CN114064930A

CN114064930A - Data display method and device, computer equipment and storage medium

Info

Publication number: CN114064930A
Application number: CN202111433600.3A
Authority: CN
Inventors: 徐晨娜; 陈智发; 黄金鑫
Original assignee: Beijing ByteDance Network Technology Co Ltd
Current assignee: Beijing ByteDance Network Technology Co Ltd
Priority date: 2021-11-29
Filing date: 2021-11-29
Publication date: 2022-02-18

Abstract

The present disclosure provides a data presentation method, apparatus, computer device and storage medium, wherein the method comprises: responding to a query request sent by a user, and determining a query entity contained in the query request; determining a recommending entity corresponding to the query entity, and determining an incidence relation between the recommending entity and the query entity based on a target knowledge graph; determining recommendation description information of the recommending entity relative to the querying entity based on the incidence relation; and displaying the recommending entity in a display interface, and displaying the recommendation description information of the recommending entity. According to the embodiment of the disclosure, the recommendation description information of the recommending entity and the recommending entity is displayed, and the correlation between the recommending entity and the query entity can be displayed for the user, so that the user can obtain more information through one-time retrieval results, and further the retrieval efficiency of the user is improved.

Description

Data display method and device, computer equipment and storage medium

Technical Field

The present disclosure relates to the field of computer technologies, and in particular, to a data display method and apparatus, a computer device, and a storage medium.

Background

With the popularization of search engines, the demand of users on the retrieval efficiency is higher and higher, and in the existing scheme of retrieving the recommending entities with the associated relationship with the query entities, the retrieval results usually only show the recommending entities related to the query entities, but do not show the associated relationship between the query entities and the recommending entities, so that the retrieval demand of users is usually difficult to meet.

For example, if the query entity retrieved by the user is a star and the recommendation entity presented by the retrieval result is a movie, when the recommendation entity is presented, whether the star is a show or a lead actor with respect to the movie is not presented at the same time. Therefore, when the user wants to know the association relationship between the recommending entity and the querying entity, the association relationship needs to be obtained through secondary retrieval and other manners, so that the retrieval efficiency is low, and the user experience is poor.

Disclosure of Invention

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

In a first aspect, an embodiment of the present disclosure provides a data display method, including: responding to a query request sent by a user, and determining a query entity contained in the query request; determining a recommending entity corresponding to the query entity, and determining an incidence relation between the recommending entity and the query entity based on a target knowledge graph; determining recommendation description information of the recommending entity relative to the inquiring entity based on the incidence relation, wherein the recommendation description information is used for representing entity correlation between the recommending entity and the inquiring entity; and displaying the recommending entity in a display interface, and displaying the recommendation description information of the recommending entity.

In an optional embodiment, the association relationship includes a plurality of association relationships; the determining recommendation description information of the recommending entity relative to the querying entity based on the incidence relation comprises: determining the priority of each incidence relation; determining a first target incidence relation meeting the priority requirement in the incidence relations; and determining recommendation description information of the recommending entity relative to the query entity based on the association description information corresponding to the first target association relation.

In an optional embodiment, the determining recommendation description information of the recommending entity relative to the querying entity based on the association relationship includes: determining first association description information corresponding to the association relationship under the condition that the association relationship is a direct association relationship; and generating first interpretation information of the recommending entity based on the first association description information and the inquiring entity, and determining the first interpretation information as the recommending description information.

In an optional embodiment, the determining recommendation description information of the recommending entity relative to the querying entity based on the association relationship includes: determining a media entity located between the recommending entity and the querying entity in the target knowledge graph under the condition that the incidence relation is an indirect incidence relation; determining second association description information based on an association relationship between the media entity and a target entity, wherein the target entity comprises: the recommending entity and/or the querying entity; and generating second interpretation information of the recommending entity based on the second association description information and the media entity, and determining the second interpretation information as the recommending description information.

In an optional implementation manner, when the association relationship is an indirect association relationship, it is determined whether the recommended entity and the query entity are located in the same data set, where entities located in the same data set correspond to the same type tag; and under the condition that the recommending entity and the inquiring entity are judged to be positioned in the same data set, generating third interpretation information of the recommending entity based on the type tag and the inquiring entity, and determining the third interpretation information as the recommendation description information.

In an optional embodiment, the determining recommendation description information of the recommending entity relative to the querying entity based on the association relationship includes: determining a second target incidence relation contained in a preset relation list in the incidence relations under the condition that the incidence relations contain multiple incidence relations; and determining recommendation description information of the recommending entity relative to the inquiring entity based on the second target incidence relation.

In an optional implementation manner, the determining a recommending entity corresponding to the querying entity includes: inquiring an initial recommending entity corresponding to the inquired entity in an entity library; performing correlation calculation on the initial recommending entities according to a correlation model to obtain a correlation calculation result of each initial recommending entity, wherein the correlation calculation result is used for representing the degree of correlation between the corresponding initial recommending entity and the inquiring entity; and determining a recommending entity meeting the relevance requirement in the initial recommending entities as a recommending entity corresponding to the query entity based on the relevance calculation result.

In an optional embodiment, the determining the association relationship between the recommending entity and the querying entity based on the target knowledge-graph includes: and under the condition that the medium entity does not exist between the recommending entity and the inquiring entity based on the target knowledge graph, determining the association relationship to be a direct association relationship.

In an optional embodiment, the method further comprises: determining whether the media entity is in direct association with the recommending entity and the querying entity under the condition that the media entity exists between the recommending entity and the querying entity based on the target knowledge graph; and under the condition that the direct association relationship is determined and the association relationship between the medium entity and the recommending entity is determined to be the same as the association relationship between the medium entity and the query entity, determining that the association relationship between the recommending entity and the query entity is an indirect association relationship.

