A result sorting method and device, computer device and storage medium

Abstract

The present disclosure provides a result sorting method and device, computer equipment and storage medium, wherein the method comprises: obtaining each first search result of a target genre and each second search result of other genres than the target genre obtained after the current search information is searched in a general search channel; determining the consumption data after deviation of each second search result corresponding to the historical consumption data of each target historical search result corresponding to the target genre obtained when the search information is historically searched and / or the historical consumption data of each second search result in the corresponding vertical search channel; wherein the target historical search result and the second search result are associated with the same theme object; and sorting the first search result and the second search result based on the historical consumption data of each first search result and the consumption data after deviation of each second search result.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and more specifically, to a result sorting method, apparatus, computer device, and storage medium. Background Technology

[0002] When using a search engine to search for relevant content, search results are often found in multiple genres. Since different users often have different search intentions, the display order of multiple search results often affects the usage rate of search results and the user's search experience.

[0003] Therefore, sorting multiple search results to improve the rationality of the search result display and thus increase the usage rate of the search results has become a technical challenge. Summary of the Invention

[0004] This disclosure provides at least one result sorting method, apparatus, computer device, and storage medium.

[0005] In a first aspect, embodiments of this disclosure provide a result sorting method, including:

[0006] After searching for the current search information in the general search channel, obtain the first search results for each target genre, and the second search results for each genre other than the target genre.

[0007] Based on the historical consumption data corresponding to each target historical search result under the target genre obtained when performing historical searches for the search information, and / or the historical consumption data of each second search result under its corresponding vertical search channel, the debiased consumption data corresponding to each second search result is determined; wherein, the target historical search results and the second search results are associated with the same topic object;

[0008] Based on the historical consumption data of each of the first search results and the debiased consumption data corresponding to each of the second search results, the first search results and the second search results are sorted.

[0009] In one possible implementation, based on the historical consumption data corresponding to each target historical search result under the target genre obtained during historical searches for the search information, the debiased consumption data corresponding to each second search result is determined, including:

[0010] For any second search result, determine a first number of first historical searches from the historical searches that yield at least one target historical search result;

[0011] Based on the historical consumption data corresponding to each target historical search result, from the first historical search, it is determined that each target historical search result has at least one second number of triggered second historical searches;

[0012] Based on the third quantity of the third search result obtained under the general search channel during the historical search, the result consumption data corresponding to the third search result, the first quantity, and the second quantity, the debiased consumption data corresponding to the second search result is determined, and the third search result is the search result consistent with the second search result.

[0013] In one possible implementation, determining the debiased consumption data corresponding to the second search result based on the third quantity of the third search result obtained under the general search channel during historical searches, the result consumption data corresponding to the third search result, the first quantity, and the second quantity includes:

[0014] From the historical searches, determine the third historical search that yielded the third search result and at least one of the target historical search results;

[0015] The total number of displays is determined based on the first difference between the third quantity and the fourth quantity of the third historical search, the second difference between the first quantity and the third quantity, and the fourth quantity.

[0016] Based on the second quantity, the result consumption data corresponding to the third search result, and the total number of displays, determine the debiased consumption data corresponding to the second search result.

[0017] In one possible implementation, determining the debiased consumption data corresponding to the second search result based on the second quantity, the result consumption data corresponding to the third search result, and the total number of impressions includes:

[0018] Based on the result consumption data corresponding to the third search result, determine the total number of triggers corresponding to the third search result, and select the fifth historical search result triggered by the third search result from the third historical search results;

[0019] From the third historical search, each of the corresponding target historical search results is selected to have at least one triggered sixth historical search;

[0020] The first trigger count is determined based on the third difference between the total number of triggers and the fifth number of the fifth historical search, and the fourth difference between the second number and the sixth number of the sixth historical search.

[0021] Based on the first number of triggers and the total number of displays, determine the debiased consumption data corresponding to the second search result.

[0022] In one possible implementation, determining the post-biasing consumption data corresponding to the second search result based on the first trigger count and the total number of displays includes:

[0023] From the third historical search, select the corresponding third search result that was triggered and the corresponding target historical search result that has at least one triggered seventh historical search.

[0024] The second trigger count is determined based on the fifth count, the sixth count, and the seventh count of the seventh historical search.

[0025] Based on the first number of triggers, the second number of triggers, and the total number of displays, the debiased consumption data corresponding to the second search result is determined.

[0026] In one possible implementation, for any second search result, the historical consumption data of the second search result under the corresponding vertical search channel includes the result consumption data of each third search result obtained under the vertical search channel corresponding to the second search result;

[0027] Based on the historical consumption data of each second search result under its corresponding vertical search channel, determine the post-biased consumption data corresponding to each second search result, including:

[0028] When determining the historical search results, the third number of third search results obtained under the general search channel;

[0029] From the historical searches, determine the eighth historical search that obtained the third search result under the general search channel and whose corresponding vertical search channel includes the third search result; and from the historical searches, filter out the ninth historical search that includes the third search result under the corresponding vertical search channel.

[0030] Based on the fifth difference between the third quantity and the eighth quantity of the eighth historical search, the sixth difference between the ninth quantity of the ninth historical search and the eighth quantity, the eighth quantity, and the result consumption data of the third search result, the debiased consumption data corresponding to the second search result is determined.

[0031] In one possible implementation, determining the debiased consumption data corresponding to the second search result based on the fifth difference between the third quantity and the eighth quantity of the eighth historical search, the sixth difference between the ninth quantity of the ninth historical search and the eighth quantity, the eighth quantity, and the consumption data of the third search result includes:

[0032] The target number of displays is determined based on the fifth difference, the sixth difference, and the eighth quantity.

[0033] Based on the consumption data of the third search result, from the eighth historical search, the obtained third search result and the third search result under the corresponding vertical search channel, there is at least one triggered tenth historical search.

[0034] Based on the number of times the target was displayed and the number of the tenth historical search, the debiased consumption data corresponding to the second search result is determined.

[0035] In one possible implementation, based on the historical consumption data corresponding to each target historical search result under the target genre obtained during historical searches for the search information, and the historical consumption data of each second search result under its corresponding vertical search channel, the post-biased consumption data corresponding to each second search result is determined, including:

[0036] For any second search result, determine a first number of first historical searches from the historical searches that yield at least one target historical search result;

[0037] Based on the historical consumption data corresponding to each target historical search result, from the first historical search, it is determined that each target historical search result has at least one second number of triggered second historical searches;

[0038] The third trigger count is determined based on the result consumption data of each third search result obtained under the general search channel when performing historical searches for the search information; the third search result is the same as the second search result.

[0039] The fourth trigger count is determined based on the result consumption data of each third search result obtained under the vertical search channel corresponding to the second search result when performing historical searches for the search information.

[0040] Based on the third quantity, the first quantity, the second quantity, the third trigger count, and the fourth trigger count of each third search result obtained under the general search channel, determine the debiased consumption data corresponding to the second search result.

[0041] In one possible implementation, the post-biasing consumption data corresponding to the second search result is determined based on the third quantity, the first quantity, the second quantity, the third trigger count, and the fourth trigger count of each third search result obtained under the general search channel, including:

[0042] From the historical searches, select the ninth historical search that includes the third search result under the corresponding vertical search channel;

[0043] Based on the third quantity, the first quantity, and the ninth quantity of the ninth historical search, determine the total number of times the target appears corresponding to the second search result;

[0044] Based on the third trigger count, the second quantity, and the fourth trigger count, determine the total number of target triggers corresponding to the second search result;

[0045] Based on the total number of times the target appears and the total number of times the target is triggered, the debiased consumption data corresponding to the second search result is determined.

[0046] In one possible implementation, determining the target total number of triggers corresponding to the second search result based on the third trigger count, the second quantity, and the fourth trigger count includes:

[0047] Obtain the preset first weight, second weight, and third weight;

[0048] The total number of triggers corresponding to the second search result is determined based on the weighted value of the first weight and the third trigger count, the weighted value of the second weight and the second quantity, and the weighted value of the third weight and the fourth trigger count.

[0049] In one possible implementation, the sorting of the first and second search results based on the historical consumption data of each of the first search results and the debiased consumption data corresponding to each of the second search results includes:

[0050] Based on the historical consumption data of each of the first search results, determine the first trigger rate of each of the first search results;

[0051] Based on the debiased consumption data corresponding to each of the second search results, determine the second trigger rate of each of the second search results;

[0052] The first and second search results are sorted based on the first trigger rate and the second trigger rate.

[0053] Secondly, embodiments of this disclosure also provide a result sorting apparatus, comprising:

[0054] The acquisition module is used to acquire the first search results of the target genre obtained after searching for the search information in the general search channel, and the second search results of other genres besides the target genre.

