predetermined number is related to the maximum number of target push topics displayed on the client corresponding to the topic requirement.

[0061] In summary, the topic push processing method according to the embodiments of the present disclosure, after identifying a plurality of reference push topics that match the characteristic information of the client, combines ranking factors such as topic hotness and topic impression rate to sort the plurality of reference push topics, selects a target push topic based on the ranking result, and improves the flexibility in identifying the target push topic.

[0062] Next, with reference to the embodiments, an explanation will be given of how to obtain the relevant push information set corresponding to each target push topic.

[0063] In one embodiment of the present disclosure, a plurality of reference push information that satisfies a predetermined push condition is identified. Here, it is understood that the information includes, but is not limited to, information of an information type such as a short video, information of a live streaming type such as a live video, information of an activity type such as item type information such as a product push message, information of a custom promotion, etc.

[0064] Here, in some possible embodiments, the predetermined push condition is that the playback count of the reference push information exceeds a predetermined number. In some possible embodiments, the predetermined push condition is that the push popularity of the reference push information is greater than a predetermined push popularity threshold, and the push popularity is obtained by adding based on at least one push popularity factor value of the reference push information. For example, the push factor value corresponding to each reference push information is obtained, the push factor is normalized to obtain the corresponding push factor value, and the push popularity factor of each reference push message varies depending on its information type. For example, when the reference push message is of an information type such as a short video, the push popularity factor includes the playback count of the reference push message, etc. When the reference push message is of an item type such as a product push message, the push popularity factor includes the purchase count of the product, etc.

[0065] Furthermore, after determining a plurality of reference push messages that satisfy the predetermined push condition, for each reference push message, a predetermined information label is obtained, which is the information label set when the reference push message is pushed. For example, when the reference push message is a product detail message of "rose", the corresponding information label includes "Chinese Valentine's Day", "love between men and women", "romantic Valentine's gift", etc.

[0066] Match the information labels of each reference push message with the target push topic. The matching method may be semantic matching, keyword matching, etc. Identify multiple reference push messages that have been successfully matched with the target push topic, generate and store the correspondence relationship between the multiple reference push messages that have been successfully matched with the target push topic. That is, after the target push topic is aggregated with the multiple reference push messages that have been successfully matched, it is bound to the target push topic.

[0067] By querying the pre-generated correspondence relationship, obtain multiple reference push information corresponding to the target push topic as multiple related push information, and generate a related push information set based on the multiple related push information.

[0068] Furthermore, after obtaining the related push information set corresponding to the target push topic, generate a push page corresponding to each of the target push topics based on the related push information set. This push page functions as the clicked landing page for each target push topic.

[0069] In this embodiment, identify at least one information type corresponding to the related push information set, and identify the display number threshold for each information type on the push page. The display number threshold may be determined based on the display number threshold of each information type defined in the automatically matched push page template, or may be customized.

[0070] Here, the style of the push page template may be predefined. For example, when the information types include content information type and product information type, in the product information type, for the corresponding related push information, if a plurality of product labels (the product labels are obtained by matching with a product library including the correspondence between each product type and the corresponding product label when the product is online) are included, and there is no product label corresponding to the related push information to be displayed in the product information type, the style of the push page template is, as shown in FIG. 5, the related push information regarding two content information types is displayed in the upper half of the page template, and the related push information of two product information types is displayed in the lower half of the page template.

[0071] In the product information, if a plurality of corresponding product tags are included in the related push information to be displayed, the push page template is, as shown in FIG. 6, the related push information regarding two content information is displayed in the upper half of the page template, and a plurality of product tags are displayed in the lower half of the page template, so that when the corresponding product tag is triggered, the related push information regarding the corresponding product tag is displayed.

[0072] After specifying the threshold number of information to be displayed on the push page for each information type, rank the related push information corresponding to each information type in descending order of the push popularity of the related push information corresponding to each information type to generate a related push information ranking list. Based on the display number threshold corresponding to each information type, identify the related push information with the first threshold display number from the related push information ranking list as the initial related push information, and generate a push page based on the initial related push information corresponding to all information types. For example, generate a push page by filling the corresponding initial related push information based on the selected push page template.

