CN117235352A

CN117235352A - Search result ordering method, device, equipment and storage medium

Info

Publication number: CN117235352A
Application number: CN202311111426.XA
Authority: CN
Inventors: 王鑫宇; 张永华
Original assignee: Beijing Zitiao Network Technology Co Ltd
Current assignee: Beijing Zitiao Network Technology Co Ltd
Priority date: 2023-08-30
Filing date: 2023-08-30
Publication date: 2023-12-15

Abstract

The application provides a search result ordering method, a device, equipment and a storage medium, wherein the method comprises the following steps: determining at least two recommended words and at least two search results according to search words input by a user, wherein the recommended words are historical search words comprising the search words; determining a ranking score of each search result according to the search word, the at least two search results and the at least two recommended words; and sorting the at least two search results according to the sorting score. The application can order the search content wanted by the user to the front of the search result, thereby improving the search efficiency.

Description

Search result ordering method, device, equipment and storage medium

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a search result ordering method, device, equipment and storage medium.

Background

The search mode is obtained by searching, so that the user can initiate search in real time in the process of inputting search words and feed back search results to the user, and the advantage that the user initiates search by clicking a search control or a carriage return control and the like is avoided, and the method is gradually applied to different Application software (Application). For example, fig. 1a to 1c show the effect obtained by the search.

However, when the user performs content searching based on the search word in the support search-and-get application software, if the search word input by the user is shorter, a larger search range is determined based on the shorter search word, which results in a larger number of search results obtained based on the search word, so that the user needs to spend a great deal of time to search for the desired search content from a plurality of search results, and the search efficiency is low.

Disclosure of Invention

The application provides a search result ordering method, a device, equipment and a storage medium, which can order the search content wanted by a user to the front of the search result, thereby improving the search efficiency.

In a first aspect, an embodiment of the present application provides a search result sorting method, including:

determining at least two recommended words and at least two search results according to search words input by a user, wherein the recommended words are historical search words comprising the search words;

determining a ranking score of each search result according to the search word, the at least two search results and the at least two recommended words;

and sorting the at least two search results according to the sorting score.

In a second aspect, an embodiment of the present application provides a search result sorting apparatus, including:

the first determining module is used for determining at least two recommended words and at least two search results according to the search words input by the user;

a second determining module, configured to determine a ranking score of each search result according to the search term, the at least two search results, and the at least two recommended terms;

and the result ordering module is used for ordering the at least two search results according to the ordering score.

In a third aspect, an embodiment of the present application provides an electronic device, including:

a processor and a memory for storing a computer program, the processor being adapted to invoke and run the computer program stored in the memory for performing the search result ordering method as described in the embodiments of the first aspect or implementations thereof.

In a fourth aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program that causes a computer to perform the search result ranking method as described in the first aspect embodiment or implementations thereof.

In a fifth aspect, embodiments of the present application provide a computer program product comprising program instructions which, when run on an electronic device, cause the electronic device to perform a search result ordering method as described in the embodiments of the first aspect or implementations thereof.

The technical scheme disclosed by the embodiment of the application has at least the following beneficial effects:

according to the search words input by the user, a plurality of recommended words and a plurality of search results which are associated with the search words are determined, the sorting score of each search result is determined according to the search words, the recommended words and the search results, and then the search results are sorted according to the sorting score, so that the search content wanted by the user can be sorted in front of the search results, and the search efficiency is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIGS. 1 a-1 c are graphs of a search effect of an application supporting a search-by-search modality;

FIG. 2 is a flowchart of a search result sorting method according to an embodiment of the present application;

FIG. 3a is a schematic diagram of the latter of ranking search results in a conventional manner;

FIG. 3b is a schematic diagram of a search result ranking determined from a search term entered by a user, provided by an embodiment of the present application;

FIG. 4 is a flow chart of determining a ranking score for each search result provided by an embodiment of the present application;

FIG. 5 is a schematic diagram of determining a ranking score for each search result based on a search term, at least two recommended terms, and at least two search results provided by an embodiment of the present application;

FIG. 6 is a flowchart of another method for sorting search results according to an embodiment of the present application;

FIG. 7 is a flowchart of yet another method for sorting search results according to an embodiment of the present application;

FIG. 8 is a schematic block diagram of a search result ordering apparatus provided by an embodiment of the present application;

fig. 9 is a schematic block diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.

It should be noted that the terms "first," "second," and the like in the description and the claims of the present application and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the application described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.

In embodiments of the application, the words "exemplary" or "such as" are used to mean that any embodiment or aspect of the application described as "exemplary" or "such as" is not to be interpreted as preferred or advantageous over other embodiments or aspects. Rather, the use of words such as "exemplary" or "such as" is intended to present related concepts in a concrete fashion.

In the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more, i.e., at least two. "at least one" means one or more.

Aiming at the problems that when a user searches for content by utilizing search words based on support, namely search and acquisition application software, the search range determined based on the shorter search words is larger when the search words input by the user are shorter, so that the number of search results acquired based on the shorter search words is larger, a great deal of time is required for the user to search for the self wanted search content from a plurality of search results, and the search effect is low. The application provides a search result ordering scheme, by which search contents intended by a user can be ordered to the front of search results, thereby improving search efficiency.

