Information push method, device, equipment and storage medium

Abstract

The present disclosure relates to an information push method, device, equipment and storage medium. The method includes: obtaining an initial set of content to be pushed corresponding to the search content display position; wherein the initial set of content to be pushed contains at least two content to be pushed; based on the negative feedback data of the information set of the push information display page, processing each content to be pushed in the initial set of content to be pushed to obtain a target set of content to be pushed; wherein the information set contains at least one pushed information; based on the target set of content to be pushed, determining each content to be pushed to the search content display position and pushing it. According to an embodiment of the present disclosure, the negative feedback data corresponding to the push information display page can be used to perform personalized optimization on each content to be pushed corresponding to the search content display position, thereby improving the degree of fit between the search content pushed at the search content display position and the user's needs and the push accuracy.

Description

Technical Field

[0001] The present disclosure relates to the field of search technology, and in particular to an information push method, device, equipment and storage medium. Background Art

[0002] In the search field, some search terms may be recommended to users at search content display locations such as search boxes for users to review and inspire search.

[0003] However, the currently recommended search terms may not meet the user's search needs. Not only will they fail to inspire search and reduce the user's search cost, but they will also interfere with the user to a certain extent. Summary of the invention

[0004] In order to solve the above technical problems, the present disclosure provides an information push method, device, equipment and storage medium.

[0005] In a first aspect, the present disclosure provides an information push method, the method comprising:

[0006] Acquire an initial set of content to be pushed corresponding to the display position of the searched content; wherein the initial set of content to be pushed includes at least two pieces of content to be pushed;

[0007] Based on the negative feedback data of the information set of the push information display page, each of the to-be-pushed contents in the initial to-be-pushed content set is processed to obtain a target to-be-pushed content set; wherein the information set includes at least one pushed information;

[0008] Based on the target set of contents to be pushed, each of the contents to be pushed to the display position of the searched content is determined and pushed.

[0009] In a second aspect, the present disclosure provides an information push device, the device comprising:

[0010] An initial content set to be pushed acquisition module is used to acquire an initial content set to be pushed corresponding to the search content display position; wherein the initial content set to be pushed includes at least two pieces of content to be pushed;

[0011] A target content set to be pushed determining module, configured to process each of the content to be pushed in the initial content set to be pushed based on the negative feedback data of the information set of the push information display page, and obtain a target content set to be pushed; wherein the information set includes at least one piece of pushed information;

[0012] The to-be-pushed content pushing module is used to determine and push each of the to-be-pushed contents to be pushed to the search content display position based on the target to-be-pushed content set.

[0013] In a third aspect, the present disclosure provides an information push device, the information push device comprising:

[0014] processor;

[0015] A memory for storing executable instructions;

[0016] The processor is used to read executable instructions from the memory and execute the executable instructions to implement the information push method described in any embodiment of the present disclosure.

[0017] In a fourth aspect, the present disclosure provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the information push method described in any embodiment of the present disclosure.

[0018] The information push method, apparatus, device and storage medium of the disclosed embodiments can, in the process of pushing search content to the search content display location, use the negative feedback data of the information set of the push information display page to sort, adjust or filter out each to-be-pushed content in the initial to-be-pushed content set corresponding to the search content display location, obtain a target to-be-pushed content set, and push the search content to the search content display location based on the target to-be-pushed content set, thereby realizing the data flow and interconnection of two different content carriers, so that the pushed content of the search content display location can be adjusted according to the user's negative feedback data, thereby improving the degree of fit between the pushed content of the search content display location and the user's needs, thereby improving the accuracy of the pushed content, reducing the user's search cost and inspiring the user to search, and improving the user's search experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description 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 drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0020] Figure 1 A schematic diagram of a push information display page provided in an embodiment of the present disclosure;

[0021] Figure 2 A flowchart of an information push method provided by an embodiment of the present disclosure;

[0022] Figure 3 A flowchart of another information push method provided by an embodiment of the present disclosure;

[0023] Figure 4 A schematic diagram of the structure of an information push device provided in an embodiment of the present disclosure;

[0024] Figure 5 A schematic diagram of the structure of an information push device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0025] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, which are instead provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0026] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0027] The term "including" and its variations used herein are open inclusions, i.e., "including but not limited to". The term "based on" means "based at least in part on". The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments". The relevant definitions of other terms will be given in the following description.

[0028] It should be noted that the concepts such as "first" and "second" mentioned in the present disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0029] It should be noted that the modifications of "one" and "plurality" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, it should be understood as "one or more".

[0030] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0031] Currently, in some search applications, some keywords can be recommended to users in the search box, search after reading in the information flow, and other search content display locations. Figure 1As shown, the client 100 displays the homepage 101 of the search application, and the homepage 101 displays a search box 102 and a plurality of pushed information 103. The search box 102 displays pushed search content 104, such as "debt rankings of major cities across the country", "movie ** Lake", etc. However, these recommended keywords may be search content that the user is not interested in, or even search content that the user dislikes, which may cause interference to the user.

[0032] However, because the area where the search content is displayed is small and the functional positions on the page are compact, it is impossible to set a convenient and easy-to-understand negative feedback interactive function for the keywords recommended in the search content display position. In this way, it is impossible to obtain user-authorized feedback behavior data on the keywords recommended in the search content display position, and it is impossible to optimize the pushed keywords determined by the relevant strategy in a personalized manner, thereby failing to improve the personalization and accuracy of the pushed keywords.

[0033] Based on the above situation, the embodiment of the present disclosure provides an information push solution to realize the scenario of pushing search content to the search content display location, through the data flow interconnection of two different content carriers, namely the push information display page (such as the homepage) and the search content display location, and by utilizing the negative feedback data authorized by the user generated by the user's negative feedback operation on the pushed information in the push information display page, to perform personalized optimization on each content to be pushed corresponding to the search content display location, thereby improving the degree of fit between the search content pushed at the search content display location and user needs, that is, improving the push accuracy of the search content at the search content display location.

[0034] Let's first combine Figure 1-3 The information push method provided by the embodiment of the present disclosure is described.

[0035] In the embodiments of the present disclosure, the information push method may be performed by an information push device, which may be implemented by software and / or hardware, and may be integrated in an electronic device with certain computing capabilities. The electronic device may include but is not limited to a laptop computer, a desktop computer, a server, or a server cluster.

[0036] Figure 2 FIG. 1 is a flow chart showing a method for pushing information provided by an embodiment of the present disclosure. Figure 2 As shown, the information push method may include the following steps:

[0037] S210: Obtain an initial set of content to be pushed corresponding to the display position of the search content.

[0038] The search content display position refers to a position where recommended search content can be displayed, such as a search content input position, a position where search content is displayed in a search results page, a search content display position after at least part of the information is displayed in an information flow page, a search content display position after the main text content in a search results landing page, a position where search content corresponding to other users is displayed in a search results landing page, etc. The search content input position here refers to a position provided by a search application where a user can input the content they want to search, such as Figure 1 The search box 102 is shown. The search application here refers to an application that provides a search function. The initial set of content to be pushed refers to at least two content to be pushed that are initially determined and will be pushed to the search content display position for recommendation display. The content to be pushed refers to the search content recommended to the user, which can be a search keyword or a search phrase.

[0039] Specifically, the electronic device generates an initial set of content to be pushed that can be pushed to the search content display position according to the push strategy. The initial set of content to be pushed thus obtained meets the user's search needs to a certain extent, but due to the existence of behavioral data generated by user misoperation and the user's lack of attention to / dislike of current hot information, the initial set of content to be pushed still contains content to be pushed that the user may not be interested in or even dislike.

[0040] In some embodiments, S210 includes: determining an initial set of content to be pushed based on a third keyword corresponding to the viewed push information of the target user, a preferred information type corresponding to the target user, and current hot information.

[0041] The target user refers to the user who is currently pushing the search content. Viewed push information refers to the push information displayed on the push information display page, which the user has clicked, viewed, liked, commented on, and other interactive behaviors. The push information display page refers to the page that displays multiple automatically pushed / personalized pushed information (i.e., pushed information). In one example, the push information display page can be as follows: Figure 1The homepage 101 of the search application shown. In another example, the push information display page can be a page displayed after the user switches the theme function; for example, the user switches from the homepage to the video function page displaying multiple recommended videos; for another example, when the homepage displays a video function area, the user triggers a video in the video function area and enters the video in-stream page; for another example, in an e-commerce search application, after the user switches from the homepage to the "shopping cart" page, the page displayed under the items in the shopping cart. The third keyword is a keyword obtained based on at least one viewed push information. The preferred information type refers to the type of information preferred by the target user, such as entertainment type, technology type, finance type, beauty type, etc. Current hot information refers to information related to current hot events.

