CN112084405A

CN112084405A - Searching method, searching device and computer storage medium

Info

Publication number: CN112084405A
Application number: CN202010921860.4A
Authority: CN
Inventors: 汪忠超; 乔超
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Beijing ByteDance Network Technology Co Ltd
Priority date: 2020-09-04
Filing date: 2020-09-04
Publication date: 2020-12-15

Abstract

The present disclosure provides a search method, apparatus, and computer storage medium, wherein the method includes: acquiring a search request of a user side; acquiring a plurality of target entities matched with the search request based on the request type of the search request; and generating a multi-entity aggregation result based on the target entities, and returning the multi-entity aggregation result to the user side. In the embodiment of the disclosure, the server acquires a plurality of target entities matched with the search request, generates a multi-entity aggregation result based on the plurality of target entities, and returns the multi-entity aggregation result to the user side, so that the user side can display the aggregation result of the plurality of target entities matched with the search request, and the user can see the plurality of target entities at a time through the aggregation result, thereby facilitating the user to further screen the interested target entities, improving the information search efficiency, and saving the search time.

Description

Searching method, searching device and computer storage medium

Technical Field

The present disclosure relates to the field of internet technologies, and in particular, to a search method, an apparatus, and a computer storage medium.

Background

Users often search for media contents of interest on terminal applications or websites, and in some cases, the media contents searched by users may involve multiple entities, for example, users search for movies suitable for lovers, and in such cases, many movie contents may be searched out.

In the above situation, the user needs to search for the media contents of interest one by one in a large amount of media contents. Meanwhile, because the screen display area of the user terminal is limited, the user needs to continuously slide the display screen to adjust and view the media content; or after the user checks a plurality of media contents and finds that the media contents are not the media contents in which the user is interested, the user needs to adjust the search keywords and reinitiate the search request; the searching efficiency in the whole process is low, and the searching requirement of the user cannot be met efficiently.

Disclosure of Invention

The embodiment of the disclosure at least provides a searching method, a searching device and a computer storage medium.

In a first aspect, an embodiment of the present disclosure provides a search method, where the method includes:

acquiring a search request of a user side, wherein the search request corresponds to a plurality of entities;

acquiring a plurality of target entities matched with the search request based on the request type of the search request;

and generating a multi-entity aggregation result based on the target entities, and returning the multi-entity aggregation result to the user side.

In a possible implementation manner, the obtaining a plurality of target entities matching the search request based on the request type of the search request includes:

under the condition that the search request is an attribute type search request, searching a plurality of target entities matched with the search request based on attribute information of different entities in a knowledge graph; wherein the attribute-class search request refers to a search request that characterizes a search intention using a plurality of attribute keywords.

In one possible embodiment, the obtaining a plurality of target entities matching the search request based on the request type of the search request includes:

under the condition that the search request is an entity set type search request, acquiring associated media content corresponding to the search request;

determining a plurality of target entities matching the search request based on the associated media content.

In one possible implementation, determining a plurality of target entities matching the search request based on the associated media content includes:

acquiring a plurality of entities corresponding to each associated media content in the associated media content;

clustering and de-duplicating the multiple entities to obtain multiple processed candidate entities;

determining the target entity from the plurality of candidate entities.

In one possible embodiment, determining the target entity from the plurality of candidate entities includes:

and sequencing the obtained candidate entities, and selecting the target entity from the candidate entities according to a sequencing result.

In one possible embodiment, the step of ranking the obtained plurality of candidate entities includes:

determining intent classification information for the search request based on the search request;

and sequencing the obtained candidate entities according to the intention classification information and the attribute information of the candidate entities.

In a possible implementation manner, the attribute information of the candidate entity includes at least one of classification information of the candidate entity, attribute characteristics of associated media content corresponding to the candidate entity, and the number of times that the same candidate entity appears in different associated media content;

the attribute characteristics corresponding to the associated media content include: attribute information of an author, a correlation degree between the associated media content and the search request, and an arrangement order of the associated media content in the search.

In one possible embodiment, the method further comprises:

and respectively extracting entities from the plurality of media contents in the search library in advance to obtain pre-extracted entities corresponding to the plurality of media contents respectively.

In one possible implementation, the associated media content corresponding to the search request is obtained according to the following steps:

determining a standard sentence corresponding to a search sentence in the search request based on a pre-trained generalization model;

and acquiring the associated media content matched with the standard sentence.

In one possible embodiment, the associated media content includes at least one of: text documents, text-text mixed documents, pictures, audio, video.

In one possible implementation, obtaining associated media content corresponding to the search request includes:

under the condition that the query intention corresponding to the search request is an objective intention, searching for associated media content with objective answers matched with the search request;

and under the condition that the query intention corresponding to the search request is the subjective category intention, searching for the associated media content with the subjective category search result matched with the search request.

In a second aspect, an embodiment of the present disclosure further provides a search method, including:

responding to a search triggering instruction, and sending a search request; the search request corresponds to a plurality of entities;

receiving a multi-entity aggregation result corresponding to the search request; the multi-entity aggregation result comprises relevant information of a plurality of target entities matched with the search request;

and displaying the multi-entity aggregation result.

In one possible embodiment, presenting the multi-entity aggregation result includes:

and displaying the attribute information of the target entities in a first display area of the display areas, and displaying the content information associated with the selected target recommending entity in the target entities in other display areas.

In a third aspect, an embodiment of the present disclosure further provides a search apparatus, including:

the first acquisition module is used for acquiring a search request of a user side, wherein the search request corresponds to a plurality of entities.