In a second aspect, an embodiment of the present disclosure further provides a data display apparatus, including: the first determination module is used for responding to a query request sent by a user and determining a query entity contained in the query request; the second determination module is used for determining a recommending entity corresponding to the query entity and determining the incidence relation between the recommending entity and the query entity based on a target knowledge graph; a third determining module, configured to determine recommendation description information of the recommending entity relative to the querying entity based on the association relationship, where the recommendation description information is used to characterize entity relevance between the recommending entity and the querying entity; and the display module is used for displaying the recommending entity in a display interface and displaying the recommendation description information of the recommending entity.

In a third 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 described above, or any possible implementation of the first aspect.

In a fourth 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 in the first aspect or any one of the possible implementation manners of the first aspect.

The embodiment of the disclosure provides a data display method and device, computer equipment and a storage medium. In the embodiment of the disclosure, the entity correlation between the query entity and the recommending entity can be embodied by determining the incidence relation between the recommending entity and the query entity based on the target knowledge graph and further determining the recommendation description information of the recommending entity relative to the query entity according to the incidence relation; by displaying the recommending entity and the recommending description information of the recommending entity, the relevance between the recommending entity and the query entity can be displayed for the user, so that the user can obtain more information through one-time retrieval results, and further the retrieval efficiency of the user is improved.

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 is a flow chart illustrating a data presentation method provided by an embodiment of the present disclosure;

FIG. 2 illustrates a structural schematic diagram of a knowledge-graph provided by an embodiment of the present disclosure;

FIG. 3 is a diagram illustrating a presentation manner of a query result according to an embodiment of the present disclosure;

FIG. 4a is a schematic diagram illustrating the structure of a partial knowledge-graph of a target knowledge-graph provided by an embodiment of the present disclosure;

FIG. 4b shows a schematic diagram of a portion of a target knowledge-graph provided by an embodiment of the present disclosure;

FIG. 5 is a flow chart illustrating another data presentation method provided by an embodiment of the present disclosure;

FIG. 6 is a schematic diagram of a data presentation device provided by an embodiment of the present disclosure;

fig. 7 shows a schematic diagram of a computer 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.

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.

The term "and/or" herein merely describes an associative relationship, meaning that three relationships may exist, e.g., a and/or B, may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the term "at least one" herein means any one of a plurality or any combination of at least two of a plurality, for example, including at least one of A, B, C, and may mean including any one or more elements selected from the group consisting of A, B and C.

Research shows that in the existing scheme of retrieving and querying the recommending entities with the association relationship, the retrieval result usually only shows the recommending entities related to the querying entity, but does not show the association relationship between the querying entity and the recommending entities, and the retrieval requirement of a user is usually difficult to meet.

Based on the research, the present disclosure provides a data display method, apparatus, computer device, and storage medium. In the embodiment of the disclosure, the entity correlation between the query entity and the recommending entity can be embodied by determining the incidence relation between the recommending entity and the query entity based on the target knowledge graph and further determining the recommendation description information of the recommending entity relative to the query entity according to the incidence relation; by displaying the recommending entity and the recommending description information of the recommending entity, the relevance between the recommending entity and the query entity can be displayed for the user, so that the user can obtain more information through one-time retrieval results, and further the retrieval efficiency of the user is improved.

To facilitate understanding of the present embodiment, first, a data presentation method disclosed in the embodiments of the present disclosure is described in detail, where an execution subject of the data presentation 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 or a server or other processing device, wherein the computer device should be installed with a client capable of performing retrieval services. In some possible implementations, the data presentation method may be implemented by a processor calling computer readable instructions stored in a memory.

Referring to fig. 1, a flowchart of a data display method provided in the embodiment of the present disclosure is shown, where the method includes steps S101 to S107, where:

s101: in response to a query request sent by a user, a query entity contained in the query request is determined.

In an embodiment of the present disclosure, the query request is a request sent by a user through a retrieval function in a client, where the client may be a client having a retrieval function.

Specifically, the user can input the search information containing the query entity in the search information input field of the client; after detecting the retrieval information, the client determines that the query request sent by the user is detected. In addition, the user can input voice information through the voice input function of the client, the client can analyze the voice information to obtain retrieval information containing the query entity, and the input form of the retrieval information is not specifically limited by the disclosure so as to be realized.

After the client side obtains the query request, the client side can analyze the retrieval information corresponding to the query request, so that a query entity in the retrieval information is obtained.

For example, if the search information is "actor liu XX", the search information may be analyzed, and "liu XX" in the search information may be determined as the query entity.

S103: and determining a recommending entity corresponding to the query entity, and determining an incidence relation between the recommending entity and the query entity based on a target knowledge graph.

In the embodiment of the present disclosure, after the query entity is determined, a recommending entity having an association relationship with the query entity may be queried.

In an optional embodiment, if the query entity is star X, the recommending entity having an association relationship with the query entity may be a work performed by star X, family and friend of star X, other stars Y performing a work simultaneously with star X, and the like.

Specifically, after the query entity is determined, a target knowledge graph can be determined, and the association relationship between the recommended entity and the query entity is determined based on the target knowledge graph. The target knowledge graph comprises an inquiry entity, a recommending entity and an incidence relation between the recommending entity and other entities.

Here, a plurality of knowledge-maps may be acquired in advance, and then, a knowledge-map containing both the recommending entity and the querying entity among the plurality of knowledge-maps is determined as a target knowledge-map. Assuming that there are multiple recommending entities, a knowledge graph containing all recommending entities and querying entities can be determined as a target knowledge graph in multiple knowledge graphs. Here, the target knowledge-graph may be one or more knowledge-graphs of a plurality of knowledge-graphs. In addition, a specified knowledge-graph determined in advance for the query entity can be determined, and a target knowledge-graph is determined according to the specified knowledge-graph.

S105: and determining recommendation description information of the recommending entity relative to the inquiring entity based on the incidence relation, wherein the recommendation description information is used for representing entity correlation between the recommending entity and the inquiring entity.