[0042] Specifically, the electronic device can obtain historical behavior data authorized by the user, and obtain the third keyword based on the historical behavior data. At the same time, the electronic device obtains the target user's preference information type and current hot information. Afterwards, the electronic device generates an initial set of content to be pushed based on the third keyword, preference information type and current hot information. In this way, an initial set of content to be pushed that is close to the user's search needs can be obtained to a certain extent, providing a more accurate data basis for subsequent push optimization.

[0043] In a specific implementation, the electronic device obtains historical behavior data authorized by the user, and the historical behavior data includes the pushed information that the target user has interacted with in the historical period. Then, the electronic device extracts keywords from the pushed information to obtain multiple keywords. After that, the electronic device uses these extracted keywords as the third keyword. Alternatively, the electronic device further obtains similar keywords (such as synonyms, near synonyms, etc.) of these extracted keywords, and uses the extracted keywords and similar keywords as the third keyword.

[0044] The electronic device can also obtain the target user's preference information type. For example, the target user actively inputs the preference information type through the search application (including text input, voice input, click selection and other input methods). For another example, the electronic device analyzes the information such as the viewed push information and the viewed search results contained in the above historical behavior data to obtain the target user's preference information type. The electronic device can also obtain the current hot information and extract keywords or core content to obtain the extracted information corresponding to the current hot information.

[0045] Finally, the electronic device screens, combines, and sorts the extracted information corresponding to the third keyword and the current hot information according to the preference information type to obtain an initial set of content to be pushed. Alternatively, the electronic device maintains a push content pool / database containing a large number of push contents, and then the electronic device screens a certain number of push contents from the push content pool / database according to the above-mentioned preference information type, the third keyword, and the extracted information corresponding to the current hot information, and sorts these push contents to obtain an initial set of content to be pushed.

[0046] S220 : Based on the negative feedback data of the information set of the push information display page, each content to be pushed in the initial content set to be pushed is processed to obtain a target content set to be pushed.

[0047] Among them, the information set refers to the set consisting of at least one pushed information displayed in the push information display page. Negative feedback data is the behavior data generated by the user performing negative feedback operations on the pushed information. It is a part of the behavior data of the target user obtained within a certain time range and authorized by the user. Negative feedback here refers to the reverse feedback that suppresses the push of related information because the user does not want to continue to see the relevant information due to reasons such as dislike or lack of interest.

[0048] Specifically, according to the above description, it is not convenient to set a feedback interaction function that is easy to operate and understand at the search content display position, so it is impossible to obtain the user behavior data corresponding to the search content display position to optimize the initial set of content to be pushed. In the embodiment of the present disclosure, although the push information display page and the search content display position belong to two different content carriers, the user behavior data corresponding to the push information display page that has been authorized by the user is also the behavior data generated by the search behavior of the same target user, which can largely reflect the interests and rejection points of the target user. Based on this, in the embodiment of the present disclosure, the negative feedback data corresponding to the push information display page is migrated to the initial set of content to be pushed corresponding to the search content display position, so as to optimize the initial set of content to be pushed and obtain multiple content to be recommended (i.e., the target set of content to be pushed) that better meets the user's search needs.

[0049] In specific implementation, the electronic device first collects and summarizes the negative feedback data of the target user on the information set displayed in the push information display page in the recent period, and then uses the negative feedback data to remove or reorder the contents to be pushed in the initial set of contents to be pushed to obtain the target set of contents to be pushed.

[0050] In some embodiments, S220 includes: matching each content to be pushed in the initial set of content to be pushed with the first-level negative feedback sub-data and the second-level negative feedback sub-data in the negative feedback data, and determining a processing method for the corresponding content to be pushed based on the matching result; processing the corresponding content to be pushed based on the processing method corresponding to each content to be pushed to obtain a target set of content to be pushed.

[0051] Among them, the first-level negative feedback sub-data and the second-level negative feedback sub-data are both subsets of the negative feedback data. Moreover, the negative feedback importance corresponding to the first-level negative feedback sub-data is higher than the negative feedback importance corresponding to the second-level negative feedback sub-data. For example, the first-level negative feedback sub-data represents the negative feedback data of the user's aversion degree, and the second-level negative feedback sub-data represents the negative feedback data of the user's lack of interest. Processing methods include filtering method and descending method. The filtering method refers to a processing method of deleting a certain content to be pushed from the initial set of content to be pushed. The descending method refers to a processing method of adjusting the sorting position of a certain content to be pushed in the initial set of content to be pushed to a sorting position that is further back in the sorting order.

[0052] Specifically, the electronic device divides the negative feedback data into at least one level of negative feedback sub-data and two level of negative feedback sub-data to distinguish the negative feedback degree of the target user. Then, the electronic device matches each content to be pushed in the initial set of content to be pushed with the first level of negative feedback sub-data and the second level of negative feedback sub-data in the negative feedback data, respectively, to determine the degree of interference that each content to be pushed may cause to the user. For example, the content to be pushed is matched with the keywords, information type and other data contained in the first level of negative feedback sub-data or the second level of negative feedback sub-data. Then, for each content to be pushed, the processing method of the content to be pushed is determined according to the matching result (such as whether the match is successful, which negative feedback sub-data is successfully matched, etc.), and the content to be pushed is processed according to the processing method. According to the above process, the target set of content to be pushed can be finally obtained. In this way, different processing can be performed on the content to be pushed according to the different interference degrees of the content to be pushed to the user, thereby further improving the push accuracy of the content to be pushed.

[0053] For example, if a certain content to be pushed successfully matches the first-level negative feedback sub-data, it means that the content to be pushed belongs to the search content that the user dislikes, and it is likely to cause strong interference to the user, so the processing method of the content to be pushed is determined to be the filtering method, and it is deleted from the initial set of content to be pushed. For another example, if a certain content to be pushed successfully matches the second-level negative feedback sub-data, it means that the content to be pushed belongs to the search content that the user is not interested in, and it may cause weak interference to the user. At this time, it does not need to be deleted, but the processing method of the content to be pushed is determined to be the descending method, and its sorting position in the initial set of content to be pushed is adjusted backward.

[0054] S230: Based on the target set of content to be pushed, determine and push each content to be pushed to the search content display position.

[0055] Specifically, the target set of content to be pushed obtained by the electronic device through the above process may contain a large number of content to be pushed, while the number of content to be pushed that can be displayed at the search content display position at one time may be small. In this way, the electronic device can intercept part of the content to be pushed from the target set of content to be pushed again based on the relevant information of the search content display position, such as the number of content to be pushed that can be displayed at one time, the number of content to be pushed that the search application needs to pull at one time, etc., such as intercepting a corresponding number of content to be pushed that is ranked at the top as the content to be pushed to be pushed to the search content display position. Then, the electronic device pushes the last intercepted content to be pushed to the client where the search application is located, so that the client can display at least part of the content to be pushed at the search content display position of the search application according to business needs.

[0056] The above-mentioned information push method provided by the embodiment of the present disclosure can, in the process of pushing search content to the search content display position, use the negative feedback data of the information set of the push information display page to sort, adjust or filter out each to-be-pushed content in the initial to-be-pushed content set corresponding to the search content display position, obtain the target to-be-pushed content set, and push the search content to the search content display position based on the target to-be-pushed content set, thereby realizing the data flow and interconnection of two different content carriers, so that the pushed content of the search content display position can be adjusted according to the user's negative feedback data, and the degree of fit between the pushed content of the search content display position and the user's needs is improved, thereby improving the accuracy of the pushed content, reducing the user's search cost and inspiring the user to search, and improving the user's search experience.

[0057] In some embodiments, in the above S220, a content to be pushed can be matched with the primary negative feedback sub-data and the secondary negative feedback sub-data at the same time, and the processing method of the content to be pushed can be determined according to the matching result, the penalty weight corresponding to the primary negative feedback sub-data, and the penalty weight corresponding to the secondary negative feedback sub-data. In this way, the processing method of the content to be pushed can be determined more finely according to the penalty weight, further improving the push accuracy.

[0058] The above-mentioned penalty weight refers to the weight value for penalizing (moving backward) the sorting position of the content to be pushed in the initial set of content to be pushed. In the embodiment of the present disclosure, reordering can be performed according to the weight value corresponding to each content to be pushed. For example, the larger the weight value, the later the sorting. Then, before the initial set of content to be pushed is processed, the penalty weight of each content to be pushed can be defaulted to 0, indicating that no penalty processing is performed on the sorting position of the content to be pushed.

