Article Push Processing Method, Device, Equipment, and Medium

Abstract

Embodiments of the present disclosure relate to an article push processing method, apparatus, device, and medium. The method includes: responding to a recommendation request for an article push start target, determining at least one article push start target candidate and a dominant push article category for each article push start target candidate; calculating a push matching degree between each article to be pushed and each article push start target candidate; determining a target article push start target for the article to be pushed from at least one article push start target candidate based on the dominant push article category and the push matching degree of each article push start target candidate; and pushing the article to be pushed to the target article push start target so that the target article push start target executes a push process for the article to be pushed. In the embodiments of the present disclosure, since the push ability of the article push start target for the article to be pushed is determined and the start target is selected based on the push ability for the article to be pushed, an intelligent determination of the article push start target is realized, which contributes to improving the push success rate of the article.

Description

Technical Field

[0001] [Cross - Reference to Related Applications] This application claims the priority of a Chinese patent application filed on September 16, 2022, with the application number 202211134376.2 and the title "Article Push Processing Method, Device, Equipment and Medium". The entire content thereof is incorporated herein by reference.

[0002] The present disclosure relates to the technical field of computer applications, and particularly to an article push processing method, device, equipment and medium.

Background Art

[0003] With the rise of computer technology, live commerce that depends on the form of short videos has become a common article push method. Therefore, for sellers, it is important to search for "influencers" with high push capabilities and push articles to them.

[0004] In related technologies, the "influencer" target is determined based on the number of followers on an e - commerce platform, and the seller selects a cooperation target from the "influencer" targets to push articles.

[0005] However, in the above - mentioned method for selecting the "influencer" target, the push ability is determined only based on the number of followers. In fact, it is not always the case that the higher the number of followers, the higher the push ability. If an "influencer" target with a large number of followers is directly selected to push articles, the success rate of article pushing may be low.

Summary of the Invention

[0006] To solve or at least partially solve the above technical problems, the present disclosure provides an article push processing method, apparatus, device, and medium, which determines the push ability of a push start target for an article to be pushed and selects a start target based on the push ability of the article to be pushed, so as to realize an intelligent determination of the push start target and contribute to improving the push success rate of the article.

[0007] An embodiment of the present disclosure provides an article push processing method, the method including: responding to a recommendation request for a push start target for an article to be pushed, and determining at least one push start target candidate; determining a dominant push article category for each of the push start target candidates; calculating a push matching degree between each of the articles to be pushed and each of the push start target candidates; determining a target push start target for the article to be pushed from the at least one push start target candidate based on the dominant push article category and the push matching degree of each of the push start target candidates; and pushing the article to be pushed to the target push start target so that the target push start target performs a push process on the article to be pushed.

[0008] Embodiments of the present disclosure also provide an article push processing apparatus, the apparatus including: a first determination module for determining at least one push start target candidate in response to a recommendation request for an article push start target; a second determination module for determining a dominant push article category for each of the push start target candidates; a calculation module for calculating a push matching degree between each of the articles to be pushed and each of the push start target candidates; a third determination module for determining a target push start target for the article to be pushed from the at least one push start target candidate based on the dominant push article category and the push matching degree of each of the push start target candidates; and a push processing module for pushing the article to be pushed to the target push start target so that the target push start target executes a push process on the article to be pushed.

[0009] Embodiments of the present disclosure also provide an electronic device, the electronic device including a processor and a memory for storing instructions executable by the processor, the processor being used to read the executable instructions from the memory and execute the instructions so as to implement the article push processing method provided by the embodiments of the present disclosure.

[0010] Embodiments of the present disclosure also provide a computer-readable storage medium storing a computer program for executing the article push processing method provided by the embodiments of the present disclosure.

[0011] The technical solutions provided by the embodiments of the present disclosure have the following advantages over the prior art.

[0012] The article push processing solution provided by the embodiments of the present disclosure responds to a recommendation request for an article push start target, determines at least one article push start target candidate, determines the dominant push article category of each article push start target candidate, calculates the push matching degree of each article to be pushed with each article push start target candidate, determines the target push start target of the article to be pushed from at least one article push start target candidate based on the dominant push article category and the push matching degree of each article push start target candidate, and pushes the article to be pushed to the target push start target so that the target push start target executes the push processing of the article to be pushed. Thereby, by combining the dominant push article category of the article push start target candidate itself and the push matching degree for the article to be pushed, the target push start target for pushing the article is determined, that is, the push ability of the article to be pushed by the article push start target is determined, and by selecting the start target based on the push ability for the article to be pushed, an intelligent determination of the article push start target is realized, contributing to increasing the push success rate of the article.

Brief Description of the Drawings

[0013] The above and other features, advantages and aspects of the embodiments of the present disclosure will become clearer by referring to the following forms for implementing the invention in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals indicate the same or similar elements. It should be understood that the accompanying drawings are illustrative and the originals and elements are not necessarily drawn to scale.

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Embodiments for Carrying out the Invention

[0014] Hereinafter, embodiments of the present disclosure will be described in more detail with reference to the accompanying drawings. Although several embodiments of the present disclosure are shown in the accompanying drawings, the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described in this specification. Rather, these embodiments are provided to enable a more thorough and complete understanding of the present disclosure. It should be understood that the accompanying drawings and embodiments of the present disclosure are merely for illustrative purposes and are not intended to limit the protection scope of the present disclosure.

[0015] It should be understood that each step described in the embodiments according to the method of the present disclosure may be executed in a different order and / or in parallel. Further, the embodiments according to the method may include additional steps and / or omit the execution of the steps shown. The scope of the present disclosure is not limited in this regard.

[0016] As used herein, the term "comprising" and variations thereof are of non-limiting inclusion, i.e., "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 provided in the following description.

[0017] It should be noted that concepts such as "first", "second", etc. referred to in the present disclosure are only used to distinguish different devices, modules, or units, and are not for limiting the order or interdependence of the functions executed by these devices, modules, or units.

