CN110543592B

CN110543592B - Information searching method and device and computer equipment

Info

Publication number: CN110543592B
Application number: CN201910797302.9A
Authority: CN
Inventors: 王灿; 卢佳俊; 李逸初; 许超
Original assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Current assignee: Beijing Baidu Netcom Science and Technology Co Ltd
Priority date: 2019-08-27
Filing date: 2019-08-27
Publication date: 2022-04-01
Anticipated expiration: 2039-08-27
Also published as: CN110543592A

Abstract

The application provides an information searching method, an information searching device and computer equipment, wherein the method comprises the following steps: the method comprises the steps of obtaining search terms, determining a searched target entity according to the search terms, inquiring a search intention model corresponding to the target entity so as to respond to user operation and determine a target intention from search intents recorded by the search intention model, wherein the search intention model is generated according to the search intents during historical search of the target entity, and a search result is displayed according to target entity associated information meeting the target intention. Because the search intention model is generated according to the search intention when the target entities are searched according to the history, the target intention concerned by the user can be determined according to the search intention model corresponding to each target entity, and then the search result is displayed according to the target entity associated information meeting the target intention, so that the search result can meet the requirements of the user better.

Description

Information searching method and device and computer equipment

Technical Field

The present application relates to the field of internet technologies, and in particular, to an information search method and apparatus, and a computer device.

Background

With the rapid development of internet technology, the information explosion era has been entered, and more users search information required by themselves through the network, and therefore, search engines are used to search various information.

At present, when the user needs multiple intentions and multiple scenes, a search engine is used for searching, and the matching degree of a search result returned by the search engine and the user needs is poor under the common condition, so that satisfactory network resources cannot be provided directly from the user needs.

Disclosure of Invention

The present application is directed to solving, at least to some extent, one of the technical problems in the related art.

According to the information searching method, the target intention concerned by the user is determined according to the searching intention model corresponding to each target entity, and then the searching result is displayed according to the target entity associated information meeting the target intention, so that the technical problem that the information searching result is poor in matching with the user requirement in the prior art is solved, and the searching result can meet the user requirement better.

An embodiment of a first aspect of the present application provides an information search method, including:

acquiring a search word;

determining a searched target entity according to the search word;

querying a search intention model corresponding to the target entity to determine a target intention from search intents recorded by the search intention model in response to a user operation; wherein the search intention model is generated according to the search intention when the target entity is searched according to the history;

and displaying the search result according to the target entity associated information meeting the target intention.

As a first possible implementation manner of the embodiment of the present application, the search intention model is used to indicate each search intention and a hierarchical relationship between upper and lower levels among the search intents;

the determining of the target intention from the search intentions recorded by the search intention model in response to the user operation comprises:

displaying a search intention at the highest level and a next-level search intention of the search intention at the highest level according to the search intention model corresponding to the target entity;

determining the target intention from the highest-level search intention and a next-level search intention of the highest-level search intention in response to a user operation.

As a second possible implementation manner of the embodiment of the present application, the displaying a search result according to target entity associated information that meets the target intention includes:

displaying target entity associated information meeting the target intention and displaying the same-level search intention of the target intention and the adjacent-level search intention of the target intention on a display page of a search result;

and updating the target intention in response to user operation, and repeatedly executing the steps of showing the target entity associated information meeting the target intention and showing the same-level search intention of the target intention and the adjacent-level search intention of the target intention according to the updated target intention.

As a third possible implementation manner of the embodiment of the present application, the search intention model is further configured to indicate a weight corresponding to each search intention; the weight value is used for indicating the possibility of meeting the corresponding search intention;

the same level search intention showing the target intention and the adjacent level search intention of the target intention comprise:

and sequencing the search intention of the same level of the target intention and the adjacent level of the target intention according to the weight corresponding to each search intention in the search intention model so as to display in sequence.

As a fourth possible implementation manner of the embodiment of the present application, before displaying a search result according to target entity associated information that meets the target intention, the method further includes:

inquiring knowledge resources stored in a knowledge base;

if the knowledge resources of the target entity meeting the target intention are inquired, the inquired knowledge resources are used as the associated information;

and if the knowledge resources of the target entity meeting the target intention are not inquired, inquiring the related network resources of the target entity meeting the target intention and the adjacent level search intention of the target intention as the associated information.