[0059] Based on the above description, for each content to be pushed in the initial set of content to be pushed, the process of determining the processing method specifically includes:

[0060] Step A: If it is determined that the content to be pushed successfully matches the primary negative feedback sub-data, and it is determined that the content to be pushed fails to match the secondary negative feedback sub-data, then the penalty weight of the content to be pushed is determined to be the first penalty weight.

[0061] The first penalty weight is a penalty weight pre-set for the first-level negative feedback sub-data.

[0062] Specifically, the electronic device matches the content to be pushed with the primary negative feedback sub-data and the secondary negative feedback sub-data respectively. If the matching result is that both fail to match, the penalty weight of the content to be pushed is kept as the default penalty weight. If the matching result is that the matching with the primary negative feedback sub-data fails, but the matching with the secondary negative feedback sub-data is successful, then step B is executed. If the matching result is that both are successfully matched, then step C is executed. If the matching result is that the matching with the primary negative feedback sub-data is successful, but the matching with the secondary negative feedback sub-data fails, then the electronic device sets the penalty weight of the content to be pushed to the first penalty weight.

[0063] Step B: if it is determined that the content to be pushed fails to match the primary negative feedback sub-data, and it is determined that the content to be pushed successfully matches the secondary negative feedback sub-data, then the penalty weight of the content to be pushed is determined to be the second penalty weight.

[0064] The second penalty weight is a penalty weight pre-set for the secondary negative feedback sub-data. Since the importance of negative feedback corresponding to the primary negative feedback sub-data is higher than the importance of negative feedback corresponding to the secondary negative feedback sub-data, the weight value of the first penalty weight is set to be greater than the weight value of the second penalty weight, so as to ensure that the penalty weight of the content to be pushed that only successfully matches the primary negative feedback sub-data is greater than the content to be pushed that only successfully matches the secondary negative feedback sub-data.

[0065] Specifically, when the content to be pushed successfully matches only the secondary negative feedback sub-data, the electronic device sets the penalty weight of the content to be pushed to the second penalty weight.

[0066] Step C: if it is determined that the content to be pushed successfully matches both the primary negative feedback sub-data and the secondary negative feedback sub-data, a third penalty weight is determined based on the first penalty weight and the second penalty weight, and the penalty weight of the content to be pushed is determined to be the third penalty weight.

[0067] The third penalty weight is another penalty weight different from the first penalty weight and the second penalty weight, and its weight value is greater than the first penalty weight and the second penalty weight. The third penalty weight can be a preset weight value, or it can be calculated by a certain method based on the first penalty weight and the second penalty weight.

[0068] Specifically, if the content to be pushed successfully matches both the primary negative feedback sub-data and the secondary negative feedback sub-data, it means that the target user has performed multiple negative feedback operations with different interference levels on the content to be pushed, which further means that the target user has a higher degree of aversion to the content to be pushed. Therefore, the electronic device sets a third penalty weight with a larger weight value for the content to be pushed. At this time, the first penalty weight and the second penalty weight can be weighted and summed to obtain the third penalty weight.

[0069] Step D: Determine a processing method corresponding to the content to be pushed based on the target penalty weight corresponding to the content to be pushed and the filtering weight threshold.

[0070] The target penalty weight is the first penalty weight, the second penalty weight or the third penalty weight. The filtering weight threshold is a preset critical value of the penalty weight, which is used to determine whether to delete the content to be pushed from the initial content to be pushed.

[0071] Specifically, when the content to be pushed successfully matches at least one of the primary negative feedback sub-data and the secondary negative feedback sub-data, the electronic device modifies the penalty weight of the content to be pushed through the above steps, that is, determines the target penalty weight of the content to be pushed. At this time, the electronic device can compare the target penalty weight with the filtering weight threshold, and determine whether to delete the content to be pushed from the initial content to be pushed according to the comparison result, that is, determine the corresponding processing method of the content to be pushed.

[0072] On the basis of the above embodiment, in the above step D, based on the target penalty weight and the filtering weight threshold corresponding to the content to be pushed, determining the processing method corresponding to the content to be pushed can be implemented as follows: if the comparison result is that the target penalty weight is greater than the filtering weight threshold, then determining the processing method corresponding to the content to be pushed is the filtering method. If the comparison result is that the target penalty weight is less than or equal to the filtering weight threshold, then determining the processing method corresponding to the content to be pushed is the descending method.

[0073] It should be noted that, when the processing method is determined to be a descending method, and when it is determined that the penalty weights of multiple contents to be pushed are equal, the sorting positions of these contents to be pushed can be set to be the same; or the sorting position can be adjusted by superimposing the initial sorting position of the contents to be pushed in the initial set of contents to be pushed on the basis of the target penalty weight. For example, in the process of descending two contents to be pushed with the same target penalty weight, the sorting position of the contents to be pushed with the earlier initial sorting position after re-sorting is higher than the sorting position of the contents to be pushed with the later initial sorting position after re-sorting.

[0074] In other embodiments, the above S220 can set priorities for the first-level negative feedback sub-data and the second-level negative feedback sub-data. For example, because the importance of negative feedback corresponding to the first-level negative feedback sub-data is higher than the importance of negative feedback corresponding to the second-level negative feedback sub-data, a higher priority is set for the first-level negative feedback sub-data, and a lower priority is set for the second-level negative feedback sub-data. In addition, different processing methods are set for different priorities. For example, the processing method corresponding to a higher priority is a filtering method, while the processing method corresponding to a lower priority is a descending method. In this way, the content to be pushed can be matched with a single negative feedback sub-data according to the priority and the processing method can be determined, which can reduce the complexity of the processing logic on the basis of ensuring the accuracy of the push, thereby reducing the number of matches to a certain extent and improving the optimization speed of the initial set of content to be pushed.

[0075] Based on the above description, for each content to be pushed in the initial set of content to be pushed, the process of determining the processing method specifically includes:

[0076] Step A′: if it is determined that the content to be pushed successfully matches the primary negative feedback sub-data, then the processing method corresponding to the content to be pushed is determined to be a filtering method.

[0077] Specifically, the electronic device first matches the content to be pushed with the first-level negative feedback sub-data with a higher priority. If the match fails, step B' is executed. If the match succeeds, it means that the target user is very likely to be disgusted with the content to be pushed, and then it can be determined that the processing method corresponding to the content to be pushed is the filtering method.

[0078] Step B′: if it is determined that the content to be pushed fails to match the primary negative feedback sub-data, then the content to be pushed is matched with the secondary negative feedback sub-data.

[0079] Specifically, if the first-level negative feedback sub-data fails to match, the electronic device further matches the content to be pushed with the second-level negative feedback sub-data with a lower priority.

[0080] Step C′: if it is determined that the content to be pushed matches the secondary negative feedback sub-data successfully, the penalty weight of the content to be pushed is determined to be the second penalty weight, and the processing method corresponding to the content to be pushed is determined to be the descending method.

[0081] Specifically, if the match fails, it means that the target user at least does not reject the content to be pushed, so the sorting position of the content to be pushed in the initial set of content to be pushed is maintained. If the match succeeds, it means that the target user is likely not interested in the content to be pushed, so the processing method corresponding to the content to be pushed can be determined to be a descending method.

[0082] In order to perform quantitative re-ordering according to the weight values ​​later, the penalty weight of the content to be pushed may be determined as the second penalty weight, that is, the target penalty weight of the content to be pushed may be determined as the second penalty weight.

[0083] On the basis of the above embodiments, determining whether the content to be pushed successfully matches the primary negative feedback sub-data in the above processes includes:

[0084] Step A1: Determine the target publisher, target information type and target keyword corresponding to the content to be pushed.

[0085] The target publisher is the author of the content to be pushed. The target information type refers to the information type to which the content to be pushed belongs, which can be a large category with a relatively rough classification, or a small category with a relatively fine classification. The target keyword is the keyword contained in the content to be pushed. In the case where the content to be pushed is a search keyword, the target keyword can be the content to be pushed itself; in the case where the content to be pushed is a search phrase, the target keyword can be the keyword obtained by keyword extraction (and similar keyword matching) of the content to be pushed.

[0086] Specifically, in order to more comprehensively match the negative feedback data, the electronic device may extract information about the content to be pushed from different dimensions to obtain the target publisher, target information type, and target keywords corresponding to the content to be pushed.

