CN111444405A

CN111444405A - User interaction method and device for searching, mobile terminal and storage medium

Info

Publication number: CN111444405A
Application number: CN202010203785.8A
Authority: CN
Inventors: 刘铭; 魏波; 仙云森; 王仲远; 王可; 许鑫; 王珺; 陈恩地; 汪祖海; 吕梅
Original assignee: Beijing Sankuai Online Technology Co Ltd
Current assignee: Beijing Sankuai Online Technology Co Ltd
Priority date: 2020-03-20
Filing date: 2020-03-20
Publication date: 2020-07-24
Also published as: WO2021185326A1

Abstract

The application discloses a user interaction method and device used in searching, a mobile terminal and a storage medium. The user interaction method for searching comprises the following steps: determining a search result cluster and navigation terms of the search result cluster in response to the search request; displaying the navigation items of the search result blocks according to the display priority of the search result blocks, and displaying the search result blocks and preview search results contained in the search result blocks; and responding to the interactive request, and performing linkage adjustment on the display focus of the search result block and the display focus of the navigation item of the search result block. According to the technical scheme, the preview search results are displayed in the search result block, the display focus of the search result block and the display focus of the navigation item of the search result block are adjusted in a linkage mode through interaction with a user, the information content contained in a search result page is improved, and the user experience is improved through improvement of an interaction mode.

Description

User interaction method and device for searching, mobile terminal and storage medium

Technical Field

The application relates to the field of search engines, in particular to a user interaction method, a user interaction device, a mobile terminal and a storage medium for searching.

Background

How to provide a better user interaction mode in a search scene is always a search field, especially a problem concerned by a mobile search field, especially a search result meeting the requirements of a user needs to be displayed in a search result page if a displayable space on a mobile terminal is relatively small, and the display effect is adjusted according to the operation of the user. Search results in the prior art are single in display mode and single in interaction mode, and user requirements cannot be met.

Disclosure of Invention

In view of the above, the present application is made to provide a user interaction method, apparatus, mobile terminal, and storage medium for use in search that overcome the above problems or at least partially solve the above problems.

According to a first aspect of the present application, there is provided a user interaction method for use in a search, comprising: determining a search result cluster and navigation terms of the search result cluster in response to the search request; displaying the navigation items of the search result blocks according to the display priority of the search result blocks, and displaying the search result blocks and preview search results contained in the search result blocks; and responding to the interactive request, and performing linkage adjustment on the display focus of the search result block and the display focus of the navigation item of the search result block.

Optionally, the displaying the navigation terms of the search result blocks, and the displaying the search result blocks and the preview search results included in the search result blocks include: displaying navigation items of at least part of search result blocks in a navigation area of a search result navigation page; at least a portion of a search clump and at least a portion of search preview results included therewith are shown in a content area of the search results navigation page.

Optionally, the performing, in response to the interaction request, a linkage adjustment on a display focus of the search result block and a display focus of the navigation item of the search result block includes: in response to a selection request for a navigation term of a target search result cluster, making the navigation term of the target search result cluster a display focus in the navigation area, and making the target search result cluster a display focus in the content area.

Optionally, the performing, in response to the interaction request, a linkage adjustment on a display focus of the search result block and a display focus of the navigation item of the search result block includes: in response to a browse request for a content area, a navigation term of a target search result cluster is brought into a presentation focus in the navigation area, and the target search result cluster is brought into the presentation focus in the content area.

Optionally, the method further comprises: and responding to a selection request of the target search result block, and displaying a search result set of the target search result block in a waterfall flow mode in a search result detail page.

Optionally, the method further comprises: displaying a screening item in the search result detail page; and responding to a selection request of a target screening item, screening the search result set according to the target screening item, and displaying the screened search result set in the search result detail page in a waterfall flow mode.

Optionally, each search result block corresponds to one or more search intents, and each search intention corresponds to one or more business categories.

Optionally, the number of preview results in the search result cluster is determined according to the display priority of the search result cluster and the maximum display number of the search result cluster; the maximum display quantity is determined according to the quantity of the search results browsed by at least part of ordering users before ordering in the search log.

Optionally, the determining the search result cluster and the navigation terms of the search result cluster comprises: determining a search intention corresponding to the search request, generating a search result cluster corresponding to the search intention, and generating navigation terms of the search result cluster; the search result blocks comprise preview search results and display priorities, and each search result block corresponds to one or more search intents respectively.

Optionally, the generating the search result cluster corresponding to the search intent comprises: determining a search result set of each search intention; determining the result weight of each search result set according to the search correlation; respectively determining the intention weight of the corresponding search intention according to the result weights; and determining the display priority of each search result block according to each intention weight.

Optionally, the determining the search result set of each search intention includes: through a distributed search, a set of search results corresponding to the search intent is obtained from one or more index services.

Optionally, the search relevance comprises at least one of: the relevance of the text of the search request and the description information of the search result, the relevance of the user preference and the search result, and the relevance of the search scene information and the search result.

Optionally, the determining the intention weight of the corresponding search intention according to each result weight respectively includes: and determining the intention weight of the corresponding search intention according to the result weight of the search result set and the initial weight of the corresponding search intention.

According to a second aspect of the present application, there is provided a user interaction apparatus for use in a search, comprising: a block unit for determining a search result block and a navigation term of the search result block in response to the search request; the display unit is used for displaying the navigation items of the search result blocks according to the display priority of the search result blocks, and displaying the search result blocks and preview search results contained in the search result blocks; and the display focus of the search result block and the display focus of the navigation item of the search result block are adjusted in a linkage mode in response to the interaction request.