As a fifth possible implementation manner of the embodiment of the present application, the querying related network resources of the target entity that meet the target intent and the adjacent level search intent of the target intent includes:

determining a target format according to the format of the searched network resource when searching the target entity according to the history;

searching in the network resource range conforming to the target format to obtain the relevant network resources of the target entity meeting the target intention and the adjacent level search intention of the target intention.

As a sixth possible implementation manner of the embodiment of the present application, after querying related network resources of the target entity that meet the target intent and the adjacent level search intent of the target intent, the method further includes:

and sequencing the network resources related to the target entity according to the characteristic information of the network resources related to the target entity so as to display the network resources in sequence.

As a seventh possible implementation manner of the embodiment of the present application, before querying the search intention model corresponding to the target entity, the method further includes:

generating a search sample according to the search behavior information of the historical search;

identifying a search intent and a search object of the search sample;

determining a search object as a target search sample of the target entity from the search samples;

determining a mapping relation between entities and search intents of the target search sample according to the entities related to the target search sample;

determining the upper and lower level relation between corresponding search intents according to the upper and lower level relation between preset entities;

and creating the search intention model according to the search intention and the corresponding upper and lower hierarchical relations of the target search sample.

As an eighth possible implementation manner of the embodiment of the present application, the searching intent model is a graph model, and after the creating of the searching intent model, the method further includes:

clustering the search intents of the target search samples to obtain clusters;

if the cluster has search intents which are not mapped with the entity, determining the search intents with the minimum common hierarchy in the search intention model for each search intention mapped with the entity in the corresponding cluster;

in the search intention model, an upper-lower level hierarchical relationship between the search intention which is not mapped with the entity and the search intention with the minimum common level is established for the search intention which is not mapped with the entity.

As a ninth possible implementation manner of the embodiment of the present application, after the creating the search intention model, the method further includes:

and according to a preset search intention relationship, increasing the upper and lower level relationship among the search intents in the search intention model.

As a tenth possible implementation manner of the embodiment of the present application, after determining, from the search samples, that a search object is a target search sample of the target entity, the method further includes:

determining a score for the search intention of the target search sample according to the search result and/or the search heat of the search word in the target search sample;

in the search intention model, calculating the sum of scores of all lower-level search intentions for each search intention, and determining the weight of the corresponding search intention according to the sum of scores and the score of the corresponding search intention;

and marking the weight of each search intention in the search intention model.

As an eleventh possible implementation manner of the embodiment of the present application, before determining, according to the entity associated with the target search sample, a mapping relationship between the entity and the search intention for the search intention of the target search sample, the method further includes:

and merging the search intentions of the target search samples according to the similarity.

According to the information searching method, the searching word is obtained, the searched target entity is determined according to the searching word, the searching intention model corresponding to the target entity is inquired, so that the target intention is determined from the searching intention recorded by the searching intention model in response to the user operation, wherein the searching intention model is generated according to the searching intention when the target entity is searched in history, and the searching result is displayed according to the target entity associated information meeting the target intention. Because the search intention model is generated according to the search intention when the target entities are searched according to the history, the target intention concerned by the user can be determined according to the search intention model corresponding to each target entity, and then the search result is displayed according to the target entity associated information meeting the target intention, so that the search result can meet the requirements of the user better.

An embodiment of a second aspect of the present application provides an information searching apparatus, including:

the acquisition module is used for acquiring search terms;

the first determining module is used for determining a searched target entity according to the search word;

the first query module is used for querying a search intention model corresponding to the target entity so as to determine a target intention from search intentions recorded by the search intention model in response to user operation; wherein the search intention model is generated according to the search intention when the target entity is searched according to the history;

and the display module is used for displaying the search result according to the target entity associated information meeting the target intention.

The information searching device of the embodiment of the application searches for the target entity by acquiring the search word, determining the searched target entity according to the search word and inquiring the search intention model corresponding to the target entity so as to respond to the user operation to determine the target intention from the search intentions recorded by the search intention model, wherein the search intention model is generated according to the search intention when the target entity is searched for historically, and the search result is displayed according to the target entity associated information meeting the target intention. The search intention model is generated according to the search intention when the target entities are searched according to the history, so that the target intention concerned by the user can be determined according to the search intention model corresponding to each target entity, and the search result is displayed according to the target entity associated information meeting the target intention, so that the search result meets the requirements of the user.