[0087] Step A2: If it is determined that the target publisher, target keyword and target information type successfully match at least one item of the publisher information, first keyword and first information type contained in the first-level negative feedback sub-data, and it is determined that the first successfully matched item in the first-level negative feedback sub-data is within the negative feedback action period, then it is determined that the content to be pushed successfully matches the first-level negative feedback sub-data.

[0088] Among them, publisher information refers to information related to the author who published the pushed information, such as the author's name, the name of the author's unit, etc. The first keyword and the first information type refer to at least one keyword and at least one information type contained in the first-level negative feedback sub-data, respectively. The first entry refers to an entry that is successfully matched, and the entry can be publisher information, the first keyword, or the first information type. The negative feedback action period refers to a period with a negative feedback effect, that is, a period when the first entry still has a corresponding negative feedback effect. The negative feedback action period is set based on the actual situation that the search interests of the target user may change over time. The first entry in the negative feedback action period is still content that the target user dislikes, and the first entry after the negative feedback action period can be considered as content that the target user's search interest has changed and is temporarily not rejected.

[0089] Specifically, the electronic device matches the target publisher in the information to be pushed with the publisher information contained in the first-level negative feedback sub-data, matches the target information type in the information to be pushed with the first information type contained in the first-level negative feedback sub-data, and matches the target keyword in the information to be pushed with the first keyword contained in the first-level negative feedback sub-data. If at least one of the above matches successfully, all successfully matched entries are determined as the first entry. Then, the electronic device determines whether the first entry is still within its negative feedback action period based on the current moment and the negative feedback action period corresponding to the first entry. If the judgment result is that the first entry is still within its negative feedback action period, it is determined that the content to be pushed successfully matches the first-level negative feedback sub-data.

[0090] It should be noted that the above process of matching the target keyword in the information to be pushed with the first keyword contained in the first-level negative feedback sub-data includes matching based on keyword similarity, and may also include knowledge graphs corresponding to keywords or collaborative filtering based on keywords. For example, for the keywords of a certain item, in addition to matching the keywords themselves, it is also possible to match the manufacturer of the item, the upstream and downstream items of the item, etc.

[0091] Step A3: If it is determined that the target publisher, target keyword and target information type successfully match at least one item of the publisher information, first keyword and first information type contained in the first-level negative feedback sub-data, and it is determined that the first item is not within the negative feedback action period, then it is determined that the content to be pushed fails to match the first-level negative feedback sub-data.

[0092] Specifically, if it is determined that at least one of the publisher, keyword and information type is matched successfully, but it is also determined that the first items that are matched successfully are not in their corresponding negative feedback effect time period, it means that the first items that are matched successfully have lost the effect of negative feedback. At this time, it can be determined that the content to be pushed fails to match the first-level negative feedback sub-data.

[0093] Step A4: If it is determined that the target publisher, target keyword and target information type fail to match any one of the publisher information, first keyword and first information type contained in the primary negative feedback sub-data, it is determined that the content to be pushed fails to match the primary negative feedback sub-data.

[0094] Specifically, if the electronic device determines that any one of the publisher, keyword and information type fails to match, it means that the primary negative feedback sub-data does not contain any information related to the content to be pushed. At this time, it can be determined that the content to be pushed fails to match the primary negative feedback sub-data.

[0095] On the basis of the above embodiment, determining whether the first entry in the first-level negative feedback sub-data is in the negative feedback action period in step A2 and step A3 includes: determining the target action duration of the first entry based on the target number of negative feedbacks corresponding to the first entry and the mapping relationship between the number of negative feedbacks and the action duration; determining whether the first entry is in the negative feedback action period based on the target negative feedback moment, target action duration and current moment of the first entry.

[0096] Among them, the target number of negative feedbacks refers to the number of times the first item in the first-level negative feedback sub-data is negatively feedbacked. The action duration refers to the duration of the first item to play a negative feedback role. The target action duration refers to the action duration of the first item, which can be the action duration corresponding to the most recent negative feedback, or the total start and end time period of the action durations corresponding to multiple consecutive negative feedbacks, for example, from the start time of the action duration of the first negative feedback in three consecutive negative feedbacks to the end time of the action duration of the third negative feedback. The target negative feedback moment refers to the execution time of the negative feedback operation corresponding to the first item. In the case where the target action duration is the action duration corresponding to the most recent negative feedback, the target negative feedback moment is the negative feedback moment closest to the current moment among the multiple negative feedback moments corresponding to the multiple negative feedbacks; in the case where the target action duration is the total start and end time period, the target negative feedback moment is the negative feedback moment of the first negative feedback in the multiple consecutive negative feedbacks.

[0097] Specifically, the electronic device maintains a mapping relationship between the number of negative feedbacks and their corresponding action durations, and the number of negative feedbacks and the action duration in the mapping relationship have a positive correlation. For example, the first negative feedback of an entry has an action duration set to 3 days; the second negative feedback of the same entry has an action duration set to 5 days, and the starting time of the action duration is recalculated. Then, after determining the first entry, the electronic device can query the target number of negative feedbacks for the first entry from the primary negative feedback sub-data, and determine the target negative feedback moment of the first entry. Then, the electronic device queries the above mapping relationship based on the target number of negative feedbacks, and can determine the target action duration of the first entry. Afterwards, the electronic device determines whether the first entry is in the negative feedback action period based on the relationship between the target negative feedback moment, the target action duration, and the current moment.

[0098] In one example, the above-mentioned determination of whether the first entry is in the negative feedback action period based on the target negative feedback moment, the target action duration and the current moment of the first entry includes: if it is determined that the time difference between the current moment and the target negative feedback moment is less than or equal to the target action duration, then it is determined that the first entry is in the negative feedback action period.

[0099] Specifically, the electronic device calculates the time difference between the current moment and the target negative feedback moment. Then, the duration of the time difference is compared with the target action duration. If the time difference is greater than the target action duration, it means that the first entry at the current moment has exceeded its negative feedback action period. On the contrary, if the time difference is less than or equal to the target action duration, it is determined that the first entry is within the negative feedback action period.

[0100] In another example, the above-mentioned determination of whether the first entry is in the negative feedback action period based on the target negative feedback moment, target action duration and current moment of the first entry includes: determining the negative feedback action end time of the first entry based on the target negative feedback moment and target action duration; if the current moment does not exceed the negative feedback action end time, determining that the successfully matched entry is in the negative feedback action period.

[0101] Specifically, the electronic device calculates the negative feedback action end time of the first item, that is, the time when the negative feedback action fails, based on the target negative feedback time and target action duration of the first item. Then, the electronic device compares the current time with the negative feedback action end time. If the current time has exceeded the negative feedback action end time, it is determined that the first item is outside the negative feedback action period. On the contrary, if the current time has not exceeded the negative feedback action end time, it is determined that the first item is within the negative feedback action period.

[0102] In some embodiments, if it is determined in each of the above processes that the content to be pushed successfully matches the secondary negative feedback sub-data, determining the penalty weight of the content to be pushed as the second penalty weight includes:

[0103] Step B1: Determine the target information type and target keyword corresponding to the content to be pushed.

[0104] Step B2: If it is determined that the target keyword and the target information type successfully match at least one item in the second keyword information and the second information type contained in the secondary negative feedback sub-data, it is determined that the content to be pushed successfully matches the secondary negative feedback sub-data, and the penalty weight of the content to be pushed is determined to be the second penalty weight.

[0105] The second keyword and the second information type refer to at least one keyword and at least one information type contained in the secondary negative feedback sub-data, respectively.

[0106] Specifically, the electronic device matches the target information type in the information to be pushed with the second information type contained in the secondary negative feedback sub-data, and matches the target keyword in the information to be pushed with the second keyword contained in the secondary negative feedback sub-data. If at least one of the above matches successfully, it is determined that the content to be pushed matches the secondary negative feedback sub-data successfully, and the penalty weight of the content to be pushed is determined to be the second penalty weight corresponding to the secondary negative feedback sub-data.

[0107] Step B3: adjusting the second penalty weight based on the number of negative feedbacks corresponding to the successfully matched second entry in the secondary negative feedback sub-data and the time difference between the target negative feedback time of the second entry and the current time, so as to update the second penalty weight.

[0108] Specifically, the electronic device determines the above-mentioned successfully matched entry as the second entry. Then, the number of negative feedbacks corresponding to the second entry is queried from the secondary negative feedback sub-data, and the target negative feedback moment of the second entry is determined (the same method as the determination of the target negative feedback moment of the first entry). After that, the electronic device calculates the time difference between the target negative feedback moment and the current moment. Finally, the electronic device adjusts the second penalty weight of the content to be pushed according to the time difference and the number of negative feedbacks. For example, the more negative feedbacks and the shorter the time difference, it means that the target user is less interested in the content to be pushed, and the second penalty weight is increased.