[0055] The determining module is used to determine the debiased consumption data corresponding to each second search result based on the historical consumption data corresponding to each target historical search result under the target genre obtained when performing historical searches for the search information, and / or the historical consumption data of each second search result under its corresponding vertical search channel; wherein the target historical search results and the second search results are associated with the same topic object;

[0056] The sorting module is used to sort the first search results and the second search results based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result.

[0057] Thirdly, an optional implementation of this disclosure also provides a computer device, a processor, and a memory, wherein the memory stores machine-readable instructions executable by the processor, and the processor is configured to execute the machine-readable instructions stored in the memory. When the machine-readable instructions are executed by the processor, the steps of the first aspect above, or any possible implementation of the first aspect, are performed.

[0058] Fourthly, an optional implementation of this disclosure also provides a computer-readable storage medium storing a computer program that, when run, performs the steps of the first aspect or any possible implementation of the first aspect.

[0059] For a description of the effects of the above-mentioned result sorting device, computer equipment, and computer-readable storage medium, please refer to the description of the above-mentioned result sorting method, which will not be repeated here.

[0060] The result ranking method, apparatus, computer equipment, and storage medium provided in this disclosure, for second search results under other genres, can reflect the consumption demand for second search results to a certain extent because the target historical search results and second search results under the target genre share the same topic object. Similarly, the historical consumption data of second search results under their respective vertical search channels can also reflect the consumption demand for second search results to a certain extent. Therefore, by combining the historical consumption data of target historical search results under the target genre, the impact of the historical consumption data of target historical search results on the consumption data of second search results can be fully considered; similarly, by combining the historical consumption data under vertical search channels, the impact of the historical consumption data under vertical search channels on the consumption data of second search results can be fully considered. Thus, by using the historical consumption data of target historical search results and / or the historical consumption data under vertical search channels to determine the debiased consumption data corresponding to the second search results, the rationality and accuracy of the obtained debiased consumption data can be improved. Finally, by ranking based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result, the ranking rationality of the first and second search results can be improved, thereby improving the display rationality of search results and the utilization rate of search results.

[0061] To make the above-mentioned objects, features and advantages of this disclosure more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0062] To more clearly illustrate the technical solutions of the embodiments of this disclosure, the accompanying drawings used in the embodiments will be briefly described below. These drawings are incorporated in and constitute a part of this specification. They illustrate embodiments conforming to this disclosure and, together with the specification, serve to explain the technical solutions of this disclosure. It should be understood that the following drawings only show some embodiments of this disclosure and should not be considered as limiting the scope. Those skilled in the art can obtain other related drawings based on these drawings without creative effort.

[0063] Figure 1 A flowchart of a result sorting method provided by an embodiment of this disclosure is shown;

[0064] Figure 2 This illustration shows a diagram of search results corresponding to a general search channel and a vertical search channel, respectively, provided in an embodiment of this disclosure.

[0065] Figure 3 A schematic diagram of a result sorting apparatus provided in an embodiment of this disclosure is shown;

[0066] Figure 4 A schematic diagram of the structure of a computer device provided in an embodiment of this disclosure is shown. Detailed Implementation

[0067] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this disclosure, and not all of them. The components of the embodiments of this disclosure described and shown herein can generally be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this disclosure is not intended to limit the scope of the claimed disclosure, but merely represents selected embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without inventive effort are within the scope of protection of this disclosure.

[0068] Furthermore, the terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this disclosure are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments described herein can be implemented in a sequence other than that illustrated or described herein.

[0069] In this article, "multiple or several" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0070] Research has found that when using search engines, multiple search results for the target genre and results for other genres can be found. Conventional methods often rank and display search results based on their historical click-through rates (CTRs). However, this approach often only considers the CTR of the search results within a general search channel, which may not accurately match the search intent, resulting in a lower reasonableness of the determined CTR. This, in turn, affects the display order of search results and reduces their usage. Furthermore, the display order of search results on the search results page often conversely affects their usage, leading to various biases in existing search result ranking schemes. For example, if a search result cannot appear on the search results page or is ranked low, its historical CTR may be lower. Conversely, if a search result is ranked high on the search results page, its historical CTR may be higher. Therefore, conventional ranking schemes affect the accuracy of search result ranking.

[0071] Based on the above research, this disclosure provides a result ranking method, apparatus, computer device, and storage medium. For second search results under other genres, since the target historical search results under the target genre and the second search results share the same subject matter, the historical consumption data of the target historical search results can, to a certain extent, reflect the consumption demand for the second search results. Similarly, the historical consumption data of the second search results under their respective vertical search channels can also, to a certain extent, reflect the consumption demand for the second search results. Therefore, by combining the historical consumption data of the target historical search results under the target genre, the impact of the target historical search results' consumption data on the consumption data of the second search results can be fully considered; similarly, by combining the historical consumption data under the vertical search channels, the impact of the historical consumption data under the vertical search channels on the consumption data of the second search results can also be fully considered. Thus, by utilizing the historical consumption data of the target historical search results and / or the historical consumption data under the vertical search channels to determine the debiased consumption data corresponding to the second search results, the rationality and accuracy of the obtained debiased consumption data can be improved. Finally, ranking based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result can improve the ranking rationality of the first and second search results, thereby improving the display rationality of the search results and the utilization rate of the search results.

[0072] The shortcomings of the above solutions are the result of the inventor's practical experience and careful research. Therefore, the discovery process of the above problems and the solutions proposed in this disclosure below should be considered as the inventor's contribution to this disclosure.

[0073] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures.

[0074] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0075] To facilitate understanding of this embodiment, a result sorting method disclosed in this disclosure will first be described in detail. The execution subject of the result sorting method provided in this disclosure is generally a terminal device or other processing device with certain computing power. The terminal device can be a user equipment (UE), mobile device, user terminal, terminal, personal digital assistant device (PDA), handheld device, computer device, etc. In some possible implementations, the result sorting method can be implemented by the processor calling computer-readable instructions stored in the memory.

[0076] The following describes the result sorting method provided in the embodiments of this disclosure, taking a computer device as the execution subject as an example.

[0077] like Figure 1 The flowchart shown is a result sorting method provided in an embodiment of this disclosure, which may include the following steps:

[0078] S101: Obtain the first search results for each target genre obtained after searching for the search information in the general search channel, and the second search results for each other genre associated with the first search results.

[0079] Here, the search information can be the search terms entered by the user. The general search channel is specifically under the comprehensive search channel, where search results of various formats can be obtained.

[0080] The target genre can be a predefined result genre, often the genre of organic search results found by the search engine; other genres can be result genres other than the target genre, often the genres of results found by the search engine other than organic results. For example, the target genre could be a video genre, and other genres could be user card genres, music card genres, tag card genres, article genres, etc. The second search result under the user card genre could be a user card, which may include authorized user information, such as username, user identifier, and user avatar. The second search result under the music card genre could be a music card, which may include music information; the second search result under the tag card genre could be a tag card, which may include topic tags; and the second search result under the article genre could be an article.

[0081] The first search result is the search result for each item with the target genre obtained under the general search channel after performing the current search using the search information. The second search result is the search result for each item with a different genre obtained under the general search channel after performing the current search using the search information. The second search result can be related to the first search result; for example, the second search result may include the same topic or the same text as the first search result.

[0082] Within each "other genre," there is only one second search result. For all "other genres," after the current search, there can be a corresponding second search result for each of the "other genres." Understandably, after the current search, the resulting second search results may include search results for some genres within all the "other genres."

[0083] For example, after performing the current search using search information, multiple first search results in the video genre obtained under the general search channel, a second search result in the user card genre, and a second search result in the tag card genre can be obtained.

[0084] S102: Based on the historical consumption data corresponding to each target historical search result under the target genre obtained when performing historical searches for the search information, and / or the historical consumption data of each second search result under its corresponding vertical search channel, determine the debiased consumption data corresponding to each second search result; wherein the target historical search results and the second search results are associated with the same topic object.

[0085] Here, when the target genre is video, the search results for videos may have different relationships with results from other genres. For example, when consuming a video, the actual consumption intent might be to consume the video from the user who uploaded it; in this case, the consumption of the video could actually be related to the search intent for that user. Similarly, if a video contains background music, the actual consumption intent might be to consume the background music; in this case, the consumption of the video could actually be related to the search intent for the background music. Likewise, if a video contains hashtags, the actual consumption intent might be to consume the hashtags associated with the video; in this case, the consumption of the video could actually be related to the search intent for the hashtags. Based on this analysis, it can be seen that for video search results that share the same thematic object with search results from other genres, the consumption data of the video search results may affect the consumption data of the search results for that genre. Therefore, the consumption data of the target genre search results can be combined to rank the search results for other genres, thereby improving the rationality of the ranking. For details on how to combine consumer data from search results for the target genre to rank search results for other genres, please see the following content.