[0018] It should be noted that the modifications of "one" and "a plurality" referred to in the present disclosure are exemplary rather than limiting, and those skilled in the art should understand that, unless otherwise explicitly stated in the context, it should be understood as "one or more".

[0019] In addition, the names of messages or information that interact between multiple devices in the embodiments of the present disclosure are only used for the purpose of explanation and are not intended to limit the scope of these messages or information.

[0020] To facilitate the understanding of the embodiments of the present disclosure, first, some technical terms related to the embodiments of the present disclosure are explained as follows.

[0021] Push start target: The push start target is the pusher in the article push scenario. For example, in a live commerce platform, the push start target may be a "talent" with high sales ability.

[0022] Push start target identifier: It is an identifier for indicating the corresponding push start target, and may be the target name, target account, target keyword, etc. of the push start target.

[0023] Push request target: The request target can be understood as the target having the push needs for the push start target. For example, in a live commerce scenario, it may be the "seller" target having the recommendation needs of the "expert", etc.

[0024] Related start target: It can be understood as the push start target having a predetermined relationship with the push request target. For example, the related start target may be several "expert" targets having a cooperative relationship with the "seller", etc.

[0025] Item: It is the target pushed in the push scenario. For example, in a live commerce platform, the item can be understood as the seller's product, etc.

[0026] Item category: Usually, it can be understood as the classification of items. In some scenarios, to facilitate the management of items, an item classification system for labeling the item categories is set up. The item classification system can include multi-level classifications. The upper-level classification can include one or more lower-level classifications. For example, "women's clothing" can be understood as the first-level classification, and "Hanfu", "sportswear" can be understood as the second-level classifications belonging to "women's clothing", etc.

[0027] Effective push item: An effective push item is an item for which the push target candidate has been successfully pushed. In an e-commerce platform, an effective push item can be understood as an item sold by the push target candidate. For example, if after push item w is pushed to user 1 and user 1 places an order for push item w, then item w is an effective push item.

[0028] Pushing ability: It is used to indicate the ability of a push start target candidate regarding the possibility of normally pushing an item to be pushed. The higher this pushing ability, the higher the possibility that the item to be pushed by the push start target candidate will be successfully pushed, and the lower the pushing ability, the higher the possibility that the item to be pushed by the push start target candidate will fail to be pushed.

[0029] Pushing matching degree: The pushing matching degree is used to finely indicate the height of the pushing ability of an item to be pushed by each push start target candidate. The higher the pushing matching degree, the higher the pushing ability of the item to be pushed by the push start target candidate, and the lower the pushing matching degree, the lower the pushing ability of the item to be pushed by the push start target candidate. For the specific determination method of the pushing matching degree, relevant embodiments can be referred to below, and the description here is omitted.

[0030] Dominant push item category: Among the item categories of all items for which the push of the push start target candidate is successful, it can be set as the push item category that meets the condition of a predetermined number of items. The number of items in the item category that is successful in pushing under the predetermined number condition meets the predetermined number threshold, and the predetermined number threshold is adjusted according to the actual situation. For example, if the top 5 item categories are those for which the number of items normally pushed by the push start target candidate is the largest, it is considered to meet the above-mentioned predetermined number threshold, and thus it is determined that the corresponding item category belongs to the dominant push item category, etc. For example, for push start target candidate A, if the number of successful pushes of items in the "women's clothing" category ranks first among all items pushed by A, the dominant push item category of push start target candidate A includes "women's clothing".

[0031] Item parameters: The item parameters correspond to the parameter information that describes an item in any dimension. For example, the item parameters can include the item category, item price range, etc.

[0032] To solve the above problems, embodiments of the present disclosure determine the pushing ability of the pushing start target for the article to be pushed, and select the start target based on the pushing ability of the article to be pushed, so as to realize an intelligent determination of the pushing start target and provide an article pushing processing method that contributes to improving the pushing success rate of the article. Hereinafter, this method will be described in conjunction with specific embodiments.

[0033] FIG. 1 is a schematic flowchart of an article pushing processing method provided by an embodiment of the present disclosure. This method may be executed by an article pushing processing device that can be implemented by software and / or hardware, and generally may be integrated into an electronic device. As shown in FIG. 1, this method includes the following steps.

[0034] Step 101: In response to a recommendation request for an article pushing start target, determine at least one pushing start target candidate, and determine the dominant pushing article category of each pushing start target candidate. After determining the pushing start target candidates, it should be understood that a further determination of the selection of the target pushing start target for realizing the current article push is made from among the pushing start target candidates.

[0035] Note that in different application scenarios, the method for determining at least one pushing start target candidate in response to a recommendation request for an article pushing start target is different, and examples are given below.

[0036] In one embodiment of the present disclosure, as shown in FIG. 2, determining at least one pushing start target candidate includes the following steps.

[0037] Step 201: Obtain a pushing start target identifier corresponding to the recommendation request.

[0038] Here, this pushing start target identifier may be the target name, target account, target keyword, etc. of the pushing start target. In this embodiment, the pushing start target identifier may also be specified.

[0039] In different application scenarios, the method for obtaining the push start target identifier corresponding to the recommendation request is different. In some possible embodiments, as shown in FIG. 3, in response to the recommendation request, a push start target selection page may be displayed, and the push start target identifier input on this page may be obtained.

[0040] Step 202: Determine at least one related target that matches the push start target identifier from the set of related targets as at least one push start target candidate. The set of related targets includes at least one related push start target having a predetermined relationship with the target of the recommendation request.

[0041] The target of the recommendation request may be, for example, the "seller" target in the live streaming scenario. In this case, it should be understood that the related start target of the predetermined relationship is, for example, several "talent" targets having a cooperative relationship with the "seller". Of course, in other possible embodiments, the target of the request and the related push start target may be other entities having a preset relationship, and this is not limited herein.