[0109] In some embodiments, before S220, negative feedback data corresponding to the information push display page may be obtained through steps E to H.

[0110] Step E: based on each negative feedback operation result in the push information display page, obtain negative feedback operation information and target pushed information corresponding to the negative feedback operation.

[0111] Among them, the negative feedback operation result refers to the data generated after the target user performs a negative feedback operation on a certain pushed information. The negative feedback operation result at least includes the negative feedback operation information and the object of the negative feedback operation, that is, the target pushed information. The negative feedback operation information refers to information related to the negative feedback operation, such as the time of the negative feedback operation (i.e., the negative feedback time), the operation type of the negative feedback (i.e., the negative feedback type), and the content corresponding to the negative feedback type (i.e., the first negative feedback content).

[0112] Specifically, Figure 1 As shown, the client 100 sets a negative feedback operation control 105 for some pushed information 103 in the push information display page 101. The target user can perform a trigger operation on the negative feedback operation control 105, and the client 100 can display ( Figure 1 The negative feedback type selection control 106 corresponding to the negative feedback operation control 105 is shown as a floating window example. The target user can select the negative feedback type selection control 106 to complete the negative feedback operation on a certain pushed information 103. The client continuously detects the above negative feedback operations performed by the target user on the push information display page, and generates a negative feedback operation result for each negative feedback operation. Then, the client sends each negative feedback operation result to the electronic device. After receiving each negative feedback operation result, the electronic device parses it and obtains the negative feedback operation information and the target pushed information contained in each negative feedback operation result.

[0113] Step F: determining the negative feedback time, the negative feedback type, and the first negative feedback content corresponding to the negative feedback type based on the negative feedback operation information in each negative feedback operation result.

[0114] Specifically, the electronic device extracts information from each negative feedback operation information to obtain the negative feedback time, negative feedback type and first negative feedback content corresponding to each negative feedback operation information. The first negative feedback content may include keywords, publisher information and information type of the negative feedback.

[0115] Step G: Determine the second negative feedback content based on the target pushed information in each negative feedback operation result.

[0116] Specifically, the electronic device extracts information from each target pushed information to obtain the second negative feedback content corresponding to each target pushed information. The second negative feedback content may include keywords and information type, etc. The keywords here may be obtained by extracting keywords and expanding similar keywords from the title and / or specific content of the target pushed information. The information type is determined by the pre-set content tag corresponding to the target pushed information.

[0117] Step H: generating negative feedback data corresponding to the target pushed information in the information set based on the negative feedback time, negative feedback type, first negative feedback content and second negative feedback content corresponding to each negative feedback operation result.

[0118] Specifically, after the above steps are processed, the electronic device can obtain the negative feedback time, negative feedback type, first negative feedback content and second negative feedback content corresponding to each negative feedback operation result. Then, the electronic device performs data cleaning, deduplication, sensitive word filtering, aggregation and other processing on the above information corresponding to multiple negative feedback operation results, and the negative feedback data corresponding to the push information display page can be obtained. The negative feedback data at least includes the publisher information of the negative feedback and its corresponding negative feedback time and number of negative feedback; each keyword of the negative feedback, the negative feedback time and number of negative feedback corresponding to each keyword; each information type of the negative feedback, the negative feedback time and number of negative feedback corresponding to each information type, etc.

[0119] In some embodiments, the negative feedback type includes a disinterest type, a blocking type, or a blacklist type.

[0120] Specifically, the negative feedback type in the embodiment of the present disclosure is an operation type that can reflect the user's search needs or search preferences. Figure 1 As shown, the negative feedback type selection control 106 may display negative feedback types, which may at least include a not interested type, a blocked type, or a blacklisted type.

[0121] Furthermore, when the negative feedback type is a blacklist type, the first negative feedback content includes publisher information corresponding to the target pushed information.

[0122] When the negative feedback type is a shielding type, the first negative feedback content includes a first keyword and / or a first information type; wherein the first keyword and the first information type are the keywords and information types hit in the negative feedback operation information, respectively. Specifically, the keywords and information types corresponding to the pushed information are set in the shielding type. When the target user performs a shielding type negative feedback operation, the target user can select keywords and / or information types that he or she does not like. In this way, the first negative feedback content obtained by the electronic device includes the first keyword and / or the first information type selected by the target user.

[0123] When the negative feedback type is a type of no interest, the first negative feedback content includes a second information type corresponding to the target pushed information.

[0124] The electronic device processes the target pushed information by extracting keywords from the title of the target pushed information and obtaining the content tag corresponding to the target pushed information, thereby obtaining the second keyword and the extracted information type. Then, the electronic device merges the extracted information type into the second information type as negative feedback data of the target user's disinterest.

[0125] In some embodiments, the negative feedback data is split into primary negative feedback sub-data and secondary negative feedback sub-data; wherein the primary negative feedback sub-data includes publisher information, a first keyword and a first information type; and the secondary negative feedback sub-data includes a second keyword and a second information type.

[0126] Specifically, according to the above description, negative feedback data can be divided into subsets with different importance of negative feedback. The blacklist type and the shielding type indicate that the user does not want to see the relevant content at all, and the uninterested type indicates that the user is not very averse to the relevant content, which reflects the importance of negative feedback to a certain extent. Therefore, the electronic device divides the first negative feedback content obtained by the blacklist type and the shielding type in the negative feedback data, that is, the publisher information, the first keyword and the first information type, into the first level of negative feedback sub-data, and divides the first negative feedback content obtained by the uninterested type in the negative feedback data and the second negative feedback content obtained by the target pushed information, that is, the second keyword and the second information type, into the second level of negative feedback sub-data.

[0127] Figure 3 FIG. 1 is a flow chart of another information push method provided by an embodiment of the present disclosure. The information push method adds the relevant steps of further optimizing the target content set to be pushed by using positive feedback data on the basis of the above embodiments. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 3 As shown, the search result display method may include the following steps:

[0128] S310: Obtain an initial set of content to be pushed corresponding to the display position of the search content.

[0129] S320: Based on the negative feedback data of the information set of the push information display page, each content to be pushed in the initial content set to be pushed is processed to obtain a target content set to be pushed.

[0130] S330 : Based on the positive feedback data of the information set, sort and adjust each content to be pushed in the target content to be pushed set to update the target content to be pushed set.

[0131] Among them, positive feedback refers to positive feedback that users perform to enhance related pushes due to reasons such as liking or being interested, such as positive interactive behaviors such as sharing, liking, and commenting. Positive feedback data is behavioral data generated when users perform positive feedback operations on pushed information. It is a part of the behavioral data of target users obtained within a certain time range and authorized by the user. The positive feedback data may at least include a second keyword and a second information type extracted from the pushed information of the positive feedback.

[0132] Specifically, in addition to using the negative feedback data corresponding to the push information display page to optimize the initial set of content to be pushed and obtain the target set of content to be pushed, the electronic device can also use the positive feedback data corresponding to the push information display page to further optimize the target set of content to be pushed. For example, the ranking position of the content to be pushed that matches the positive feedback data in the target set of content to be pushed is adjusted to the front of the ranking.

[0133] In some embodiments, S330 may be implemented as follows:

[0134] Step I: for each content to be pushed in the target set of content to be pushed, if the content to be pushed successfully matches the positive feedback data, the reward weight of the content to be pushed is determined to be the target reward weight.

[0135] Among them, the reward weight refers to the weight value for rewarding (moving forward) the ranking position of the content to be pushed in the initial set of content to be pushed. In some embodiments, the reward weight may default to 0. The target reward weight is a pre-set reward weight value. In an implementation method where the larger the weight value, the lower the ranking, the target reward weight may be a weight value less than the basic weight. The basic weight is a default weight value set for each content to be pushed, which is the basis for sorting by weight. For example, the basic weight can be set to 0; then, the target reward weight is a value less than 0. In the case of this example, the above-mentioned target penalty weight (i.e., the first penalty weight, the second penalty weight, or the third penalty weight) is a value greater than 0.

[0136] Specifically, the electronic device matches each content to be pushed in the target set of content to be pushed with the positive feedback data (the matching process can refer to the matching implementation method of negative feedback data). If the match fails, the reward weight of the corresponding content to be pushed is not changed, that is, the ranking position of the corresponding content to be pushed in the target set of content to be pushed is maintained. If the match is successful, the reward weight of the corresponding content to be pushed is modified to the target reward weight.