[0073] Thus, in one embodiment of the present disclosure, as shown in FIG. 7, in the push processing method of the topic of the present disclosure, first, hot topics, recommended topics, etc. are automatically generated according to methods such as knowledge graph and hot spot collection, and the hot topics are filtered by online review, etc. to obtain the filtered hot topics. In the topic filtering stage, duplicate topics are aggregated, topics containing a predetermined character are deleted, or topics of related push information not exceeding a predetermined number are deleted. Specific filtering can be set according to the needs of the scene.

[0074] Furthermore, the push information is aggregated according to the information tags of the push information, etc. The filtered hot topics are bound to the aggregated related push information to generate a push page, etc. The target push topic bound to the push page is released as a topic in the current push topic pool. For example, in response to a topic push request, the target topic is pushed to the client corresponding to the topic push request. When a click instruction for the target push topic is detected, it can be ranked in combination with various ranking factors, etc. when released, so as to display the push page of the clicked target push topic.

[0075] In one embodiment of the present disclosure, in order to further ensure the interactive effect, the push pages of related push topics are also automatically cycled, and some push topics with ineffective jumps and push topics containing duplicate related push information are reported to the related clients, which facilitates the processing of the push pages by the related clients.

[0076] In summary, the method for pushing topics according to the embodiments of the present disclosure aggregates relevant push information associated with each target push topic, generates a push page for the target push topic based on the relevant push information, and constructs a link relationship with the push page corresponding to each target push topic. When a target push topic is clicked, several popular relevant push information items regarding the corresponding target push topic are pushed and displayed, thereby improving the interactive experience.

[0077] To further ensure the push effect of the pushed relevant target topics, topic filtering can also be performed before pushing the corresponding target push topic to the corresponding client. In this way, clients with the same client characteristic information can obtain different target push topics even if they send topic push requests simultaneously, further ensuring the effect of topic push.

[0078] In one embodiment of the present disclosure, it is determined whether at least one target push topic meets a predetermined filter condition. If the predetermined filter condition is met, a switched target push topic corresponding to the target push topic is obtained. Here, the switched target topic can be identified from other reference push topics other than at least one target push topic in the reference push topic ranking list. For example, the switched target push topic is identified from other reference push topics in descending order of hot information, and the topic ranking of the switched target push topic in the reference push topic ranking list is located ahead of the topic rankings of the remaining reference push topics other than the switched target push topic among other reference push topics.

[0079] In some possible embodiments, if the corresponding switched target push topic cannot be obtained from the reference push topic ranking list, a fallback strategy is used to obtain the corresponding switched target push topic so as to ensure that the number of target push topics displayed last does not decrease.

[0080] For example, among the remaining reference push topics in the reference push topic ranking list, it is determined whether the number of topics that meet a predetermined filter condition is less than a predetermined lower limit value. If it is not less than the predetermined lower limit value, at least a part of the reference push topics that do not meet the predetermined filter condition may be directly deleted, and the remaining reference push topics may be pushed. If it is less than the predetermined lower limit value, a switching target topic can be identified from a reference topic library that may include the current push topic pool. The current push topic pool includes search topics determined based on hot search terms, etc. When identifying a switching target push topic from the current push topic pool, one topic may be randomly selected as the switching target push topic so that at least one of the switched target push topics meets the predetermined filter condition. The reference topic library may include a plurality of predetermined replacement topics. In other arbitrary embodiments, other methods may be adopted to identify the switching target topic.

[0081] The above-mentioned predetermined filter condition varies depending on different application scenarios. In some possible embodiments, in order to avoid pushing the same target push topic to the same client multiple times, the predetermined filter condition may correspond to the filtering of the push frequency control of the topic. When the current total number of pushes of the target push topic to the client corresponding to the topic push request is equal to or greater than a second predetermined push count threshold, the target push topic is considered to meet the predetermined push condition. Here, the second predetermined push count threshold can be determined according to needs and may be, for example, 10 times or the like.