[0042] In this embodiment, a reference target identifier may be obtained for each related push start target in the set of related targets, the reference target identifier is matched with the push start target identifier, and the related push start target that succeeds in the matching is determined as at least one push start target candidate.

[0043] In one embodiment of the present disclosure, according to the needs of the scenario, several push start targets that meet the screening conditions may be screened as start target candidates. The screening conditions may be set according to the needs of the scenario. For example, the target level of the request start target of the recommendation request may be obtained, and the push start target that matches based on the target level may be screened. For example, the predetermined sales category of the push start target may be obtained, the item category of the item to be pushed is determined, and the push start target of the item category including the item to be pushed among the predetermined sales categories is screened as the push start target candidate, etc.

[0044] In some possible embodiments, the dominant push item category may be, for example, the first-level classification of the item classification system. For example, the dominant push item category of the push start target candidate B may include "women's clothing, beauty care, digital products", etc. Here, the number of dominant push item categories may be set according to the needs of the scenario and is not limited here.

[0045] Step 102: Calculate the push matching degree of each item to be pushed with each push start target candidate.

[0046] In one embodiment of the present disclosure, in order to finely determine the push ability of the item to be pushed by each push start target candidate, the push matching degree between the item to be pushed and each push start target candidate is also calculated. The higher the push matching degree, the higher the push ability of the item to be pushed by the corresponding push start target candidate.

[0047] In some possible embodiments, when there are multiple push start target candidates, the push start target candidates are sorted in descending order of the push matching degree to generate a sorted list, thereby facilitating intuitively knowing the matching degree between the corresponding item to be pushed and each push start target candidate based on the sorted list.

[0048] Here, the item push processing method in this embodiment may be applied to a scenario including one item to be pushed or a scenario including multiple items to be pushed. In a scenario including multiple items to be pushed, each item to be pushed has the same push processing method. Among them, the item to be pushed in this embodiment may be the item to be pushed that corresponds to the recommendation request, or may be the item to be pushed of other objects having a cooperative relationship with the request target.

[0049] Step 103: Based on the dominant push item category and push matching degree of each push start target candidate, determine the target push start target of the item to be pushed from at least one push start target candidate.

[0050] As described above, the dominant push item category is used to identify the item category with higher push ability for each push start target candidate, and the push matching degree is used to finely identify the push ability of the item to be pushed by each push start target candidate. Therefore, by combining the dominant push item category and the push matching degree to determine the target push start target of the item to be pushed from at least one push start target candidate, it can be easily understood that the target push start target has a strong push ability for the item to be pushed, ensuring the push success rate of the item to be pushed.

[0051] Step 104: Push the item to be pushed to the target push start target so that the target push start target executes a push process on the item to be pushed.

[0052] In an embodiment of the present disclosure, the item to be pushed is pushed to the target push start target so that the target push start target executes a push process on the item to be pushed. Since the push ability of the item to be pushed by the target start target is high, the push success rate of the item to be pushed by the target push start target is high.

[0053] In some possible embodiments, the step of pushing the article to be pushed to the target push start object includes obtaining the push reason information and article detail information of the article to be pushed. The push reason may be edited by the request target. Usually, the recommended reason is used to persuade the corresponding target push object to accept the corresponding push request. Of course, the recommended reason may also be randomly selected from a preset template. The article detail information includes the price of the article, the picture of the article, the functional description of the article, etc. The specific content included in the article detail information can be set according to the needs of the scenario.

[0054] Furthermore, generate an article push link corresponding to the push reason information and article detail information. The article push link may be in any style, such as QR code (registered trademark) style, URL link style, etc. The specific style of the article push link may be negotiated with the request target by the target push start object according to preferences, etc. After generating the article push link, push it to the target push start object.

[0055] Therefore, by triggering this article push link, the target push start object can know the corresponding push reason information and article detail information. When obtaining the acceptance of the push operation of the target push object, the corresponding article to be pushed can be added to the push article set of the target push object to perform the corresponding push process. For example, it can be added to the "window" tool of the target push object and displayed to the followers of the target push object to achieve the push.

[0056] In this embodiment, the manner of accepting the push operation for the target push object varies depending on the application scenario. In some selectable embodiments, this article push link may further include "push confirmation" controller information. Therefore, after detecting that the target push object has triggered the corresponding article push link, the "push confirmation" controller can be displayed. When it is detected that the target push object has triggered the "push confirmation" controller, the acceptance of the push operation for the target push object is obtained.

[0057] To summarize the above, the article push processing method according to the embodiments of the present disclosure responds to a recommendation request for an article push start target, determines at least one article push start target candidate, determines the dominant push article category of each article push start target candidate, calculates the push matching degree of each article to be pushed with each article push start target candidate, determines the target push start target of the article to be pushed from at least one article push start target candidate based on the dominant push article category and the push matching degree of each article push start target candidate, and pushes the article to be pushed to the target push start target so that the target push start target performs a push process on the article to be pushed. As a result, by combining the dominant push article category of the article push start target candidate itself and the push matching degree to the article to be pushed, the target push start target for pushing the article is determined, that is, the push ability of the article to be pushed by the article push start target is determined, and by selecting the start target based on the push ability for the article to be pushed, an intelligent determination of the article push start target is realized, contributing to increasing the push success rate of the article.

[0058] Hereinafter, in combination with specific embodiments, how to determine the dominant push article will be described.

[0059] In some possible embodiments, as shown in FIG. 3, determining the dominant push article category of each article push start target candidate includes the following steps.

[0060] Step 301: Obtain at least one first article category of valid push articles for each push start target candidate in the first reference period.

[0061] Here, the period corresponding to the first reference period can be set according to the needs of the scenario. For example, the first reference period can be a period within 30 days from the current time. Valid push articles can be understood as articles that have been normally pushed by the push target candidates. In an e-commerce platform, valid push articles can be understood as push articles sold by the push target candidates.