Optionally, the presentation unit is configured to present navigation items of at least part of the search result blocks in a navigation area of the search result navigation page; at least a portion of a search clump and at least a portion of search preview results included therewith are shown in a content area of the search results navigation page.

Optionally, the presentation unit is configured to, in response to a selection request for a navigation item of the target search result cluster and/or a browsing request for the content area, make the navigation item of the target search result cluster a presentation focus in the navigation area, and make the target search result cluster a presentation focus in the content area.

Optionally, the presenting unit is further configured to present, in response to a selection request for the target search result block, a search result set of the target search result block in a form of a waterfall flow in the search result detail page.

Optionally, the presentation unit is further configured to present a screening item in the search result detail page; and responding to a selection request of a target screening item, screening the search result set according to the target screening item, and displaying the screened search result set in the search result detail page in a waterfall flow mode.

Optionally, the block clustering unit is configured to determine a search intention corresponding to the search request, generate a search result block corresponding to the search intention, and generate a navigation term of the search result block; the search result blocks comprise preview search results and display priorities, and each search result block corresponds to one or more search intents respectively.

Optionally, the block clustering unit is configured to determine a search result set of each search intention; determining the result weight of each search result set according to the search correlation; respectively determining the intention weight of the corresponding search intention according to the result weights; and determining the display priority of each search result block according to each intention weight.

Optionally, the block clustering unit is configured to obtain a search result set corresponding to the search intention from one or more index services through distributed search.

Optionally, the clustering unit is configured to determine an intention weight of the corresponding search intention according to a result weight of the search result set and an initial weight of the corresponding search intention.

According to a third aspect of the present application, there is provided a mobile terminal comprising: a processor; and a memory arranged to store computer executable instructions that, when executed, cause the processor to perform a method of user interaction for use in a search as claimed in any one of the preceding claims.

According to a fourth aspect of the present application, there is provided a computer readable storage medium storing one or more programs which, when executed by a processor, implement a user interaction method for use in a search as claimed in any preceding claim.

According to the technical scheme, the search result blocks and the navigation items of the search result blocks can be determined according to the search request of the user, the navigation items of the search result blocks are displayed according to the display priority of the search result blocks, the search result blocks and the preview search results contained in the search result blocks are displayed, and the display focus of the search result blocks and the display focus of the navigation items of the search result blocks are adjusted in a linkage mode in response to the interaction request. According to the technical scheme, the preview search results are displayed in the search result cluster, the display focus of the search result cluster and the display focus of the navigation item of the search result cluster are adjusted in a linkage mode through interaction with a user, the information content contained in a search result page is improved, the user experience is improved through improvement of an interaction mode, the search result cluster can correspond to the search intention according to requirements, and therefore a brand-new multi-intention interaction organization form is achieved.

The foregoing description is only an overview of the technical solutions of the present application, and the present application can be implemented according to the content of the description in order to make the technical means of the present application more clearly understood, and the following detailed description of the present application is given in order to make the above and other objects, features, and advantages of the present application more clearly understandable.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:

FIG. 1 shows a flow diagram of a method for user interaction in a search, according to one embodiment of the present application;

FIG. 2 illustrates a search results navigation page in accordance with one embodiment of the present application;

FIG. 3 illustrates a search result navigation page change state diagram according to one embodiment of the present application;

FIG. 4 illustrates an interactive presentation of search results according to one embodiment of the present application;

FIG. 5 shows a flow diagram of a method for user interaction data generation in a search, according to an embodiment of the present application;

FIG. 6 illustrates a schematic structural diagram of a user interaction device for use in searching, according to an embodiment of the present application;

FIG. 7 is a schematic structural diagram of an apparatus for generating user interaction data for use in a search according to an embodiment of the present application;

FIG. 8 illustrates a block diagram of a mobile terminal according to an embodiment of the present application;

FIG. 9 shows a schematic structural diagram of a computer-readable storage medium according to an embodiment of the present application.

Detailed Description

Exemplary embodiments of the present application will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

FIG. 1 shows a flow diagram of a method for user interaction in a search, according to one embodiment of the present application. As shown in fig. 1, the user interaction method for use in a search includes:

step S110, in response to the search request, determines a search result cluster and navigation terms of the search result cluster.

The embodiments of the present application can be applied to various scenarios using search engine technology, including but not limited to general search engines such as Baidu, Google (the trade name is merely exemplary), special search engines in the fields of patent, trademark, etc., and search engines within APP.

The user may generate the search request in various manners such as text, image, voice, etc., for example, the text may be a search keyword or a representation of a search sentence.

The search result cluster is an aggregation of search results as the name implies, and specifically, the search results may be clustered according to categories to obtain the search result cluster. There are many clustering methods, such as clustering according to semantic relevance, clustering according to geographical locations corresponding to search results, and so on.

One preferred approach is to cluster according to the user's search intent. In one embodiment of the present application, each search result block corresponds to one or more search intents, and each search intention corresponds to one or more business categories.

For example, each search intention corresponds to a local life service category, which may include take-out, flash purchase, menu, and the like. See the following example of this particular scenario: the user searches for the wife bean curd, and the search result related to the wife bean curd includes a merchant who uses the wife bean curd as a takeaway commodity, a supermarket that sells bean curd and seasonings, a practice of the wife bean curd, and the like. Then at least three search result clusters may be generated: take-out blocks, flash purchase blocks and menu blocks, take-out blocks as examples, and the search results covered by the blocks are the merchants taking Mapo tofu as take-out commodities.