[0086] The debiased consumption data is the consumption data obtained after considering the impact of historical consumption data of the target historical search results and / or historical consumption data under vertical search channels on the consumption data of the second search result. It can eliminate the ranking bias problem of the target historical search results and / or search results under vertical search channels on the second search result. For example, the debiased consumption data can be used to characterize the trigger rate, usage rate, etc. of the second search result.

[0087] The target historical search results are the search results obtained from previous searches. They share the same topic object with the second search result, and the topic object can be determined based on the genre of the second search result. For example, if the second search result is a user card, the topic object can be the user in the user card; if the second search result is a music card, the topic object can be the music in the music card; if the second search result is a tag card, the topic object can be the topic tag in the tag card; and if the second search result is an article, the topic object can be the article's source, summary, or other information.

[0088] Historical searches can refer to all previous searches performed within a preset historical time period using search information. For each historical search, corresponding historical search results can be obtained under the general search channel. These historical search results may include target historical search results that share the same topic as the second search result, or they may exclude other results of the target genre (and these results may not share the same topic as the second search result). Historical search results may include third search results that are consistent with the second search result, or they may exclude third search results.

[0089] Historical searches for search information can be authorized for each search within a preset historical time period for the user who initiated the current search, or for all users across the network within a preset historical time period.

[0090] Historical consumption data is used to characterize consumption information of target historical search results, such as whether the target historical search results were triggered (after being triggered, the target historical search results can be viewed), whether they were favorited, whether they were tagged, etc.

[0091] Different vertical search channels correspond to different genres, and the search results under a vertical search channel are all results within the genre corresponding to that vertical search channel. For example, the vertical search channel corresponding to a user card could be the user channel, the vertical search channel corresponding to a music card could be the music channel, and the vertical search channel corresponding to a tag card could be the tag channel. In practice, for each historical search, the search results page can display all historical search results under the general search channel, but the search results page can also display the trigger tags corresponding to the general search channel and the trigger tags corresponding to each vertical search channel. By triggering the trigger tags corresponding to the vertical search channel, the search results under that vertical search channel can be obtained. That is, for each search, there can be corresponding search results under both the general search channel and the vertical search channel. Figure 2 The diagram shown illustrates search results for a general search channel and a vertical search channel, respectively, provided in this embodiment of the disclosure. The search information is "User A". Figure 2 'a' represents a search result illustration under the General Search channel. The General Search channel (i.e., the Comprehensive channel) can include a user card (User Card 1) displaying user A. Below User Card 1 are multiple aggregation tags used to filter videos uploaded by user A. Below the user card are multiple videos of user A (i.e., Videos 1-3), and below these videos are the first search results for each video genre (e.g.,...). Figure 2 Videos 4 and 5 in the video), where video 5 is a video uploaded by user A, so video 5 and user card 1 are associated with the same subject object (i.e. user A). Figure 2 In the image, b represents a diagram illustrating the search results under the vertical search channel (user channel) corresponding to user card 1. Figure 2 Following 'a', it can respond to triggering the channel tag corresponding to the user's channel and display... Figure 2 b in. Figure 2 In section b, multiple user cards (i.e., user cards 1 to 6) are displayed, each corresponding to a different user.

[0092] The historical consumption data of the second search result under the corresponding vertical search channel can specifically refer to the consumption data of the third search result under the corresponding vertical search channel when performing historical searches using the search information. The third search result can be the same as the second search result. That is, for any historical search, if the search yields the second search result, then the second search result obtained in that search can be used as the third search result. Understandably, for any historical search, there may or may not be a third search result under the corresponding vertical search channel of the second search result.

[0093] In practice, for each second search result, the historical search results under the general search channel for each historical search performed using search information within a preset historical time period can be obtained. This allows for the acquisition of target historical search results related to the same topic as the second search result. Similarly, the historical search results under the vertical search channel corresponding to the second search result for each historical search performed using search information within a preset historical time period can be obtained, and the third search result can be determined from these historical search results. Then, based on the historical consumption data corresponding to each target historical search result and / or the result consumption data of each third search result, the debiased consumption data corresponding to each second search result can be determined. The result consumption data of the third search result is the historical consumption data of the third search result during the historical search.

[0094] For example, the total number can be determined based on the number of target historical search results and the number of third-party search results. The number of triggers for target historical search results is determined based on historical consumption data of the target historical search results, and the number of triggers for third-party search results is determined based on the result consumption data of the third-party search results. The debiased consumption data is determined based on the ratio between the total number and the sum of the two trigger numbers.

[0095] S103: Sort the first search results and the second search results based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result.

[0096] For example, the trigger count for each first search result can be determined based on historical consumption data, and the trigger count for each second search result can be determined based on debiased consumption data. Then, the first and second search results can be sorted in descending order of trigger count.

[0097] Thus, for second search results under other genres, since the target historical search results under the target genre and the second search results share the same subject matter, the historical consumption data of the target historical search results can, to some extent, reflect the consumption demand for the second search results. Similarly, the historical consumption data of the second search results under their respective vertical search channels can also, to some extent, reflect the consumption demand for the second search results. Therefore, by combining the historical consumption data of the target historical search results under the target genre, the impact of the target historical search results consumption data on the second search results consumption data can be fully considered; similarly, by combining the historical consumption data under the vertical search channels, the impact of the historical consumption data under the vertical search channels on the second search results consumption data can also be fully considered. Therefore, by using the historical consumption data of the target historical search results and / or the historical consumption data under the vertical search channels to determine the debiased consumption data corresponding to the second search results, the rationality and accuracy of the obtained debiased consumption data can be improved. Finally, sorting based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result can improve the ranking rationality of the first and second search results, thereby improving the display rationality of the search results and the usage rate of the search results.

[0098] In one embodiment, the step of "determining the debiased consumption data corresponding to each second search result based on the historical consumption data corresponding to each target historical search result under the target genre obtained when performing historical searches for search information" can be implemented according to the following steps:

[0099] S1: For any second search result, determine a first number of first historical searches from the historical searches that yield at least one target historical search result.

[0100] Here, in the case where the second search result obtained in the current search includes multiple cases, the debiased consumption data corresponding to each second search result can be determined separately.

[0101] The first historical search is any historical search within the general search channel that includes at least one target historical search result. For example, in the case where the second search result is a music card, the first historical search could be either a historical search within the general search channel that includes only at least one target historical search result (with background music corresponding to the music card), or a historical search within the general search channel that includes at least one target historical search result and also includes the music card.

[0102] For example, for each historical search, it can be determined whether the target historical search results are included in the general search channel when the historical search is performed. If so, the historical search is regarded as the first historical search; if not, the historical search is not regarded as the first historical search.

[0103] S2: Based on the historical consumption data corresponding to each target's historical search results, determine from the first historical search results that each target's historical search results has at least one second number of triggered second historical searches.

[0104] Here, the historical consumption data corresponding to the target historical search results can be used to indicate whether the target historical search results have been triggered. The second historical search is the first historical search, in which at least one of the target historical search results under the general search channel has been triggered.

[0105] For example, for each first historical search, the existence of a triggered target historical search result can be determined based on the historical consumption data of each target historical search result corresponding to that first historical search. If so, the first historical search can be used as the second historical search; otherwise, it can be excluded from the second historical search.

[0106] S3: Based on the third quantity of the third search result obtained under the general search channel during the historical search, the result consumption data corresponding to the third search result, the first quantity, and the second quantity, determine the debiased consumption data corresponding to the second search result, and the third search result is the search result that is consistent with the second search result.

[0107] Here, for example, one can filter out each third search result from the historical search results under the general search channel for each historical search. Result consumption data is used to characterize the consumption information of the third search result, such as whether the third search result was triggered (after triggering, the third search result can be viewed), whether it was saved, whether it was tagged, etc. The result consumption data corresponding to the third search result obtained under the general search channel can be the historical consumption data of the third search result obtained under the general search channel during previous searches. The debiased consumption data can specifically be used to characterize the trigger rate corresponding to the second search result.

[0108] The third quantity can be the number of third search results obtained under the general search channel during each historical search. Specifically, the third quantity of third search results obtained under the general search channel during historical searches can include the number of historical searches that include only at least one target historical search result, and the number of historical searches that include both at least one target historical search result and a third search result.

[0109] In practice, the number of triggered third search results can be determined based on the consumption data of the third search results obtained under the general search channel during historical searches. Then, the sum of this number and the second number, as well as the sum of the third number and the first number, can be determined. Finally, the trigger rate corresponding to the second search result can be determined based on the ratio of these two sums.