[0062] In this embodiment, obtaining at least one first article category of valid push articles for each push start target candidate in the first reference period is to identify the first article category of the articles that have been normally pushed. The first article category can be understood as, for example, the first-level classification in the article classification system.

[0063] Step 302: Count the first article quantity of valid push articles corresponding to each first article category.

[0064] In this embodiment, by counting the first article quantity of valid push articles corresponding to each first article category, it becomes easy to determine the sales of articles under each first article category among the articles that have been normally pushed by the push start target candidates based on the first article quantity.

[0065] Step 303: Sort at least one first article category based on the first article quantity, and determine a dominant push article category from at least one first article category based on the sorting result.

[0066] In one embodiment of the present disclosure, at least one first article category may be sorted in descending order of the first article count. That is, in this embodiment, the higher the sorting result, the more clearly it indicates that the possibility regarding the push success rate of the articles under the corresponding first article category is high during the first reference period. Therefore, that is, the push ability of the corresponding first article category is high. Thus, in order to determine the dominant push article category with high push ability, in this embodiment, based on the sorting result, the dominant push article category is determined among at least one first article category. For example, a predetermined number of the first article categories in the order of the top of the sorting result are determined as the dominant push article categories. Here, the predetermined number may be set according to the needs of the scenario. For example, when the predetermined number is 5, the top 5 first article categories based on the sorting result can be selected as the dominant push article categories.

[0067] In some possible embodiments, as shown in FIG. 4, determining the dominant push article category for each push start target candidate includes the following steps.

[0068] Step 401: Obtain at least one second article category of the valid received articles by the follower target for each push start target candidate during the second reference period.

[0069] Here, the period corresponding to the second reference period can be set according to the needs of the scenario. For example, the second reference period may be a period within 30 days from the current time. Furthermore, it can be understood that the follower target is, for example, the "fan" target among the push start target candidates. Follower targets usually preferentially view the push content of the push target candidates. An effective received item can be understood as an item that the follower target has received the push normally. In an e-commerce platform, an effective received item can be understood as an item that has been normally purchased by the follower target. Among these, the push start target of the effective received item may be any one of the push start targets in the corresponding platform, and does not necessarily have to be a push start target candidate that follows the follower target.

[0070] Since the follower target is the push receiver of the push start target candidate, by further exploring the needs of the follower target, potential item categories that are likely to be normally pushed by each push start target candidate can be obtained. In an embodiment of the present disclosure, obtaining the follower target of each push start target candidate and obtaining at least one second item category of the effective received items in the second reference period is to identify the second item category of the items purchased by the follower target. The second item category can be understood as, for example, the first-level classification in the item classification system.

[0071] Step 402: Count the second item number of the effective received items corresponding to each second item category.

[0072] In this embodiment, by counting the second item number of the effective received items corresponding to each second item category, based on the second item number, it is possible to easily determine the purchase number of the items under each second item category among the items that the follower target has received normally.

[0073] Step 403: Based on the number of second items, at least one second item category is sorted, and based on the sorting result, a dominant push item category is determined from at least one second item category.

[0074] In one embodiment of the present disclosure, at least one second item category may be sorted in descending order of the number of second items. That is, in this embodiment, the higher the sorting result, the higher the push success rate of the items under the corresponding second item category in the second reference period. Therefore, that is, the push ability of the corresponding first item category by the push start target candidate is high. Thus, in order to determine the dominant push item category with high push ability, in this embodiment, based on the sorting result, a dominant push item category is determined from at least one second item category. For example, a predetermined number of second item categories are determined as the dominant push item categories from the top of the sorting result. Here, the predetermined number may be set according to the needs of the scenario. For example, when the predetermined number is 5, the top 5 second item categories based on the sorting result can be selected as the dominant push item categories.

[0075] In some possible embodiments, determining the dominant push item category for each push start target candidate may include the determination method shown in FIGS. 3 and 4 above. In this embodiment, when determining the second item category, in order to further explore the potential push categories of the push start target, the second item categories that overlap with the first item category among the second item categories may be removed, and based on the sorting result corresponding to the second item category, the second item categories different from the first item category can be determined as alternatives and carried down.

[0076] To summarize the above, the item push processing method according to the embodiment of the present disclosure discovers the dominant push item category of the push transmission candidate, and then serves as a reference for determining the target push start target of the item to be pushed, contributing to the improvement of the push success rate of the item.

[0077] Hereinafter, with reference to the embodiments, it will be described how to calculate the push matching degree between the article to be pushed and each push start target candidate.

[0078] In one embodiment of the present disclosure, at least one push matching factor value between the article to be pushed and each push start target candidate is determined. Each push matching factor is used to indicate the recommendation matching degree between the article to be pushed and each push start target candidate in the corresponding dimension. The higher the recommendation matching degree, the higher the possibility regarding the push success rate of the article to be pushed by the corresponding push start target candidate is identified.

[0079] Furthermore, after determining at least one push matching factor value, the push matching degree is calculated based on the at least one push matching factor value. For example, for each push matching factor value, the push matching factor value is normalized to obtain a normalized value corresponding to the push matching factor value, a predetermined weight value corresponding to the push matching factor value is obtained, the multiplication of the predetermined weight value corresponding to the push matching factor value and the normalized value is performed to obtain a multiplication value corresponding to the push matching factor value, and the sum of the multiplication values corresponding to each of the plurality of push matching factor values is taken as the push matching degree.

[0080] Taking an example, when the normalized values of the push matching factor values corresponding to a certain obtained push target candidate include a, b, c, and d, and the corresponding predetermined weight values are 0.2, 0.2, 0.3, and 0.3 respectively, the push matching degree is 0.2a + 0.2b + 0.3c + 0.3d.