The technical scheme of the application is described in detail through some embodiments. The embodiments described below may be combined with each other and may not be described in detail in some embodiments for the same or similar concepts or processes.

Fig. 2 is a flowchart of a search result sorting method according to an embodiment of the present application. The search result sorting method provided by the embodiment of the application can be executed by the search result sorting device. The search result ordering means may be comprised of hardware and/or software and may be integrated in an electronic device. Optionally, the electronic device of the present application may be various terminal devices, and exemplary electronic devices may be tablet computers, smart phones (such as Android mobile phones, IOS mobile phones, windows phone mobile phones, etc.), notebook computers, personal digital assistants (personal digital assistant, PDA), wearable devices, smart televisions, smart screens, high-definition televisions, 4K televisions, etc., which do not limit the types of electronic devices. The terminal device may be a User Equipment (UE), a terminal, a User Equipment, or the like, and is not limited in this regard.

As shown in fig. 2, the method comprises the steps of:

s101, determining at least two recommended words and at least two search results according to search words input by a user, wherein the recommended words are historical search words comprising the search words.

S102, determining the sorting score of each search result according to the search word, at least two search results and at least two recommended words.

S103, sorting at least two search results according to the sorting score.

Optionally, in the process that the user uses any application software supporting the search form, the user can input the search word in a search box provided by the application software, so that the electronic equipment searches a plurality of search results matched with the search word in the database in real time according to the process that the user inputs the search word. Wherein the search term may be, but is not limited to: chinese, pinyin, size english, and digits.

The application software can be software in any field, such as any music software or video playing software in the video and audio field.

The search results may be video, pictures, documents, or other forms of content, to which the present application is not limited in any way.

The database may be determined based on the type of application software. For example, when the application software type is music class software, the database may be selected as the music resource database. For another example, when the application software is document-type software, the database may be selected as a document resource database, and the present application does not limit the database.

For example, when a user uses a certain piece of music software, a search word "r" can be input in a search box provided by the music software, and the electronic device screens a plurality of matched search results with prefix information "r" from a music resource library in real time according to the search word "r" input by the user. For another example, when the user inputs the search term "ri" in the search box provided by the music software, the electronic device may screen the matched plurality of search results with prefix information "ri" from the music resource library in real time according to the search term "ri" input by the user.

In some embodiments, the present application may also determine at least two associated recommended words from the search words entered by the user, so that the search words entered by the user may be supplemented based on the determined recommended words, thereby laying a foundation for ordering the search content desired by the user to a previous location of the search results.

The search content emphasis points corresponding to different regions and/or different application software are considered to be different. For example, for music software, users in different regions may be different for familiar or favorite singers, such as a search term "ba" entered by a user in western European regions, as opposed to a search result obtained by a search term "ba" entered by a user in the middle subunit regions. For another example, for cross-domain software such as music software and news software, music software focuses on recommending singers or songs to users, and news software focuses on recommending latest information to users, so when users input the same search word "learn" in different types of application software, the search results obtained by the different types of application software according to the search word "learn" are also different.

Therefore, when determining the associated at least two recommended words according to the search words input by the user, the application can firstly determine the region where the user is located, and then determine the target dictionary corresponding to the region in the currently used application software based on the region where the user is located. Then, at least two recommended words corresponding to the search word are searched in the target dictionary.

In the application, the structure of the dictionary corresponding to the region can be selected as a key-value structure, and the dictionary can be updated periodically. Wherein the key is a search word, the value includes two parts of content, the first part is a plurality of recommended words associated with the search word, and the second part is an occurrence probability of each recommended word. Illustratively, assuming that the region where a user is located is australia, the region where the user is located is simply referred to as "AU" in australia, and the target dictionary corresponding to "AU" may be as shown in table 1 below.

TABLE 1

Therefore, when searching at least two recommended words corresponding to the search word in the target dictionary, all recommended words associated with the key value can be searched in the target dictionary by taking the search word input by the user as the key value. That is, the dictionary in the application software has a correspondence relationship with the region, that is, different regions have different dictionaries.

In the application, the associated at least two recommended words are determined based on the search words input by the user, and the prefix information is selected as all historical search words of the search words. For example, when the search term is "ta", it may be determined that the recommended term including the prefix "ta" is selectable as "tankxxx", "taylor aaa", and "tame bbb" in the target dictionary based on "ta".

The occurrence probability of each recommended word may be obtained by counting historical query data in application software. For example, if 53.8% of users selecting the recommended word "baby xxx" are counted based on the historical query data, the occurrence probability of the recommended word "baby xxx" is 0.538. As another example, if 23.1% of users have clicked on the recommended word "baby" as the end of the search based on historical query data statistics, then the probability of occurrence of the recommended word "baby" is 0.231.

After determining a plurality of search results and a plurality of recommended words corresponding to the search words input by the user, the application can determine the ranking score of each search result according to the plurality of search results, the plurality of recommended words and the search words input by the user. The plurality of search results is then ranked based on the ranking score for each search result.