Here, it is assumed that S is denoted as a query entity, O is denoted as a recommending entity, and P is used to denote entity correlation between the query entity and the recommending entity, where S is an abbreviation for Subject, O is an abbreviation for Object, and P is an abbreviation for Predicate.

Fig. 2 is a schematic diagram showing a partial graph of a target knowledge-graph corresponding to a query entity S. As can be seen from fig. 2, the partial map shown in the display diagram is a map of a net structure. In FIG. 2, the symbol S is the query entity and the symbol O₁Is recommended to the entity "Liu X", where S → O₁Represented as an entity relationship in the knowledge-graph as shown in figure 2.

In the target knowledge-graph, P is used to characterize S and O₁The relationship between them, in FIG. 2, P₁Denoted as daughter, and therefore, the recommendation description information of the recommending entity determined based on the incidence relation with respect to the querying entity is "O₁Daughter of S ".

In addition, the recommendation description information is used to characterize entity correlation between the recommending entity and the querying entity, where the entity correlation may be an association relationship between the recommending entity and the querying entity, for example, as shown in fig. 2, the recommending entity O₁The entity correlation with the query entity S may be a "parent-child relationship".

S107: and displaying the recommending entity in a display interface, and displaying the recommendation description information of the recommending entity.

In an embodiment of the present disclosure, when a query result determined for the query request is displayed in a display interface, the query result may include the recommending entity and recommendation description information of the recommending entity.

In the embodiment of the present disclosure, a presentation manner of the query result may be as shown in fig. 3, and the search result may be presented through a card template, where a first portion of the card template is used to present the recommending entity, including a related picture of the recommending entity and an entity name of the recommending entity, and a second portion is used to present recommendation description information of the recommending entity. For example, the first part shows the recommending entity O₁The picture and the name of "Liu X", and the second part is used for showing the women with the recommendation description information of "Liu XXAnd (c) a child.

In the embodiment of the disclosure, the entity correlation between the query entity and the recommending entity can be embodied by determining the incidence relation between the recommending entity and the query entity based on the target knowledge graph and further determining the recommendation description information of the recommending entity relative to the query entity according to the incidence relation; by displaying the recommending entity and the recommending description information of the recommending entity, the relevance between the recommending entity and the query entity can be displayed for the user, so that the user can obtain more information through one-time retrieval results, and further the retrieval efficiency of the user is improved.

In an optional embodiment, in step S103, determining the recommending entity corresponding to the querying entity specifically includes the following processes:

and S1031, querying the initial recommending entity corresponding to the query entity in the entity library.

In the embodiment of the disclosure, the entity having an association relationship with the query entity may be determined as an initial recommended entity by performing retrieval in the entity library according to the determined query entity.

In an alternative embodiment, an entity having a mapping relationship with the query entity may be searched in the entity library, and the searched entity may be determined as the initial recommended entity.

In another alternative embodiment, at least one knowledge-graph associated with the querying entity may also be determined in the entity repository, and then the initial recommended entity may be looked up in the at least one knowledge-graph associated with the querying entity. In specific implementation, in a knowledge graph associated with a query entity, an entity having a corresponding association relationship with the query entity may be determined as an initial recommended entity, where the corresponding association relationship may be understood as a one-degree-edge association relationship or a two-degree-edge association relationship.

Here, the one-degree-edge association relationship is used to characterize that no other entity is included between the query entity and the recommending entity, such as the query entity S and the recommending entity O shown in FIG. 2₁There are no other entities in between; the above two-degree edge association relation is used for the watchOther entities (i.e., media entities in the following) are included between the query entity and the recommending entity, and the media entities have the same entity relevance between the recommending entity and the query entity. Entity relationships S → O such as those shown in FIG. 2₃Query entity S and recommendation entity O₃There are other entities O in between₂(i.e., media entities).

In the knowledge-graph shown in FIG. 2, wherein the entity O₂The association relationship between the "film and television works" and the entity S "liu XX" is a one-degree edge association relationship, wherein the one-degree edge association relationship is as follows: entity O₂The leading actor P of the' film and television works₁Is entity "Liu XX". As shown in fig. 2, the relationship between the entity "XX" and the entity "liu XX" is a two-degree edge relationship, wherein the two-degree edge relationship is: the entity "Liu XX" and the entity "Wenxx" together have a "movie and television work O₂”。

S1032, performing relevance calculation on the initial recommended entities according to the relevance model to obtain a relevance calculation result of each initial recommended entity, wherein the relevance calculation result is used for representing the relevance degree between the corresponding initial recommended entity and the query entity.

In the embodiment of the present disclosure, after the initial recommending entity is determined, the initial recommending entity and the recommending entity may be respectively input into a correlation model, and the correlation between each initial recommending entity and the recommending entity is respectively calculated, so as to obtain a corresponding correlation calculation result.

In specific implementation, the entity type of each initial recommended entity can be determined, the calculation mode of the correlation is determined according to the determined entity type, the correlation between the initial recommended entity and the query entity is calculated according to the corresponding calculation mode, and then the corresponding correlation calculation result is obtained. Wherein the entity type comprises at least one of: characters, works (movie works, book works, photographic works), honor, awards, and the like.

In the embodiment of the present disclosure, after the calculation mode is determined, the correlation between the initial recommending entity and the querying entity may be calculated according to the calculation mode through the correlation mode, so as to obtain a corresponding correlation calculation result.

For example, assume that the entity type of the initial recommending entity is a person. At this time, the above-described correlation may be calculated from the relationship between the persons. Specifically, a relationship between the query entity and the initial recommending entity may be determined, and then a correlation calculation result of the initial recommending entity is determined according to the determined relationship. For example, the relativity of the direct family such as spouse, parents and children is greater than that of the collateral family such as Bo, T, Gu, Jiu and aunt.