In one embodiment of the application, the search intention is determined according to the search request and search scene information related to the search request, specifically, one search request of a user can obtain a distribution of a plurality of search intentions, and the presentation priority of the search clumps is determined according to the intention strength distribution of the search intentions. The search scene information may include weather, location, user behavior, and the like, and the search scene information and the search request may be subjected to composite modeling in advance, and a search intention recognition model is obtained through training, so that the search scene information related to the search request and the search request is input to the pre-trained search intention recognition model in an actual application scene to determine the search intention. And for the application cold start (initial start after initial installation or initial start after not being used for a period of time), the robustness of the search intention identification can be ensured by recommending the search intention by the service party.

And step S120, displaying the navigation items of the search result blocks according to the display priority of the search result blocks, and displaying the search result blocks and the preview search results contained in the search result blocks.

The presentation priority may be expressed only in the order of the first and second presentation weights, or may be embodied as one presentation weight. For example, the presentation weights of the five search result clumps A, B, C, D, E are 0.33, 0.1, 0.2, 0.3, and 0.07, respectively, then the presentation order of the navigation terms of the search result clumps, and the presentation order of the search result clumps, are both A, D, C, B, E.

On a device such as a mobile terminal, because of the limited screen size, the information that can be presented is limited, and therefore, although each search result block is an aggregation of many search results, all search results cannot be presented in the screen area, and thus, preview search results can be presented. The preview search result may be a search result with a higher weight among a plurality of search results aggregated by the search result block, and specifically, the weight of the search result may be determined by semantic relevance or a service recommendation policy.

And S130, responding to the interaction request, and performing linkage adjustment on the display focus of the search result block and the display focus of the navigation item of the search result block.

The navigation terms of the search result cluster can be used for quickly positioning the search result cluster and can be regarded as an index or a quick entry of the search result cluster, and when a user actively browses the search result cluster, the corresponding relation between the navigation terms and the search result cluster can be familiar through the change of the display focus of the navigation terms. And the whole process can be completed in one screen page.

The display focus adjustment refers to displaying the target search result block or the navigation item thereof in a more striking manner, including but not limited to highlighting, pop-up window displaying, or moving to a striking position such as the first position of the display area for displaying, and the like.

It can be seen that, in the user interaction method for search shown in fig. 1, the search result is displayed and previewed in the search result block, and the display focus of the search result block and the display focus of the navigation term of the search result block are adjusted in a linkage manner through interaction with the user, so that the information content contained in the search result page is improved, the user experience is improved through improvement of an interaction manner, and the search result block can be corresponding to the search intention according to the requirement, thereby realizing a brand-new multi-intention interaction organization form.

In an embodiment of the application, in the user interaction method for search, displaying the navigation terms of each search result block, and displaying each search result block and the preview search results included in the search result block include: displaying navigation items of at least part of search result blocks in a navigation area of a search result navigation page; at least a portion of the search clump and at least a portion of the search preview results contained therein are presented in a content area of the search results navigation page.

In particular implementations, the navigation area and the content area may have a variety of different layouts. For example, the navigation area is above, the content area is below; the navigation area is at the side and can be hidden according to the requirement, and the content area is persistently displayed at the central part. In addition, the layout of the navigation area and the content area may also be different for different devices, for example, a dual-screen device (the dual screen is not necessarily two independent display screen hardware, and may be two screen areas formed by a folding screen according to a folding mechanism, for example) may display the navigation area on one screen and the content area on the other screen.

For example, FIG. 2 shows a search results navigation page diagram in accordance with one embodiment of the present application. In fig. 2, the top is a search bar for inputting voice, search keywords, images, and the like to generate a search request. Six controls under the search bar, namely 'take-out-of-order', 'eating-in-store', 'preferential group purchase', 'buying food material', 'menu' and 'comment', respectively correspond to the navigation items of a search result block. The area in which the navigation terms of these search result clusters are located is the navigation area. Below the navigation area is a content area where the search result cluster of "point take away" is shown, along with the two preview search results it contains.

In one embodiment of the present application, in the user interaction method used in the search, in response to an interaction request, performing linkage adjustment on a display focus of a search result block and a display focus of a navigation term of the search result block includes: in response to a selection request for a navigation term of the target search result cluster, the navigation term of the target search result cluster is made a presentation focus in the navigation area, and the target search result cluster is made a presentation focus in the content area.

Taking fig. 2 as an example, the display position corresponding to the upper preview search result is the display focus position, and when the navigation item of a search result block is clicked, the search result block moves correspondingly, so that the first preview search result included in the search result block is displayed at the display focus position, and the search result block becomes the display focus of the content area.

In one embodiment of the present application, in the user interaction method used in the search, in response to an interaction request, performing linkage adjustment on a display focus of a search result block and a display focus of a navigation term of the search result block includes: in response to a browse request for the content area, the navigation terms of the target search result cluster are brought into a presentation focus in the navigation area, and the target search result cluster is brought into a presentation focus in the content area.

In addition to clicking on the navigation terms of the target search result cluster, the user can also browse the plurality of search result clusters through sliding and other operations. In this case, as the user slides, the display focus of the navigation item in the navigation area changes. For example, when the user browses the "buy food material" block and starts browsing the "menu", the display focus in the navigation bar is changed from "buy food material" to "menu", and specifically, the display focus may be realized by moving or highlighting the navigation item.

It can be seen that the user can click on the navigation item of any search result block, so that the interface slides rapidly and the corresponding search result block becomes the display focus, and the user can click on any control in the search result navigation page to execute more operations. When the user performs the sliding-up operation, the search result cluster also moves, and other search result clusters which are not shown in fig. 2 can be seen, such as "eat to store", "offer group purchase", "buy food material", "menu", and "comment", fig. 3 shows a schematic diagram of a change state of the search result navigation page, and two search result clusters of "eat to store" and "offer group purchase" are shown in fig. 3, limited by the screen size, and the "offer group purchase" search result cluster only shows a part of the preview search result.