[0110] For example, when the second search result is a music card corresponding to the target music, a first number of historical searches containing at least one historical search video can be determined from the historical searches. A second number of historical searches can be determined from the first historical searches, identifying at least one triggered historical search for each historical search video. Simultaneously, a third number of historical music cards (consistent with the music card corresponding to the second search result) obtained under the general search channel during the historical searches can be determined, and the number of triggered historical music cards can be determined based on the result consumption data for each historical music card. Then, the trigger rate corresponding to the music card can be determined based on the sum of the number of triggered historical music cards and the second number, and the sum of the third number and the first number.

[0111] In one embodiment, S3 described above can be implemented according to the following steps:

[0112] S3-1: From the historical searches, identify the third historical search that yields the third search result and at least one target historical search result.

[0113] Here, regarding historical searches, the corresponding historical search results under the general search channel can appear in the following ways:

[0114] Historical search results include at least one target historical search result and a third search result; historical search results include only at least one target historical search result; and historical search results include only a third search result.

[0115] In practice, the third historical search can be selected from the historical search results under the general search channel that includes both the third search result and at least one target historical search result.

[0116] S3-2: Determine the total number of impressions based on the first difference between the third quantity and the fourth quantity of the third historical search, the second difference between the first quantity and the third quantity, and the fourth quantity.

[0117] Here, the first difference represents the number of historical search results obtained under the general search channel that include only the third search result. The second difference represents the number of historical search results obtained under the general search channel that include only at least one target historical search result. The total number of impressions represents the total number of historical impressions corresponding to the second search result, which can be represented by (impreA|impreB), where impreA represents the number of target historical search results obtained under the general search channel during the historical search, impreB represents the number of third search results obtained under the general search channel during the historical search, and "|" represents an OR operation. That is, for a single historical search, if the historical search obtained both at least one target historical search result and a third search result under the general search channel, it can be counted only once, meaning the total number of impressions is only incremented by 1. If the historical search obtained only at least one target historical search result under the general search channel, it can also be counted only once, meaning the total number of impressions is only incremented by 1. If a historical search in the general search channel only yields a third search result, it can be counted only once, meaning the total number of impressions is incremented by 1. If a historical search in the general search channel yields neither at least one target historical search result nor a third search result, it can be left uncounted, meaning the total number of impressions is incremented by 0.

[0118] In practice, the sum of the first difference, the second difference, and the fourth quantity can be calculated and used as the total number of displays.

[0119] S3-3: Based on the second quantity, the result consumption data corresponding to the third search result, and the total number of impressions, determine the debiased consumption data corresponding to the second search result.

[0120] For example, the number of triggered third search results can be determined based on the result consumption data corresponding to the third search result. Then, the sum of this number and the second number can be determined, and this sum can be used as the target number. Afterward, the debiased click-through rate corresponding to the second search result can be determined based on the target number and the total number of impressions, and this debiased click-through rate can be used as the debiased consumption data corresponding to the second search result.

[0121] In one embodiment, S3-3 described above can be implemented according to the following steps:

[0122] S3-3-1: Based on the result consumption data corresponding to the third search result, determine the total number of triggers corresponding to the third search result, and select the fifth historical search triggered by the third search result from the third historical search results.

[0123] Here, the total number of triggers is used to represent the number of historical triggers corresponding to the third search result. The fifth historical search may include the third historical search in which the third search result under the general search channel is triggered and at least one target historical search result under the general search channel is triggered, as well as the third historical search in which the third search result under the general search channel is triggered only.

[0124] In practice, the number of triggered third search results can be determined based on the result consumption data corresponding to each third search result, and this number can be used as the total number of triggers. Simultaneously, based on the result consumption data of each third search result corresponding to a third historical search, the fifth historical search triggered by the obtained third search result can be selected from the third historical searches.

[0125] S3-3-2: From the third historical search, filter out the corresponding target historical search results where there is at least one triggered sixth historical search.

[0126] Here, the sixth historical search can include the third historical search in which at least one of the target historical search results under the general search channel is triggered and the third search result under the general search channel is triggered, as well as the third historical search in which at least one of the target historical search results under the general search channel is triggered.

[0127] For example, based on the historical consumption data of each target historical search result corresponding to the third historical search, a sixth historical search can be selected from the third historical search that has at least one target historical search result triggered.

[0128] S3-3-3: Determine the first trigger count based on the third difference between the total number of triggers and the fifth number of the fifth historical search, and the fourth difference between the second number and the sixth number of the sixth historical search.

[0129] Here, the third difference is used to characterize the number of historical searches triggered by the third search result in a historical search that yielded only the third search result under the general search channel. The fourth difference is used to characterize the number of historical searches triggered by at least one target historical search result in a historical search that yielded only at least one target historical search result under the general search channel. If a historical search yields only one target historical search result under the general search channel, the count of the first trigger can be incremented by 1 if that target historical search result is triggered, and the count of the first trigger can be incremented by 0 if that target historical search result is triggered. If a historical search yields multiple target historical search results under the general search channel, the count of the first trigger can be incremented by 1 if at least one target historical search result is triggered, and the count of the first trigger can be incremented by 0 if none of the target historical search results are triggered.

[0130] In practice, the sum of the third and fourth differences can be used as the first trigger count.

[0131] S3-3-4: Based on the first trigger count and the total number of displays, determine the post-biased consumption data corresponding to the second search result.

[0132] In practice, the number of third historical searches triggered by a third search result can be determined based on the result consumption data of the third search result corresponding to each third historical search. Simultaneously, the number of third historical searches triggered by at least one target historical search result can be determined based on the historical consumption data of each target historical search result corresponding to each third historical search. First, the sum of these two quantities is determined, then the sum of this sum and the first number of triggers is calculated. Finally, the debiased trigger rate corresponding to the second search result can be determined based on the ratio of this sum plus the first number of triggers to the total number of impressions.

[0133] In one embodiment, S3-3-4 described above can be implemented according to the following steps:

[0134] S3-3-4-1: From the third historical search, filter out the corresponding third search results that are triggered and the corresponding target historical search results have at least one triggered seventh historical search.

[0135] S3-3-4-2: Determine the second trigger count based on the fifth count, the sixth count, and the seventh count from the seventh historical search.

[0136] Here, the second trigger count is used to characterize the number of times that at least one third historical search is triggered in the third search result under the general search channel and the target historical search result under the general search channel.

[0137] Specifically, the fifth and sixth historical searches may contain duplicate historical searches. A duplicate historical search is defined as a third historical search in the third historical search where at least one of the target historical search results under the general search channel is triggered, and this third historical search result under the general search channel is also triggered. The seventh historical search can be a duplicate historical search from the fifth and sixth historical searches. Therefore, we can first add the fifth and sixth counts to obtain the sum. When duplicate historical searches exist in the fifth and sixth historical searches, the sum is obtained by counting the duplicate historical searches. Therefore, to remove the duplicate count, we can subtract the seventh count from the sum and use the resulting value as the second trigger count.

[0138] S3-3-4-3: Determine the post-biased consumption data corresponding to the second search result based on the first and second trigger counts and the total number of displays.

[0139] For example, the sum of the first and second trigger counts can be determined first, and the debiased trigger rate corresponding to the second search result can be determined based on the ratio of this sum to the total number of displays.

[0140] The sum of the first and second trigger counts represents the total historical trigger count corresponding to the second search result. The total historical trigger count can be represented by (clickA|clickB), where clickA represents the number of historical searches triggered by the target historical search result obtained under the general search channel in each historical search, clickB represents the number of historical searches triggered by the third search result obtained under the general search channel in each historical search, and "|" represents an OR operation. That is, for a single historical search, if the search, under the general search channel, yields both at least one target historical search result and a third search result, and at least one result in either the target historical search result or the third search result is triggered, then only one trigger count is counted, meaning the total historical trigger count is incremented by 1. Conversely, if the search, under the general search channel, yields both at least one target historical search result and a third search result, but neither result in either the target historical search result or the third search result is triggered, then no trigger count is counted, meaning the total historical trigger count is incremented by 0.

[0141] For example, regarding music card A obtained in the current search, when determining the debiased trigger rate corresponding to music card A, the debiased trigger rate can be calculated using the following formula:

[0142] CTR=(clickA|clickB) / (impreA|impreB); (Formula 1)

[0143] Wherein, CTR represents the trigger rate after bias correction; clickA represents the number of historical searches within a preset historical time period where at least one target historical search result obtained under the general search channel was triggered (the background music corresponding to the target historical search result can be music A corresponding to music card A); clickB represents the number of historical searches within a preset historical time period where music card A obtained under the general search channel was triggered; "|" represents an OR operation, (clickA|clickB) represents the total number of historical triggers. For a single historical search, if at least one of the target historical search result and music card A corresponding to that historical search is triggered, the count is incremented by 1; if neither the target historical search result nor music card A corresponding to that historical search is triggered, the count is incremented by 0. impreA represents the number of target historical search results obtained under the general search channel within a preset historical time period. If a historical search includes at least one target historical search result under the general search channel, impreA can be incremented by 1; if a historical search does not include a target historical search result under the general search channel, impreA can be incremented by 0. impreB represents the number of music cards A obtained in the general search channel during the historical search within the preset historical time period. "|" represents the OR operation. (impreA|impreB) represents the total number of historical impressions. For a historical search, if at least one of the target historical search result and music card A is obtained in the historical search, the count can be incremented by 1. If at least one of the target historical search result and music card A is not obtained in the historical search, the count can be incremented by 0.