An embodiment of the third aspect of the present application provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the information search method described in the foregoing embodiment is implemented.

A fourth aspect of the present application is directed to a non-transitory computer-readable storage medium, on which a computer program is stored, the computer program, when executed by a processor, implementing the information search method as described in the above embodiments.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

fig. 1 is a schematic flowchart of an information search method according to an embodiment of the present application;

fig. 2 is a diagram illustrating a first example of information search result presentation provided in an embodiment of the present application;

fig. 3 is a diagram illustrating a second example of information search results provided in an embodiment of the present application;

fig. 4 is a diagram illustrating a third example of information search results provided in the embodiment of the present application;

fig. 5 is a schematic flowchart of an information search method according to a second embodiment of the present application;

fig. 6 is a diagram illustrating a fourth example of information search result presentation provided in the embodiment of the present application;

fig. 7 is an exemplary illustration of a fifth information search result presentation provided in an embodiment of the present application;

fig. 8 is a diagram illustrating an example of a sixth information search result provided in an embodiment of the present application;

fig. 9 is a schematic flowchart of an information search method according to a third embodiment of the present application;

fig. 10 is a schematic flowchart of an information search method according to a fourth embodiment of the present application;

fig. 11 is a schematic flowchart of an information search method according to a fifth embodiment of the present application;

fig. 12 is a schematic structural diagram of an information search apparatus according to an embodiment of the present application;

FIG. 13 illustrates a block diagram of an exemplary computer device suitable for use to implement embodiments of the present application.

Detailed Description

Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.

Aiming at the technical problem that in the prior art, when a user searches information, the matching degree of a search result and the user requirement is poor, and the network resource meeting the user requirement cannot be searched directly from the user requirement, the embodiment of the application provides an information search method. The search intention model is generated according to the search intention when the target entities are searched according to the history, so that the target intention concerned by the user can be determined according to the search intention model corresponding to each target entity, and then the search result is displayed according to the target entity associated information meeting the target intention, so that the search result meets the requirements of the user.

An information search method, an apparatus, and a computer device according to embodiments of the present application are described below with reference to the accompanying drawings.

Fig. 1 is a schematic flowchart of an information search method according to an embodiment of the present application.

The embodiment of the present application is exemplified in that the information searching method is configured in an information searching apparatus, and the information searching apparatus can be applied to any computer device, so that the computer device can execute an information searching function.

The Computer device may be a Personal Computer (PC), a cloud device, a mobile device, and the like, and the mobile device may be a hardware device having various operating systems, touch screens, and/or display screens, such as a mobile phone, a tablet Computer, a Personal digital assistant, a wearable device, and an in-vehicle device.

As shown in fig. 1, the information search method includes the steps of:

step 101, obtaining a search term.

In the embodiment of the application, when a user searches information through computer equipment, a search word can be input in the search box, so that the computer equipment can acquire the search word input by the user, and information search can be performed according to the search word.

It should be noted that, in practical applications, when a user inputs a search term in a search box, the user may manually input the search term, or input the search term in a form of voice, and the like.

And step 102, determining a searched target entity according to the search word.

An entity refers to things in the real world, such as people, place names, companies, telephones, animals, and so on.

In the embodiment of the application, after the search word input by the user is obtained, entity analysis is performed on the search word to determine the searched target entity.

For example, if the search term is "red wine", after the search term is obtained and analyzed, it may be determined that the target entity of the search is "red wine".

Step 103, inquiring a search intention model corresponding to the target entity so as to determine the target intention from the search intentions recorded by the search intention model in response to the user operation.

The search intention model is generated according to the search intention when searching the target entity.

In the information search, the search cannot be performed directly according to the literal meaning of the target entity to be searched, but the target intention of the target entity corresponding to the search word is understood. Therefore, the technical problems that the search results are inaccurate due to the fact that the search words input by the user are not standard, the search words have multiple intentions and the like are avoided.