In fig. 2 and 3, the blank area is subject content, such as subject wallpaper, poster picture, video cover, business head portrait, control icon, and the like. The crosses represent letters and/or numbers.

In an embodiment of the application, the user interaction method for searching further includes: and responding to a selection request of the target search result block, and displaying a search result set of the target search result block in a waterfall flow mode in a search result detail page.

For example, FIG. 4 shows an interactive presentation of search results according to one embodiment of the present application. As shown in fig. 4, the left side is a search result navigation page and the right side is a search result detail page. And after any search result block in the search result navigation page is clicked, skipping from the search result navigation page to a search result detail page, and displaying each search result of the search result set of the search result block in the search result detail page. The waterfall flow is a multi-column layout, and data blocks are continuously loaded and attached to the current tail part along with the downward rolling of a page scroll bar, so that the waterfall flow is suitable for a display scene of multiple search results.

In an embodiment of the application, the user interaction method for searching further includes: displaying the screening items in a search result detail page; and responding to a selection request of the target screening item, screening the search result set according to the target screening item, and displaying the screened search result set in a waterfall flow form in a search result detail page.

Also shown in FIG. 4 are filter terms that a user may filter through a search result set by checking out filter options such as "see only brand merchants", "see only business" and so on. The user may also return to the search results navigation page by sliding right, etc. from the search results details page.

In an embodiment of the application, in the above user interaction method for search, the number of preview results in the search result block is determined according to the presentation priority of the search result block and the maximum presentation number of the search result block.

As mentioned above, presentation priorities may be expressed in terms of presentation weights, and thus in one embodiment, the number of preview results for each search result tile may be calculated in terms of presentation weights × for the largest number of presentations, rounding down or rounding up if the calculated results are not integers.

In an embodiment of the application, in the above user interaction method for use in searching, the maximum number of presentations is determined according to the number of search results that have been browsed by at least part of ordering users before ordering in a search log.

The maximum number of presentations reflects the selection tendency of all or at least most users, and particularly in the scenes of shopping and the like, the following list is a factor capable of strongly showing the forward tendency. If most users select one product for placing orders after browsing 4-5 products, then 4-5 products are given as preview search results, and users are very likely to place orders after browsing the 4-5 products, and do not need to jump to a search result detail page, thereby further saving the time cost of searching.

In a specific embodiment, statistics can be made on the number of search results browsed by 95% of ordering users before ordering, and the maximum display number is determined by means of median calculation. The method has high universality and is suitable for cold start scenes. In other embodiments, the proportion and the statistical mode of the order placing users may be modified according to the requirements, or the maximum display number may be directly specified in a manual mode, which is not limited in the present application.

In an embodiment of the application, in the above user interaction method for searching, determining the search result cluster and the navigation terms of the search result cluster includes: determining a search intention corresponding to the search request, generating a search result cluster corresponding to the search intention, and generating navigation terms of the search result cluster; the search result blocks comprise preview search results and display priorities, and each search result block corresponds to one or more search intents respectively.

Accurately predicting the search intention of a user is a vital capability of a search engine. The search intention generally refers to the real needs of the user reflected in the back of the search behavior, for example, searching for "badminton", possibly because the user wants to buy badminton equipment, possibly searching for badminton stadiums, possibly learning badminton rules, and the like. In this example, "buy instruments", "find venues", and "learn rules" are three different types of search intentions related to the search keyword "badminton".

In more specific examples, the search intention may include take-out, food, menu, comment, offer, etc., which reflect the user's needs, and particularly, the name determination and category classification of the search intention may be performed by a business party, a domain expert, etc. In other words, it can be understood as a generalized user requirement.

Specifically, in a business scenario, the search intention may correspond to a category of goods or services, and the category of goods and services may be defined according to business requirements, for example, the takeout and the food service provided above are categories of service providing manners.

A search result may correspond to one or more search intentions, for example, if a restaurant offers both hall food sales and takeaway services, then the search intentions corresponding to the restaurant may include takeaway and hall food; and another restaurant only provides takeaway services, the search intent corresponding to that restaurant only includes takeaway. Conversely, it is apparent that a search intent can also correspond to one or more search results, and typically a plurality of search results, such as many restaurants that provide take-away services. The more the search intent matches the user's real needs, the more easily the search results presented to the user will correspondingly achieve the user's search goals.

Therefore, the search results are clustered according to the search intention and the search result cluster block is generated, so that the user can pay attention to the required search results more quickly.

In an embodiment of the application, in the above user interaction method in a search, generating a search result block corresponding to a search intention includes: determining a search result set of each search intention; determining the result weight of each search result set according to the search correlation; respectively determining the intention weight of the corresponding search intention according to the result weights; and determining the display priority of each search result block according to each intention weight.

Specifically, in an embodiment of the present application, in the above user interaction method for searching, determining a search result set of each search intention includes: through a distributed search, a set of search results corresponding to the search intent is obtained from one or more index services.

The robustness is enhanced by a scheme of obtaining a search result based on a search intention, further determining a result weight of a search result set based on search relevance, determining an intention weight by the result weight, and determining a presentation priority by the intention weight, specifically, one search intention may correspond to one or more search result sets, one search result block may correspond to one or more search intents, and in the case of one-to-one, the result weight may be regarded as the intention weight, and the intention weight may also be taken as the presentation weight embodying the presentation priority; in the case of one-to-many, the intention weight may be obtained through a mean operation or a weighted mean operation of the result weights, the display weight may be obtained similarly, and the like, and the above manners may be combined according to needs, which is not limited in the present application.