For example, assume that the entity type of the initial recommending entity is a movie work. At this time, the correlation may be calculated from the popularity of the movie. Specifically, the popularity tag of each movie and television work can be acquired, and whether the movie and television work is a hot-broadcast work or not is determined according to the popularity tag of the movie and television work. If a hot-cast work is determined, then a determination may be made that the association between the movie work and the query entity is high.

Or, when the entity type of the initial recommending entity is a work, the relevance can be determined according to the participation degree of the inquiring entity in the recommending entity. For example, the recommending entity is a movie work. Specifically, the participation degree between the query entity and the initial recommending entity can be determined, and then the correlation calculation result of the initial recommending entity is determined according to the determined participation degree.

Specifically, the participation degree of the query entity in the movie and television work as the lead actor is higher than that of the lead actor, so that the relevance of the query entity in the movie and television work as the lead actor is higher than that of the query entity in the movie and television work.

S1033, based on the correlation calculation result, determining a recommending entity meeting the correlation requirement in the initial recommending entity as the recommending entity corresponding to the query entity.

After the correlation calculation result is obtained, the correlation calculation result may be analyzed, and the initial recommending entity with a higher degree of correlation may be determined as the recommending entity corresponding to the query entity.

In the disclosed embodiment, the correlation calculation result may be a percentage class value, for example, the correlation calculation result may be N%, where N is a value within 0-100. In addition, the correlation calculation result may be the rank identification information, for example, all the rank identification information is divided into one to M ranks, where M ranks are the highest and one rank is the lowest, for example, the correlation calculation result is P ranks, where P is a positive integer between 1 and M.

Assume that the correlation calculation results are percentage class values. At this time, whether the initial recommending entity satisfies the relevance requirement may be determined by a relevance threshold. Specifically, each correlation calculation result may be compared with a correlation threshold, and further, the initial recommending entity corresponding to the correlation calculation result that is greater than or equal to the correlation threshold is determined as the recommending entity corresponding to the query entity. For example, the correlation calculation results are respectively 62%, 32%, and the like, the correlation threshold is set to 60%, and it can be known through calculation that 62% of the correlation calculation results is greater than the correlation threshold, at this time, the initial recommending entity corresponding to 62% of the correlation calculation results may be determined as the recommending entity corresponding to the query entity.

Further assume that the correlation calculation result may also be rank identification information. At this time, whether the initial recommending entity satisfies the relevance requirement may be determined by a relevance rank threshold. Specifically, each correlation calculation result may be compared with a correlation level threshold, and further, the initial recommended entity corresponding to the correlation calculation result that is greater than or equal to the correlation level threshold is determined as the recommended entity corresponding to the query entity. For example, the correlation calculation results are respectively three levels, one level, and the threshold of the correlation level is set as two levels, and it can be known through calculation that the three levels of the correlation calculation results are greater than the two levels of the threshold of the correlation level, at this time, the initial recommending entity corresponding to the three levels of the correlation calculation results can be determined as the recommending entity corresponding to the query entity.

According to the description, the initial recommending entities are screened in a correlation calculation mode of the initial recommending entities and the query entities, the recommending entities meeting the correlation requirement can be accurately determined for the query entities from the initial recommending entities, and therefore the initial recommending entities with low correlation degree with the query entities in the initial recommending entities can be filtered, and the determined recommending entities can better meet the query requirements of users.

In the embodiment of the present disclosure, after determining the recommending entity corresponding to the query entity in the manner described above, the association relationship between the recommending entity and the query entity may be determined based on the target knowledge graph.

In an optional implementation manner, the step of determining the association relationship between the recommending entity and the querying entity based on the target knowledge graph in step S103 specifically includes the following processes:

and under the condition that the medium entity does not exist between the recommending entity and the inquiring entity based on the target knowledge graph, determining the association relationship to be a direct association relationship.

In the embodiment of the disclosure, if the first-degree association relationship between the query entity and the recommending entity is determined, the query entity and the recommending entity are determined to be in a direct association relationship.

For example, a local knowledge-graph used to characterize the association between the query entity and the recommending entity in the target knowledge-graph shown in FIG. 2. Wherein the recommending entity "O₁A relationship branch is included between Liu X 'and the query entity Liu XX', and the corresponding relationship of the relationship branch is P₁Then there is a one-degree-edge association, i.e. a direct association, between the querying entity and the recommending entity.

In addition, in FIG. 2, if the entity O is recommended₃Is "week XX", at which time, the recommending entity O₃And the query entity S contains two incidence relations, then the entity O between the two incidence relations₂The media entities are the query entities and the recommendation entities, and the query entities and the recommendation entities are related in two degrees, namely, are indirectly relatedIs described.

According to the description, the incidence relation between the recommending entity and the inquiring entity can be accurately determined by judging the incidence relation between the recommending entity and the inquiring entity according to the medium entity, so that different recommending description information can be determined according to different incidence relations, and more accurate recommending description information can be obtained.

In the embodiment of the present disclosure, when querying the association relationship between the entity and the media entity, the following process is specifically included:

s11, determining whether the media entity is in direct association with the recommending entity and the inquiring entity under the condition that the media entity exists between the recommending entity and the inquiring entity based on the target knowledge graph;

s12, determining that the association relationship between the recommending entity and the inquiring entity is indirect association relationship under the condition that the direct association relationship is determined and the association relationship between the media entity and the recommending entity is determined to be the same as the association relationship between the media entity and the inquiring entity.

As can be seen from the above description, the embodiment of the present disclosure determines the association relationship between the recommending entity and the querying entity through the media entity. If no medium entity exists between the recommending entity and the inquiring entity, the incidence relation between the recommending entity and the inquiring entity is a direct incidence relation; if the media entity exists, it can be determined through the above steps S11 and S12 whether the media entity meets the requirements described in the above steps, and if so, it is determined that the recommended entity and the query entity are in an indirect association relationship.