And the second acquisition module is used for acquiring a plurality of target entities matched with the search request based on the request type of the search request.

And the generating module is used for generating a multi-entity aggregation result based on the target entities and returning the multi-entity aggregation result to the user side.

In a possible implementation manner, the second obtaining module is specifically configured to, when the search request is an attribute type search request, find a plurality of target entities matching the search request based on attribute information of different entities in a knowledge graph; wherein the attribute-class search request refers to a search request that characterizes a search intention using a plurality of attribute keywords.

In a possible implementation manner, the second obtaining module further obtains, specifically when the search request is an entity set type search request, associated media content corresponding to the search request; determining a plurality of target entities matching the search request based on the associated media content.

In a possible implementation manner, the second obtaining module is further specifically configured to obtain a plurality of entities corresponding to each associated media content in the associated media contents; clustering and de-duplicating the multiple entities to obtain multiple processed candidate entities; determining the target entity from the plurality of candidate entities.

In a possible implementation manner, the second obtaining module is further specifically configured to rank the obtained multiple candidate entities, and select the target entity from the multiple candidate entities according to a ranking result.

In a possible implementation manner, the second obtaining module is further specifically configured to determine intention classification information of the search request based on the search request; and sequencing the obtained candidate entities according to the intention classification information and the attribute information of the candidate entities.

the attribute characteristics of the associated media content include: attribute information of an author, a correlation degree between the associated media content and the search request, and an arrangement order of the associated media content in the search.

In a possible implementation manner, the apparatus further includes an entity extraction module, configured to perform entity extraction on each of the plurality of media contents in the search library in advance, so as to obtain a pre-extracted entity corresponding to each of the plurality of media contents.

In a possible implementation manner, the second obtaining module is further specifically configured to determine, based on a pre-trained generalization model, a standard statement corresponding to a search statement in the search request; and acquiring the associated media content matched with the standard sentence.

In a possible implementation manner, the second obtaining module is further specifically configured to, in a case that a query intention corresponding to the search request is an objective-type intention, search for associated media content having an objective answer matching the search request; and under the condition that the query intention corresponding to the search request is the subjective category intention, searching for the associated media content with the subjective category search result matched with the search request.

In a fourth aspect, an embodiment of the present disclosure further provides a search apparatus, including:

the sending module is used for responding to the search triggering instruction and sending a search request; the search request corresponds to a plurality of entities.

A receiving module, configured to receive a multi-entity aggregation result corresponding to the search request; and the multi-entity aggregation result comprises the relevant information of a plurality of target entities matched with the search request.

And the display module is used for displaying the multi-entity aggregation result.

In a possible implementation manner, the presentation module is specifically configured to present, in a first presentation area of a plurality of presentation areas, the attribute information of the target entities, and present, in other presentation areas, content information associated with a selected target recommending entity of the target entities.

In a fifth aspect, an embodiment of the present disclosure further provides a computer device, including: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating via the bus when the computer device is running, the machine-readable instructions when executed by the processor performing the steps of the first aspect, or any one of the possible implementations of the first aspect, or the second aspect, or one of the possible implementations of the second aspect.

In a sixth aspect, this disclosed embodiment also provides a computer readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the first aspect, or any one of the possible embodiments of the first aspect, or to perform the steps of the second aspect, or one of the possible embodiments of the second aspect.

According to the searching method, the searching device and the computer storage medium provided by the embodiment of the disclosure, after the searching request sent by the user side is obtained, the server obtains a plurality of target entities matched with the searching request, generates a multi-entity aggregation result based on the plurality of target entities, and returns the multi-entity aggregation result to the user side, so that the user side can display the aggregation result of the plurality of target entities matched with the searching request, and the user can see the plurality of target entities at a time through the aggregation result, thereby facilitating the user to further screen the interested target entities, improving the information searching efficiency and saving the searching time.

For the effect description of the above search apparatus, electronic device, and computer-readable storage medium, reference is made to the description of the above search method, which is not repeated herein.

In order to make the aforementioned objects, features and advantages of the present disclosure more comprehensible, preferred embodiments accompanied with figures are described in detail below.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly described below, and the drawings herein incorporated in and forming a part of the specification illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the technical solutions of the present disclosure. It is appreciated that the following drawings depict only certain embodiments of the disclosure and are therefore not to be considered limiting of its scope, for those skilled in the art will be able to derive additional related drawings therefrom without the benefit of the inventive faculty.

Fig. 1 shows a flowchart of a search method provided by an embodiment of the present disclosure;

FIG. 2 is a schematic diagram illustrating an entity extraction result in the search method provided by the embodiment of the present disclosure;

FIG. 3 is a schematic diagram illustrating a presentation page presenting a plurality of target entities matching a search request in a search method provided by an embodiment of the present disclosure;

FIG. 4 is a flow chart illustrating another searching method provided by the disclosed embodiments;

FIG. 5 is a schematic diagram illustrating a presentation page presenting related information of a target recommending entity in the search method provided by the embodiment of the disclosure;

fig. 6 shows a schematic diagram of a search apparatus provided by an embodiment of the present disclosure;

FIG. 7 is a schematic diagram of another search apparatus provided in the embodiments of the present disclosure;

fig. 8 shows a schematic diagram of an electronic device provided by an embodiment of the present disclosure.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present disclosure more clear, the technical solutions of the embodiments of the present disclosure will be described clearly and completely with reference to the drawings in the embodiments of the present disclosure, and it is obvious that the described embodiments are only a part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure, generally described and illustrated in the figures herein, can be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present disclosure, presented in the figures, is not intended to limit the scope of the claimed disclosure, but is merely representative of selected embodiments of the disclosure. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the disclosure without making creative efforts, shall fall within the protection scope of the disclosure.