In an embodiment of the application, in the above user interaction method for searching, the search relevance includes at least one of: the relevance of the text of the search request and the description information of the search result, the relevance of the user preference and the search result, and the relevance of the search scene information and the search result.

The search request can be regarded as a direct expression given by the user to the search intention, the user preference can be obtained through data input by the user in advance or the user portrait, the search scene information can be regarded as an indirect expression given by the user to the search intention, and the potential search intention which is not reflected by the search keyword can be supplemented. In particular, searching for context information may cover multiple context dimensions, such as a time dimension, a location dimension, a weather dimension, and so forth.

For example, the user searches for "palace chicken bouillon", possibly because he wants to learn about how to go to palace chicken bouillon, possibly because he wants to order the take-out of palace chicken bouillon, or may wish to go to a restaurant selling the palace chicken bouillon to have a meal. However, when a user searches, the user does not necessarily express his/her search intention clearly with the search keyword, and this requires the user to search in the search or perform a secondary search, which reduces the user experience.

However, starting from searching for scene information, this problem can be improved. For example, if the user is searching for a palace chicken bouillon in a store, it is more likely that the user wishes to eat to a restaurant selling the palace chicken bouillon rather than looking for a menu or order for sale. At this time, the effect of the environment is reflected. If the user skips over a plurality of physical restaurants selling palace chicken dices, clicks on pages entering a plurality of takeaway restaurants, and places an order at one takeaway restaurant, the user can be determined to wish to take the takeaway, but not other intentions. This reflects the role of user behavior.

When the search relevance comprises a plurality of classes, different relevance weights can be distributed to each class, and the weights can be obtained through experience, for example, the relevance weights of the search keywords can be distributed higher; the correlation weight can also be determined by statistical modeling, such as by searching logs, generating positive examples for exposure and click of search result blocks, generating negative examples for exposure and no click, and determining the correlation weight through supervised learning.

In an embodiment of the application, in the above user interaction method in search, determining an intention weight of a corresponding search intention according to each result weight includes: and determining the intention weight of the corresponding search intention according to the result weight of the search result set and the initial weight of the corresponding search intention.

A search request may correspond to multiple search intents that have different initial weights, such as determined manually, or determined by statistical modeling, etc. And obtaining the intention weight by linear weighted summation and other modes of the result weight and the initial weight.

In the above embodiments, referring to the weighting scheme, preferably, the sum of the weights of the same type should be 1, and can be implemented by utilizing Softmax normalization calculation.

It should be noted here that the user interaction method for searching may be applied to the mobile terminal side, and specifically may be applied to the application APP. However, this does not mean that all the flow of the user interaction method in the search needs to be completely implemented on the mobile terminal side, and a part of the process having a large amount of calculation or not depending on the private information may be implemented on the server side.

For example, in one embodiment, the determination of search intent may be implemented by the server side; the server side is responsible for providing the distribution of the strength of the search intention and returning the distribution to the mobile terminal side, and the mobile terminal side generates search result blocks and navigation items, and the like.

In this regard, the present application also provides an example that some steps are performed on the server side, and specifically, the present application will be described as a user interaction data generation method used in the search by the following embodiments.

FIG. 5 shows a flow diagram of a method for user interaction data generation in a search, according to one embodiment of the present application. As shown in fig. 5, the user interaction data generation method for use in searching includes:

step S510, a search request sent by the mobile terminal is obtained.

Step S520, determining a search intention corresponding to the search request, generating a search result cluster corresponding to the search intention, and generating a navigation term of the search result cluster. The search result blocks comprise preview search results and display priorities, and each search result block corresponds to one or more search intents respectively.

Step S530, the search result block and the navigation item of the search result block are returned to the mobile terminal.

And displaying the search result blocks and the navigation items of the search result blocks according to the display priority, and adjusting the display focus of the search result blocks and the display focus of the navigation items of the search result blocks in a linkage manner according to the interactive request.

The method for generating user interaction data for searching shown in fig. 5 can be implemented in cooperation with the method for generating user interaction data for searching of the foregoing embodiments, and provides data support for innovation of user interaction. And each search result block corresponds to one or more search intentions respectively, and each search intention corresponds to one or more service categories respectively, so that the requirements of a service party and a user are reasonably met, and the win-win situation is realized.

In an embodiment of the application, in the method for generating user interaction data, the number of preview results in the search result cluster is determined according to the display priority of the search result cluster and the maximum display number of the search result cluster; the maximum number of presentations is determined according to the number of search results in the search log that have been browsed by at least part of ordering users before ordering.

The presentation priority may be expressed in terms of presentation weight, so in one embodiment, the number of preview results for each search result tile may be calculated in terms of presentation weight ×, maximum number of presentations, and rounded down or rounded up if the calculated results are not integers.

The search intention corresponding to the search request can be determined in various ways, for example, based on a rule formulated by a business expert, the search intention is determined by matching a search keyword with a text of the rule; predicting search intent based on text classification or clustering; the keywords are mapped to a high-dimensional semantic vector space by means of a topic model and the like to express the search intention, and the like. However, these solutions have problems that only the text is concerned and the other factors are not concerned.

Therefore, in a preferred scheme, search scene information related to a search request can be acquired, composite features for identifying search intentions are generated according to the search scene information and the search request, the composite features are input into a search intention identification model, and search intention identification results output by the search intention identification model are acquired.