For example, as shown in FIG. 2, S is the query entity, O₃Recommending entities, S and O, for querying entity S₃In the middle of which the above-mentioned mediator entity O is present₂. At this time, the medium entity O can be judged₂And recommending entity S₁The correlation between them, and determining the media entity O₂And whether the association relation with the query entity S is a direct association relation or not. If it is determined that the relationship is a direct association relationship, the correlation is determinedMass entity O₂And recommending entity O₃The association relationship between them, and the media entity O₂Whether the association relation with the query entity S is the same or not is the medium entity O₂And recommending entity O₃P and a media entity O between₂Whether P is the same as between querying entities S.

As shown in fig. 2, the media entity O₂Association relation 'P' with query entity S₂Dielectric entity O ═ director₂And recommending entity O₃Association relation "P" between₃Then, P is given as a lead actor₂And P₃If the two entities are the same, the query entity S and the recommending entity O₃The association relationship between them is an indirect association relationship.

According to the description, if the medium entity exists between the recommending entity and the inquiring entity, whether the recommending entity and the inquiring entity are in the indirect association relationship can be determined by determining the relationship between the medium entity and the recommending entity and the inquiring entity, and after the indirect association relationship is determined, more accurate recommendation description information can be determined according to the indirect association relationship.

In the embodiment of the present disclosure, when the association relationship between the recommending entity and the querying entity includes a plurality of association relationships, the step S105: determining recommendation description information of the recommending entity relative to the querying entity based on the incidence relation, specifically comprising the following processes:

(1) and determining the priority of each incidence relation.

(2) And determining a first target association relation meeting the priority requirement in the plurality of association relations.

(3) And determining recommendation description information of the recommending entity relative to the query entity based on the association description information corresponding to the first target association relation.

In the embodiment of the present disclosure, it is assumed that a plurality of association relationships are included between the query entity and any one of the recommending entities, and at this time, the priority of each association relationship may be set. Then, a first target association that satisfies the priority requirement is determined among the plurality of associations, for example, an association with the highest priority may be selected among the plurality of associations as the first target association.

For example, the entity types of the recommending entity and the querying entity are both persons, and in this case, the priority order of the plurality of association relationships between the recommending entity and the querying entity may be: the direct relatives > the collateral relatives > the friends > the colleagues > the native place > the nationality.

For example, the recommending entity is O₁Query entity S is "Liu XX", where S and O₁The correlation relationship is as follows: the immediate relatives and nationality are China. Then, recommending entity O₁The priority of the association relation of the direct relatives in the plurality of association relations with the query entity S is higher than the priority of the association relation with the same nationality. At this time, the association "immediate" with the highest priority among the plurality of associations may be set as the first target association.

After the first target association relationship between the recommending entity and the inquiring entity is determined, association description information corresponding to the first target association relationship can be determined, and then recommendation description information of the recommending entity relative to the inquiring entity is determined according to the association description information. Specifically, the association description information may be used to indicate a generation rule of the recommendation description information.

For example, if S is the query entity "Liu XX", O₁For recommending entity "Liu X", the first target association between the querying entity and the recommending entity is P₁Girl. Then, the association description information corresponding to the first target association relationship may be "daughter", and at this time, based on the association description information, it may be determined that the recommendation description information of the recommending entity relative to the querying entity is "daughter of liu XX".

According to the description, the first target incidence relation meeting the priority requirement is determined in the incidence relations through the priorities of the incidence relations, and then the recommendation description information is determined according to the first target incidence relation, so that the incidence relations capable of accurately describing the correlation between the recommendation entity and the query entity can be screened out from the incidence relations, and more accurate recommendation description information can be preferentially displayed for a user.

In an optional embodiment, in S105, determining recommendation description information of the recommending entity relative to the querying entity based on the association relationship, further includes the following processes:

s1051, determining the first association description information corresponding to the association relation under the condition that the association relation is a direct association relation.

S1052, generating first interpretation information of the recommending entity based on the first association description information and the inquiring entity, and determining the first interpretation information as the recommending description information.

In the embodiment of the present disclosure, when it is determined that the association relationship between the recommending entity and the querying entity is a direct association relationship, the first association description information corresponding to the association relationship may be determined.

As can be seen from the above description, if multiple direct association relationships may exist between the recommending entity and the querying entity, at this time, the multiple direct association relationships may be sorted according to priority, a direct association relationship with the highest priority (i.e., the first target association relationship) is determined, and the first association description information corresponding to the direct association relationship with the highest priority is determined.

As can be seen from the above description, S is used to characterize Subject (i.e., S is the Subject), P is used to characterize Predicate (i.e., P is the Predicate), and O is used to characterize Object (i.e., O is the Object).

The first association description information contains at least one generation rule of the first interpretation information. For example, the generation rule may be "S → O", i.e.: p of S; alternatively, the generation rule may be "S ← O", that is: p is S. It should be understood that the first interpretation information here is used to determine the recommendation description information described above.

When the generation rule of the first association description information is 'P of S', if the query entity S is 'Liu XX', recommending the entity O₁To "liux", P ═ daughter, then, based on the generation rule "P of S", it can be determined that the first interpretation information of the recommending entity with respect to the querying entity is "Daughter of Liu XX ". At this time, the first interpretation information may be determined as corresponding recommendation description information.

Or, when the generation rule of the first association description information is "P is S", if the query entity S is "liu XX", recommending the entity O₁To "liu X", P ═ daughter, then, based on the generation rule "P is S", it may be determined that the first interpretation information of the recommending entity with respect to the querying entity is "daughter is liu X". At this time, the first interpretation information may be determined as corresponding recommendation description information.

For another example, if the query entity S is "Liu XX", the recommendation entity is the movie and television work O₃，P₁Then, based on the generation rule of the first interpretation information included in the first association description information, it may be determined that the recommendation description information of the recommending entity relative to the querying entity is "the lead actor is liuxx", or "liuxx is the lead actor".

According to the description, after the incidence relation is judged to be the direct incidence relation, the first interpretation information between the query entity and the recommending entity can be generated through the first incidence description information, so that the first interpretation information between the query entity and the recommending entity can be accurately determined, and a user can more intuitively acquire the incidence relation between the query entity and the recommending entity.