In some optional embodiments, considering that the determined recommended word is a historical search word with prefix information as a search word input by the user, the present application optionally fuses the search word with at least two recommended words, so as to complement the search word by the recommended word, so that the fused first fused search word is more prone to the recommended word with high occurrence probability. In addition, the application also carries out similarity matching on the search word and each recommended word with each search result respectively, fuses the two types of similarity results according to each search result to obtain a second fused search word corresponding to each search result, so that the fused second fused search word is more prone to the corresponding search result, namely, the second fused search word can be closer to the presentation form of the corresponding search result.

Further, a first relevance of the first fused search term and each search result, and a second relevance of the second fused search term and each search result corresponding to each search result are calculated, and a ranking score of each search result is determined according to the first relevance and the second relevance corresponding to each search result. Thus, the plurality of search results obtained are ranked in order from high to low based on the ranking score of each search result. Therefore, the method and the device can realize the supplement of the short search words input by the user based on the determined recommended words, so that when the user searches for the content based on the short search words, a higher sorting score can be provided for the content which the user wants to search, the search content which the user wants can be sorted to the position in front of the search result, and the user can conveniently and quickly find the search content which the user wants to search.

For example, when a search word input by a user in a search box of a certain music software is "Ri", determining an associated recommended word and an occurrence probability of the recommended word in a target dictionary corresponding to a region where the user is located through the search word "Ri" is: [ Rihanxx,0.222], [ ritaccc,0.148], [ scriptddd, 0.139], [ riverxyy, 0.083], [ ritzzz,0.083]. And, the search results determined according to the search term "Ri" include: artist: RIEXX, artist: RIOZZ, artist: rihanxx, and the like. A conventional effect diagram of ranking search results may be as shown in fig. 3 a. The effect diagram of the application after determining the ranking score of each search result based on the recommended word, the search word and the search result and ranking at least two search results based on the ranking score of each search result can be shown in fig. 3 b. Based on fig. 3b, the application can rank the search results "Rihanxx" and "ritzzz" that the user wants to acquire at the first 2 positions of all the search results, so that the user can acquire the search content that the user wants to search for more quickly.

According to the search result sorting method provided by the embodiment of the application, the plurality of recommended words and the plurality of search results which are associated with the search words are determined according to the search words input by the user, the sorting score of each search result is determined according to the search words, the plurality of recommended words and the plurality of search results, and the plurality of search results are sorted according to the sorting score, so that the search content which is wanted by the user can be sorted in front of the search results, and the search efficiency is improved.

Based on the foregoing embodiments, the following further explains the determination of the ranking score of each search result according to the search term, at least two search results and at least two recommended terms in the present application, with reference to fig. 4 and 5. As shown in fig. 4, the step S102 includes the following steps S102-1 to S102-3:

s102-1, determining a first fusion search word according to the search word and each recommended word.

The expression form of the first fusion search word can be selected as a vector form, namely the first fusion search word is a first fusion search word vector.

In some alternative embodiments, the first fused search term may be determined by determining the probability of occurrence of the search term and the probability of occurrence of each recommended term, and based on the probability of occurrence of the search term and the probability of occurrence of each recommended term.

The probability of occurrence of a search term entered by a user in this search operation is considered to be known, i.e., one hundred percent. That is, the occurrence probability of the search word input by the user is 1. The occurrence probability of each recommended word is stored in the dictionary in advance, so that the occurrence probability of each recommended word can be obtained from the target dictionary while at least two recommended words are searched in the target dictionary according to the search word input by the user.

In some alternative embodiments, the determining the first fused search term according to the occurrence probability of the search term and the occurrence probability of each recommended term may include, but is not limited to, the following cases:

in the first case, the occurrence probability of the search word and the occurrence probability of each recommended word are summed, and the obtained sum value is used as a first fusion search word.

In the second case, a weighted sum of the occurrence probability of the search word and the occurrence probability of each recommended word is calculated, and the obtained weighted sum is used as a first fusion search word.

The above calculation of the weighted sum value may be understood as calculating a first product of the occurrence probability of the search word and the first weight, and a second product of each recommended word and the respective corresponding second weight. Then, a sum of the first product and the second product is calculated, and the calculated weighted sum is used as a first fusion search term.

The first weight and each second weight are adjustable parameters, and are specifically flexibly set according to actual needs, and are not limited herein.

The search term specifically refers to a search term input by a user.

S102-2, determining a second fusion search word corresponding to each search result according to the first similarity between the search word and each search result and the second similarity between each recommended word and each search result.

The expression form of the second fusion search word can be selected as a vector form, namely the second fusion search word is a second fusion search word vector.

Optionally, the method and the device calculate the first similarity between the search word input by the user and each search result, and calculate the second similarity between each recommended word and each search result, and optionally realize the calculation by using a similarity algorithm; alternatively, the above search word and each search result may be input as input values to a matching model to determine a first similarity between the search word and each search result by the matching model, and each recommended word and each search result may be input as input values to a matching model to determine a second similarity between each recommended word and each search result by the matching model, and so on, the present application does not limit the implementation of determining the similarity.