In an embodiment of the application, in the above method for generating user interaction data in a search, generating a search result block corresponding to a search intention includes: determining a search result set of each search intention; determining the result weight of each search result set according to the search correlation; respectively determining the intention weight of the corresponding search intention according to the result weights; and determining the display priority of each search result block according to each intention weight.

Specifically, in an embodiment of the present application, the determining a search result set of each search intention in the method includes: through a distributed search, a set of search results corresponding to the search intent is obtained from one or more index services.

In an embodiment of the application, the method above, wherein searching for the correlation includes at least one of: the relevance of the text of the search request and the description information of the search result, the relevance of the user preference and the search result, and the relevance of the search scene information and the search result.

In an embodiment of the application, the determining the intention weight of the corresponding search intention according to each result weight in the method includes: and determining the intention weight of the corresponding search intention according to the result weight of the search result set and the initial weight of the corresponding search intention.

Besides the above solutions provided in the present application, there are also some solutions that can present search results based on search intentions, but the presentation methods all have some drawbacks.

For example, the search results correspond to only a single search intent, presented using a fixed template. The method needs to accurately identify the first search intention of the user and organize and display the first search intention by the corresponding template, and the defects are obvious: firstly, the search intention is accurate to predict completely, and ambiguity elimination can not be realized; secondly, the fixed template display can kill the potential growth space even if the current main user requirements are met under certain conditions.

For another example, search results corresponding to multiple search intents may be mixed and inserted in the search result page. The method can perform mixed sequencing on a plurality of search result sets with different services and meeting different requirements. The defects are as follows: the user is difficult to predict the next page after clicking the list, which causes confusing understanding of the search result set, and is difficult to form user habits, thereby influencing the use experience.

As another example, a secondary intention card may be inserted in the idea diagram for presentation. This type of approach generally requires identifying one first search intent as the primary intent and other identified search intents as secondary intents. The idea graph is directly expanded into a result list, and the auxiliary graph only shows a summary card and needs a user to click to expand the result list. The disadvantages of such methods are: one is that the presentation of secondary intent may not be complete (ranked below), imperceptible to the user; secondly, the insertion of multiple cards can interfere with the browsing of the result list by the user.

The search result display scheme combined with the search intention can predict the multi-search intention distribution of the current search request aiming at each search request of the user, obtain a plurality of search result sets through distributed retrieval recall, and automatically generate a navigation area and a search result cluster through final judgment on the quality of the search result sets, thereby forming an interactive display form of the search results. Due to the adoption of the solution of the effect, the problem that the search results with multiple search intentions are not displayed enough due to the limitation of the size of the screen of the mobile terminal is greatly improved, and the problems that the screen is too large due to the single search intention and the potential search intentions cannot be displayed can be effectively solved.

FIG. 6 shows a schematic diagram of a user interaction device for use in a search, according to an embodiment of the present application. As shown in fig. 6, a user interaction apparatus 600 for use in searching includes:

a cluster block unit 610, configured to obtain the search result cluster and the navigation terms of the search result cluster in response to the search request.

The display unit 620 is configured to display the navigation terms of the search result blocks according to the display priority of the search result blocks, and display the search result blocks and the preview search results included in the search result blocks; and the display focus of the search result block and the display focus of the navigation item of the search result block are adjusted in a linkage mode in response to the interaction request.

It can be seen that the user interaction device for use in search shown in fig. 6 displays the preview search result in the search result cluster, and performs linkage adjustment on the display focus of the search result cluster and the display focus of the navigation term of the search result cluster through interaction with the user, so that the information content included in the search result page is improved, the user experience is improved through improvement of an interaction manner, and the search result cluster can be associated with the search intention according to the requirement, thereby realizing a brand-new multi-intention interaction organization form.

In an embodiment of the present application, in a user interaction device used in a search, a presentation unit 620 is configured to present navigation terms of at least a part of a search result block in a navigation area of a search result navigation page; at least a portion of the search clump and at least a portion of the search preview results contained therein are presented in a content area of the search results navigation page.

In an embodiment of the present application, in a user interaction device used in a search, a presentation unit 620 is configured to make a navigation item of a target search result block a presentation focus in a navigation area and make a target search result block a presentation focus in a content area in response to a selection request for the navigation item of the target search result block.

In an embodiment of the present application, in the user interaction device for use in a search, the presentation unit 620 is configured to make a navigation item of a target search result cluster a presentation focus in a navigation area and make the target search result cluster a presentation focus in a content area in response to a browse request for the content area.

In an embodiment of the present application, in the user interaction device used in the search, the presentation unit 620 is further configured to present a search result set of the target search result block in a form of a waterfall flow in the search result detail page in response to a selection request for the target search result block.

In an embodiment of the present application, in the user interaction device used in the search, the presentation unit 620 is further configured to present the screening items in the search result detail page; and responding to a selection request of the target screening item, screening the search result set according to the target screening item, and displaying the screened search result set in a waterfall flow form in a search result detail page.

In one embodiment of the application, in the user interaction device used in the search, each search result block corresponds to one or more search intents respectively, and each search intention corresponds to one or more business categories respectively.

In one embodiment of the present application, in a user interaction device used in a search, the number of preview results in a search result cluster is determined according to a presentation priority of the search result cluster and a maximum presentation number of the search result cluster; the maximum number of presentations is determined according to the number of search results in the search log that have been browsed by at least part of ordering users before ordering.

In one embodiment of the present application, in a user interaction device for use in a search, a clump unit 610 for determining a search intention corresponding to a search request, generating a search result clump corresponding to the search intention, and generating a navigation term of the search result clump; the search result blocks comprise preview search results and display priorities, and each search result block corresponds to one or more search intents respectively.