[0144] In one embodiment, for any second search result, the historical consumption data of the second search result under the corresponding vertical search channel may include the result consumption data of each third search result obtained under the vertical search channel corresponding to the second search result.

[0145] To determine the post-biasing consumption data for each second search result based on its historical consumption data within its respective vertical search channel, the following steps can be taken:

[0146] P1: When determining the historical search, the third number of the third search results obtained under the general search channel.

[0147] Here, the third search result can be a historical search result that is consistent with the second search result, which is required to determine the debiased consumption data, under the general search channel.

[0148] P2: From the historical searches, identify the eighth historical search that yields the third search result under the general search channel and includes the third search result under the corresponding vertical search channel; and from the historical searches, select the ninth historical search that includes the third search result under the corresponding vertical search channel.

[0149] Here, for any given historical search, this historical search can correspond to a general search channel and a vertical search channel. The vertical search channel can be the channel corresponding to the second search result for which the debiased consumption data needs to be determined. For example, if the second search result for which the debiased consumption data needs to be determined is a music card, the vertical search channel could be as follows: Figure 2 The music channel shown.

[0150] The eighth historical search can be the historical search that yielded the third search result under the general search channel and the third search result under the vertical search channel corresponding to the second search result.

[0151] The ninth historical search can be a historical search that finds the third search result within the vertical search channel corresponding to the second search result. The ninth historical search can include the eighth historical search and historical searches that find the third search result only within the vertical search channel corresponding to the second search result.

[0152] For example, taking music card A as the second search result, the eighth historical search can be a historical search within a preset historical time period that finds music card A under the general search channel and also under the music channel. The ninth historical search can be a historical search within a preset historical time period that finds music card A under the music channel.

[0153] P3: Based on the fifth difference between the third quantity and the eighth quantity of the eighth historical search, the sixth difference between the ninth quantity and the eighth quantity of the ninth historical search, the eighth quantity, and the consumption data of the third search result, determine the debiased consumption data corresponding to the second search result.

[0154] Here, the consumption data of the third search results can include historical consumption data of the third search results obtained under the general search channel and historical consumption data of the third search results obtained under the vertical search channel.

[0155] The fifth difference is used to characterize the number of historical searches that yielded the third search result only under the general search channel, and the fifth difference is used to characterize the number of historical searches that yielded the third search result only under the vertical search channel.

[0156] In practice, the number of triggered third search results can be determined based on the consumption data of the third search results. Then, the debiased consumption data corresponding to the second search result can be determined based on the ratio of the sum of the fifth, sixth, and eighth differences to the number of triggered third search results.

[0157] In one embodiment, for the above-mentioned P3, the following steps can be followed:

[0158] P3-1: Determine the target display count based on the fifth difference, the sixth difference, and the eighth quantity.

[0159] Here, the target impression count is used to represent the total historical impression count of the second search result. The target impression count can be represented by (impreB|impreC), where impreB represents the number of third search results obtained under the general search channel in the historical search, impreC represents the number of third search results obtained under the vertical search channel in the historical search, and "|" represents the OR operation. That is, for a historical search, if the historical search has a third search result under both the general search channel and the vertical search channel, it can be counted only once, that is, the target impression count is incremented by 1. If the historical search has a third search result only under the general search channel, it can be counted only once, that is, the target impression count is incremented by 1. If the historical search has a third search result only under the vertical search channel, it can be counted only once, that is, the target impression count is incremented by 1. If the historical search has no third search result under either the general search channel or the vertical search channel, it can be ignored, that is, the target impression count is incremented by 0.

[0160] For example, the fifth difference, the sixth difference, and the eighth quantity can be added together to obtain the target number of impressions.

[0161] P3-2: Based on the consumption data of the third search result, from the eighth historical search, filter out the obtained third search result and the third search result under the corresponding vertical search channel, and find that there is at least one triggered tenth historical search.

[0162] Here, the tenth historical search can include the historical search triggered only by the third search result obtained in the general search channel in the eighth historical search, the historical search triggered only by the third search result under the corresponding vertical search channel in the eighth historical search, and the historical search triggered by the third search result obtained in the general search channel and the third search result under the corresponding vertical search channel.

[0163] Taking music card A as the third search result, the consumption data of each music card A obtained from the historical searches within a preset historical time period can be used to filter out music card A obtained from the general search channel and music card A under the music channel from the historical searches. There is at least one triggered tenth historical search.

[0164] P3-3: Determine the debiased consumption data corresponding to the second search result based on the number of times the target was displayed and the number of searches in the tenth historical search.

[0165] In practice, the eleventh historical search can be filtered from the historical searches to find the third search result obtained only under the general search channel, and the twelfth historical search can be filtered to find the third search result obtained only under the vertical search channel. Then, based on the result data of the third search result, the thirteenth historical search triggered by the third search result can be filtered from the eleventh historical search, and the fourteenth historical search triggered by the third search result can be filtered from the twelfth historical search. The number of the tenth, thirteenth, and fourteenth historical searches can then be added together to obtain the target trigger count for the second search result. Here, the target trigger count represents the total historical trigger count for the second search result. The target trigger count can be represented by (clickB|clickC), where clickB represents the number of historical searches triggered by the third search result obtained under the general search channel, clickC represents the number of historical searches triggered by the third search result obtained under the vertical search channel, and "|" represents an OR operation. In other words, for a single historical search, if a third search result exists in both the general search channel and the vertical search channel, and at least one of the third search results in either channel is triggered, then it can be counted only once, meaning the target trigger count is incremented by 1. Conversely, if a third search result exists in both the general search channel and the vertical search channel, but none of the third search results in either channel are triggered, then it can be left uncounted, meaning the target trigger count is incremented by 0.

[0166] Furthermore, the debiased trigger rate can be determined based on the ratio of the number of target triggers to the number of target displays, and this debiased trigger rate can be used as the debiased consumption data corresponding to the second search result.

[0167] In one embodiment, the step of "determining the debiased consumption data corresponding to each second search result based on the historical consumption data corresponding to each target historical search result under the target genre obtained when performing historical searches for search information, and the historical consumption data of each second search result under its corresponding vertical search channel" can be implemented according to the following steps:

[0168] T1: For any second search result, determine a first number of first historical searches from the historical searches that yield at least one target historical search result.

[0169] T2: Based on the historical consumption data corresponding to each target historical search result, determine from the first historical search that each target historical search result has at least one second number of triggered second historical searches;

[0170] The specific implementation steps for T1 and T2 mentioned above can be referred to S1 and S2 above, and will not be repeated here.

[0171] T3: Determine the third trigger count based on the result consumption data of each third search result obtained under the general search channel when performing historical searches for the search information; the third search result is the same as the second search result.

[0172] Here, the third trigger count is used to represent the number of historical searches triggered by the third search result obtained under the general search channel in each historical search. That is, the third trigger count can be clickB as mentioned above.

[0173] In practice, the fifteenth historical search that yielded the third search result under the general search channel can be selected from the historical searches. Then, based on the result consumption data of each third search result, the number of historical searches triggered by the third search result can be determined from the fifteenth historical search result, and this number can be used as the third trigger count.

[0174] T4: Determine the fourth trigger number based on the result consumption data of each third search result obtained under the vertical search channel corresponding to the second search result when performing historical searches for the search information.

[0175] Here, the fourth trigger count is used to represent the number of historical searches triggered by the third search result obtained under the vertical search channel in each historical search. That is, the fourth trigger count can be clickC as mentioned above.

[0176] In practice, the sixteenth historical search that yielded the third search result under the vertical search channel can be selected from the historical searches. Then, based on the result consumption data of each third search result, the number of historical searches triggered by the third search result can be determined from the sixteenth historical search, and this number can be used as the fourth trigger number.

[0177] T5: Based on the third, first, second, third, and fourth trigger counts of each third search result obtained under the general search channel, determine the debiased consumption data corresponding to the second search result.

[0178] In practice, the number of historical searches that yielded a third search result under the vertical search channel can be determined. This number, along with the third and first search results, is summed to obtain the total number of impressions. Then, the second, third, and fourth trigger counts are summed to obtain the total number of triggers. Finally, the ratio of the total number of triggers to the total number of impressions can be used to determine the debiased consumption data corresponding to the second search result.