[0081] Note that in the actual execution process, the method for determining at least one push matching factor value between the article to be pushed and each push start target candidate includes one or more of the following embodiments.

[0082] In some possible embodiments, for each push start target candidate in the third reference period, obtain the first article parameter of the effective push article, and obtain the second article parameter of the article to be pushed. Here, the period corresponding to the third reference period can be set according to the needs of the scenario. For example, the third reference period can be a period within 30 days from the current time. Further, the first article parameter and the second article parameter correspond to the same parameter category. In different application scenarios, the first article parameter and the second article parameter include different parameters. For example, the first article parameter includes the article category of the effective push article by the push start target candidate in the third reference period (in order to finely determine the push ability of the article to be pushed by the corresponding push start target candidate, this article category may be, for example, the second-level classification in the article classification system), price range, etc. In this case, the corresponding second article parameter includes the article category, price range, etc. of the article to be pushed.

[0083] In this embodiment, match the second article parameter with the first article parameter. Based on the matching result, determine the number of the third articles that have succeeded in matching from the effective push articles in the third reference period, and determine the number of the third articles as the push matching factor value.

[0084] For example, in an e-commerce platform, when the second article parameter includes the article category, price range, etc. of the article to be pushed, the number of the third articles can be understood as the number of articles sold in the third reference period that belong to the same article category and price range as the article to be pushed.

[0085] That is, in this embodiment, based on the actual article push situation by each push start target candidate, determine the push ability for the article to be pushed.

[0086] In some possible embodiments, for each candidate target for push start in the fourth reference period, obtain the third article parameter of the valid received articles by the followers of the target, and obtain the fourth article parameter of the article to be pushed.

[0087] Here, the period corresponding to the fourth reference period can be set according to the needs of the scenario. For example, the fourth reference period can be a period within 30 days from the current time. Further, the third article parameter and the fourth article parameter correspond to the same parameter category. In different application scenarios, the third article parameter and the fourth article parameter include different parameters. For example, the fourth article parameter includes the followers of the candidate target for push start, the article category of the valid received articles in the fourth reference period (in order to finely determine the push ability of the article to be pushed by the corresponding candidate target for push start, this article category may be, for example, the second-level classification in the article classification system), the price range, etc. In this case, the corresponding fourth article parameter may include the article category, price range, etc. of the article to be pushed. The valid received articles in the fourth reference period are not necessarily the articles pushed by the candidate target for push start who follows the followers, but may be the articles pushed by any candidate target for push start on the e-commerce platform.

[0088] In this embodiment, match the third article parameter with the fourth article parameter. Based on the matching result, determine the number of fourth articles that succeed in matching from the valid received articles in the fourth reference period, and determine the number of fourth articles as the push matching factor value.

[0089] For example, in an e-commerce platform, when the fourth article parameter includes the article category and price range of the article to be pushed, the number of fourth articles can be understood as the number of article purchases in the fourth reference period by the followers of the candidate target for push start for articles belonging to the same article category and price range as the article to be pushed.

[0090] That is, in this embodiment, based on the situation of the items actually ordered by the follower targets of each push start target candidate, the potential push ability of the items to be pushed by each push start target candidate is explored.

[0091] In some possible embodiments, similar push start targets that meet a predetermined similarity condition are determined for each push start target candidate. For example, a push start target whose overlap rate between the push item category and the push item category of the push start target candidate is greater than a predetermined overlap threshold can be set as a similar push start target that meets the predetermined similarity condition for each push start target candidate. For example, in an e-commerce scenario, a push start target whose top 3 selling push item categories are the same as the top 3 selling push item categories of the push start target candidate can be set as a similar push start target that meets the predetermined similarity condition for each push start target candidate.

[0092] Furthermore, the effective push items of the similar push start targets in the fifth reference period are obtained, and from the effective push items in the fifth reference period, the fifth number of items of the effective push items that match the items to be pushed is determined (here, the effective push items that match the items to be pushed may be exactly the same effective push items that match the items to be pushed, or may be similar effective push items that match the items to be pushed), and the fifth number of items is determined as the push matching factor value. Here, the period corresponding to the fifth reference period may be set according to the needs of the scenario. For example, the fifth reference period may be a period within 30 days from the current time.

[0093] That is, in this embodiment, based on the push ability of the items to be pushed by the similar push start targets, the push ability of the items to be pushed by the corresponding push start target candidates is estimated.

[0094] In some possible embodiments, obtain the effective push items for each push start target candidate in the sixth reference period, where the period corresponding to the sixth reference period may be set according to the needs of the scenario. For example, the sixth reference period may be a period within 30 days from the current time.

[0095] Count the number of sixth items whose similarity to the item category of the item to be pushed is greater than a predetermined similarity threshold from the effective push items in the sixth reference period, and determine the number of sixth items as the push matching factor value.

[0096] That is, in this embodiment, based on the push ability of the items similar to the item category of the item to be pushed by the push start target candidate, predict the push ability of the item to be pushed by the push start target candidate.

[0097] Here, the item parameters of the item to be pushed involved above may be input by the requester on the corresponding page. Also, the above push matching factor may be actively selected, or may be actively obtained by querying a predetermined database based on the item identifier of the item to be pushed. Further, the push matching factor in this embodiment may also be used as a reference for the reason for recommendation when pushing the item to be pushed to the target push start candidate. For example, when the push matching factor value is the above number of fifth items, in some possible live streaming scenarios, "similar pushers sold more than 1,000 of this item in 30 days" can be displayed as a reference for the push reason.

[0098] To summarize the above, the item push processing method according to the embodiments of the present disclosure can further promote the improvement of the item push success rate by calculating the push matching degree between the item to be pushed and each push start target candidate, and finely determining the push ability of each push start target candidate for the item to be pushed.