The above matching model may be understood as any network model that supports determining the similarity between two data, such as a neural network model or a deep network model, and is not limited in any way herein. In the application, when the matching model is a neural network model, the network model can be selected as DeepNet and the like.

In the present application, the similarity algorithm may be selected from, but not limited to: cosine similarity algorithm, euclidean distance, manhattan distance, etc.

In consideration of the search word, the recommended word, and the search result input by the user, the text character string may be selected, so that the similarity between the search word and the search result, and the similarity between the recommended word and the search result are determined more conveniently. According to the application, the search words, recommended words and search results input by the user are optionally converted into vector expression forms. Then, a first similarity between the search term and each search result is determined, and a second similarity between the recommended term and each search result is determined, using a similarity algorithm or a matching model.

Further, after calculating the first similarity between the search word and each search result and the second similarity between each recommended word and each search result, the present application optionally performs weighted summation or sums the first similarity and the second similarity corresponding to each search result with each search result as a unit to obtain a sum value. The sum is then determined as a second fused search term corresponding to each search result.

That is, each search result corresponding to the search term input by the user corresponds to one second fused search term, so that it can be ensured that each second fused search term is closer to a form more similar to the corresponding search result.

The weight of the first similarity and the weight of the second similarity are adjustable parameters, and are specifically and flexibly set according to actual needs, and are not limited herein.

It should be noted that, the execution sequence of the step S102-1 and the step S102-2 may be that the step S102-1 is executed first and then the step S102-2 is executed. Alternatively, step S102-2 may be performed first, and then step S102-1 may be performed. Alternatively, the step S102-1 and the step S102-2 may be performed in parallel, and the present application is not limited in this respect.

S102-3, determining the sorting score of each search result according to the first fusion search word, each second fusion search word and each search result.

In some alternative embodiments, the present application determines a ranking score for each search result, which may include the steps of:

step 1, determining a third similarity between the first fusion search word and each search result and a fourth similarity between each search result and a second fusion search word corresponding to the search result.

And step 2, determining the sorting score of each search result according to the third similarity and the fourth similarity corresponding to each search result.

The implementation principle of determining the third similarity and the fourth similarity corresponding to each search result in step 1 is the same as or similar to the implementation principle of determining the first similarity and the second similarity corresponding to each search result in step S102-2, and specific reference may be made to the foregoing step S102-2, which is not repeated herein.

In some alternative embodiments, when determining the ranking score of each search result in step 2, the following methods are optionally included, but are not limited to:

in a first mode, the third similarity and the fourth similarity corresponding to each search result are used as input values and are input into a scoring model, and the scoring model is used for processing the third similarity and the fourth similarity corresponding to each search result to obtain the ranking score of each search result.

The scoring model may be any network model that supports scoring based on at least two similarities, or a network model that is trained based on a large number of similarity sample data, which the present application is not limited in any way.

And secondly, determining the sorting score of each search result according to the third similarity and the fourth similarity corresponding to each search result according to a preset scoring rule.

The preset scoring rule can be any scoring calculation method or scoring algorithm, and the application is not limited in any way. It may be appreciated that the preset scoring rule may be calculated by calculating the third similarity and the fourth similarity, and quantitatively evaluate each search result corresponding to the third similarity and the fourth similarity, so as to implement the evaluation of each search result. Wherein the evaluation of each search result may be embodied by a score.

For a clearer description of steps S102-1 to S102-3, an example is described below with reference to fig. 5.

As shown in fig. 5, assuming that the search word input by the user is xx, the number of recommended words determined according to the search word xx is 5, and the recommended words are respectively: recommended word 1 (sug 1 in the figure), recommended word 2 (sug 2 in the figure), recommended word 3 (sug 3 in the figure), recommended word 4 (sug 4 in the figure) and recommended word 5 (sug 5 in the figure), and the occurrence probability of recommended word 1 is probability a, the occurrence probability of recommended word 2 is probability b, the occurrence probability of recommended word 3 is probability c, the occurrence probability of recommended word 4 is probability d and the occurrence probability of recommended word 5 is probability e. The number of search results specified by the search term xx is 10, and is set to be search result 10, search result 11, search result 12, search result 13, search result 14, search result 15, search result 16, search result 17, search result 18, and search result 19, respectively. Then a first fused search term (weighted query in the figure) may be determined based on the probability of occurrence of the search term xx and the probabilities of occurrence of the 5 recommended terms, respectively, and a second fused search term (Doc Attentioned Query in the figure) corresponding to each search result may be determined based on the first similarity between the search term xx and each search result and the second similarity between each recommended term and each search result. Wherein each search result corresponds to a second fused search term, i.e., when the search results are different, the second fused search terms are also different. And then, determining a third similarity between the first fused search word and each search result and a fourth similarity between each search result and a second fused search word corresponding to the search result, and carrying out weighted summation on the third similarity and the fourth similarity corresponding to each search result to take the sum value as a ranking score of each search result.