Generally, after a search request is initiated at a user end, the content of a search result page, which includes a list of search results, may be returned to the user end, where each search result generally includes: the title of the search result web page, a brief introduction to the search result, etc. In some cases, in a search result related to a certain search request (query), related media contents of multiple entities are involved, and the number of media contents related to one entity may be many, and the related media contents of one entity occupy a large part of the display positions in the search result page, so that it is difficult for a user to see a desired search result at a glance.

Based on the research, the present disclosure provides a searching method, a searching device, and a computer storage medium, where after a search request sent by a user terminal is obtained, a server obtains a plurality of target entities matching the search request, generates a multi-entity aggregation result based on the plurality of target entities, and returns the multi-entity aggregation result to the user terminal, so that the user terminal can display the aggregation result of the plurality of target entities matching the search request, and the user can view the plurality of target entities at a time through the aggregation result, thereby quickly locating a target entity interested by the user, improving information search efficiency, and saving search time.

The above-mentioned drawbacks are the results of the inventor after practical and careful study, and therefore, the discovery process of the above-mentioned problems and the solutions proposed by the present disclosure to the above-mentioned problems should be the contribution of the inventor in the process of the present disclosure.

It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be further defined and explained in subsequent figures.

To facilitate understanding of the present embodiment, first, a search method disclosed in the embodiments of the present disclosure is described in detail, where an execution subject of the search method provided in the embodiments of the present disclosure is generally a computer device with certain computing capability, and the computer device includes, for example: a terminal device, which may be a User Equipment (UE), a mobile device, a User terminal, a cellular phone, a cordless phone, a Personal Digital Assistant (PDA), a handheld device, a computing device, a vehicle mounted device, a wearable device, or a server or other processing device. In some possible implementations, the search method may be implemented by a processor calling computer readable instructions stored in a memory.

Example one

The following describes a search method provided by the embodiments of the present disclosure by taking an execution subject as a server.

Referring to fig. 1, which is a flowchart of a searching method provided in the embodiment of the present disclosure, the method includes steps S101 to S103, where:

s101, obtaining a search request of a user side.

The User terminal may be a terminal device, a server, or other processing devices, and the terminal device may be a User Equipment (UE), a mobile device, a User terminal, a Personal Digital Assistant (PDA), or the like.

Here, the search request may carry search content input by the user, and the search request processed by the embodiment of the present disclosure is related to a plurality of entities, for example, the user searches "female star with a height of 170cm after 90", and this search request corresponds to a plurality of star entities.

In a specific implementation, a user inputs search content on a search interface, after the user clicks a "search" button, a user side generates a search request and sends the search request to a server, and the server obtains the search request of the user and executes the following step S102.

S102, acquiring a plurality of target entities matched with the search request based on the request type of the search request.

The request type of the search request may include an attribute class and an entity set class.

In a possible implementation manner, when the search request is an attribute-type search request, a plurality of target entities matching the search request may be found based on attribute information of different entities in the knowledge graph.

Wherein the attribute-class search request refers to a search request that characterizes a search intention using a plurality of attribute keywords. Such as: when the search content input by the user in the search page is "women star with a height of 170cm after 90", the plurality of attribute keywords "after 90", "height", "170 cm", "women star" herein represent the search intention of the user.

The knowledge graph may be a semantic network formed by a plurality of nodes and connecting edges between the nodes, where the nodes may represent entities, information of the nodes is related information of the corresponding entities, and the connecting edges between the nodes may represent various semantic relationships between the entities, such as a parental relationship, a couple relationship, a broker, a friend, and the like.

Specifically, after acquiring a search request of a user, a server determines a search type of the search request, extracts a plurality of attribute keywords contained in search content corresponding to the search request after determining that the search type of the search request is an attribute type search request, queries a knowledge graph based on the attribute keywords, and determines whether entities matched with the attribute keywords are stored in the knowledge graph; when the knowledge graph stores the entities matched with the attribute keywords, the entities in the knowledge graph, which accord with the search request of the user, can be fed back to the user.

Illustratively, when the search content input by the user in the search page is "female star with a height of 170cm after 90", and the "search" button is clicked, the user side sends the search request to the server, the server receives the search request, determines that the type of the search request is an attribute type search request, extracts a plurality of attribute keywords contained in the search content corresponding to the search request as "90", "height", "170 cm" and "female star", queries a knowledge graph based on the plurality of attribute keywords, can find out stars matching the attributes of the gender, age and height from a plurality of star entities stored in the knowledge graph, and feeds back the information of the found stars to the user.

In another possible implementation manner, when the search request is an entity set type search request, obtaining associated media content corresponding to the search request; determining a plurality of target entities matching the search request based on the associated media content.

Here, the entity set type search request means that the search intention of the search request corresponds to a plurality of entities, but the search intention is not directly characterized by a plurality of attribute keywords. Such as: when the search content is ' a movie suitable for lovers ' to see ', the search content relates to a plurality of movie entities, but the related entity information cannot be found in the knowledge graph through keywords of the lovers and the movie. In this case, a plurality of target entities matching the search content corresponding to the search request are determined in a manner of acquiring the associated media content corresponding to the search request and determining the target entities from the associated media content.

Wherein the associated media content may include one or more of text documents, text-text mixed documents, pictures, audio, video, and the like.