In an embodiment of the present disclosure, the step S105: determining recommendation description information of the recommending entity relative to the querying entity based on the incidence relation, and further comprising the following processes:

(1) determining a medium entity positioned between the recommending entity and the inquiring entity in the target knowledge graph under the condition that the incidence relation is an indirect incidence relation;

(2) determining second association description information based on the association relationship between the medium entity and a target entity, wherein the target entity comprises: the recommending entity and/or the querying entity;

(3) and generating second interpretation information of the recommending entity based on the second association description information and the media entity, and determining the second interpretation information as the recommending description information.

In the embodiment of the disclosure, if the association relationship between the recommending entity and the querying entity is an indirect association relationship, at this time, the association relationship between the recommending entity (or the querying entity) and the media entity may be determined, and then the second association description information is determined according to the association relationship, and the second interpretation information of the recommending entity is generated based on the second association description information and the media entity.

Fig. 4a shows a partial knowledge-graph of the target knowledge-graph, and fig. 4a shows that the partial knowledge-graph comprises the following entities: entity S "Liu XX", entity O₂"Jiang XX" (i.e., the film and television works shown in FIG. 2), entity O₃To entity O₅。

Here, assume that entity "Liu XX" is query entity S, entity O₃To entity O₅Recommending entities for querying entity S, entity O₂"Jiang XX" is a media entity between the querying entity S and the recommending entity.

After determining the media entity between the query entity and the recommending entity, the second association description information may be determined based on the association relationship between the media entity and the recommending entity (or the query entity). For example, as shown in fig. 4a, it may be determined that the second association description information is "lead actor". After the second association description information is determined, second interpretation information of the recommending entity, namely recommendation description information of the recommending entity, can be generated based on the second association description information and the media entity.

For example, in fig. 4a, the second interpretation information of the recommending entity generated based on the second association description information and the media entity is: "being the leading performance of Jiang XX".

FIG. 4b shows a partial knowledge-graph of the target knowledge-graph, and FIG. 4b shows the following entities: entity S "& ltJiang XX & gt", entity O₆"Liu XX", and entity O₇"Blind X" and entity O₈"none XX". Suppose that query entity S is "Jiang XX" and the recommended entity for query entity S is entity O₇And entity O₈Wherein the entity O₆Is a media entity between the querying entity and the recommending entity. At this time, an association relationship between the media entity and the query entity (or the recommending entity) may be determined, and second association description information, for example, "the lead actor" may be determined according to the association relationship. After the second association description information is determined, second interpretation information of the recommending entity, namely recommendation description information of the recommending entity, can be generated based on the second association description information and the media entity.

For example, in fig. 4b, the second interpretation information of the recommending entity generated based on the second association description information and the media entity is: "the principal and subordinate" are Liu XX ".

According to the description, under the condition that the incidence relation between the recommending entity and the inquiring entity is judged to be the indirect incidence relation, the medium entity between the recommending entity and the inquiring entity can be determined, so that the second interpretation information between the recommending entity is determined according to the incidence relation between the medium entity and the inquiring entity (and/or the recommending entity), and a user can know the relation between the recommending entity and the inquiring entity conveniently.

In an embodiment of the present disclosure, the method further includes the following steps:

(1) judging whether the recommended entity and the query entity are in the same data set or not under the condition that the association relationship is an indirect association relationship, wherein the entities in the same data set correspond to the same type tags;

(2) and under the condition that the recommending entity and the inquiring entity are judged to be positioned in the same data set, generating third interpretation information of the recommending entity based on the type tag and the inquiring entity, and determining the third interpretation information as the recommendation description information.

In the embodiment of the present disclosure, entities in the entity library may be classified by data sets, and for each data set, one or more type tags may be set, and a corresponding type tag is added to an entity belonging to the data set in the entity library. For example, the entity contained in the data collection is a person participating in the "XX event," and then the type tag of the entity in the data collection may be the "XX event.

And under the condition that the recommending entity and the inquiring entity are determined to be in indirect incidence relation, whether the recommending entity and the inquiring entity belong to the same data set or not can be judged. And if the type labels of the query entity and the recommending entity correspond to the same data set, determining that the query entity and the recommending entity belong to the same data set.

Then, a data generation rule corresponding to the data collection set may be obtained, and third interpretation information may be generated according to the data generation rule.

According to the description, the third interpretation information of the recommending entity can be determined by judging whether the recommending entity and the inquiring entity belong to the same data set or not, so that the recommendation description information of the recommending entity can be determined according to the third interpretation information, and the type and the content of the recommendation description information can be enriched through the processing mode.

In this disclosure, in step S105, determining recommendation description information of the recommending entity relative to the querying entity based on the association relationship further includes the following steps:

(1) and under the condition that the incidence relations comprise a plurality of incidence relations, determining a second target incidence relation contained in a preset relation list in the incidence relations.

(2) And determining recommendation description information of the recommending entity relative to the inquiring entity based on the second target incidence relation.

In this disclosure, a plurality of association relationships between the query entity and the recommending entity may be further filtered through a preset relationship list, where the preset relationship list may be a preset white list. The preset white list contains preset incidence relation among preset entities.

For example, when the association relationship between the query entity and the recommending entity is a direct association relationship, the preset relationship list may include a preset association relationship preset for the query entity and the recommending entity, for example, the preset association relationship is a "direct relative". When a direct incidence relation of a direct relative exists in the incidence relations of the recommending entity and the inquiring entity, determining that a second target incidence relation contained in a preset relation list exists in the incidence relations of the inquiring entity and the recommending entity; recommendation description information for the recommending entity relative to the querying entity may then be determined based on the second target association.