According to the application, the search words input by the user are supplemented based on the recommended words, the first fusion search word is determined based on the supplemented search words, and the ranking score of each search result is determined based on the search words input by the user, each search result and the second fusion search word determined by each recommended word, so that when the user performs search operation based on the shorter search words, the search content more relevant to the shorter search words can be ranked to a front position, and the user can quickly find the search content wanted by the user.

In another alternative implementation, the present application optionally further includes determining a first score for each search result based on the search term and each search result after determining at least two search results based on the search term entered by the user, and ranking each search result based on the first score and the ranking score determined in the foregoing embodiment. The search result ranking method provided by the application is further explained below with reference to fig. 6.

As shown in fig. 6, the method may include the steps of:

s201, determining at least two recommended words and at least two search results according to search words input by a user, wherein the recommended words are historical search words comprising the search words.

S202, determining the sorting score of each search result according to the search word, at least two search results and at least two recommended words.

S203, determining a first score of each search result according to the search word and at least two search results.

In some alternative embodiments, a first score for each search result is determined, optionally including: a fifth similarity between the search term and each search result is determined, and each fifth similarity is taken as a first score for each search result. It should be appreciated that the fifth similarity between the determined search term and each search result in the present application is the same as the implementation of the first similarity between the determined search term and each search result in the S102-2 part of the foregoing embodiment.

In some alternative embodiments, determining a fifth similarity between the search term and each search result may be accomplished using a similarity algorithm; alternatively, the search term and each search result may be input as input values to a matching model, to determine a fifth similarity between the search term and each search result by the matching model, and so on, and the present application does not impose any limitation on the implementation of determining the similarity between the search term and each search result.

Wherein, the similarity algorithm can be selected from but not limited to: cosine similarity algorithm, euclidean distance, manhattan distance, etc.

It should be noted that, S202 and S203 may be executed first S202 and then S203; or, S203 is performed first and S202 is performed next; alternatively, S202 and S203 may be performed in parallel, which is not limited in this regard by the present application.

S204, sorting at least two search results according to the sorting score and the first score of each search result.

In some alternative embodiments, the present application may determine a first composite score for each search result based on the rank score and the first score for each search result. At least two search results are then ranked according to the first composite score for each search result.

In the present application, determining a first composite score for each search result may include, but is not limited to, the following:

In case one, the ranking score and the first score of each search result are summed or weighted and the resulting sum is taken as the first composite score of each search result.

The weight values corresponding to the sequencing scores and the first scores in the weighted summation are adjustable parameters, and the weight values can be flexibly adjusted according to the search requirements of users.

And secondly, taking the ranking score and the first score of each search result as input values, and inputting the input values into a fusion model to obtain a first comprehensive score of each search result through fusion based on the ranking score and the first score of each search result by the fusion model.

The fusion model can be selected as any network model supporting the fusion of at least two scores to obtain a total score or a network model obtained by training based on a large number of score sample data, and the application is not limited in any way.

In case three, the ranking score and the first score of each search result are spliced, and the spliced result is input into a scoring model to determine the first comprehensive score of each search result based on the spliced result of each search result through the scoring model.

The scoring model can be selected as any network model supporting scoring based on input data or a network model trained based on a large number of scoring sample data, and the scoring model is not limited in the application.

Alternatively, the scoring model and the fusion model may be selected as the same network model, or different network models, which are not particularly limited herein.

According to the search result sorting method provided by the embodiment of the application, the plurality of recommended words and the plurality of search results which are associated with the search words are determined according to the search words input by the user, the sorting score of each search result is determined according to the search words, the plurality of recommended words and the plurality of search results, and the plurality of search results are sorted according to the sorting score, so that the search content which is wanted by the user can be sorted in front of the search results, and the search efficiency is improved. In addition, the first score is increased on the basis of the sorting score of each search result, so that the score of the search content wanted by the user is improved, and the user can more conveniently and quickly find the wanted search content from a plurality of search results.

As yet another alternative implementation, the user's scoring of the search results may take into account at least one characteristic information for each search result, such as whether the search result is a trending search result, or the like. Thus, on the basis of the foregoing embodiments, the present application further includes: a second score for each search result is determined based on the characteristic information for each search result. Then, each search result is ranked according to the ranking score and the second score of each search result. The search result sorting method provided by the present application is explained below with reference to fig. 7.

As shown in fig. 7, the method may include the steps of:

s301, determining at least two recommended words and at least two search results according to search words input by a user, wherein the recommended words are historical search words comprising the search words.

S302, determining the sorting score of each search result according to the search word, at least two search results and at least two recommended words.

S303, determining a second score of each search result according to the characteristic information of each search result.

In the present application, the feature information of the search result at least includes: whether it is at least one of a trending search result, whether it is a primary recommended search result, a number of times it was collected, and a content quality score. Wherein the content quality score refers to a user's scoring of the search result content.

In some alternative embodiments, when determining the second score for each search result, feature information for each search result is optionally input into a feature fusion model, through which the second score for each search result is determined based on the feature information for each search result. If the number of the feature information of any search result is at least two, the feature information of the search result is spliced, and the spliced result is input into the feature fusion model to determine a second score of the search result.