In a specific implementation, the plurality of associated media contents corresponding to the search request may be determined by the following method, which is specifically described as follows: under the condition that the query intention corresponding to the search request is an objective intention, searching for associated media content with objective answers matched with the search request; and under the condition that the query intention corresponding to the search request is the subjective category intention, searching for the associated media content with the subjective category search result matched with the search request.

Here, the query intention type corresponding to the search request may include an objective class intention and a subjective class intention. The related media content containing the objective answers is recalled according to the search request of the objective intention, and the related media content of the published related subjective opinion-like content is recalled according to the search request of the subjective intention. When searching for the associated media content aiming at the two types of search requests, a standard sentence corresponding to the search request can be obtained by adopting a standard semantic extraction mode, and the associated media content matched with the obtained standard sentence is further searched.

Specifically, a standard sentence corresponding to a search sentence in the search request may be determined based on a pre-trained generalization model; and then based on the standard sentence, obtaining the associated media content matched with the search request. The generalized model is obtained by training a large number of search sentence samples marked with standard sentences, and the generalized model can extract keywords from the search sentences and further convert the extracted keywords into the standard sentences.

For example, when the user inputs search content on the search interface: when the "what the four great works are" or "what the four great works contain", a generalization model trained in advance in the server performs keyword extraction on the search content "what the four great works are" or "what the four great works contain", extracts a search keyword "the four great works" corresponding to the search content, and forms a standard sentence "what the four great works are".

Specifically, after receiving a search request of a user, the server inputs search content corresponding to the search request into the generalized model, determines a standard sentence corresponding to the search request, queries a media content library based on the standard sentence, and determines a plurality of associated media content corresponding to the search request.

Illustratively, the search content input by the user in the search interface is: the server inputs the search content "which of the four great names" into the generalized model after the user clicks the "search" button, determines what the standard sentence corresponding to the search content is "what the four great names are", and queries the related media content corresponding to the search content in the media content library based on the standard sentence.

In a specific implementation, after determining the associated media content matching the search request, a plurality of target entities matching the search request may be determined in the associated media content by the following method, which is described in detail as follows:

acquiring a plurality of entities corresponding to each associated media content in the associated media content; clustering and de-duplicating the multiple entities to obtain multiple processed candidate entities; determining the target entity from the plurality of candidate entities.

Here, the server extracts entities of a plurality of media contents in advance, and may store a correspondence between the identifiers of the media contents and the related information of the extracted entities; the extracted related information of the entity may include identification information of the entity, and information such as an entity name and an entity thumbnail. Fig. 2 shows a schematic diagram of an entity extraction result.

In a specific implementation, the obtained multiple candidate entities are ranked, and the target entity is selected from the multiple candidate entities according to a ranking result, and the obtained multiple candidate entities may be ranked in the following manner, which is specifically described as follows: identifying the intention of the user on the acquired search request, and determining intention classification information of the search request; and sequencing the obtained candidate entities according to the intention classification information and the attribute information of each candidate entity.

The attribute information of the candidate entity may include at least one of classification information of the candidate entity, attribute characteristics of associated media content corresponding to the candidate entity, and the number of times that the same entity information appears in different associated media content.

The classification information of the candidate entity may represent the type of the candidate entity, and may include literature, books, movies, art, life, vehicles, automobiles, society, brands, gourmet food, and the like.

Wherein the attribute characteristics of the associated media content may include: attribute information of an author corresponding to the associated media content, a correlation degree between the associated media content and the search request, and a ranking order of the associated media content in the search.

Here, the attribute information of the author corresponding to the associated media content may include author authority, author influence, and the like; the relevance between the associated media content and the search request is used for indicating whether the associated media content meets the search requirement of the user, and the higher the relevance is, the more the associated media content meets the search requirement of the user; the ranking order of the associated media content in the search may be the ranking order of each associated media content in the search result obtained by searching the search request of the user in the search engine, where the higher the ranking, the more in line with the search requirement of the user.

The intention classification information may be used to indicate a requirement corresponding to the search request of the user, that is, a type of content that the user wants to search for, which may be life, transportation, automobile, society, brand, food, and the like; such as: the method comprises the steps that a search content input by a user on a search interface is 'SUV with which chassis is high', intention identification is carried out on the search content, and intention classification information of a search request is determined to be life, vehicles and automobiles; for another example: the method comprises the steps that search content input by a user on a search interface is 'what a world ten-name form has', intention identification is carried out on the search content, and intention classification information of a search request is determined to be a society, a brand and a watch. The rank of candidate entities that match the intent classification information of the search request is higher than the rank of candidate entities that do not match the intent classification information of the search request.

Here, the more times the same candidate entity appears in different associated media content, the more front the candidate entity ranks.

With reference to the above description, in an implementation, after obtaining a search request of a user, a server determines a search type of the search request, and if the search type of the search request is an entity set type search request, obtains a plurality of associated media contents corresponding to the search request; acquiring a plurality of entities corresponding to each associated media content in a plurality of associated media contents, clustering and de-duplicating the acquired entities, and determining a plurality of candidate entities; the server identifies the intention of the user for the acquired search request, determines intention classification information of the search request, sorts the acquired multiple candidate entities according to the intention classification information, the classification information of each candidate entity, the author authority and the author influence of the associated media content respectively corresponding to each candidate entity, the correlation degree between the associated media content respectively corresponding to each candidate entity and the search request, the ranking order of the associated media content respectively corresponding to each candidate entity in the search, the occurrence frequency of the same candidate entity in different associated media contents and the like, and determines multiple target entities matched with the search request of the user according to the sorting result.