[0082] In some possible embodiments, although some target push topics may be pushed to clients corresponding to the same topic request more frequently, the target push topics have been clicked by the clients, which proves that the clients may be interested in the target push topics. Therefore, in this embodiment, in order to avoid filtering out the target push topics that the clients are interested in based on the number of pushes, in response to the instruction that at least one client corresponding to the topic push request clicks on at least one target push topic, the current total number of pushes of the clicked target push topic is cleared to zero and a new count is performed. That is, after the target push topic is clicked and then pushed to the same client next time, in order to avoid filtering out the target push topics that the client is interested in, the current total number of pushes of the target push topic becomes 1, and the count of the number of times the target push topic is pushed to the clients corresponding to the topic push request is restarted.

[0083] When identifying target push topics based on at least one of the above-mentioned ranking factors, it is also possible to flexibly select based on other methods according to the needs of the scene. For example, in an embodiment of the present disclosure, as shown in FIG. 8, when the ranking factors are the topic impression rate score, the topic type (in this embodiment, the recommended topic), and the topic popularity, after the target push topic is pushed to the clients corresponding to the topic push request, the client identifier and push time of the pushed target push topic, etc. are recorded in the form of a message queue, and the current total number of pushes of the target push topic to the clients corresponding to the topic push request is updated asynchronously. In response to the instruction that at least one client corresponding to the topic push request clicks on at least one target push topic, the number of times clicked by the clients corresponding to the topic push request is used as the current total number of pushes of the target push topic.

[0084] In this embodiment, in the current push topic pool, a plurality of reference push topics that match the client feature information are identified. Each reference push topic has a topic popularity, and the plurality of reference push topics are ranked in descending order of topic popularity. The top N reference push topics are selected from the ranking results. N can be determined according to the needs of the scene. Further, the topic impression rate score of the top N reference push topics is obtained, and the top N reference push topics are ranked in descending order of the topic impression rate score to obtain the final topic ranking result. When a recommended topic is obtained, the recommended topic is inserted as the first topic in the topic ranking result, and according to the final ranking result, the push process of the topic is realized. For example, the first predetermined number of reference push topics are selected as the target push topics.

[0085] In one embodiment of the present disclosure, in order to ensure that the target push topic conforms to the trend hot spot of the current push scene, the push topics in the current push topic pool can also be retrieved offline.

[0086] In this embodiment, in the current push topic pool, it is determined whether there is a third push topic that meets the predetermined retrieval conditions. If the third push topic exists, the third push topic is deleted from the current push topic pool.

[0087] Regarding that the predetermined cycle conditions vary depending on different application scenarios, the following is an exemplary explanation.

[0088] In some possible embodiments, the predetermined recovery condition includes that the current time does not belong to the predetermined push time corresponding to the third push topic, that is, the third push topic has a predetermined push time. For example, when the third push topic is a push topic corresponding to a special sales activity, the push time corresponding to the third push topic is the effective time corresponding to the special sales activity. Also, for example, when the third push topic is a topic related to summer, the third push topic is the time corresponding to summer. For example, when the third push topic is a topic related to the Mid-Autumn Festival, the third push topic is the time corresponding to the Mid-Autumn Festival. Since the third push topic can only meet the push requirement when pushed at the predetermined push time, in this embodiment, when the current time does not belong to the predetermined push time corresponding to the third push topic, the third push topic is considered to meet the predetermined recovery condition.

[0089] In some possible embodiments, when the topic popularity of the third push topic is less than a predetermined popularity threshold, the third push topic is considered to be "timed out" and not in line with the current hot trend. Therefore, the third push topic is considered to meet the predetermined recovery condition.

[0090] For example, when the topic popularity of the third push topic corresponds to the impression click-through rate and the impression click-through rate is less than 0.18, the third push topic is considered to be "timed out", and the third push topic is considered to meet the predetermined recovery condition.

[0091] In some possible embodiments, the related push information set corresponding to the third push topic includes push objects that can be products, etc. When the effective push quantity of the product (for example, the purchase quantity of the product, etc.) is less than a threshold value of a predetermined number, the third push topic is considered to meet the predetermined recovery condition.