The feature fusion model can be selected as any network model supporting the determination of the score based on the feature information or a network model obtained by training based on a large amount of feature information sample data, and the feature fusion model is not particularly limited. When the feature fusion model is a network model, the network model can be selected as Wi deNet and the like.

Illustratively, when the feature information of a certain search result includes: if the characteristic 1, the characteristic 2 and the characteristic 3 are the characteristic information of the search result, the characteristic information can be spliced according to the mode of the characteristic 1+the characteristic 2+the characteristic 3, or the characteristic information can be spliced according to the mode of the characteristic 1+the characteristic 3+the characteristic 2, or the characteristic information can be spliced according to different modes of the characteristic 2+the characteristic 1+the characteristic 3, and the splicing mode of the plurality of characteristic information with the search result is not particularly limited.

It should be noted that, S302 and S303 may be executed first S302 and then S303; or, S303 is executed first and S302 is executed next; alternatively, S302 and S303 may be performed in parallel, which is not limited in this regard by the present application.

S304, sorting at least two search results according to the sorting score and the second score of each search result.

In some alternative embodiments, the present application may determine a second composite score for each search result based on the rank score and the second score for each search result. At least two search results are then ranked according to the second composite score for each search result.

In the present application, determining a second composite score for each search result may include, but is not limited to, the following:

in case one, the rank score and the second score of each search result are summed or weighted and the resulting sum is taken as the second composite score of each search result.

The weight values corresponding to the ranking score and the second score in the weighted summation are adjustable parameters, and particularly can be flexibly adjusted according to the search requirements of users.

And secondly, taking the ranking score and the second score of each search result as input values, and inputting the input values into a fusion model to obtain a second comprehensive score of each search result through fusion based on the ranking score and the second score of each search result by the fusion model.

In case three, the ranking score and the second score of each search result are spliced, and the spliced result is input into a scoring model to determine a second composite score of each search result based on the spliced result of each search result through the scoring model.

In some alternative embodiments, the application may optionally rank at least two search results according to the rank score, the first score, and the second score for each search result, in view of the fact that the rank score and the first score for each search result are determined in the previous embodiments.

As an alternative implementation, the ranking of at least two search results according to the ranking score, the first score and the second score of each search result may include: a third composite score for each search result is determined based on the rank score, the first score, and the second score for each search result. At least two search results are then ranked according to the third composite score for each search result.

In the present application, a third composite score for each search result is determined, which may include, but is not limited to, the following:

in a first scenario, the rank score, the first score, and the second score for each search result are summed or weighted and the resulting sum is taken as the third composite score for each search result.

The weight values corresponding to the sorting score, the first score and the second score in the weighted summation are adjustable parameters, and particularly can be flexibly adjusted according to the search requirement of the user.

In the second case, the ranking score, the first score and the second score of each search result are input as input values into a fusion model, so that a third comprehensive score of each search result is obtained through fusion based on the ranking score, the first score and the second score of each search result by the fusion model.

In a third scenario, the ranking score, the first score, and the second score for each search result are stitched, and the stitched results are input into a scoring model to determine a third composite score for each search result based on the stitched results for each search result through the scoring model.

According to the search result sorting method provided by the embodiment of the application, the plurality of recommended words and the plurality of search results which are associated with the search words are determined according to the search words input by the user, the sorting score of each search result is determined according to the search words, the plurality of recommended words and the plurality of search results, and the plurality of search results are sorted according to the sorting score, so that the search content which is wanted by the user can be sorted in front of the search results, and the search efficiency is improved. In addition, the ranking of each search result is updated based on the characteristic information of each search result, so that the score of the search content wanted by the user is further improved, and the user can more conveniently and quickly find the wanted search content from a plurality of search results.

A search result sorting apparatus according to an embodiment of the present application is described below with reference to fig. 8. FIG. 8 is a schematic block diagram of a search result ordering apparatus provided by an embodiment of the present application.

As shown in fig. 8, the search result sorting apparatus 400 includes: a first determination module 410, a second determination module 420, and a result ordering module 430.

Wherein, the first determining module 410 is configured to determine at least two recommended words and at least two search results according to the search words input by the user;

a second determining module 420, configured to determine a ranking score of each of the search results according to the search term, the at least two search results, and the at least two recommended terms;

and a result ranking module 430, configured to rank the at least two search results according to the ranking score.

An alternative implementation manner of the embodiment of the present application, the second determining module 420 includes:

the first determining unit is used for determining a first fusion search word according to the search word and each recommended word;

a second determining unit, configured to determine a second fused search term corresponding to each search result according to a first similarity between the search term and each search result, and a second similarity between each recommended term and each search result;

and the sorting unit is used for determining a sorting score of each search result according to the first fusion search word, each second fusion search word and each search result.

An optional implementation manner of the embodiment of the present application, a first determining unit is specifically configured to: determining the occurrence probability of the search word and the occurrence probability of each recommended word; and determining the first fusion search word according to the occurrence probability of the search word and the occurrence probability of each recommended word.