For another example, when the association relationship between the query entity and the recommending entity is an indirect association relationship, the preset relationship list may include a preset association relationship preset for the query entity and the recommending entity, for example, the preset association relationship is "lead actor". Under the condition that the association relationship between the recommending entity and the medium entity is "lead actor" and the association relationship between the querying entity and the medium entity is "lead actor", it can be determined that a second target association relationship contained in a preset relationship list exists in a plurality of association relationships between the querying entity and the recommending entity in a hit manner; recommendation description information for the recommending entity relative to the querying entity may then be determined based on the second target association.

According to the above description, when there are a plurality of association relations, the association relations can be further screened according to the preset relation list, so that the efficiency of determining the second target association relation is improved.

In the embodiment of the present disclosure, referring to fig. 5, a flowchart of another data displaying method provided in the embodiment of the present disclosure is shown, where the method includes steps S201 to S215, where:

s201: acquiring a query request sent by a user;

s202: determining a query entity S contained in the query request and a recommending entity O corresponding to the query entity S;

s203: judging whether a direct association relationship exists between the query entity and the recommended entity; if yes, executing S204, otherwise, executing S209;

s204: judging whether at least one corresponding association relation between the query entity and the recommended entity is contained in a preset relation list or not; if yes, executing S206, otherwise executing S205;

s205: not generating recommendation description information;

s206: determining first association description information based on at least one association relation, and generating first interpretation information based on the first association description information;

s207: sequencing the incidence relations according to the priorities of the incidence relations to obtain first interpretation information with the priorities meeting requirements;

for step S207, the multiple association relations may be sorted based on the priorities of the association relations, so that the association relations meeting the requirements of the priorities are selected from the sorting results, and then the first interpretation information with the priorities meeting the requirements is determined according to the association relations meeting the requirements.

S208: determining first interpretation information with the priority meeting the requirement as recommendation description information;

s209: judging whether the query entity and the recommending entity have an indirect association relation or not; if yes, executing S211, otherwise executing S210;

s210: not generating recommendation description information;

s211: judging whether the corresponding association relation between the query entity and the recommended entity is contained in a preset relation list or not; if yes, go to step S213, otherwise, go to step S212;

s212: not generating recommendation description information;

s213: generating corresponding second interpretation information based on second association description information corresponding to the association relation between the query entity and the recommending entity;

s214: sequencing the incidence relations according to the priorities of the incidence relations to obtain second interpretation information with the priorities meeting requirements;

s215: and determining the second interpretation information with the priority meeting the requirement as the recommendation description information.

In summary, in the embodiment of the present disclosure, by determining the recommendation description information of the entity relevance of the recommending entity with respect to the query entity, the association relationship between the query entity and the recommending entity is embodied, so that the user can obtain more information through one-time retrieval result, and the retrieval efficiency is improved.

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 data display device corresponding to the data display 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 data display 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.

Referring to fig. 6, a schematic diagram of a data display device provided in an embodiment of the present disclosure is shown, where the data display device includes: a first determining module 61, a second determining module 62, a third determining module 63 and a displaying module 64; wherein the content of the first and second substances,

a first determining module 61, configured to determine, in response to an inquiry request sent by a user, an inquiry entity included in the inquiry request;

a second determining module 62, configured to determine a recommending entity corresponding to the query entity, and determine an association relationship between the recommending entity and the query entity based on a target knowledge graph;

a third determining module 63, configured to determine recommendation description information of the recommending entity relative to the querying entity based on the association relationship, where the recommendation description information is used to characterize entity relevance between the recommending entity and the querying entity;

and the display module 64 is configured to display the recommending entity in a display interface and display the recommendation description information of the recommending entity.

In a possible implementation, the third determining module 63 is further configured to: determining the priority of each incidence relation under the condition that the incidence relation comprises a plurality of incidence relations; determining a first target incidence relation meeting the priority requirement in the incidence relations; and determining recommendation description information of the recommending entity relative to the query entity based on the association description information corresponding to the first target association relation.

In a possible implementation, the third determining module 63 is further configured to: determining first association description information corresponding to the association relationship under the condition that the association relationship is a direct association relationship; and generating first interpretation information of the recommending entity based on the first association description information and the inquiring entity, and determining the first interpretation information as the recommending description information.

In a possible implementation, the third determining module 63 is further configured to: determining a media entity located between the recommending entity and the querying entity in the target knowledge graph under the condition that the incidence relation is an indirect incidence relation; determining second association description information based on an association relationship between the media entity and a target entity, wherein the target entity comprises: the recommending entity and/or the querying entity; and generating second interpretation information of the recommending entity based on the second association description information and the media entity, and determining the second interpretation information as the recommending description information.

In a possible implementation, the third determining module 63 is further configured to: judging whether the recommended entity and the query entity are in the same data set or not under the condition that the association relationship is an indirect association relationship, wherein the entities in the same data set correspond to the same type tags; and under the condition that the recommending entity and the inquiring entity are judged to be positioned in the same data set, generating third interpretation information of the recommending entity based on the type tag and the inquiring entity, and determining the third interpretation information as the recommendation description information.

In a possible implementation, the third determining module 63 is further configured to: determining a second target incidence relation contained in a preset relation list in the incidence relations under the condition that the incidence relations contain multiple incidence relations; and determining recommendation description information of the recommending entity relative to the inquiring entity based on the second target incidence relation.

In a possible implementation, the first determining module 61 is further configured to: inquiring an initial recommending entity corresponding to the inquired entity in an entity library; performing correlation calculation on the initial recommending entities according to a correlation model to obtain a correlation calculation result of each initial recommending entity, wherein the correlation calculation result is used for representing the degree of correlation between the corresponding initial recommending entity and the inquiring entity; and determining a recommending entity meeting the relevance requirement in the initial recommending entities as a recommending entity corresponding to the query entity based on the relevance calculation result.

In one possible implementation, the second determining module 62 is further configured to: and under the condition that the medium entity does not exist between the recommending entity and the inquiring entity based on the target knowledge graph, determining the association relationship to be a direct association relationship.