[0092] Here, in order to facilitate the refined recovery management of the target push topic, different levels of recovery conditions can be set, and different recovery processes can be performed for different levels of recovery conditions. For example, when the level of the satisfied recovery condition is the third predetermined level, the third push topic is directly deleted offline. For example, when the level of the satisfied recovery condition is the second predetermined level, the third push topic is sent to the relevant person in charge for review. Here, in an embodiment where it is determined whether the third push topic meets the predetermined recovery condition according to the above-mentioned topic popularity, a predetermined popularity threshold corresponding to the level of the recovery condition can be set. In an embodiment where it is determined whether the third push topic meets the predetermined recovery condition according to the effective push number of the push object, a predetermined threshold corresponding to the level of the recovery condition can be set.

[0093] To sum up, the push processing method for topics in the embodiments of the present disclosure filters the target push topic in combination with the click operation of the client on the target topic, further realizes the effect of topic push, recovers some push topics, and can ensure the topic quality of the pushed target push topic.

[0094] To implement the above embodiments, the present disclosure further provides a push processing device for topics.

[0095] FIG. 9 is a schematic diagram of the configuration of a push processing device for topics according to an embodiment of the present disclosure. The device can be realized by software and / or hardware, and generally can be integrated into an electronic device to execute push processing of topics. As shown in FIG. 9, the device includes a first acquisition module 910 for acquiring client feature information corresponding to the client in response to acquiring a topic push request sent from the client, a specific module 920 for specifying a plurality of reference push topics that match the client feature information in the current push topic pool, A second acquisition module 930 for acquiring a ranking score corresponding to each reference push topic based on at least one ranking factor corresponding to each reference push topic; Based on the ranking score, at least one target push topic to be currently pushed is identified from a plurality of reference push topics, and by sending at least one target push topic to a client corresponding to a topic push request, when a click instruction for at least one target push topic is detected, the client corresponding to the topic push request is controlled to display a push page in which a link relationship has been previously established between the clicked target push topic and the push page, and the push page includes relevant push information of the clicked target push topic. A transmission module 940 for performing the above operations.

[0096] The topic push processing apparatus according to an embodiment of the present disclosure is capable of executing the topic push processing method according to any embodiment of the present disclosure, and has functional modules and beneficial effects corresponding to the executed method, which will not be repeated herein.

[0097] To implement the above-described embodiments, the present disclosure further provides a computer program product including a computer program / instruction that, when executed by a processor, implements the topic push processing method according to the above-described embodiments.

[0098] FIG. 10 is a schematic diagram of the configuration of an electronic device according to an embodiment of the present disclosure.

[0099] Hereinafter, specifically, FIG. 10 shows a schematic configuration diagram applicable to realizing the configuration of the electronic device 1000 according to an embodiment of the present disclosure. The electronic device 1000 according to an embodiment of the present disclosure includes, but is not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (tablets), PMPs (Portable Multimedia Players), in-vehicle terminals (e.g., car navigation terminals), and fixed terminals such as digital TVs and desktop computers. The electronic device shown in FIG. 10 is merely an example and does not limit the functions and application ranges of the embodiments of the present disclosure.

[0100] As shown in FIG. 10, the electronic device 1000 can include a processing device (e.g., a central processor, a graphics processor, etc.) 1001 capable of executing various appropriate operations and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a memory 1008 into a random access memory (RAM) 1003. Various programs and data necessary for the operation of the electronic device 1000 are also stored in the RAM 1003. The processing device 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. An input / output (I / O) interface 1005 is also connected to the bus 1004.

[0101] Generally, for example, an input device 1006 including a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc., an output device 1007 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc., a memory 1008 including, for example, a magnetic tape, a hard disk, etc., and a communication device 1009 are connected to the I / O interface 1005. Through the communication device 1009, the electronic device 1000 can communicate with other devices wirelessly or wiredly to exchange data. Although FIG. 10 shows the electronic device 1000 equipped with various devices, it should be understood that it is not necessary to implement or include all the illustrated devices. Alternatively, more or fewer devices may be implemented or included.