[0137] Step J: Determine the target weight corresponding to the corresponding content to be pushed based on the reward weight, basic weight and penalty weight corresponding to each content to be pushed in the target content to be pushed set.

[0138] Specifically, based on the above description, each content to be pushed in the target set of content to be pushed corresponds to a reward weight, a basic weight and a penalty weight. The basic weights of each content to be pushed are the same. For the content to be pushed whose reward weight has not been modified, its reward weight is the default weight value; for the content to be pushed whose reward weight has been modified, its reward weight is the target reward weight. For the content to be pushed whose penalty weight has not been modified, its penalty weight is the default weight value; for the content to be pushed whose penalty weight has been modified, its penalty weight is the target penalty weight. On this basis, for each content to be pushed in the target set of content to be pushed, its corresponding reward weight, basic weight and penalty weight can be summed up to obtain the total weight value corresponding to each content to be pushed, that is, the target weight. The target weight serves as the basis for the final sorting of each content to be pushed in the target set of content to be pushed.

[0139] Step K: Based on the target weight of each content to be pushed, the order of each content to be pushed is adjusted to update the target set of content to be pushed.

[0140] Specifically, the electronic device re-sorts the contents to be pushed according to the target weight of each content to be pushed, and obtains an updated set of target contents to be pushed.

[0141] For example, the first content to be pushed has a base weight of 0, a penalty weight of a target penalty weight greater than 0, and a reward weight of a target reward weight less than 0, so its target weight is the sum of the target penalty weight and the target reward weight. The second content to be pushed has a base weight of 0, a penalty weight of a target penalty weight greater than 0, and a reward weight of the default weight value 0, so its target weight is the target penalty weight. In this way, the target weight of the first content to be pushed is less than the target weight of the second content to be pushed, so in the updated target content to be pushed set, the first content to be pushed is ranked before the second content to be pushed.

[0142] It should be noted that, for at least two to-be-pushed contents with the same target weight, they can be further reordered according to their original order positions in the target to-be-pushed contents set. For details, see the relevant contents of step D above.

[0143] S340: Based on the updated target set of contents to be pushed, determine and push each content to be pushed to the search content display position.

[0144] The above-mentioned information push method provided by the embodiment of the present disclosure can sort and adjust each content to be pushed in the target content set to be pushed based on the positive feedback data of the information set to update the target content set to be pushed. It realizes the optimization of the initial content set to be pushed by using the positive and negative feedback data corresponding to the push information display page at the same time, and obtains a more optimized updated target content set to be pushed, thereby further improving the accuracy of the search content pushed at the search content display position, and further improving the user's search experience.

[0145] Figure 4 FIG. 1 is a schematic diagram showing the structure of an information push device provided by an embodiment of the present disclosure. Figure 4 As shown, the information push device 400 may include:

[0146] The initial content set to be pushed acquisition module 410 is used to acquire the initial content set to be pushed corresponding to the search content display position; wherein the initial content set to be pushed includes at least two pieces of content to be pushed;

[0147] The target content set to be pushed determining module 420 is used to process each content to be pushed in the initial content set to be pushed based on the negative feedback data of the information set of the push information display page to obtain the target content set to be pushed; wherein the information set includes at least one pushed information;

[0148] The to-be-pushed content pushing module 430 is used to determine and push each to-be-pushed content to be pushed to the search content display position based on the target to-be-pushed content set.

[0149] Through the information push device in the embodiment of the present invention, in the process of pushing search content to the search content display position, the negative feedback data of the information set of the push information display page can be used to sort, adjust or filter out each to-be-pushed content in the initial to-be-pushed content set corresponding to the search content display position, so as to obtain the target to-be-pushed content set, and push the search content to the search content display position based on the target to-be-pushed content set, thereby realizing the data flow and interconnection of two different content carriers, so that the pushed content of the search content display position can be adjusted according to the user's negative feedback data, and the degree of fit between the pushed content of the search content display position and the user's needs can be improved, thereby improving the accuracy of the pushed content, reducing the user's search cost and inspiring the user to search, thereby improving the user's search experience.

[0150] In some embodiments, the target content set to be pushed determining module 420 includes:

[0151] A processing method determination submodule is used to match each to-be-pushed content in the initial to-be-pushed content set with the primary negative feedback sub-data and the secondary negative feedback sub-data in the negative feedback data, and determine a processing method for the corresponding to-be-pushed content based on the matching result;

[0152] A target content set to be pushed obtaining submodule, used to process the corresponding content to be pushed based on the processing method corresponding to each content to be pushed, and obtain the target content set to be pushed;

[0153] Among them, the first-level negative feedback sub-data and the second-level negative feedback sub-data are both subsets of the negative feedback data, and the negative feedback importance corresponding to the first-level negative feedback sub-data is higher than the negative feedback importance corresponding to the second-level negative feedback sub-data; the processing methods include filtering method and descending method.

[0154] In some embodiments, the processing mode determination submodule includes:

[0155] a first penalty weight determination unit, for determining, for any content to be pushed in the initial set of content to be pushed, a penalty weight of the content to be pushed as a first penalty weight if it is determined that the content to be pushed successfully matches the primary negative feedback sub-data and it is determined that the content to be pushed fails to match the secondary negative feedback sub-data;

[0156] A second penalty weight determination unit is used for, for any content to be pushed in the initial set of content to be pushed, if it is determined that the content to be pushed fails to match the primary negative feedback sub-data, and it is determined that the content to be pushed successfully matches the secondary negative feedback sub-data, then determining the penalty weight of the content to be pushed as the second penalty weight; wherein the first penalty weight is greater than the second penalty weight;

[0157] A third penalty weight determination unit is used to determine, for any content to be pushed in the initial set of content to be pushed, a third penalty weight based on the first penalty weight and the second penalty weight if it is determined that the content to be pushed successfully matches both the primary negative feedback sub-data and the secondary negative feedback sub-data, and determine the penalty weight of the content to be pushed as the third penalty weight;

[0158] The processing method determination unit is used to determine the processing method corresponding to any content to be pushed in the initial set of content to be pushed based on the target penalty weight corresponding to the content to be pushed and the filtering weight threshold; wherein the target penalty weight is the first penalty weight, the second penalty weight or the third penalty weight.

[0159] Furthermore, the processing mode determination unit is specifically used for:

[0160] If it is determined that the target penalty weight is greater than the filtering weight threshold, then the processing method corresponding to the content to be pushed is determined to be a filtering method;

[0161] If it is determined that the target penalty weight is less than or equal to the filtering weight threshold, then the processing method corresponding to the content to be pushed is determined to be a descending method.

[0162] In some other embodiments, the processing mode determination submodule is specifically used for:

[0163] For any content to be pushed in the initial set of content to be pushed:

[0164] If it is determined that the content to be pushed successfully matches the first-level negative feedback sub-data, then the processing method corresponding to the content to be pushed is determined to be a filtering method;

[0165] If it is determined that the content to be pushed fails to match the first-level negative feedback sub-data, then the content to be pushed is matched with the second-level negative feedback sub-data;

[0166] If it is determined that the content to be pushed successfully matches the secondary negative feedback sub-data, the penalty weight of the content to be pushed is determined to be the second penalty weight as the target penalty weight of the content to be pushed, and the processing method corresponding to the content to be pushed is determined to be a descending method.

[0167] In some embodiments, the processing mode determination submodule further includes:

[0168] A first information determination unit, used to determine a target publisher, target information type and target keywords corresponding to the content to be pushed;

[0169] A first matching unit, configured to determine that the content to be pushed successfully matches the first-level negative feedback sub-data if it is determined that the target publisher, the target keyword, and the target information type successfully match at least one item of the publisher information, the first keyword, and the first information type contained in the first-level negative feedback sub-data, and it is determined that the first successfully matched item in the first-level negative feedback sub-data is within the negative feedback action period;

[0170] A second matching unit is used to determine that the content to be pushed fails to match the primary negative feedback sub-data if it is determined that the target publisher, the target keyword and the target information type successfully match at least one item of the publisher information, the first keyword and the first information type contained in the primary negative feedback sub-data, and it is determined that the first item is not within the negative feedback action period;

[0171] The third matching unit is used to determine that the content to be pushed fails to match the first-level negative feedback sub-data if it is determined that the target publisher, target keyword and target information type all fail to match any one of the publisher information, first keyword and first information type contained in the first-level negative feedback sub-data.