In a specific implementation, after determining a plurality of target entities matching the search request in step S102, a multi-entity aggregation result including the plurality of target entities may be generated in step S103, and the multi-entity aggregation result is returned to the user, which is described in detail below.

S103, generating a multi-entity aggregation result based on the target entities, and returning the multi-entity aggregation result to the user side.

The user side can be an electronic device with a display function, such as a mobile phone, a tablet computer, a computer device and the like.

The multi-entity aggregation result may include identification information of a plurality of target entities, encyclopedic knowledge information and recommendation information corresponding to each target entity, at least one associated media content corresponding to each target entity, function entry information corresponding to each target entity, and the like; here, the identification information may include an entity name, an entity thumbnail, and an arrangement order of the entity in a plurality of target entities; an entity thumbnail can be a hyphen of the entity; the recommendation information can be text introduction content, image-text introduction content, video or audio introduction content and the like for the entity, and can also be encyclopedic knowledge content; the associated media content can be media content related to the entity, and can be a text document, a picture-text mixed document, a picture, audio, video and the like; the function entry information may be used to instruct the user to click on a consumption page entering the target entity, where the consumption page may be, for example, a play interface or a purchase page of the target entity.

In a specific implementation, based on the multiple target entities determined in step S102, a multiple entity aggregation result including the multiple target entities is generated, and the multiple entity aggregation result is returned to the user side, so that the user side displays the multiple entity aggregation result to the user, and the user side can display the multiple target entities matching the search request, and then display a search result related to the target entity based on the target entity of interest selected by the user. The user can see a plurality of target entities at a time through the aggregation result, so that the user can conveniently further screen interested target entities and finally display the media contents related to the target entities interested by the user.

Illustratively, the search content input by the user in the search interface is: "which of the four great works" is available, after a user clicks a "search" button, the server judges that the search type of the search request is an entity set type search request, and then the server inputs the "which of the four great works" of the search sentence into a generalization model, determines what the four great works are of a standard sentence corresponding to the search content, and extracts a keyword corresponding to the standard sentence: the four famous works are used for inquiring the media content library based on the keywords, and all the book information, the article information and the movie information which are stored in the media content library and are related to the four famous works, the water business biography, the dream of the Red mansions, the three countries 'rehearsal' and the Western notes are used as a plurality of related media contents; determining a plurality of entities corresponding to a plurality of associated media contents respectively based on the corresponding relation between the identification of the media contents stored by the server and the extracted relevant information of the entities, acquiring a plurality of entities corresponding to each associated media content in the associated media contents, and clustering and de-duplicating the acquired entities to obtain a plurality of processed candidate entities; identifying user intention for the search content corresponding to the received search request, and determining intention classification information corresponding to the search content as literature and books; according to intention classification information, classification information of a plurality of candidate entities, author authority and author influence of associated media contents corresponding to the candidate entities respectively, correlation degree between the associated media contents corresponding to the candidate entities and the search request, arrangement sequence position of the associated media contents corresponding to the candidate entities in the search and frequency of occurrence of the same book information in different associated media contents, the obtained candidate entities are sequenced, and according to sequencing results, a plurality of target entities matched with the search request of the user are determined to be books ' West Yong ' records, ' Shuihu biography, ' three kingdoms ' and ' Hongtou dream ', and the server generates identification information containing the target entities, encyclopedic knowledge information and/or recommendation information corresponding to the target entities, at least one associated media content corresponding to each target entity, and the like on the basis of the target entities, And a multi-entity aggregation result of information such as function entry information corresponding to each target entity is sent to the user side, and the user side can firstly display a plurality of target entities matched with the search request and then display the search result related to the target entities based on the interested target entities selected by the user.

Illustratively, the search content input by the user in the search interface is: "what movies are suitable for lovers at night" is provided, after a user clicks a "search" button, a server judges that the search type of the search request is an entity set type search request, inputs the search content "what movies are suitable for lovers at night" into a generalized model, determines that a standard sentence corresponding to the search content is "movies suitable for lovers at night", and extracts keywords corresponding to the standard sentence: the search library is queried based on the keywords, and the entity results matched with the attributes of the "night", "lovers" and "movies" are determined to be "love june flower", "love notebook", "old and young", "love you nine weeks and half", "blue lover's festival", and articles, movie works, movie comment contents and the like containing the "love june flower", "love notebook", "old and young", "love you nine weeks and half", "blue lover's festival" stored in the search library are taken as related media contents; determining a plurality of entities respectively corresponding to a plurality of associated media contents according to the corresponding relation between the identification of the media contents stored in the server and the extracted relevant information of the entities, acquiring the plurality of entities corresponding to the associated media contents, and clustering and de-duplicating the acquired plurality of entities to obtain a plurality of processed candidate entities; and identifying the user intention of the search content corresponding to the received search request, and determining intention classification information corresponding to the search content as follows: life, entertainment, movies; sorting the obtained multiple candidate entities according to the intention classification information, classification information of the multiple candidate entities, author authority and author influence of the associated media content corresponding to each candidate entity, correlation degree between the associated media content corresponding to each candidate entity and the search request, arrangement order of the associated media content corresponding to each candidate entity in the search, and the occurrence frequency of the same movie information in different associated media contents, to obtain sorting results of 'fan june-hua', 'love you nine weeks and a half', 'blue valentine' and 'love notebook', 'retroversion and retroversion', aggregating the identification information corresponding to each sorted entity and the related information corresponding to the entity information to generate a multiple entity aggregation result, and sending the multiple entity aggregation result to a user side, the user side can firstly display a plurality of target entities matched with the search request, and then display the search results related to the target entities based on the target entities of interest selected by the user. A specific display page of the multiple target entities displayed by the user side and matched with the search request is shown in fig. 3, when the user does not select an entity with a self-perception from the multiple displayed target entities, the target entities arranged at the top are used as target recommending entities, and the related information of the target recommending entities is displayed on the display page, where the specific display page is shown in fig. 3, where the user side is taken as a mobile phone for example.