[0102] In particular, the above-described process described with reference to the flowchart may be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product including a computer program loaded on a non-transitory computer-readable medium including program code for executing the method shown in the flowchart. In this embodiment, the computer program may be downloaded and installed from a network via the communication device 1009, or may be installed from the memory 1008 or the ROM 1002. When executed by the processing device 1001, this computer program executes the above-described functions limited to the push processing method of the topic according to the embodiments of the present disclosure.

[0103] Note that the computer-readable medium described above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium may be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above, but is not limited thereto. More specific examples of the computer-readable storage medium may include, but are not limited to, electrical connections having 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 thereof. In the present disclosure, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable storage medium may also be any tangible medium that includes or stores a program that can be used by or in combination with an instruction execution system, apparatus, or device. On the other hand, in the present disclosure, the computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave on which a computer-readable program code is carried. Such a propagated data signal may adopt various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the above. Furthermore, the computer-readable signal medium may be any computer-readable medium other than the computer-readable storage medium that can transmit, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device.The program code contained in the computer-readable medium may be transmitted over any suitable medium, including, but not limited to, wires, optical cables, RF (radio frequency), or any suitable combination of the foregoing.

[0104] In some embodiments, the client and server can communicate using any network protocol known now or developed in the future, such as HTTP (Hyper Text Transfer Protocol), and can be connected to digital data communication of any form or medium (e.g., communication network). Examples of communication networks include local area network ("LAN"), wide area network ("WAN"), extranet (e.g., Internet), end-to-end network (e.g., ad hoc end-to-end network), and networks known now or developed in the future.

[0105] The computer-readable medium may be included in the above-mentioned electronic device or may exist separately without being incorporated into the electronic device.

[0106] The computer-readable medium stores one or more programs that, when executed by an electronic device, cause the electronic device to perform the following: in response to obtaining a topic push request sent from a client, obtain client feature information corresponding to the client, identify a plurality of reference push topics that match the client feature information in the current push topic pool, obtain a ranking score corresponding to each reference push topic based on at least one ranking factor corresponding to each reference push topic, identify at least one target push topic to be currently pushed from the plurality of reference push topics based on the ranking score, send the at least one target push topic to the client corresponding to the topic push request, and when a click instruction for the at least one target push topic is detected, control the client corresponding to the topic push request to display a push page that has a pre-established link relationship with the clicked target push topic, where the push page includes relevant push information for the clicked target push topic. Thereby, the success rate of pushing topics is improved, and the push topic link includes the push page of the corresponding relevant push information, improving the effect of the push.

[0107] The electronic device may write computer program code for executing the operations of the present disclosure in one or more programming languages, or a combination thereof. The programming languages include, but are not limited to, object-oriented programming languages such as Java (registered trademark), Smalltalk, C++, etc., and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computer, partially executed on the user computer, executed as an independent software package, partially executed on the user computer and partially executed on a remote computer, or executed entirely on a remote computer or server. When a remote computer is involved, it may be connected to the user computer via any type of network including a local area network (LAN) or a wide area network (WAN), or connected to an external computer (e.g., connected using an Internet service provider via the Internet).

[0108] Flowcharts and block diagrams in the drawings illustrate the architecture, functionality, and operation that can be implemented according to systems, methods, and computer program products of various embodiments of the present disclosure. In this regard, each block in a flowchart or block diagram may represent one module, program segment, or part of code that includes one or more executable instructions for implementing a given logic function. It should also be noted that in some realizations as an alternative, the functions represented within a block may occur in a different order than that shown in the drawings. For example, two blocks shown consecutively may actually be executed substantially in parallel or may sometimes be executed in the reverse order depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, as well as combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs a given function or operation, or may be implemented by a combination of dedicated hardware and computer instructions.

[0109] The units according to the embodiments of the present disclosure described may be implemented in software or in hardware. Here, the name of the unit does not, in some cases, limit the unit itself.