[0179] In one embodiment, for the above-described T5, the following steps can be performed:

[0180] T5-1: Filter out the ninth historical search result from the corresponding vertical search channel, including the third search result.

[0181] For the specific implementation steps of T5-1 above, please refer to the steps for determining the ninth historical search in P2 above.

[0182] T5-2: Determine the total number of times the target appears in the second search result based on the third number, the first number, and the ninth number of the ninth historical search.

[0183] Here, the total number of times the target appears is used to represent the total number of times the second search result appears in history.

[0184] In practice, the number of third search results obtained under the vertical search channel during the ninth historical search can be determined based on the ninth number of the ninth historical search. That is, the ninth number can be determined as impreC as mentioned above. At the same time, the third number can be determined as impreB, and the first number can be taken as impreA. Then, the total number of times the target appears can be determined using the following formula two.

[0185] Sum1=(impreA|impreB|impreC); (Formula 2)

[0186] Where Sum1 represents the total number of times the target appears, and "|" represents an OR operation. According to Formula 2 above, for a single historical search, if there are no historical search results for the target in the general search channel, and no third search result, and also no third search result in the vertical search channel, then it is not counted, meaning the total number of times the target appears is incremented by 0. If the historical search occurs in at least one of the following three scenarios: there is at least one historical search result for the target in the general search channel, there is a third search result in the general search channel, or there is a third search result in the vertical search channel, then it is counted, meaning the total number of times the target appears is incremented by 1.

[0187] In practice, the third, first, and ninth quantities mentioned above can be substituted into Formula 2 to obtain the total number of times the target appears in the second search result.

[0188] T5-3: Determine the total number of target triggers corresponding to the second search result based on the third trigger count, the second quantity, and the fourth trigger count.

[0189] Here, the total number of target triggers is used to represent the total number of historical triggers corresponding to the second search result.

[0190] In practice, the second number can be defined as clickA, the third trigger number as clickB, and the fourth trigger number as clickC. Then, the total number of times the target appears can be determined using Formula 3 below.

[0191] Sum2 = (clickA|clickB|clickC); (Formula 3)

[0192] Where Sum2 represents the total number of target triggers, and "|" represents an OR operation. According to Formula 3 above, for a single historical search, if the historical search has at least one target historical search result in the general search channel and a third search result in both the general and vertical search channels, and if the historical search has no triggered target historical search result in the general search channel and neither the general nor vertical search channels have triggered a third search result, then no statistics are counted, meaning the total number of target triggers is incremented by 0. If the historical search falls into at least one of the following three scenarios: at least one target historical search result is triggered in the general search channel, a third search result is triggered in the general search channel, or a third search result is triggered in the vertical search channel, then statistics are counted, meaning the total number of target triggers is incremented by 1.

[0193] In practice, the third trigger count, the second quantity, and the fourth trigger count can be substituted into Formula 3 to obtain the total number of target triggers corresponding to the second search result.

[0194] T5-4: Determine the debiased consumption data corresponding to the second search result based on the total number of times the target appears and the total number of times the target is triggered.

[0195] For example, the debiased trigger rate corresponding to the second search result can be determined based on the ratio of the total number of times the target is triggered to the total number of times the target appears, and the debiased trigger rate can be used as the debiased consumption data corresponding to the second search result.

[0196] For example, the debiased trigger rate can be determined according to the following formula four:

[0197] CTR = (clickA|clickB|clickC) / (impreA|impreB|impreC); (Formula 4)

[0198] CTR can represent the trigger rate after debiasing.

[0199] In one embodiment, since triggering the target historical search result under the general search channel, triggering the third historical search result under the general search channel, and triggering the third historical search result under the vertical search channel may have different degrees of impact on the debiased consumption data corresponding to the determined second search result, in order to further improve the rationality of the determined debiased consumption data, different weights can be set to determine the total number of target triggers. Specifically, for T5-3 above, it can also be implemented according to the following steps:

[0200] T5-3-1: Obtain the preset first weight, second weight, and third weight.

[0201] Here, the first weight, second weight, and third weight can all be set based on experience, and this embodiment does not impose specific limitations. Specifically, the first weight can be the weight corresponding to the third trigger count, that is, the first weight can be the weight of clickB; the second weight can be the weight corresponding to the second number, that is, the second weight can be the weight of clickA; and the third weight can be the weight of the fourth trigger count, that is, the third weight can be the weight of clickC.

[0202] T5-3-2: Determine the total number of target triggers corresponding to the second search result based on the weighted value of the first weight and the third trigger count, the weighted value of the second weight and the second number, and the weighted value of the third weight and the fourth trigger count.

[0203] In practice, the first weight can be used to weight the third trigger count to obtain a first weighted value, the second weight can be used to weight the second number to obtain a second weighted value, and the third weight can be used to weight the fourth trigger count to obtain a third weighted value. Then, the sum of the first weighted value, the second weighted value, and the third weighted value can be used as the target total number of triggers.

[0204] For example, the total number of times the target is triggered can also be determined according to Formula 5 below:

[0205] Sum2 = w1*clickA + w2*clickB + w3*clickC; (Formula 5)

[0206] Where w1 represents the second weight, w2 represents the first weight, w3 represents the third weight, w1*clickA represents the second weighted value, w2*clickB represents the first weighted value, and w3*clickC represents the third weighted value.

[0207] Optionally, a corresponding weight can be set for at least one of clickA, clickB, and clickC to determine the total number of times the target is triggered.

[0208] In one embodiment, S103 described above can be implemented according to the following steps:

[0209] S103-1: Determine the first trigger rate of each first search result based on the historical consumption data of each first search result.

[0210] For example, for each first search result, the number of times the first search result has been triggered can be determined based on the historical consumption data of that first search result during previous searches. Then, the first trigger rate of that first search result can be determined based on the number of times it has been triggered and the number of that first search result obtained under the general search channel during previous searches.

[0211] S103-2: Determine the second trigger rate for each second search result based on the debiased consumption data corresponding to each second search result.

[0212] Here, the debiased consumption data corresponding to the second search result can be used to characterize the debiased trigger rate corresponding to the second search result.

[0213] In practice, the debiased consumption data corresponding to each second search result, and the debiased trigger rate indicated by each data point, can be used as the second trigger rate for each second search result.

[0214] S103-3: Sort the first search result and the second search result based on the first trigger rate and the second trigger rate.

[0215] In practice, the first and second search results can be sorted in descending order of their trigger rates, based on the first trigger rate of each first search result and the second trigger rate of each second search result.

[0216] Those skilled in the art will understand that, in the above-described method of the specific implementation, the order in which each step is written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0217] Based on the same inventive concept, this disclosure also provides a result sorting device corresponding to the result sorting method. Since the principle of the device in this disclosure for solving the problem is similar to the result sorting method described above in this disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be described again.

[0218] like Figure 3 The diagram shown is a schematic representation of a result sorting apparatus provided in an embodiment of this disclosure, comprising:

[0219] The acquisition module 301 is used to acquire the first search results of the target genre obtained after searching for the search information in the general search channel, and the second search results of other genres besides the target genre.

[0220] The determining module 302 is used to determine the debiased consumption data corresponding to each second search result based on the historical consumption data corresponding to each target historical search result under the target genre obtained when performing historical searches for the search information, and / or the historical consumption data of each second search result under its corresponding vertical search channel; wherein the target historical search results and the second search results are associated with the same topic object;

[0221] The sorting module 303 is used to sort the first search results and the second search results based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result.

[0222] In one possible implementation, the determining module 302, when determining the debiased consumption data corresponding to each of the second search results based on the historical consumption data corresponding to each historical search result under the target genre obtained during historical searches for the search information, is configured to:

[0223] For any second search result, determine a first number of first historical searches from the historical searches that yield at least one target historical search result;

[0224] Based on the historical consumption data corresponding to each target historical search result, from the first historical search, it is determined that each target historical search result has at least one second number of triggered second historical searches;

[0225] Based on the third quantity of the third search result obtained under the general search channel during the historical search, the result consumption data corresponding to the third search result, the first quantity, and the second quantity, the debiased consumption data corresponding to the second search result is determined, and the third search result is the search result consistent with the second search result.

[0226] In one possible implementation, the determining module 302, when determining the debiased consumption data corresponding to the second search result based on the third quantity of the third search result obtained under the general search channel during historical searches, the result consumption data corresponding to the third search result, the first quantity, and the second quantity, is used to:

[0227] From the historical searches, determine the third historical search that yielded the third search result and at least one of the target historical search results;

[0228] The total number of displays is determined based on the first difference between the third quantity and the fourth quantity of the third historical search, the second difference between the first quantity and the third quantity, and the fourth quantity.