In the embodiment of the application, in order to determine the target intention, after the target entity of the search is determined, the target intention is determined from the search intentions recorded by the search intention model in response to the user operation by querying the search intention model corresponding to the target entity. The search intention model is generated according to the search intention when searching the target entity.

It should be noted that each target entity has a corresponding search intention model, and after the target entity of the search is determined, the target intention is determined from the search intention recorded by the search intention model by querying the corresponding search intention model of the target entity in response to the user operation. Thus, the target intention of the user can be determined more accurately.

As one possible scenario, the search intention model may be used to indicate each search intention, and the hierarchical relationship between each search intention, both top and bottom. In this case, after the target entity of the search is determined according to the search term, the corresponding search intention model is queried according to the target entity, so that the search intention at the highest level and the next-level search intention of the search intention at the highest level are displayed according to the search intention model corresponding to the target entity. Further, in response to a user operation, a target intention is determined from the highest-ranked search intention and a next-ranked search intention of the highest-ranked search intention.

For example, if the target entity is "red wine", after querying the corresponding search intention model according to the target entity, the next level search intention showing the search intention at the highest level and the search intention at the highest level according to the search intention model is: the benefits of red wine and how red wine is consumed. If the user's goal is "Red wine benefits," the user may select "Red wine benefits," thereby determining that the goal is "Red wine benefits.

As another possible scenario, the search intention model may also be used to indicate a weight value corresponding to each search intention. Wherein the weight value is used for indicating the possibility of corresponding search intention. It can be understood that the greater the weight value corresponding to the search intention, the stronger the demand of the user for the search intention. In this case, after the target entity of the search is determined according to the search term, the corresponding search intention model is queried according to the target entity, and the weight corresponding to each search intention is determined according to the search intention model corresponding to the target entity. Further, a target intention is determined from the respective search intents corresponding to the search intention model in response to a user operation.

For example, if the target entity is "red wine", after the corresponding search intention model is found according to the target entity, the weight corresponding to the search intention "benefit of red wine" is determined to be 70% according to the search intention model, the weight corresponding to the search intention "how red wine is drunk" is 20%, and the weight corresponding to the search intention "how red wine is opened" is 10%. If the user's target intention is "a benefit of red wine", the target intention can be determined by the user operation.

And 104, displaying the search result according to the target entity associated information meeting the target intention.

In the embodiment of the application, after the target intention is determined from all the search intents recorded by the search intention model corresponding to the target entity, the search result is displayed according to the target entity associated information meeting the target intention.

As a possible case, after the target intention is determined from the search intents described in the search intention model corresponding to the target entity, when the search result is presented on the presentation page of the search result, the target entity associated information satisfying the target intention is presented, and the search intention of the same level showing the target intention and the search intention of the adjacent level showing the target intention are presented.

Furthermore, the user can operate the target entity associated information which is displayed on the display page and meets the target intention, the same-level search intention for displaying the target intention and the adjacent-level search intention for displaying the target intention according to the requirement of the user, so as to determine the target intention. Further, in response to a user operation, the target intention is updated, and the steps of presenting the target entity associated information satisfying the target intention, and presenting the same-level search intention of the target intention and the adjacent-level search intention of the target intention are repeatedly performed according to the updated target intention.

As an example, referring to fig. 2, when the search word input by the user is "pueraria", the search result is shown as shown in fig. 2, including a basic recognition area and a resource satisfaction area. The highest level search intention and the next level search intention of the highest level search intention, and the network resource content satisfying the search intention are shown in the resource satisfaction area.

After the user operates the intention tag in the resource satisfaction area or clicks 'view more', the displayed search result page jumps to the corresponding scene page according to the user operation, as shown in fig. 3, and displays the corresponding search result including the search intention and the intention resource satisfaction area. In the search intention index region, the same-level search intention and adjacent-level search intents of the target intention may be presented.

For example, the relationship between the search intention levels may be set in advance, and when the user clicks any search intention, the user jumps to another scene page. As shown in fig. 4, if the target search intention of the current scene page is "ancient text" and the search intention of the same hierarchy, the user clicks the "ancient text", and then the next hierarchy of search intentions is shown. And further responding to the user operation, updating the target intention, and showing the same-level search intention of the target intention and the adjacent-level search intention of the target intention. After the user clicks the right triangle, the last click state of the user may be returned.