[0172] Furthermore, the processing mode determination submodule further includes a fourth matching module, which is used to:

[0173] In the case where it is determined that the target publisher, the target keyword, and the target information type successfully match at least one item of the publisher information, the first keyword, and the first information type included in the primary negative feedback sub-data, based on the target number of negative feedbacks corresponding to the first item and the mapping relationship between the number of negative feedbacks and the action duration, the target action duration of the first item is determined;

[0174] Based on the target negative feedback time, the target action duration and the current time of the first entry, it is determined whether the first entry is within the negative feedback action period.

[0175] In some embodiments, the processing mode determination submodule further includes:

[0176] A second information determination unit, used to determine a target information type and a target keyword corresponding to the content to be pushed;

[0177] a fifth matching unit, configured to determine that the content to be pushed successfully matches the secondary negative feedback sub-data, and determine that the penalty weight of the content to be pushed is the second penalty weight, if it is determined that the target keyword and the target information type successfully match at least one item in the second keyword information and the second information type contained in the secondary negative feedback sub-data;

[0178] The second penalty weight adjustment unit is used to adjust the second penalty weight based on the number of negative feedbacks corresponding to the successfully matched second entry in the secondary negative feedback sub-data and the time difference between the target negative feedback time of the second entry and the current time, so as to update the second penalty weight.

[0179] In some embodiments, the information push device 400 further includes a negative feedback data generating module, which is used to:

[0180] Based on the negative feedback data of the information set of the push information display page, each content to be pushed in the initial content set to be pushed is processed to obtain the target content set to be pushed, and based on each negative feedback operation result in the push information display page, negative feedback operation information and target pushed information corresponding to the negative feedback operation are obtained;

[0181] Based on the negative feedback operation information in each negative feedback operation result, determining the negative feedback time, the negative feedback type and the first negative feedback content corresponding to the negative feedback type;

[0182] Determining the second negative feedback content based on the target pushed information in each negative feedback operation result;

[0183] Based on the negative feedback time, negative feedback type, first negative feedback content and second negative feedback content corresponding to each negative feedback operation result, negative feedback data corresponding to the target pushed information in the information set is generated.

[0184] Among them, negative feedback types include uninterested type, blocked type or blacklisted type.

[0185] In some embodiments, when the negative feedback type is a blacklist type, the first negative feedback content includes publisher information corresponding to the target pushed information;

[0186] When the negative feedback type is a blocking type, the first negative feedback content includes a first keyword and / or a first information type; wherein the first keyword and the first information type are the keyword and the information type hit in the negative feedback operation information, respectively;

[0187] When the negative feedback type is a type of not interested, the first negative feedback content includes a second information type corresponding to the target pushed information;

[0188] The negative feedback data generation module is specifically used for:

[0189] Information extraction is performed on the target pushed information to obtain a second keyword and an extracted information type as the second negative feedback content, and the extracted information type is merged into the second information type.

[0190] Further, the negative feedback data is split into primary negative feedback sub-data and secondary negative feedback sub-data;

[0191] The first-level negative feedback sub-data includes publisher information, a first keyword, and a first information type; the second-level negative feedback sub-data includes a second keyword and a second information type.

[0192] In some embodiments, the module for obtaining the initial set of content to be pushed is specifically used for:

[0193] An initial set of content to be pushed is determined based on the third keyword corresponding to the viewed push information of the target user, the preferred information type corresponding to the target user, and the current hot information.

[0194] In some embodiments, the information push device 400 further includes a target content set to be pushed update module, which is used to:

[0195] Before determining and pushing each content to be pushed to the search content display position based on the target content set to be pushed, the content to be pushed in the target content set to be pushed is sorted and adjusted based on the positive feedback data of the information set to update the target content set to be pushed.

[0196] Furthermore, the target content set to be pushed updating module is specifically used for:

[0197] For each content to be pushed in the target set of content to be pushed, if the content to be pushed successfully matches the positive feedback data, the reward weight of the content to be pushed is determined to be the target reward weight;

[0198] Determine the target weight corresponding to the corresponding content to be pushed based on the reward weight, basic weight and penalty weight corresponding to each content to be pushed in the target content to be pushed set;

[0199] Based on the target weight of each content to be pushed, the order of each content to be pushed is adjusted to update the target set of content to be pushed.

[0200] It should be noted that Figure 4 The information push device 400 shown can execute Figures 1 to 3 The various steps in the method embodiment shown in the figure are implemented Figures 1 to 3 The various processes and effects in the method embodiment shown are not described in detail here.

[0201] The disclosed embodiment also provides an information push device, which may include a processor and a memory, wherein the memory may be used to store executable instructions. The processor may be used to read the executable instructions from the memory and execute the executable instructions to implement the information push method in the above embodiment.

[0202] Figure 5 The structure diagram of an information push device provided by an embodiment of the present disclosure is shown. It should be noted that: Figure 5 The information push device 500 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0203] It should be noted that Figure 5 The information push device 500 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0204] like Figure 5 As shown, the information push device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the information processing device 500 are also stored. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output interface (I / O interface) 505 is also connected to the bus 504.

[0205] Typically, the following devices may be connected to the I / O interface 505: input devices 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 508 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 509. The communication devices 509 may allow the information push device 500 to communicate with other devices wirelessly or by wire to exchange data. Figure 5 The information push device 500 having various devices is shown, but it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0206] The embodiments of the present disclosure further provide a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the processor implements the information push method in any embodiment of the present disclosure.

[0207] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the information push method of the embodiment of the present disclosure are executed.

[0208] It should be noted that the computer-readable medium disclosed above 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, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The computer readable signal medium may also be any computer readable medium other than a computer readable storage medium, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0209] In some embodiments, the client and server may communicate using any currently known or future developed network protocol such as HTTP, and may be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0210] The computer-readable medium may be included in the information pushing device; or may exist independently without being assembled into the information pushing device.

[0211] The computer-readable medium carries one or more programs. When the one or more programs are executed by the information push device, the information push device executes the information push method described in any embodiment of the present disclosure.

[0212] In embodiments of the present disclosure, computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including but not limited to object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as a separate software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0213] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0214] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware, wherein the name of a unit does not, in some cases, limit the unit itself.

[0215] The functions described above herein may be performed 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 (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0216] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0217] The above description is only a preferred embodiment of the present disclosure and an explanation of the technical principles used. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above disclosed concept. For example, the above features are replaced with the technical features with similar functions disclosed in the present disclosure (but not limited to) by each other to form a technical solution.

[0218] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0219] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. An information push method, characterized in that: include: Acquire an initial set of content to be pushed corresponding to the display position of the searched content; wherein the initial set of content to be pushed includes at least two pieces of content to be pushed; Based on the negative feedback data of the information set of the push information display page, each of the to-be-pushed contents in the initial to-be-pushed content set is processed to obtain a target to-be-pushed content set; wherein the information set includes at least one pushed information; Based on the target set of content to be pushed, determining and pushing each of the content to be pushed to the display position of the search content; The negative feedback data of the information set of the push information display page is used to process each of the contents to be pushed in the initial set of contents to be pushed to obtain the target set of contents to be pushed, including: Matching each of the to-be-pushed contents in the initial to-be-pushed content set with the primary negative feedback sub-data and the secondary negative feedback sub-data in the negative feedback data, and determining a processing method for the corresponding to-be-pushed contents based on the matching result; Processing the corresponding content to be pushed based on the processing method corresponding to each content to be pushed to obtain the target content set to be pushed; Among them, the first-level negative feedback sub-data and the second-level negative feedback sub-data are both subsets of the negative feedback data, and the negative feedback importance corresponding to the first-level negative feedback sub-data is higher than the negative feedback importance corresponding to the second-level negative feedback sub-data; the processing method includes a filtering method and a descending method.

2. The method according to claim 1, characterized in that The step of matching each of the to-be-pushed content in the initial to-be-pushed content set with the primary negative feedback sub-data and the secondary negative feedback sub-data in the negative feedback data, and determining a processing method for the to-be-pushed content based on the matching result includes: For any content to be pushed in the initial set of content to be pushed: If it is determined that the content to be pushed successfully matches the primary negative feedback sub-data, and it is determined that the content to be pushed fails to match the secondary negative feedback sub-data, determining the penalty weight of the content to be pushed to be the first penalty weight; If it is determined that the content to be pushed fails to match the primary negative feedback sub-data, and it is determined that the content to be pushed successfully matches the secondary negative feedback sub-data, then the penalty weight of the content to be pushed is determined to be the second penalty weight; wherein the first penalty weight is greater than the second penalty weight; If it is determined that the content to be pushed successfully matches both the primary negative feedback sub-data and the secondary negative feedback sub-data, a third penalty weight is determined based on the first penalty weight and the second penalty weight, and the penalty weight of the content to be pushed is determined to be the third penalty weight; Based on the target penalty weight corresponding to the content to be pushed and the filtering weight threshold, the processing method corresponding to the content to be pushed is determined; wherein the target penalty weight is the first penalty weight, the second penalty weight or the third penalty weight.