The method comprises the steps that after a search request sent by a user side is obtained, a server obtains a plurality of target entities matched with the search request, a multi-entity aggregation result is generated based on the target entities, and the multi-entity aggregation result is returned to the user side.

In an optional implementation manner, before a core algorithm process corresponding to the search method is online, whether a multi-entity aggregation result obtained by the search method is accurate may be detected, if it is determined by the detection that the multi-entity aggregation result obtained by the search method is not accurate, the sorting algorithm, the classification algorithm, and the like are adjusted, and after the multi-entity aggregation result is determined to be accurate, the search method of the steps S101 to S103 is online, where the specific detection step may be the following process: the target entities corresponding to some search requests with objective-like intentions can be sampled and confirmed manually, such as: the keywords corresponding to the sampling detection search content are as follows: in the case of ' four famous works ', whether the obtained entity result is book media content related to ' journey to the West ', ' three kingdoms ' praise ', ' Shuihu Chuan ' and ' Red dream ' is confirmed, and if not, the algorithm needs to be optimized and adjusted; in addition, the target entity corresponding to the search request of the subjective intention can be sampled and evaluated according to an evaluation rule which is manually formulated, wherein the evaluation rule can be a rule based on understanding of a search engine and understanding of user requirements, and the result is manually formulated; the evaluation rule may be that when the plurality of sorted target entities meet the search requirement of the user well, the plurality of sorted target entities are scored as 3; when the plurality of ordered target entities need to be thought by the user to obtain entity results meeting the search requirements of the user, the plurality of ordered target entities are scored as 2; when the plurality of ordered target entities do not meet the entity result of the user search requirement, the plurality of ordered target entities are scored as 0; and sampling and detecting a target entity corresponding to the search request of the subjective intention by adopting the evaluation rule, wherein when the score result is greater than a preset score, the target entity is accurate, and when the accuracy of the sampling detection is greater than or equal to a preset threshold value, the multi-entity aggregation result obtained by the search method is accurate.

The following describes the search method provided by the embodiment of the present disclosure by taking the execution subject as the user side.

Referring to fig. 4, which is a flowchart of a searching method provided in the embodiment of the present disclosure, the method includes steps S401 to S403, where:

s401, responding to the search triggering instruction, and sending a search request.

Here, the search trigger instruction may be a click operation of a search button by a user in a search page. The search request corresponds to a plurality of entities.

In a specific implementation, after a user inputs search content on a search page of a user terminal and clicks a "search" button, the user terminal sends a search request of the user to a server.

In a specific implementation, after the user side sends the search request of the user to the server, the server determines, based on the received search request, the multi-entity aggregation result corresponding to the search request of the user according to the steps S101 to S103 described in the server side, and returns the multi-entity aggregation result to the user side.

S402, receiving a multi-entity aggregation result corresponding to the search request.

And the multi-entity aggregation result comprises relevant information of a plurality of target entities matched with the search request.

Here, the related information of the plurality of target entities may include identification information of the plurality of target entities, encyclopedia knowledge information and/or recommendation information corresponding to each target entity, at least one associated media content corresponding to each target entity, and function portal information corresponding to each recommendation entity, etc.

In a specific implementation, the user side receives a multi-entity aggregation result including information related to a plurality of target entities, which is returned by the server.

And S403, displaying the multi-entity aggregation result.

After receiving the multi-entity aggregation result based on step S402, the identification information of the multiple target entities may be displayed in a first display area of the multiple display areas, and the content information associated with the selected target recommendation entity in the multiple target entities may be displayed in other display areas.

The identification information of the target entities comprises an entity name of each target entity, a thumbnail corresponding to the entity and an arrangement order of the target entities; the thumbnail corresponding to the entity can be a propaganda picture, an introduction picture and the like.

Here, the target recommending entity is a target entity selected by the user among the plurality of target entities.

The content information associated with the target recommending entity may include at least one associated media content corresponding to the target recommending entity, encyclopedia knowledge information and/or recommendation information of the target recommending entity, and function entry information corresponding to the target recommending entity, and the like; the recommendation information can comprise a text introduction, a picture and text introduction, a video or audio introduction and the like of the entity, and the encyclopedic knowledge information is encyclopedic knowledge content for introducing the target recommendation entity; the associated media content can be media content related to the target recommending entity, and can be a text document, a picture and text mixed document, a picture, audio, video and the like; here, the function portal information may be used to indicate that the user clicked into the consumption page of the target recommending entity.

In specific implementation, in a first area of a plurality of display areas, sequentially displaying entity names and thumbnails corresponding to a plurality of target entities in a multi-entity aggregation result according to the arrangement sequence, displaying encyclopedic knowledge information and/or recommendation information of a target recommendation entity selected by a user in a second area of other display areas, displaying information of at least one associated media content corresponding to the target recommendation entity in a third display area of other display areas, and displaying function entry information corresponding to the target recommendation entity in a fourth display area of other display areas.