[0229] Based on the second quantity, the result consumption data corresponding to the third search result, and the total number of displays, determine the debiased consumption data corresponding to the second search result.

[0230] In one possible implementation, the determining module 302, when determining the debiased consumption data corresponding to the second search result based on the second quantity, the result consumption data corresponding to the third search result, and the total number of displays, is used to:

[0231] Based on the result consumption data corresponding to the third search result, determine the total number of triggers corresponding to the third search result, and select the fifth historical search result triggered by the third search result from the third historical search results;

[0232] From the third historical search, each of the corresponding target historical search results is selected to have at least one triggered sixth historical search;

[0233] The first trigger count is determined based on the third difference between the total number of triggers and the fifth number of the fifth historical search, and the fourth difference between the second number and the sixth number of the sixth historical search.

[0234] Based on the first number of triggers and the total number of displays, determine the debiased consumption data corresponding to the second search result.

[0235] In one possible implementation, the determining module 302, when determining the post-biased consumption data corresponding to the second search result based on the first trigger count and the total number of displays, is used to:

[0236] From the third historical search, select the corresponding third search result that was triggered and the corresponding target historical search result that has at least one triggered seventh historical search.

[0237] The second trigger count is determined based on the fifth count, the sixth count, and the seventh count of the seventh historical search.

[0238] Based on the first number of triggers, the second number of triggers, and the total number of displays, the debiased consumption data corresponding to the second search result is determined.

[0239] In one possible implementation, for any second search result, the historical consumption data of the second search result under the corresponding vertical search channel includes the result consumption data of each third search result obtained under the vertical search channel corresponding to the second search result;

[0240] The determining module 302, when determining the debiased consumption data corresponding to each of the second search results based on the historical consumption data of each of the second search results under their respective corresponding vertical search channels, is used for:

[0241] When determining the historical search results, the third number of third search results obtained under the general search channel;

[0242] From the historical searches, determine the eighth historical search that obtained the third search result under the general search channel and whose corresponding vertical search channel includes the third search result; and from the historical searches, filter out the ninth historical search that includes the third search result under the corresponding vertical search channel.

[0243] Based on the fifth difference between the third quantity and the eighth quantity of the eighth historical search, the sixth difference between the ninth quantity of the ninth historical search and the eighth quantity, the eighth quantity, and the result consumption data of the third search result, the debiased consumption data corresponding to the second search result is determined.

[0244] In one possible implementation, the determining module 302, when determining the debiased consumption data corresponding to the second search result based on the fifth difference between the third quantity and the eighth quantity of the eighth historical search, the sixth difference between the ninth quantity of the ninth historical search and the eighth quantity, the eighth quantity, and the consumption data resulting from the third search result, is configured to:

[0245] The target number of displays is determined based on the fifth difference, the sixth difference, and the eighth quantity.

[0246] Based on the consumption data of the third search result, from the eighth historical search, the obtained third search result and the third search result under the corresponding vertical search channel, there is at least one triggered tenth historical search.

[0247] Based on the number of times the target was displayed and the number of the tenth historical search, the debiased consumption data corresponding to the second search result is determined.

[0248] In one possible implementation, the determining module 302, when determining the debiased consumption data corresponding to each second search result based on the historical consumption data corresponding to each target historical search result under the target genre obtained during historical searches for the search information, and the historical consumption data of each second search result under its corresponding vertical search channel, is used to:

[0249] For any second search result, determine a first number of first historical searches from the historical searches that yield at least one target historical search result;

[0250] Based on the historical consumption data corresponding to each target historical search result, from the first historical search, it is determined that each target historical search result has at least one second number of triggered second historical searches;

[0251] The third trigger count is determined based on the result consumption data of each third search result obtained under the general search channel when performing historical searches for the search information; the third search result is the same as the second search result.

[0252] The fourth trigger count is determined based on the result consumption data of each third search result obtained under the vertical search channel corresponding to the second search result when performing historical searches for the search information.

[0253] Based on the third quantity, the first quantity, the second quantity, the third trigger count, and the fourth trigger count of each third search result obtained under the general search channel, determine the debiased consumption data corresponding to the second search result.

[0254] In one possible implementation, the determining module 302, when determining the debiased consumption data corresponding to the second search result based on the third quantity, the first quantity, the second quantity, the third trigger count, and the fourth trigger count of each third search result obtained under the general search channel, is configured to:

[0255] From the historical searches, select the ninth historical search that includes the third search result under the corresponding vertical search channel;

[0256] Based on the third quantity, the first quantity, and the ninth quantity of the ninth historical search, determine the total number of times the target appears corresponding to the second search result;

[0257] Based on the third trigger count, the second quantity, and the fourth trigger count, determine the total number of target triggers corresponding to the second search result;

[0258] Based on the total number of times the target appears and the total number of times the target is triggered, the debiased consumption data corresponding to the second search result is determined.

[0259] In one possible implementation, the determining module 302, when determining the total number of target triggers corresponding to the second search result based on the third trigger count, the second quantity, and the fourth trigger count, is configured to:

[0260] Obtain the preset first weight, second weight, and third weight;

[0261] The total number of triggers corresponding to the second search result is determined based on the weighted value of the first weight and the third trigger count, the weighted value of the second weight and the second quantity, and the weighted value of the third weight and the fourth trigger count.

[0262] In one possible implementation, the sorting module 303, when sorting the first and second search results based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result, is configured to:

[0263] Based on the historical consumption data of each of the first search results, determine the first trigger rate of each of the first search results;

[0264] Based on the debiased consumption data corresponding to each second search result, determine the second trigger rate of each second search result;

[0265] The first and second search results are sorted based on the first trigger rate and the second trigger rate.

[0266] The processing flow of each module in the device and the interaction flow between each module can be referred to the relevant descriptions in the above method embodiments, and will not be detailed here.

[0267] Based on the same technical concept, embodiments of this application also provide a computer device. (Refer to...) Figure 4 The diagram shown is a structural schematic of a computer device provided in an embodiment of this application, comprising:

[0268] The system includes a processor 41, a memory 42, and a bus 43. The memory 42 stores machine-readable instructions executable by the processor 41. The processor 41 executes these machine-readable instructions, and when executed, performs the following steps: S101: Obtaining the first search results for the target genre obtained after searching the search information in the general search channel, and the second search results for other genres associated with the first search results; S102: Determining the debiased consumption data corresponding to each second search result based on the historical consumption data corresponding to each target historical search result under the target genre obtained during historical searches of the search information, and / or the historical consumption data of each second search result under its corresponding vertical search channel; wherein the target historical search results and the second search results are associated with the same topic object; and S103: Ranking the first and second search results based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result.

[0269] The aforementioned memory 42 includes a main memory 421 and an external memory 422. The main memory 421, also known as internal memory, is used to temporarily store the computational data in the processor 41, as well as the data exchanged with external memory such as a hard disk. The processor 41 exchanges data with the external memory 422 through the main memory 421. When the computer device is running, the processor 41 and the memory 42 communicate through the bus 43, so that the processor 41 executes the execution instructions mentioned in the above method embodiments.

[0270] This disclosure also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, performs the steps of the result sorting method described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0271] The computer program product of the result sorting method provided in this disclosure includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the steps of the result sorting method described in the above method embodiments. For details, please refer to the above method embodiments, which will not be repeated here.

[0272] The computer program product can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0273] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here. In the several embodiments provided in this disclosure, it should be understood that the disclosed device and method can be implemented in other ways. The device embodiments described above are merely illustrative. For example, the division of units is only a logical functional division; in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined, or some features may be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection may be through some communication interfaces; the indirect coupling or communication connection of devices or units may be electrical, mechanical, or other forms.

[0274] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0275] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0276] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0277] If the technical solution of this application involves personal information, the product using this technical solution has clearly informed the user of the personal information processing rules and obtained the user's voluntary consent before processing the personal information. If the technical solution of this application involves sensitive personal information, the product using this technical solution has obtained the user's separate consent before processing the sensitive personal information, and also meets the requirement of "express consent". For example, at personal information collection devices such as cameras, clear and prominent signs are set up to inform users that they have entered the scope of personal information collection and that personal information will be collected. If an individual voluntarily enters the collection scope, it is deemed that they have agreed to the collection of their personal information; or on the personal information processing device, with clear signs / information informing users of the personal information processing rules, authorization is obtained from the user through pop-up information or by asking the user to upload their personal information; wherein, the personal information processing rules may include information such as the personal information processor, the purpose of personal information processing, the processing method, and the types of personal information processed.

[0278] Finally, it should be noted that the above-described embodiments are merely specific implementations of this disclosure, used to illustrate the technical solutions of this disclosure, and not to limit it. The protection scope of this disclosure is not limited thereto. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this disclosure. Such modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure, and should all be covered within the protection scope of this disclosure. Therefore, the protection scope of this disclosure should be determined by the protection scope of the claims.