An optional implementation manner of the embodiment of the present application, the second determining unit is specifically configured to: and carrying out weighted summation on the first similarity and the second similarity corresponding to each search result, and determining a sum value as a second fusion search word corresponding to each search result.

An optional implementation manner of the embodiment of the present application, the ordering unit is specifically configured to: determining a third similarity between the first fused search term and each of the search results and a fourth similarity between each of the search results and the second fused search term corresponding to the search result; determining a ranking score of each search result according to the third similarity and the fourth similarity corresponding to each search result

An optional implementation manner of the embodiment of the present application further includes:

a third determining module, configured to determine a first score of each search result according to the search term and the at least two search results;

Accordingly, the result sorting module 430 is specifically configured to: and ranking the at least two search results according to the ranking score and the first score of each search result.

An optional implementation manner of the embodiment of the present application, a third determining module is specifically configured to:

and determining fifth similarity between the search word and each search result, and taking each fifth similarity as a first score corresponding to the search result.

An alternative implementation of the embodiment of the present application, the result ordering module 430 is further configured to:

determining a first composite score for each of the search results based on the rank score and the first score for each of the search results;

and sorting the at least two search results according to the first comprehensive score of each search result.

and the fourth determining module is used for determining a second score of each search result according to the characteristic information of each search result.

An optional implementation manner of the embodiment of the present application, the feature information of the search result at least includes: whether it is at least one of a popular search result, a main recommended search result, a number of times it is collected, and a content rating score.

An optional implementation manner of the embodiment of the present application, a fourth determining module is specifically configured to:

inputting the characteristic information of each search result into a characteristic fusion model, and determining a second score of each search result based on the characteristic information of each search result through the characteristic fusion model;

and if the number of the characteristic information of any search result is at least two, splicing the characteristic information of the search result, and inputting the spliced result into the characteristic fusion model to determine a second score of the search result.

An alternative implementation of the embodiment of the present application, the result ordering module 430 is specifically configured to:

ranking the at least two search results according to the ranking score and the second score for each of the search results; or, ranking the at least two search results according to the ranking score, the first score, and the second score for each of the search results.

determining a second composite score for each of the search results based on the rank score and the second score for each of the search results;

And sorting the at least two search results according to the second comprehensive score of each search result.

determining a third composite score for each of the search results based on the rank score, the first score, and the second score for each of the search results;

and sorting the at least two search results according to the third comprehensive score of each search result.

An optional implementation manner of the embodiment of the present application, the first determining module 410 is specifically configured to:

determining a target dictionary according to the region of the user;

and searching at least two recommended words corresponding to the search word in the target dictionary.

According to the search result sorting device provided by the embodiment of the application, the plurality of recommended words and the plurality of search results which are associated with the search words are determined according to the search words input by the user, the sorting score of each search result is determined according to the search words, the plurality of recommended words and the plurality of search results, and the plurality of search results are sorted according to the sorting score, so that the search content which is wanted by the user can be sorted in front of the search results, and the search efficiency is improved.

It should be understood that apparatus embodiments and the foregoing method embodiments may correspond to each other, and similar descriptions may refer to the method embodiments. To avoid repetition, no further description is provided here. Specifically, the apparatus 400 shown in fig. 8 may perform the method embodiment corresponding to fig. 2, and the foregoing and other operations and/or functions of each module in the apparatus 400 are respectively for implementing the corresponding flow in each method in fig. 2, and are not further described herein for brevity.

The apparatus 400 of the embodiment of the present application is described above in terms of functional modules with reference to the accompanying drawings. It should be understood that the functional module may be implemented in hardware, or may be implemented by instructions in software, or may be implemented by a combination of hardware and software modules. Specifically, each step of the method embodiment of the first aspect in the embodiment of the present application may be implemented by an integrated logic circuit of hardware in a processor and/or an instruction in software, and the steps of the method of the first aspect disclosed in connection with the embodiment of the present application may be directly implemented as a hardware decoding processor or implemented by a combination of hardware and software modules in the decoding processor. Alternatively, the software modules may be located in a well-established storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, and the like. The storage medium is located in a memory, and the processor reads information in the memory, and in combination with hardware, performs the steps in the method embodiment of the first aspect.

Fig. 9 is a schematic block diagram of an electronic device according to an embodiment of the present application. As shown in fig. 9, the electronic device 500 may include:

a memory 510 and a processor 520, the memory 510 being for storing a computer program and for transmitting the program code to the processor 520. In other words, the processor 520 may call and run a computer program from the memory 510 to implement the search result ordering method in an embodiment of the present application.

For example, the processor 520 may be configured to perform the search result ranking method embodiments described above according to instructions in the computer program.

In some embodiments of the application, the processor 520 may include, but is not limited to:

a general purpose processor, digital signal processor (Digital Signal Processor, DSP), application specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like.

In some embodiments of the application, the memory 510 includes, but is not limited to:

volatile memory and/or nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM) which acts as an external cache. By way of example, and not limitation, many forms of RAM are available, such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (Double Data Rate SDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), and Direct memory bus RAM (DR RAM).