3. The method according to claim 2, characterized in that The determining, based on the target penalty weight and the filtering weight threshold corresponding to the content to be pushed, the processing method corresponding to the content to be pushed includes: If it is determined that the target penalty weight is greater than the filtering weight threshold, determining that the processing method corresponding to the content to be pushed is the filtering method; If it is determined that the target penalty weight is less than or equal to the filtering weight threshold, it is determined that the processing method corresponding to the content to be pushed is the descending method.

4. The method according to claim 1, characterized in that: The step of matching each of the to-be-pushed content in the initial to-be-pushed content set with the primary negative feedback sub-data and the secondary negative feedback sub-data in the negative feedback data, and determining a processing method for the to-be-pushed content based on the matching result includes: For any content to be pushed in the initial set of content to be pushed: If it is determined that the content to be pushed successfully matches the primary negative feedback sub-data, determining that the processing method corresponding to the content to be pushed is the filtering method; If it is determined that the content to be pushed fails to match the primary negative feedback sub-data, matching the content to be pushed with the secondary negative feedback sub-data; If it is determined that the content to be pushed successfully matches the secondary negative feedback sub-data, the penalty weight of the content to be pushed is determined to be the second penalty weight as the target penalty weight of the content to be pushed, and the processing method corresponding to the content to be pushed is determined to be the descending method.

5. The method according to any one of claims 1 to 4, characterized in that: Determining whether the content to be pushed successfully matches the primary negative feedback sub-data includes: Determine the target publisher, target information type and target keyword corresponding to the content to be pushed; If it is determined that the target publisher, the target keyword and the target information type successfully match at least one item among the publisher information, the first keyword and the first information type contained in the primary negative feedback sub-data, and it is determined that the first successfully matched item in the primary negative feedback sub-data is within the negative feedback action period, then it is determined that the content to be pushed successfully matches the primary negative feedback sub-data; If it is determined that the target publisher, the target keyword and the target information type successfully match at least one item of the publisher information, the first keyword and the first information type contained in the primary negative feedback sub-data, and it is determined that the first item is not within the negative feedback action period, then it is determined that the content to be pushed fails to match the primary negative feedback sub-data; If it is determined that the target publisher, the target keyword and the target information type all fail to match any one of the publisher information, the first keyword and the first information type contained in the primary negative feedback sub-data, then it is determined that the content to be pushed fails to match the primary negative feedback sub-data.

6. The method according to claim 5, characterized in that Determining whether the first entry in the primary negative feedback sub-data is within the negative feedback action period includes: Determine the target action duration of the first item based on the target number of negative feedbacks corresponding to the first item and the mapping relationship between the number of negative feedbacks and the action duration; Based on the target negative feedback time of the first entry, the target action duration and the current time, it is determined whether the first entry is within the negative feedback action period.

7. The method according to any one of claims 1 to 4, characterized in that: If it is determined that the content to be pushed successfully matches the secondary negative feedback sub-data, determining the penalty weight of the content to be pushed as the second penalty weight includes: Determine the target information type and target keywords corresponding to the content to be pushed; If it is determined that the target keyword and the target information type successfully match at least one item in the second keyword information and the second information type contained in the secondary negative feedback sub-data, then it is determined that the content to be pushed successfully matches the secondary negative feedback sub-data, and the penalty weight of the content to be pushed is determined to be the second penalty weight; Based on the number of negative feedbacks corresponding to the successfully matched second entry in the secondary negative feedback sub-data and the time difference between the target negative feedback time of the second entry and the current time, the second penalty weight is adjusted to update the second penalty weight.

8. The method according to claim 1, characterized in that Before processing each of the to-be-pushed contents in the initial to-be-pushed contents set based on the negative feedback data of the information set of the push information display page to obtain the target to-be-pushed contents set, the method further includes: Based on each negative feedback operation result in the push information display page, negative feedback operation information and target pushed information corresponding to the negative feedback operation are obtained; Based on the negative feedback operation information in each of the negative feedback operation results, determining a negative feedback time, a negative feedback type, and a first negative feedback content corresponding to the negative feedback type; Determining second negative feedback content based on the target pushed information in each of the negative feedback operation results; The negative feedback data corresponding to the target pushed information in the information set is generated based on the negative feedback time, the negative feedback type, the first negative feedback content, and the second negative feedback content corresponding to each negative feedback operation result.

9. The method according to claim 8, characterized in that The negative feedback types include a disinterest type, a blocking type, or a blacklist type.

10. The method according to claim 9, characterized in that When the negative feedback type is the blacklist type, the first negative feedback content includes publisher information corresponding to the target pushed information; When the negative feedback type is the blocking type, the first negative feedback content includes a first keyword and / or a first information type; wherein the first keyword and the first information type are respectively the keywords and information types hit in the negative feedback operation information; When the negative feedback type is the uninterested type, the first negative feedback content includes a second information type corresponding to the target pushed information; Information extraction is performed on the target pushed information to obtain a second keyword and an extracted information type as the second negative feedback content, and the extracted information type is merged into the second information type.

11. The method according to claim 10, characterized in that Splitting the negative feedback data into primary negative feedback sub-data and secondary negative feedback sub-data; The first-level negative feedback sub-data includes the publisher information, the first keyword and the first information type; and the second-level negative feedback sub-data includes the second keyword and the second information type.

12. The method according to claim 1, characterized in that The step of obtaining an initial set of content to be pushed corresponding to the display position of the searched content includes: The initial set of content to be pushed is determined based on the third keyword corresponding to the viewed push information of the target user, the preference information type corresponding to the target user, and the current hot information.

13. The method according to any one of claims 1 to 4, characterized in that: Before determining and pushing each of the to-be-pushed contents to be pushed to the search content display position based on the target to-be-pushed contents set, the method further includes: Based on the positive feedback data of the information set, the order of each of the to-be-pushed contents in the target to-be-pushed content set is adjusted to update the target to-be-pushed content set.

14. The method according to claim 13, characterized in that The step of adjusting the order of each of the to-be-pushed contents in the target to-be-pushed content set based on the positive feedback data of the information set to update the target to-be-pushed content set includes: For each of the to-be-pushed contents in the target to-be-pushed content set, if the to-be-pushed contents successfully match the positive feedback data, determining the reward weight of the to-be-pushed contents to be the target reward weight; Determine a target weight corresponding to each content to be pushed based on the reward weight, basic weight and penalty weight corresponding to each content to be pushed in the target content to be pushed set; Based on the target weight of each of the to-be-pushed contents, the order of each of the to-be-pushed contents is adjusted to update the target to-be-pushed content set.

15. An information push device, characterized in that: include: An initial content set to be pushed acquisition module is used to acquire an initial content set to be pushed corresponding to the search content display position; wherein the initial content set to be pushed includes at least two pieces of content to be pushed; A target content set to be pushed determining module, configured to process each of the content to be pushed in the initial content set to be pushed based on the negative feedback data of the information set of the push information display page, and obtain a target content set to be pushed; wherein the information set includes at least one piece of pushed information; A to-be-pushed content pushing module, used to determine and push each of the to-be-pushed content to be pushed to the search content display position based on the target to-be-pushed content set; The module for determining the target content set to be pushed includes: A processing method determination submodule, used to match each of the to-be-pushed content in the initial to-be-pushed content set with the primary negative feedback sub-data and the secondary negative feedback sub-data in the negative feedback data, and determine a processing method for the corresponding to-be-pushed content based on the matching result; A target content set to be pushed obtaining submodule, used for processing the corresponding content to be pushed based on the processing method corresponding to each content to be pushed, to obtain the target content set to be pushed; Among them, the first-level negative feedback sub-data and the second-level negative feedback sub-data are both subsets of the negative feedback data, and the negative feedback importance corresponding to the first-level negative feedback sub-data is higher than the negative feedback importance corresponding to the second-level negative feedback sub-data; the processing method includes a filtering method and a descending method.

16. An information push device, characterized in that: include: processor; A memory for storing executable instructions; The processor is used to read the executable instructions from the memory and execute the executable instructions to implement the information push method described in any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the processor implements the information push method according to any one of claims 1 to 14.

Images