In an embodiment of the present application, in a user interaction device used in a search, a clustering unit 610 for determining a search result set for each search intention; determining the result weight of each search result set according to the search correlation; respectively determining the intention weight of the corresponding search intention according to the result weights; and determining the display priority of each search result block according to each intention weight.

In an embodiment of the present application, in a user interaction device for use in a search, a clumping unit 610 is configured to obtain a search result set corresponding to a search intention from one or more index services through a distributed search.

In one embodiment of the present application, in a user interaction device for use in a search, the search relevance comprises at least one of: the relevance of the text of the search request and the description information of the search result, the relevance of the user preference and the search result, and the relevance of the search scene information and the search result.

In an embodiment of the present application, in a user interaction device for use in a search, a clumping unit 610 is configured to determine an intention weight of a corresponding search intention according to a result weight of a search result set and an initial weight of the corresponding search intention.

It should be noted that the user interaction apparatuses for searching in the foregoing embodiments can be respectively used for executing the user interaction methods for searching in the foregoing embodiments, and therefore, detailed description thereof is omitted.

Fig. 7 shows a schematic structural diagram of a user interaction data generation device for searching according to an embodiment of the present application. As shown in fig. 7, the user interaction data generation apparatus 700 for use in searching includes:

a communication unit 710, configured to obtain a search request sent by a mobile terminal.

A generating unit 720 for determining a search intention corresponding to the search request, generating a search result cluster corresponding to the search intention, and generating a navigation term of the search result cluster; the search result blocks comprise preview search results and display priorities, and each search result block corresponds to one or more search intents respectively.

The communication unit 710 is further configured to return the search result cluster and the navigation terms of the search result cluster to the mobile terminal, so that the navigation terms of the search result cluster and the search result cluster are displayed according to the display priority, and the display focus of the search result cluster and the display focus of the navigation terms of the search result cluster are adjusted in a linkage manner according to the interaction request.

The user interaction data generation device for searching shown in fig. 7 can be implemented in cooperation with the user interaction device for searching of the foregoing embodiment, and provides data support for innovation of user interaction. And each search result block corresponds to one or more search intentions respectively, and each search intention corresponds to one or more service categories respectively, so that the requirements of a service party and a user are reasonably met, and the win-win situation is realized.

In one embodiment of the application, in the user interaction data generation device for use in searching, the number of preview results in the search result cluster is determined according to the presentation priority of the search result cluster and the maximum presentation number of the search result cluster; the maximum number of presentations is determined according to the number of search results in the search log that have been browsed by at least part of ordering users before ordering.

In an embodiment of the present application, in the apparatus for generating user interaction data in a search, the generating unit 720 is configured to determine a search result set of each search intention; determining the result weight of each search result set according to the search correlation; respectively determining the intention weight of the corresponding search intention according to the result weights; and determining the display priority of each search result block according to each intention weight.

In an embodiment of the present application, in a user interaction data generation apparatus for use in a search, a generation unit 720 is configured to obtain a search result set corresponding to a search intention from one or more index services through a distributed search.

In one embodiment of the present application, in the user interaction data generation apparatus for use in searching, the search relevance includes at least one of: the relevance of the text of the search request and the description information of the search result, the relevance of the user preference and the search result, and the relevance of the search scene information and the search result.

In an embodiment of the application, in the apparatus for generating user interaction data in a search, the generating unit 720 is configured to determine an intention weight of a corresponding search intention according to a result weight of a search result set and an initial weight of the corresponding search intention.

It should be noted that, the user interaction data generation apparatus for search in the foregoing embodiment may be respectively used to execute the user interaction data generation method for search in the foregoing embodiment, and therefore, detailed description is not given one by one.

In summary, according to the technical scheme of the application, the search result blocks and the navigation terms of the search result blocks can be obtained according to the search request of the user, the navigation terms of the search result blocks are displayed according to the display priority of the search result blocks, the search result blocks and the preview search results contained in the search result blocks are displayed, and the target search result blocks are moved to the display focus to be displayed in response to the selection request of the navigation terms of the target search result blocks. According to the technical scheme, the preview search results are displayed in the search result cluster, the display focus of the search result cluster and the display focus of the navigation item of the search result cluster are adjusted in a linkage mode through interaction with a user, the information content contained in a search result page is improved, the user experience is improved through improvement of an interaction mode, the search result cluster can correspond to the search intention according to requirements, and therefore a brand-new multi-intention interaction organization form is achieved.

It should be noted that:

the algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may be used with the teachings herein. The required structure for constructing such a device will be apparent from the description above. In addition, this application is not directed to any particular programming language. It will be appreciated that a variety of programming languages may be used to implement the teachings of the present application as described herein, and any descriptions of specific languages are provided above to disclose the best modes of the present application.

In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the application may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.

Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the application, various features of the application are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the application and aiding in the understanding of one or more of the various inventive aspects. However, the disclosed method should not be interpreted as reflecting an intention that: this application is intended to cover such departures from the present disclosure as come within known or customary practice in the art to which this invention pertains. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this application.

Those skilled in the art will appreciate that the modules in the device in an embodiment may be adaptively changed and disposed in one or more devices different from the embodiment. The modules or units or components of the embodiments may be combined into one module or unit or component, and furthermore they may be divided into a plurality of sub-modules or sub-units or sub-components. All of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where at least some of such features and/or processes or elements are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.

Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the application and form different embodiments. For example, in the following claims, any of the claimed embodiments may be used in any combination.

The various component embodiments of the present application may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components of the user interaction means for searching and the user interaction data generation means for searching according to embodiments of the present application. The present application may also be embodied as apparatus or device programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present application may be stored on a computer readable medium or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.