In some embodiments of the present application, the computer program may be partitioned into one or more modules that are stored in the memory 510 and executed by the processor 520 to perform the search result ordering method provided by the present application. The one or more modules may be a series of computer program instruction segments capable of performing the specified functions, which are used to describe the execution of the computer program in the electronic device.

As shown in fig. 9, the electronic device 500 may further include:

a transceiver 530, the transceiver 530 being connectable to the processor 520 or the memory 510.

The processor 520 may control the transceiver 530 to communicate with other devices, and in particular, may send information or data to other devices or receive information or data sent by other devices. The transceiver 530 may include a transmitter and a receiver. The transceiver 530 may further include antennas, the number of which may be one or more.

It will be appreciated that the various components in the electronic device are connected by a bus system that includes, in addition to a data bus, a power bus, a control bus, and a status signal bus.

The present application also provides a computer storage medium having stored thereon a computer program which, when executed by a computer, enables the computer to perform the search result ranking method of the above-described method embodiments.

The embodiment of the application also provides a computer program product containing program instructions, which when run on electronic equipment, cause the electronic equipment to execute the search result ordering method of the method embodiment.

When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a digital video disc (digital video disc, DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.

Those of ordinary skill in the art will appreciate that the various illustrative modules and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the modules is merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or modules, which may be in electrical, mechanical, or other forms.

The modules illustrated as separate components may or may not be physically separate, and components shown as modules may or may not be physical modules, i.e., may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. For example, functional modules in various embodiments of the present application may be integrated into one processing module, or each module may exist alone physically, or two or more modules may be integrated into one module.

The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for ranking search results, comprising:

and sorting the at least two search results according to the sorting score.

2. The method of claim 1, wherein the determining a ranking score for each of the search results based on the search term, the at least two search results, and the at least two recommended terms comprises:

determining a first fusion search term according to the search term and each recommended term;

determining a second fusion search word corresponding to each search result according to the first similarity between the search word and each search result and the second similarity between each recommended word and each search result;

and determining a ranking score of each search result according to the first fusion search word, each second fusion search word and each search result.

3. The method of claim 2, wherein said determining a first fused search term from said search term and each of said recommended terms comprises:

determining the occurrence probability of the search word and the occurrence probability of each recommended word;

And determining the first fusion search word according to the occurrence probability of the search word and the occurrence probability of each recommended word.

4. The method of claim 2, wherein the determining a second fused search term corresponding to each of the search results based on a first similarity between the search term and each of the search results and a second similarity between each of the recommended terms and each of the search results comprises:

and carrying out weighted summation on the first similarity and the second similarity corresponding to each search result, and determining a sum value as a second fusion search word corresponding to each search result.

5. The method of claim 2, wherein said determining a ranking score for each of said search results based on said first fused search term, each of said second fused search terms, and each of said search results comprises:

determining a third similarity between the first fused search term and each of the search results and a fourth similarity between each of the search results and the second fused search term corresponding to the search result;

and determining a ranking score of each search result according to the third similarity and the fourth similarity corresponding to each search result.

6. The method as recited in claim 1, further comprising:

determining a first score for each of the search results based on the search term and the at least two search results;

accordingly, the ranking the at least two search results includes:

and ranking the at least two search results according to the ranking score and the first score of each search result.

7. The method of claim 6, wherein said determining a first score for each of said search results based on said search term and said at least two search results comprises:

8. The method of claim 6, wherein the ranking the at least two search results according to the ranking score and the first score for each of the search results comprises:

9. The method according to claim 1 or 6, further comprising:

and determining a second score of each search result according to the characteristic information of each search result.

10. The method of claim 9, wherein the feature information of the search result includes at least: whether it is at least one of a trending search result, whether it is a primary recommended search result, a number of times it was collected, and a content quality score.

11. The method of claim 10, wherein determining a second score for each of the search results based on the characteristic information for each of the search results comprises:

12. The method of claim 9, wherein the ranking the at least two search results comprises:

ranking the at least two search results according to the ranking score and the second score for each of the search results;

or,

and ranking the at least two search results according to the ranking score, the first score, and the second score of each of the search results.

13. The method of claim 12, wherein the ranking the at least two search results according to the ranking score and the second score for each of the search results comprises:

14. The method of claim 12, wherein ranking the at least two search results according to the ranking score, first score, and second score for each of the search results comprises:

15. The method of claim 1, wherein the determining at least two recommended words from the search words entered by the user comprises:

determining a target dictionary according to the region of the user;

16. A search result ordering apparatus, comprising:

17. An electronic device, comprising:

A processor and a memory for storing a computer program, the processor for invoking and running the computer program stored in the memory to perform the search result ordering method of any of claims 1 to 15.

18. A computer-readable storage medium storing a computer program for causing a computer to perform the search result ranking method of any one of claims 1 to 15.

19. A computer program product comprising program instructions which, when run on an electronic device, cause the electronic device to perform the search result ranking method of any one of claims 1 to 15.