Illustratively, when the user inputs the search content at the user end as "a movie suitable for lovers at night", the server determines, according to the search request of the user, that the plurality of target entities meeting the search request of the user are movie and television works respectively: the method comprises the steps that a fan of june blossoms, a fan of rejuvenescence, a fan of lingering children, a fan of lingering notebook and a fan of beauty legend in western west are sequentially arranged, a plurality of target entities are sequentially arranged in sequence, namely the fan of june blossoms, the fan of rejuvenescence, the fan of lingering notebooks and the fan of beauty legend in western west, a plurality of entity aggregation results are generated based on the target entities and are returned to a user side, the user side receives the plurality of entity aggregation results sent by a server side, and entity names and entity thumbnails corresponding to each target entity in the target entities are displayed in a first display area according to the arrangement sequence; when the user selects the 'beauty story in west' in the plurality of target entities in the first display area, the 'beauty story in west' is taken as a target recommendation entity, encyclopedic information and recommendation information corresponding to the 'beauty story in west' are displayed in the second display area (here, after the user clicks the 'view encyclopedic information', the user can jump to an encyclopedic knowledge detail page corresponding to the movie and television work), brief information corresponding to related media contents such as movie and television comment contents and highlight segment contents related to the 'beauty story in west' is displayed in the third display area, and function entry information indicating user operation is displayed in the fourth display area (here, the function entry information can be used for viewing the 'beauty story in west'). The display interface of the specific target recommending entity takes the user side as a mobile phone, as shown in fig. 5.

In the embodiment of the disclosure, when a user initiates a search request at a user side, the user side sends the search request to a server, receives a multi-entity aggregation result corresponding to the search request returned by the server, and displays the multi-entity aggregation result to the user; here, the related information of the plurality of target entities included in the multi-entity aggregation result, so that the user side can intuitively display the related information of the plurality of target entities matched with the search request to the user, the user can conveniently and further screen the interested target entities, the information search efficiency is improved, and the search time is saved.

It will be understood by those skilled in the art that in the method of the present invention, the order of writing the steps does not imply a strict order of execution and any limitations on the implementation, and the specific order of execution of the steps should be determined by their function and possible inherent logic.

Based on the same inventive concept, a search device corresponding to the search method is also provided in the embodiments of the present disclosure, and as the principle of solving the problem of the device in the embodiments of the present disclosure is similar to the above search method in the embodiments of the present disclosure, the implementation of the device may refer to the implementation of the method, and repeated details are not repeated.

Example two

Referring to fig. 6, a schematic diagram of a search apparatus 600 according to an embodiment of the present disclosure is shown, where the apparatus includes: a first obtaining module 601, a second obtaining module 602 and a generating module 603; wherein,

the first obtaining module 601 is configured to obtain a search request of a user side, where the search request corresponds to multiple entities.

A second obtaining module 602, configured to obtain, based on a request type of the search request, a plurality of target entities matching the search request.

The generating module 603 is configured to generate a multi-entity aggregation result based on the multiple target entities, and return the multi-entity aggregation result to the user side.

In a possible implementation manner, the second obtaining module 602 is specifically configured to, when the search request is an attribute type search request, find a plurality of target entities matching the search request based on attribute information of different entities in a knowledge graph; wherein the attribute-class search request refers to a search request that characterizes a search intention using a plurality of attribute keywords.

In a possible implementation manner, the second obtaining module 602 is further specifically configured to, in a case that the search request is an entity set type search request, obtain associated media content corresponding to the search request; determining a plurality of target entities matching the search request based on the associated media content.

In a possible implementation manner, the second obtaining module 602 is further specifically configured to obtain a plurality of entities corresponding to each associated media content in the associated media content; clustering and de-duplicating the multiple entities to obtain multiple processed candidate entities; determining the target entity from the plurality of candidate entities.

In a possible implementation manner, the second obtaining module 602 is further specifically configured to rank the obtained multiple candidate entities, and select the target entity from the multiple candidate entities according to a ranking result.

In a possible implementation manner, the second obtaining module 602 is further specifically configured to determine intention classification information of the search request based on the search request; and sequencing the obtained candidate entities according to the intention classification information and the attribute information of the candidate entities.

In a possible implementation manner, the attribute information of the candidate entity includes at least one of classification information of the candidate entity, attribute characteristics of associated media content corresponding to the candidate entity, and the number of times that the same candidate entity appears in different associated media content; the attribute characteristics of the associated media content include: attribute information of an author, a correlation degree between the associated media content and the search request, and an arrangement order of the associated media content in the search.

In a possible implementation manner, the second obtaining module 602 is further specifically configured to determine, based on a pre-trained generalization model, a standard statement corresponding to a search statement in the search request; and acquiring the associated media content matched with the standard sentence.

In a possible implementation manner, the second obtaining module 602 is further specifically configured to, in a case that a query intention corresponding to the search request is an objective-type intention, search for associated media content having an objective answer matching the search request; and under the condition that the query intention corresponding to the search request is the subjective category intention, searching for the associated media content with the subjective category search result matched with the search request.

According to the method and the device for searching the information, after the search request sent by the user side is obtained, the server obtains the target entities matched with the search request, the multi-entity aggregation result is generated based on the target entities, and the multi-entity aggregation result is returned to the user side.

Referring to fig. 7, a schematic diagram of another search apparatus 700 provided in the embodiment of the present disclosure is shown, the apparatus including: a sending module 701, a receiving module 702 and a display module 703; wherein,

a sending module 701, configured to send a search request in response to a search trigger instruction; the search request corresponds to a plurality of entities.

A receiving module 702, configured to receive a multi-entity aggregation result corresponding to the search request; and the multi-entity aggregation result comprises the relevant information of a plurality of target entities matched with the search request.

A display module 703, configured to display the multi-entity aggregation result.