[0099] Based on the above embodiments, in different application scenarios, the methods for determining the target push start target of the item to be pushed from at least one push start target candidate are different according to the dominant push item category and the push matching degree, which are exemplified below.

[0100] In one embodiment of the present disclosure, an initial push start target corresponding to the dominant push item category including the item category of the item to be pushed is determined from at least one push start target candidate, that is, from at least one push start target candidate, first, an initial push start target with high push ability for the item category of the item to be pushed is selected.

[0101] Furthermore, when a plurality of initial push start targets are obtained, the initial push start target corresponding to the maximum value of the plurality of push matching degrees corresponding to the plurality of initial push start targets is determined as the target push start target, that is, next, from the initial push start targets, the initial push start target with the highest push ability of the item to be pushed is selected as the target push start target.

[0102] When one initial push start target is obtained, the initial push start target can be directly used as the target push start target.

[0103] In one embodiment of the present disclosure, in order to enhance the interaction feeling of the requested object, the target push start target of the item to be pushed can also be determined manually.

[0104] In this embodiment, a recommendation page is displayed, and the recommendation page includes at least one push start target candidate, and the dominant push item category and the push matching degree corresponding to at least one push start target candidate. In response to receiving a trigger operation on the recommendation page, the push start target candidate corresponding to the trigger operation is determined as the target push start target.

[0105] For example, as shown in FIG. 5, when the push start target candidates include D1 to D10, the corresponding recommended page includes the relevant information of D1 to D10, the push matching degree corresponding to D1 to D10, and the dominant push item category. On this recommended page, the item category of the item to be pushed can also be input. The item category of the item to be pushed can be input by triggering the selection controller of the item category corresponding to the request target. On this recommended page, the item parameters of the item to be pushed can also be manually selected and input.

[0106] When it is detected that a predetermined selection controller is triggered, based on the selected item category, push matching factor, etc., D1 to D10 are selected, sorted, or items to be pushed, etc. are input into the selection input box corresponding to the selection controller, and the corresponding item category is matched based on the item to be pushed. As shown in FIG. 6, when the item category of the item to be pushed is item category 1 and the push matching factor includes push matching factor 1 and push matching factor 2, from the dominant push item categories corresponding to D1 to D10, the push start target candidates including the item category of the item to be pushed are selected as D2 to D6. Here, the result of sorting in descending order of the push matching degree is D2 to D6. The request target can select the corresponding target push target from D2 to D6.

[0107] Here, in this embodiment, continuing to refer to FIG. 5, the push matching factor corresponding to the push matching degree may also be selected by the request target. For example, when the push matching includes push matching factors 1 to 4, the request target may trigger the selection controller corresponding to the push matching factor to select the push matching factor corresponding to the current recommended matching degree.

[0108] To sum up, according to the article push processing method according to the embodiments of the present disclosure, the target push start target can be flexibly selected, and the personalized selection needs for the target push target can be satisfied.

[0109] To implement the above embodiments, the present disclosure also provides an article push processing device.

[0110] FIG. 7 is a schematic configuration diagram of an article push processing device provided according to an embodiment of the present disclosure, which may be implemented by software and / or hardware, and generally, it can be integrated into an electronic device to execute article push processing. As shown in FIG. 7, this device includes a first determination module 710, a second determination module 720, a calculation module 730, a third determination module 740, and a push processing module 750.

[0111] The first determination module 710 is used to determine at least one push start target candidate in response to a recommendation request for an article push start target.

[0112] The second determination module 720 is used to determine the dominant push article category for each push start target candidate.

[0113] The calculation module 730 is used to calculate the push matching degree between the article to be pushed and each push start target candidate.

[0114] The third determination module 740 is used to determine the target push start target of the article to be pushed from at least one push start target candidate based on the dominant push article category and the push matching degree.

[0115] The push processing module 750 is used to push the article to be pushed to the target push start target so that the target push start target executes the push processing of the article to be pushed.

[0116] The article push processing device provided by an embodiment of the present disclosure can execute the article push processing method provided by any embodiment of the present disclosure, and has a function module and beneficial effects corresponding to the execution method. However, their implementation principles are the same, and the description here will not be repeated.

[0117] To implement the above embodiments, the present disclosure also provides a computer program product including a computer program / instruction that, when executed by a processor, implements the article push processing method in the above embodiments.

[0118] FIG. 8 is a schematic configuration diagram of an electronic device provided by an embodiment of the present disclosure.

[0119] Referring specifically to FIG. 8 below, FIG. 8 shows a schematic configuration diagram suitable for implementing the electronic device 800 in an embodiment of the present disclosure. The electronic device 800 in 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 (tablet computers), PMPs (Portable Multimedia Players), in-vehicle terminals (e.g., vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. It should be noted that the electronic device shown in FIG. 8 is merely an example and does not limit the functions and usage scope of the embodiments of the present disclosure in any way.

[0120] As shown in FIG. 8, the electronic device 800 may include a processor (e.g., a central processing unit, a graphics processor, etc.) 801 that can execute various appropriate operations and processes based on a program stored in a read-only memory (ROM) 802 or based on a program loaded from a memory 808 into a random access memory (RAM) 803. Also, various programs and data necessary for the operation of the electronic device 800 are stored in the RAM 803. The processor 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0121] Typically, the I / O interface 805 may be connected to an input device 806 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc., an output device 807 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc., a memory 808 including, for example, a magnetic tape, a hard disk, etc., and a communication device 809. The communication device 809 may enable the electronic device 800 to communicate with other devices wirelessly or wiredly to exchange data. Although FIG. 8 shows an electronic device 800 equipped with various devices, it should be understood that it is not necessary to implement or include all of the shown devices. More or fewer devices may alternatively be implemented or included.