Claims

1. A result sorting method, characterized in that, include: After searching for the current search information in the general search channel, obtain the first search results for each target genre, and the second search results for each genre other than the target genre. Based on the historical consumption data corresponding to each target historical search result under the target genre obtained when performing historical searches for the search information, and / or the historical consumption data of each second search result under its corresponding vertical search channel, the post-biased consumption data corresponding to each second search result is determined; wherein, the target historical search result and the second search result are associated with the same topic object, the historical consumption data represents the consumption information of the target historical search result, including at least one of whether the target historical search result is triggered, whether it is favorited, and whether it is marked, the post-biased consumption data is the consumption data obtained after considering the impact of the historical consumption data corresponding to the target historical search result and / or the historical consumption data under the vertical search channel on the consumption data of the second search result, and the post-biased consumption data represents at least one of the trigger rate and usage rate of the second search result; Based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result, the first search results and the second search results are sorted.

2. The method according to claim 1, characterized in that, Based on the historical consumption data corresponding to each target historical search result under the target genre obtained during historical searches for the search information, the post-biased consumption data corresponding to each second search result is determined, including: For any second search result, determine a first number of first historical searches from the historical searches that yield at least one target historical search result; Based on the historical consumption data corresponding to each target historical search result, from the first historical search, it is determined that each target historical search result has at least one second number of triggered second historical searches; Based on the third quantity of the third search result obtained under the general search channel during the historical search, the result consumption data corresponding to the third search result, the first quantity, and the second quantity, the debiased consumption data corresponding to the second search result is determined, and the third search result is the search result consistent with the second search result.

3. The method according to claim 2, characterized in that, The step of determining the debiased consumption data corresponding to the second search result based on the third quantity of the third search result obtained under the general search channel during historical searches, the result consumption data corresponding to the third search result, the first quantity, and the second quantity includes: From the historical searches, determine the third historical search that yielded the third search result and at least one of the target historical search results; The total number of displays is determined based on the first difference between the third quantity and the fourth quantity of the third historical search, the second difference between the first quantity and the third quantity, and the fourth quantity. Based on the second quantity, the result consumption data corresponding to the third search result, and the total number of displays, determine the debiased consumption data corresponding to the second search result.

4. The method according to claim 3, characterized in that, The step of determining the post-biased consumption data corresponding to the second search result based on the second quantity, the result consumption data corresponding to the third search result, and the total number of displays includes: Based on the result consumption data corresponding to the third search result, determine the total number of triggers corresponding to the third search result, and select the fifth historical search result triggered by the third search result from the third historical search results; From the third historical search, each of the corresponding target historical search results is selected to have at least one triggered sixth historical search; The first trigger count is determined based on the third difference between the total number of triggers and the fifth number of the fifth historical search, and the fourth difference between the second number and the sixth number of the sixth historical search. Based on the first number of triggers and the total number of displays, determine the debiased consumption data corresponding to the second search result.

5. The method according to claim 4, characterized in that, The step of determining the post-biased consumption data corresponding to the second search result based on the first trigger count and the total number of displays includes: From the third historical search, select the corresponding third search result that was triggered and the corresponding target historical search result that has at least one triggered seventh historical search. The second trigger count is determined based on the fifth count, the sixth count, and the seventh count of the seventh historical search. Based on the first number of triggers, the second number of triggers, and the total number of displays, the debiased consumption data corresponding to the second search result is determined.

6. The method according to claim 1, characterized in that, For any second search result, the historical consumption data of the second search result under the corresponding vertical search channel includes the result consumption data of each third search result obtained under the vertical search channel corresponding to the second search result; Based on the historical consumption data of each second search result under its corresponding vertical search channel, determine the post-biased consumption data corresponding to each second search result, including: When determining the historical search results, the third number of third search results obtained under the general search channel; From the historical searches, determine the eighth historical search that obtained the third search result under the general search channel and whose corresponding vertical search channel includes the third search result; and from the historical searches, filter out the ninth historical search that includes the third search result under the corresponding vertical search channel. Based on the fifth difference between the third quantity and the eighth quantity of the eighth historical search, the sixth difference between the ninth quantity of the ninth historical search and the eighth quantity, the eighth quantity, and the result consumption data of the third search result, the debiased consumption data corresponding to the second search result is determined.

7. The method according to claim 6, characterized in that, The step of determining the debiased consumption data corresponding to the second search result based on the fifth difference between the third quantity and the eighth quantity of the eighth historical search, the sixth difference between the ninth quantity of the ninth historical search and the eighth quantity, the eighth quantity, and the consumption data of the third search result includes: The target number of displays is determined based on the fifth difference, the sixth difference, and the eighth quantity. Based on the consumption data of the third search result, from the eighth historical search, the obtained third search result and the third search result under the corresponding vertical search channel, there is at least one triggered tenth historical search. Based on the number of times the target was displayed and the number of the tenth historical search, the debiased consumption data corresponding to the second search result is determined.

8. The method according to claim 1, characterized in that, Based on the historical consumption data corresponding to each target historical search result under the target genre obtained during historical searches for the search information, and the historical consumption data of each second search result under its corresponding vertical search channel, the post-biased consumption data corresponding to each second search result is determined, including: For any second search result, determine a first number of first historical searches from the historical searches that yield at least one target historical search result; Based on the historical consumption data corresponding to each target historical search result, from the first historical search, it is determined that each target historical search result has at least one second number of triggered second historical searches; The third trigger count is determined based on the result consumption data of each third search result obtained under the general search channel when performing historical searches for the search information; the third search result is the same as the second search result. The fourth trigger count is determined based on the result consumption data of each third search result obtained under the vertical search channel corresponding to the second search result when performing historical searches for the search information. Based on the third quantity, the first quantity, the second quantity, the third trigger count, and the fourth trigger count of each third search result obtained under the general search channel, determine the debiased consumption data corresponding to the second search result.

9. The method according to claim 8, characterized in that, Based on the third quantity, first quantity, second quantity, third trigger count, and fourth trigger count of each third search result obtained under the general search channel, determine the post-biased consumption data corresponding to the second search result, including: From the historical searches, select the ninth historical search that includes the third search result under the corresponding vertical search channel; Based on the third quantity, the first quantity, and the ninth quantity of the ninth historical search, determine the total number of times the target appears corresponding to the second search result; Based on the third trigger count, the second quantity, and the fourth trigger count, determine the total number of target triggers corresponding to the second search result; Based on the total number of times the target appears and the total number of times the target is triggered, the debiased consumption data corresponding to the second search result is determined.

10. The method according to claim 9, characterized in that, Based on the third trigger count, the second quantity, and the fourth trigger count, the total target trigger count corresponding to the second search result is determined, including: Obtain the preset first weight, second weight, and third weight; The total number of triggers corresponding to the second search result is determined based on the weighted value of the first weight and the third trigger count, the weighted value of the second weight and the second quantity, and the weighted value of the third weight and the fourth trigger count.

11. The method according to claim 1, characterized in that, The process of sorting the first and second search results based on historical consumption data of each first search result and debiased consumption data corresponding to each second search result includes: Based on the historical consumption data of each of the first search results, determine the first trigger rate of each of the first search results; Based on the debiased consumption data corresponding to each second search result, determine the second trigger rate of each second search result; The first and second search results are sorted based on the first trigger rate and the second trigger rate.

12. A result sorting device, characterized in that, include: The acquisition module is used to acquire the first search results of the target genre obtained after searching for the search information in the general search channel, and the second search results of other genres besides the target genre. The determining module is configured to determine the post-biased consumption data corresponding to each second search result based on the historical consumption data corresponding to each target historical search result under the target genre obtained during historical searches for the search information, and / or the historical consumption data of each second search result under its corresponding vertical search channel; wherein the target historical search results and the second search results are associated with the same topic object, the historical consumption data represents the consumption information of the target historical search results, including at least one of whether the target historical search results are triggered, whether they are favorited, and whether they are marked, the post-biased consumption data is the consumption data obtained after considering the impact of the historical consumption data corresponding to the target historical search results and / or the historical consumption data under the vertical search channel on the consumption data of the second search results, and the post-biased consumption data represents at least one of the trigger rate and usage rate of the second search results; The sorting module is used to sort the first search results and the second search results based on the historical consumption data of each first search result and the debiased consumption data corresponding to each second search result.

13. A computer device, characterized in that, include: A processor and a memory, the memory storing machine-readable instructions executable by the processor, the processor executing the machine-readable instructions stored in the memory, wherein when the machine-readable instructions are executed by the processor, the processor performs the steps of the result sorting method as described in any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a computer device, performs the steps of the result sorting method as described in any one of claims 1 to 11.

Images