In a possible implementation manner, the presentation module 703 is specifically configured to present, in a first presentation area of a plurality of presentation areas, the attribute information of the target entities, and present, in other presentation areas, content information associated with a selected target recommending entity in the target entities.

The description of the processing flow of each module in the device and the interaction flow between the modules may refer to the related description in the above method embodiments, and will not be described in detail here.

Based on the same technical concept, the embodiment of the application also provides computer equipment. Referring to fig. 8, a schematic structural diagram of a computer device 800 provided in the embodiment of the present application includes a processor 801, a memory 802, and a bus 803. The memory 802 is used for storing execution instructions and includes a memory 8021 and an external memory 8022; the memory 8021 is also referred to as an internal memory, and is used for temporarily storing operation data in the processor 801 and data exchanged with an external storage 8022 such as a hard disk, the processor 801 exchanges data with the external storage 8022 through the memory 8021, and when the computer apparatus 800 operates, the processor 801 communicates with the storage 802 through the bus 803, so that the processor 801 executes the following instructions:

acquiring a search request of a user side, wherein the search request corresponds to a plurality of entities; acquiring a plurality of target entities matched with the search request according to the request type of the search request; and generating a multi-entity aggregation result based on the target entities, and returning the multi-entity aggregation result to the user side.

Or cause the processor 801 to execute the following instructions:

responding to a search triggering instruction, and sending a search request; the search request corresponds to a plurality of entities; receiving a multi-entity aggregation result corresponding to the search request; the multi-entity aggregation result comprises relevant information of a plurality of target entities matched with the search request; and displaying the multi-entity aggregation result.

The embodiments of the present disclosure also provide a computer-readable storage medium, on which a computer program is stored, where the computer program is executed by a processor to perform the steps of the search method described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The computer program product of the search method provided in the embodiments of the present disclosure includes a computer-readable storage medium storing a program code, where instructions included in the program code may be used to execute the steps of the search method described in the above method embodiments, which may be referred to specifically for the above method embodiments, and are not described herein again.

The embodiments of the present disclosure also provide a computer program, which when executed by a processor implements any one of the methods of the foregoing embodiments. The computer program product may be embodied in hardware, software or a combination thereof. In an alternative embodiment, the computer program product is embodied in a computer storage medium, and in another alternative embodiment, the computer program product is embodied in a Software product, such as a Software Development Kit (SDK), or the like.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the system and the apparatus described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system, apparatus, and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and there may be other divisions when actually implemented, and for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection of devices or units through some communication interfaces, and may be in an electrical, mechanical or other form.

The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.

In addition, functional units in the embodiments of the present disclosure may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer-readable storage medium executable by a processor. Based on such understanding, the technical solution of the present disclosure may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present disclosure. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.

Finally, it should be noted that: the above-mentioned embodiments are merely specific embodiments of the present disclosure, which are used for illustrating the technical solutions of the present disclosure and not for limiting the same, and the scope of the present disclosure is not limited thereto, and although the present disclosure is described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: any person skilled in the art can modify or easily conceive of the technical solutions described in the foregoing embodiments or equivalent technical features thereof within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the embodiments of the present disclosure, and should be construed as being included therein. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.

Claims

1. A method of searching, comprising:

2. The method of claim 1, wherein obtaining a plurality of target entities matching the search request based on the request type of the search request comprises:

3. The method according to claim 1 or 2, wherein the obtaining a plurality of target entities matching the search request based on the request type of the search request comprises:

4. The method of claim 3, wherein determining a plurality of target entities matching the search request based on the associated media content comprises:

determining the target entity from the plurality of candidate entities.

5. The method of claim 4, wherein determining the target entity from the plurality of candidate entities comprises:

6. The method of claim 5, wherein ranking the obtained plurality of candidate entities comprises:

7. The method according to claim 6, wherein the attribute information of the candidate entity comprises at least one of classification information of the candidate entity, attribute characteristics of associated media content corresponding to the candidate entity, and the number of times that the same candidate entity appears in different associated media content;

8. The method of any one of claims 1 to 7, further comprising:

9. The method of claim 3, wherein the associated media content corresponding to the search request is obtained according to the following steps:

and acquiring the associated media content matched with the standard sentence.

10. The method of claim 3, wherein the associated media content comprises at least one of:

text documents, text-text mixed documents, pictures, audio, video.

11. The method of claim 3, wherein obtaining the associated media content corresponding to the search request comprises:

12. A method of searching, comprising:

and displaying the multi-entity aggregation result.

13. The method of claim 12, wherein presenting the multi-entity aggregation result comprises:

14. A search apparatus, comprising:

the first acquisition module is used for acquiring a search request of a user side, wherein the search request corresponds to a plurality of entities;

the second acquisition module is used for acquiring a plurality of target entities matched with the search request based on the request type of the search request;

15. A search apparatus, comprising:

the sending module is used for responding to the search triggering instruction and sending a search request; the search request corresponds to a plurality of entities;

a receiving module, configured to receive a multi-entity aggregation result corresponding to the search request; the multi-entity aggregation result comprises relevant information of a plurality of target entities matched with the search request;

16. A computer device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, the processor and the memory communicating over the bus when a computer device is run, the machine-readable instructions when executed by the processor performing the steps of the search method of any one of claims 1 to 11 or performing the steps of the search method of any one of claims 12 to 13.

17. A computer-readable storage medium, characterized in that a computer program is stored thereon, which computer program, when being executed by a processor, is adapted to carry out the steps of the search method according to one of the claims 1 to 11 or to carry out the steps of the search method according to one of the claims 12 to 13.