For example, fig. 8 shows a schematic structural diagram of a mobile terminal according to an embodiment of the present application. The mobile terminal 800 comprises a processor 810 and a memory 820 arranged to store computer executable instructions (computer readable program code). The memory 820 may be an electronic memory such as a flash memory, an EEPROM (electrically erasable programmable read only memory), an EPROM, a hard disk, or a ROM. The memory 820 has a storage space 830 storing computer readable program code 831 for performing any of the method steps described above. For example, the storage space 830 for storing the computer-readable program code may include respective computer-readable program codes 831 for respectively implementing various steps in the above methods. The computer readable program code 831 may be read from or written to one or more computer program products. These computer program products comprise a program code carrier such as a hard disk, a Compact Disc (CD), a memory card or a floppy disk. Such a computer program product is typically a computer readable storage medium such as described in fig. 9. FIG. 9 shows a schematic diagram of a computer-readable storage medium according to an embodiment of the present application. The computer readable storage medium 900 stores computer readable program code 831 for executing the steps of the method according to the present application, which is readable by the processor 810 of the mobile terminal 800, and when the computer readable program code 831 is executed by the mobile terminal 800, causes the mobile terminal 800 to perform the steps of the method described above, and in particular, the computer readable program code 831 stored by the computer readable storage medium may perform the method shown in any of the embodiments described above. The computer readable program code 831 may be compressed in a suitable form.

It should be noted that the above-mentioned embodiments illustrate rather than limit the application, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.

Claims

1. A method of user interaction for use in a search, comprising:

determining a search result cluster and navigation terms of the search result cluster in response to the search request;

displaying the navigation items of the search result blocks according to the display priority of the search result blocks, and displaying the search result blocks and preview search results contained in the search result blocks;

and responding to the interactive request, and performing linkage adjustment on the display focus of the search result block and the display focus of the navigation item of the search result block.

2. The method of claim 1, wherein presenting the navigation terms of each search result cluster, and presenting each search result cluster and its contained preview search results comprises:

displaying navigation items of at least part of search result blocks in a navigation area of a search result navigation page;

at least a portion of a search clump and at least a portion of search preview results included therewith are shown in a content area of the search results navigation page.

3. The method of claim 2, wherein the coordinated adjustment of the presentation focus of the search result cluster and the presentation focus of the navigation terms of the search result cluster in response to the interactive request comprises:

in response to a selection request for a navigation term of a target search result cluster, making the navigation term of the target search result cluster a display focus in the navigation area, and making the target search result cluster a display focus in the content area.

4. The method of claim 2, wherein the coordinated adjustment of the presentation focus of the search result cluster and the presentation focus of the navigation terms of the search result cluster in response to the interactive request comprises:

in response to a browse request for a content area, a navigation term of a target search result cluster is brought into a presentation focus in the navigation area, and the target search result cluster is brought into the presentation focus in the content area.

5. The method of claim 1, wherein the method further comprises:

and responding to a selection request of the target search result block, and displaying a search result set of the target search result block in a waterfall flow mode in a search result detail page.

6. The method of claim 5, wherein the method further comprises:

displaying a screening item in the search result detail page;

and responding to a selection request of a target screening item, screening the search result set according to the target screening item, and displaying the screened search result set in the search result detail page in a waterfall flow mode.

7. The method of claim 1, wherein each search result cluster corresponds to one or more search intents, each search intention corresponding to one or more business categories, respectively.

8. The method of claim 1, wherein the number of preview results in the search result cluster is determined based on a presentation priority of the search result cluster and a maximum number of presentations of the search result cluster;

the maximum display quantity is determined according to the quantity of the search results browsed by at least part of ordering users before ordering in the search log.

9. The method of claim 1, wherein the determining the search result clump and the navigation terms of the search result clump comprises:

determining a search intention corresponding to the search request, generating a search result cluster corresponding to the search intention, and generating navigation terms of the search result cluster; the search result blocks comprise preview search results and display priorities, and each search result block corresponds to one or more search intents respectively.

10. The method of claim 9, wherein the generating a search result cluster corresponding to a search intent comprises:

determining a search result set of each search intention;

determining the result weight of each search result set according to the search correlation;

respectively determining the intention weight of the corresponding search intention according to the result weights;

and determining the display priority of each search result block according to each intention weight.

11. The method of claim 10, wherein the determining a set of search results for each search intent comprises:

through a distributed search, a set of search results corresponding to the search intent is obtained from one or more index services.

12. The method of claim 10, wherein the search for relevance comprises at least one of: the relevance of the text of the search request and the description information of the search result, the relevance of the user preference and the search result, and the relevance of the search scene information and the search result.

13. The method of claim 10, wherein determining an intent weight for a respective search intent from each result weight comprises:

and determining the intention weight of the corresponding search intention according to the result weight of the search result set and the initial weight of the corresponding search intention.

14. A user interaction apparatus for use in a search, comprising:

a block unit for determining a search result block and a navigation term of the search result block in response to the search request;

the display unit is used for displaying the navigation items of the search result blocks according to the display priority of the search result blocks, and displaying the search result blocks and preview search results contained in the search result blocks; and the display focus of the search result block and the display focus of the navigation item of the search result block are adjusted in a linkage mode in response to the interaction request.

15. A mobile terminal, characterized in that the mobile terminal comprises: a processor; and a memory arranged to store computer-executable instructions that, when executed, cause the processor to perform the method for user interaction in a search of any of claims 1-13.

16. A computer-readable storage medium, characterized in that the computer-readable storage medium stores one or more programs which, when executed by a processor, implement the user interaction method for use in a search according to any one of claims 1-13.