[0122] In particular, according to the embodiments of the present disclosure, the processes described above with reference to the flowchart may be implemented as a computer software program. For example, the embodiments of the present disclosure have a computer program product including a computer program stored in a non-transitory computer-readable medium, and the computer program includes program code for executing the method shown in the flowchart. In such an embodiment, this computer program may be downloaded and installed from a network via the communication device 809, or may be installed from the memory 808, or may be installed from the ROM 802. When this computer program is executed by the processor 801, it executes the above-described functions defined in the article push processing method of the embodiments of the present disclosure.

[0123] In the present disclosure, the computer-readable medium described above may be a computer-readable signal medium, a computer-readable storage medium, or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of the computer-readable storage medium 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, compact disc 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 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 baseband or as part of a carrier carrying a computer-readable program code. Such a propagated data signal can take various forms, including, but not limited to, electromagnetic signals, optical signals, or any suitable combination of the foregoing. The computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that transmits, propagates, or conveys a program for use by or in combination with an instruction execution system, apparatus, or device. The program code included in the computer-readable medium can be transmitted using any suitable medium, including, but not limited to, wires, optical fiber cables, RF (radio frequency), or any suitable combination of the foregoing.

[0124] In some embodiments, the client and server may communicate using any network protocol known currently or developed in the future, such as HTTP (Hyper Text Transfer Protocol), and may be interconnected with digital data communication in any form or medium (e.g., communication network). Examples of communication networks include local area networks ("LAN"), wide area networks ("WAN"), the Internet network (e.g., the Internet), and end-to-end networks (e.g., ad hoc end-to-end networks), as well as networks known currently or developed in the future.

[0125] The computer-readable medium may be included in the electronic device or may be separate and not assembled into the electronic device.

[0126] The computer-readable medium stores one or more programs, and when the one or more programs are executed by the electronic device, the electronic device is caused to perform the following processes: In response to a recommendation request for an item push start target, determine at least one item push start target candidate, determine the dominant push item category of each item push start target candidate, calculate the push matching degree of each item to be pushed with each item push start target candidate, based on the dominant push item category and the push matching degree of each item push start target candidate, determine the target item push start target of the item to be pushed from at least one item push start target candidate, and push the item to be pushed to the target item push start target so that the target item push start target executes the push process of the item to be pushed. Thereby, by combining the dominant push item category of the item push start target candidate itself and the push matching degree for the item to be pushed, the target item push start target for pushing the item is determined, that is, the push ability of the item to be pushed by the item push start target is determined, and the start target is determined based on the push ability for the item to be pushed, so that an intelligent determination of the item push start target is realized, contributing to increasing the push success rate of the item.

[0127] The computer program code for the electronic device to execute the operations of the present disclosure can be written in one or more programming languages or combinations thereof, including, but not limited to, object-oriented programming languages such as Java, Smalltalk, C++, and 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 on the user computer, as a stand-alone software package, partially on the user computer and partially on a remote computer, or entirely on a remote computer or server. In the context of a remote computer, the remote computer may be connected to the user computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or to an external computer (e.g., connected through the Internet using an Internet service provider).

[0128] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram may represent a module, a program segment, or a portion of code, which contains one or more executable instructions for implementing the specified logical function. Note that in some alternative implementations, the functions attached to the boxes may occur in an order different from that shown in the accompanying drawings. For example, two consecutive boxes may actually be executed substantially in parallel, or depending on the related functions, may be executed in reverse order. Also, it should be noted that each box in the block diagrams and / or flowcharts, as well as combinations of boxes in the block diagrams and / or flowcharts, may be implemented by a dedicated hardware-based system that performs a given function or operation, or by a combination of dedicated hardware and computer instructions.

[0129] The units described in the embodiments of the present disclosure may be implemented by software or by hardware. Here, the name of the unit does not constitute a limitation to the unit itself in a given situation.

[0130] The functions described above in this specification may be executed, at least in part, by one or more hardware logic components. For example, without limitation, usable and exemplary hardware logic components include field programmable gate arrays (FPGA), application specific integrated circuits (ASIC), application specific standard products (ASSP), system on chip (SOC), complex programmable logic devices (CPLD), and the like.

[0131] In the context of the present disclosure, a machine-readable medium may be a tangible medium that can include or store a program for use by or in conjunction 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 includes, but is not limited to, electronics, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. More specific examples of the machine-readable storage medium 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, CD-ROMs, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0132] The above description is merely an explanation of the preferred embodiments of the present disclosure and the technical principles employed. It should be understood by those skilled in the art that the scope of the disclosure of the present disclosure is not limited to the technical solutions formed by specific combinations of the above technical features, but also covers other technical solutions formed by any combination of the above technical features or equivalent features without departing from the disclosed concepts. For example, it includes technical solutions formed by replacing the above features with technical features (but not limited thereto) having similar functions disclosed in the present disclosure.

[0133] Furthermore, although the operations are depicted using a particular order, these operations should not be construed as requiring that they be performed in the particular order shown or sequentially. Multitasking and parallel processing may be advantageous in certain environments. Similarly, although some specific implementation details are included in the above discussion, these should not be construed as limiting the scope of the present disclosure. Some features described in the context of separate embodiments may also be implemented in combination in a single embodiment. Conversely, each feature described in the context of a single embodiment may also be implemented in multiple embodiments, individually or in any suitable sub-combination.

[0134] The subject matter has been described in language specific to structural features and / or methodological acts, but it is to be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely exemplary forms of implementing the claims.

Claims

1. responding to a recommendation request for an item push start target to determine at least one item push start target candidate and determine the dominant push item category for each said item push start target candidate; calculating the push matching degree of each of the items to be pushed with each said item push start target candidate; determining a target item push start target for the item to be pushed from the at least one item push start target candidate based on the dominant push item category and the push matching degree of each said item push start target candidate; pushing the item to be pushed to the target item push start target so that the target item push start target executes a push process for the item to be pushed; An item push processing method, characterized by including the above.