[0110] The functions described hereinabove may be executed, at least in part, by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on a chip (SOC), complex programmable logic devices (CPLD), and the like.

[0111] In the context of the present disclosure, a machine-readable medium may be a tangible medium that includes or stores a program used by or in combination with an instruction execution system, apparatus, or device. The machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. The machine-readable medium may include, 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 the machine-readable storage medium may 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, convenient compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0112] The above description is only an explanation of the preferred embodiments of the present disclosure and the applicable technical principles. It should be understood by those skilled in the art that the scope of the disclosure according to the present disclosure is not limited to the technical solutions formed by specific combinations of the above technical features, and other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept should also be covered. For example, a technical solution in which the above features are replaced with technical features having similar functions disclosed in the present disclosure (not limited thereto).

[0113] Furthermore, although the operations have been described in a particular order, this should not be construed as requiring that these operations be performed in the particular or sequential order shown. Multitasking and parallel processing may be advantageous in certain environments. Similarly, although details of some specific embodiments are included in the above description, these should not be construed as limiting the scope of the present disclosure. Specific features described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, various features described in the context of a single embodiment may also be implemented separately or in any suitable sub-combination in multiple embodiments.

[0114] The subject matter has been described using language specific to structural features and / or methodological logic acts, but it should be understood that the claimed subject matter is not necessarily limited to the specific features or acts described above. Conversely, the specific features and acts described above are merely exemplary forms of implementing the claims.

Claims

1. In response to obtaining a topic push request sent from a client, obtaining client feature information corresponding to the client, and in a current push topic pool, identifying a plurality of reference push topics that match the client feature information; obtaining a ranking score corresponding to each reference push topic based on at least one ranking factor corresponding to each reference push topic; identifying at least one target push topic to be currently pushed from the plurality of reference push topics based on the ranking score, and sending the at least one target push topic to a client corresponding to the topic push request, and when a click instruction for the at least one target push topic is detected, controlling the client corresponding to the topic push request to display a push page in which a clicked target push topic and a link relationship are pre-constructed; the push page includes related push information of the clicked target push topic; A method for push processing of a topic, characterized in that.

2. Obtaining a ranking score corresponding to each reference push topic includes: determining a normalized value corresponding to each ranking factor, and adding all the normalized values corresponding to each reference push topic to obtain a ranking score of each reference push topic. The method according to claim 1, characterized in that.

3. Identifying at least one target push topic to be currently pushed from the plurality of reference push topics based on the ranking score includes: ranking the plurality of reference push topics in descending order of the ranking score to obtain a reference push topic ranking list; identifying the first predetermined number of reference push topics in the reference push topic ranking list as the at least one target push topic. The method according to claim 2, characterized in that.

4. The ranking factor includes: at least one of a topic type, a topic impression rate, and a topic popularity. The method according to any one of claims 1 to 3, characterized in that.

5. When the ranking factor includes the topic impression rate, Calculating the difference between the first predetermined push count threshold at which each target push topic is pushed to a client corresponding to the topic push request and the current total push count; Calculating a reference ratio of the difference with respect to the first predetermined push count threshold; Calculating a product value of the reference ratio and the topic impression rate, and updating the topic impression rate of each target push topic based on the product value corresponding to each target push topic; The method according to claim 4, further comprising the above.

6. When the ranking factor includes the topic popularity; In response to receiving a topic click instruction for a first push topic among the at least one target push topics at a client, specifying a first ratio of the current total click count to the current total push count of the first push topic, and updating the topic popularity of the first push topic based on the first ratio; Identifying a second push topic that has not been clicked among the at least one target push topics, specifying a second ratio of the total click count to the current total push count of the second push topic, and updating the topic popularity of the second push topic based on the second ratio; The method according to claim 4, further comprising the above.

7. Before transmitting the at least one target push topic to a client corresponding to the topic push request, Obtaining a related push information set corresponding to each target push topic; Generating a push page corresponding to each target push topic based on the related push information set; Constructing a link relationship between each target push topic and the corresponding push page; The method according to claim 1, further comprising the above.