In one possible implementation, the second determining module 62 is further configured to: determining whether the media entity is in direct association with the recommending entity and the querying entity under the condition that the media entity exists between the recommending entity and the querying entity based on the target knowledge graph; and under the condition that the direct association relationship is determined and the association relationship between the medium entity and the recommending entity is determined to be the same as the association relationship between the medium entity and the query entity, determining that the association relationship between the recommending entity and the query entity is an indirect association relationship.

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.

Corresponding to the data display method in fig. 1, an embodiment of the present disclosure further provides a computer device 700, as shown in fig. 7, a schematic structural diagram of the computer device 700 provided in the embodiment of the present disclosure includes:

a processor 71, a memory 72, and a bus 73; the memory 72 is used for storing execution instructions and includes a memory 721 and an external memory 722; the memory 721 is also referred to as an internal memory, and is used for temporarily storing the operation data in the processor 71 and the data exchanged with the external memory 722 such as a hard disk, the processor 71 exchanges data with the external memory 722 through the memory 721, and when the computer device 700 is operated, the processor 71 communicates with the memory 72 through the bus 73, so that the processor 71 executes the following instructions:

responding to a query request sent by a user, and determining a query entity contained in the query request;

determining a recommending entity corresponding to the query entity, and determining an incidence relation between the recommending entity and the query entity based on a target knowledge graph;

determining recommendation description information of the recommending entity relative to the inquiring entity based on the incidence relation, wherein the recommendation description information is used for representing entity correlation between the recommending entity and the inquiring entity;

and displaying the recommending entity in a display interface, and displaying the recommendation description information of the recommending entity.

The embodiments of the present disclosure also provide a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program performs the steps of the data presentation method described in the above method embodiments. The storage medium may be a volatile or non-volatile computer-readable storage medium.

The embodiments of the present disclosure also provide a computer program product, where the computer program product carries a program code, and instructions included in the program code may be used to execute the steps of the data display method in the foregoing method embodiments, which may be referred to specifically in the foregoing method embodiments, and are not described herein again.

The computer program product may be implemented by 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 for displaying data, comprising:

2. The method of claim 1, wherein the association comprises a plurality of associations;

the determining recommendation description information of the recommending entity relative to the querying entity based on the incidence relation comprises:

determining the priority of each incidence relation;

determining a first target incidence relation meeting the priority requirement in the incidence relations;

and determining recommendation description information of the recommending entity relative to the query entity based on the association description information corresponding to the first target association relation.

3. The method of claim 1, wherein the determining recommendation description information of the recommending entity relative to the querying entity based on the incidence relation comprises:

determining first association description information corresponding to the association relationship under the condition that the association relationship is a direct association relationship;

and generating first interpretation information of the recommending entity based on the first association description information and the inquiring entity, and determining the first interpretation information as the recommending description information.

4. The method of claim 1, wherein the determining recommendation description information of the recommending entity relative to the querying entity based on the incidence relation comprises:

determining a media entity located between the recommending entity and the querying entity in the target knowledge graph under the condition that the incidence relation is an indirect incidence relation;

determining second association description information based on an association relationship between the media entity and a target entity, wherein the target entity comprises: the recommending entity and/or the querying entity;

and generating second interpretation information of the recommending entity based on the second association description information and the media entity, and determining the second interpretation information as the recommending description information.

5. The method of claim 4, further comprising:

judging whether the recommended entity and the query entity are in the same data set or not under the condition that the association relationship is an indirect association relationship, wherein the entities in the same data set correspond to the same type tags;

and under the condition that the recommending entity and the inquiring entity are judged to be positioned in the same data set, generating third interpretation information of the recommending entity based on the type tag and the inquiring entity, and determining the third interpretation information as the recommendation description information.

6. The method of claim 1, wherein the determining recommendation description information of the recommending entity relative to the querying entity based on the incidence relation comprises:

determining a second target incidence relation contained in a preset relation list in the incidence relations under the condition that the incidence relations contain multiple incidence relations;

and determining recommendation description information of the recommending entity relative to the inquiring entity based on the second target incidence relation.

7. The method of claim 1, wherein the determining the recommending entity to which the querying entity corresponds comprises:

inquiring an initial recommending entity corresponding to the inquired entity in an entity library;

performing correlation calculation on the initial recommending entities according to a correlation model to obtain a correlation calculation result of each initial recommending entity, wherein the correlation calculation result is used for representing the degree of correlation between the corresponding initial recommending entity and the inquiring entity;

and determining a recommending entity meeting the relevance requirement in the initial recommending entities as a recommending entity corresponding to the query entity based on the relevance calculation result.

8. The method of claim 1, wherein determining the associative relationship between the recommending entity and the querying entity based on the target knowledge-graph comprises:

9. The method of claim 8, further comprising:

determining whether the media entity is in direct association with the recommending entity and the querying entity under the condition that the media entity exists between the recommending entity and the querying entity based on the target knowledge graph;

and under the condition that the direct association relationship is determined and the association relationship between the medium entity and the recommending entity is determined to be the same as the association relationship between the medium entity and the query entity, determining that the association relationship between the recommending entity and the query entity is an indirect association relationship.

10. A data presentation device, comprising:

the first determination module is used for responding to a query request sent by a user and determining a query entity contained in the query request;

the second determination module is used for determining a recommending entity corresponding to the query entity and determining the incidence relation between the recommending entity and the query entity based on a target knowledge graph;

a third determining module, configured to determine recommendation description information of the recommending entity relative to the querying entity based on the association relationship, where the recommendation description information is used to characterize entity relevance between the recommending entity and the querying entity;

and the display module is used for displaying the recommending entity in a display interface and displaying the recommendation description information of the recommending entity.

11. 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 via the bus when a computer device is running, the machine-readable instructions when executed by the processor performing the steps of the data presentation method of any one of claims 1 to 9.

12. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the data presentation method according to any one of claims 1 to 9.