2. Determining the at least one item push start target candidate includes: obtaining a push start target identifier corresponding to the recommendation request; determining, from a set of related targets, at least one related push start target that matches the push start target identifier as the at least one item push start target candidate, where the set of related targets includes at least one related push start target having a predetermined related relationship with the request target corresponding to the recommendation request. The item push processing method according to Claim 1. The item push processing method according to Claim 1, characterized in that the set of related targets includes at least one related push start target having a predetermined related relationship with the request target corresponding to the recommendation request.

3. Determining the dominant push item category for each said item push start target candidate includes: obtaining at least one first item category of valid push items for each said item push start target candidate in a first reference period; counting the first number of items of valid push items corresponding to each said first item category; sorting the at least one first item category based on the first number of items, and determining the dominant push item category from the at least one first item category based on the sorting result. The item push processing method according to Claim 1. The item push processing method according to Claim 1, characterized by including the above.

4. The item push processing method according to Claim 3, characterized in that the first item category includes a first belt classification within the item classification.

5. Determining the dominant push item category for each said item push start target candidate includes: Obtain the follower targets of each of the push start target candidates, and obtain at least one second article category of valid received articles in the second reference period, Count the number of second articles of valid received articles corresponding to each of the second article categories, Sort the at least one second article category based on the number of second articles, and based on the sorting result, determine the dominant push article category from the at least one second article category, The article push processing method according to claim 1 or 3, characterized by including the above.

6. Calculating the push matching degree between the article to be pushed and each of the push start target candidates includes: Determining at least one push matching factor value between the article to be pushed and each of the push start target candidates, Calculating the push matching degree based on the at least one push matching factor value, The article push processing method according to claim 1, characterized by including the above.

7. Determining at least one push matching factor value between the article to be pushed and each of the push start target candidates includes: Obtain the first article parameter of the valid push article of each of the push start target candidates in the third reference period, and obtain the second article parameter of the article to be pushed, match the second article parameter with the first article parameter, and based on the matching result, determine the number of third articles that have successfully matched from the valid push articles in the third reference period, and determine the number of third articles as the push matching factor value, and / or, Obtain the third article parameter of the valid received article by the follower target of each of the push start target candidates in the fourth reference period, and obtain the fourth article parameter of the article to be pushed, match the third article parameter with the fourth article parameter, and based on the matching result, determine the number of fourth articles that have successfully matched from the valid received articles in the fourth reference period, and determine the number of fourth articles as the push matching factor value, and / or, Determine similar push start target candidates that meet the predetermined similarity conditions for each of the above push start target candidates, and obtain valid push items for the similar push start target candidates in the fifth reference period. From the valid push items in the fifth reference period, determine the fifth number of items of valid push items that match the item to be pushed, and determine the fifth number of items as the push matching factor value, and / or, Obtain valid push items for each of the above push start target candidates in the sixth reference period. From the valid push items in the sixth reference period, count the sixth number of items whose similarity to the item category of the item to be pushed is greater than a predetermined similarity threshold, and determine the sixth number of items as the push matching factor value, The method for processing item push according to claim 6, characterized by including the above.

8. When there are a plurality of the push matching factor values, calculating the push matching degree based on the at least one push matching factor value is For each push matching factor value, normalize the push matching factor value to obtain a normalized value corresponding to the push matching factor value, obtain a predetermined weight value corresponding to the push matching factor value, and perform multiplication of the predetermined weight value corresponding to the push matching factor value and the normalized value to obtain a multiplication value corresponding to the push matching factor value, Taking the sum of the multiplication values corresponding to each of the plurality of push matching factor values as the push matching degree, The method for processing item push according to claim 6 or 7, characterized by including the above.

9. Based on the dominant push item category and the push matching degree, determining the target push start target of the item to be pushed from the at least one push start target candidate is Determining an initial push start target corresponding to the dominant push item category including the item category of the item to be pushed from the at least one push start target candidate, When a plurality of the initial push start targets are obtained, determining the maximum value among the plurality of push matching degrees corresponding to the plurality of the initial push start targets, Determining the initial push start target corresponding to the maximum value as the target push start target; The article push processing method according to any one of claims 1 to 8, characterized by including this.

10. Based on the dominant push article category and the push matching degree, determining the target push start target of the article to be pushed from the at least one push start target candidate means: Displaying a recommendation page, the recommendation page including the at least one push start target candidate, the dominant push article category corresponding to the at least one push start target candidate, and the push matching degree; In response to receiving a trigger operation on the recommendation page, determining the push start target candidate corresponding to the trigger operation as the target push start target; The article push processing method according to any one of claims 1 to 8, characterized by including this.

11. Pushing the article to be pushed to the target push start target means: Obtaining the push reason information and the article detailed information of the article to be pushed; Generating an article push link corresponding to the push reason information and the article detailed information; Pushing the article push link to the target push start target; The article push processing method according to any one of claims 1 to 8, characterized by including this.

12. The article push processing method according to claim 11, characterized in that the push reason information is edited by the request target.

13. A first determination module for determining at least one push start target candidate in response to a recommendation request for an article push start target; A second determination module for determining the dominant push article category of each push start target candidate; A calculation module for calculating the push matching degree of each article to be pushed with each push start target candidate; A third determination module for determining the target push start target of the article to be pushed from the at least one push start target candidate based on the dominant push article category and the push matching degree of each push start target candidate; A push processing module for pushing the article to be pushed to the target push start target so as to execute a push process on the article to be pushed; An article push processing apparatus, characterized by comprising the same. **Claim 14** A processor; A memory for storing instructions executable by the processor, and comprising: The processor reads the executable instructions from the memory and is used to execute the executable instructions so as to implement the article push processing method according to any one of Claims 1 to 12. An electronic device, characterized in that. **Claim 15** A computer-readable storage medium, characterized in that a computer program for executing the article push processing method according to any one of Claims 1 to 12 is stored therein.

Images