8. Obtaining a related push information set corresponding to each target push topic includes: Searching a pre-generated correspondence relationship and obtaining a plurality of reference push information corresponding to the target push topic as a plurality of related push information; Generating the related push information set based on the plurality of related push information; The method according to claim 7, further comprising the above.

9. Before searching a pre-generated correspondence relationship and obtaining a plurality of reference push information corresponding to the target push topic as a plurality of related push information, Identifying a plurality of reference push information that satisfies a predetermined push condition, and obtaining an information label determined in advance for each reference push information; Matching the information label of each reference push information with the target push topic, and identifying a plurality of reference push information that is successfully matched with the target push topic; Generating and storing a correspondence relationship between the target push topic and the plurality of reference push information that is successfully matched; The method according to claim 8, further comprising:

10. The predetermined push condition is: The push popularity of the reference push information obtained by addition based on at least one push popularity factor value of the reference push information is greater than a predetermined push popularity threshold. The method according to claim 9, characterized in that:

11. Generating a push page corresponding to each target push topic based on the related push information set includes: Identifying at least one information type corresponding to the related push information set, and determining a display number threshold for each information type in the push page; Ranking the related push information corresponding to each information type in descending order of the push popularity of the related push information corresponding to each information type, and generating a related push information ranking list; Based on the display number threshold corresponding to each information type, in the related push information ranking list corresponding to each information type, identifying the related push information of the first display number threshold as the initial related push information; Generating the push page based on the initial related push information corresponding to all the information types. The method according to claim 7, characterized in that:

12. Before sending the at least one target push topic to a client corresponding to the topic push request, Determining whether the at least one target push topic satisfies a predetermined filter condition; When the at least one target push topic satisfies the predetermined filter condition, obtaining a switched target push topic corresponding to the target push topic; Switching the target push topic to the switched target push topic corresponding to the target push topic to obtain an updated at least one target push topic that satisfies the predetermined filter condition. The method according to claim 1, further comprising:

13. The predetermined filter condition is: including that the current total number of pushes of the target push topic to the client corresponding to the topic push request is equal to or greater than a second predetermined push count threshold The method according to claim 12, characterized in that.

14. further including that, in response to a click instruction on the at least one target push topic by the client corresponding to the topic push request, the current total number of pushes of the target push topic clicked on by the client corresponding to the topic push request is cleared to zero The method according to any one of claims 1 to 13, characterized in that.

15. determining whether there is a third push topic in the current push topic pool that meets a predetermined recovery condition when the third push topic exists, deleting the third push topic from the current push topic pool The method according to any one of claims 1 to 13, characterized in that.

16. the predetermined recovery condition is that the current time does not belong to a predetermined push time corresponding to the third push topic, and / or that the topic popularity of the third push topic is less than a predetermined popularity threshold, and / or that the effective push number of the push object corresponding to the related push information set corresponding to the third push topic is less than a predetermined number threshold The method according to claim 15, characterized in that.

17. a first acquisition module for acquiring client characteristic information corresponding to the client in response to acquiring a topic push request sent from the client a specifying module for specifying a plurality of reference push topics matching the client characteristic information in the current push topic pool a second acquisition module for acquiring a ranking score corresponding to each reference push topic based on at least one ranking factor corresponding to each reference push topic Based on the ranking scores, identify at least one target push topic to be currently pushed from the plurality of reference push topics, and by sending the at least one target push topic to a client corresponding to the topic push request, when a click instruction for the at least one target push topic is detected, control the client corresponding to the topic push request to display a push page in which a link relationship has been previously established between the clicked target push topic and the push page, and a transmission module for this purpose. The push page includes related push information of the clicked target push topic. A topic push processing device characterized by this.

18. A processor, A memory for storing instructions executable by the processor, comprising: The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the topic push processing method according to any one of claims 1 to 16. An electronic device characterized by this.

19. A computer program used to execute the topic push processing method according to any one of claims 1 to 16 is stored. A computer-readable storage medium characterized by this.

Images