As a possible implementation manner of the embodiment of the present application, when displaying the same-level search intention of the target intention and the adjacent-level search intention of the target intention, specifically, after determining the weight value corresponding to each search intention according to the search intention model corresponding to the target entity, the same-level search intention of the target intention and the adjacent-level search intention of the target intention may be sorted according to the weight value corresponding to each search intention in the search intention model, so as to display in order.

Because the weight value corresponding to the search intention corresponds to the user demand, the greater the weight value, the greater the user demand, and therefore, when the search intention of the same level of the target intention and the search intention of the adjacent level of the target intention are ranked, the higher the weight value is ranked in the front, and the search intention of the same level of the target intention and the search intention of the adjacent level of the target intention with the higher weight value are preferentially shown.

According to the information searching method, the searching word is obtained, the searched target entity is determined according to the searching word, the searching intention model corresponding to the target entity is inquired, so that the target intention is determined from the searching intention recorded by the searching intention model in response to the user operation, wherein the searching intention model is generated according to the searching intention when the target entity is searched in history, and the searching result is displayed according to the target entity associated information meeting the target intention. The search intention model is generated according to the search intention when the target entities are searched according to the history, so that the target intention concerned by the user can be determined according to the search intention model corresponding to each target entity, and then the search result is displayed according to the target entity associated information meeting the target intention, so that the search result meets the requirements of the user.

On the basis of the above embodiment, in step 104, before presenting the search result according to the target entity associated information satisfying the target intention, the target entity associated information satisfying the target intention needs to be determined. As a possible implementation manner, the knowledge resources stored in the knowledge base may be queried, so that the queried knowledge resources serve as the target entity association information, or the related network resources of the target entity, which are queried to meet the target intention and the adjacent level search intention of the target intention, serve as the target entity association information. Next, the above processes are described in detail with reference to the second embodiment, and fig. 5 is a schematic flow chart of an information search method provided in the second embodiment of the present application.

As shown in fig. 5, before step 104, the following steps may also be included:

step 201, inquiring knowledge resources stored in a knowledge base.

The knowledge base is a structured, easy-to-operate, easy-to-use and comprehensive and organized knowledge cluster in knowledge engineering, and is an interconnected knowledge slice set which is stored, organized, managed and used in a computer memory by adopting a certain (or a plurality of) knowledge representation modes according to the requirement of solving problems in a certain (or certain) field. Also, the knowledge in the knowledge base is hierarchical.

In the embodiment of the application, after the target intention is determined from the search intents recorded by the search intention model, the knowledge resources stored in the knowledge base are inquired according to the target intention so as to obtain the entity resources meeting the intention of the user.

It should be noted that the knowledge resources stored in the knowledge base may be in the form of text articles, pictures, videos, and the like, which is not limited in this embodiment.

Step 202, judging whether the knowledge resources of the target entity meeting the target intention are inquired.

In the embodiment of the application, when querying the stored knowledge resources in the knowledge base, further, whether the knowledge resources of the target entity meeting the target intention are queried is determined.

As a possible scenario, when querying the knowledge resources stored in the knowledge base, querying the knowledge resources of the target entity satisfying the target intent, step 203 is executed.

As another possible scenario, when querying the knowledge resources stored in the knowledge base, the knowledge resources of the target entity satisfying the target intent are not queried, and step 204 is executed.

In step 203, if the knowledge resource of the target entity meeting the target intention is queried, the queried knowledge resource is used as the associated information.

In the embodiment of the application, when the knowledge resources stored in the knowledge base are queried, and when the knowledge resources of the target entity meeting the target intention are queried, the queried knowledge resources are used as the target entity associated information meeting the target intention.

Step 204, if the knowledge resource of the target entity meeting the target intention is not queried, querying the related network resource of the target entity meeting the target intention and the adjacent level search intention of the target intention as the associated information.

In the embodiment of the application, when the knowledge resources stored in the knowledge base are queried and the knowledge resources of the target entity meeting the target intention are not queried, the related network resources of the target entity meeting the target intention and the adjacent level search intention of the target intention are further queried, and the queried related network resources of the target entity are used as the related information of the target entity meeting the target intention.

Specifically, when the knowledge resources stored in the knowledge base are queried, and when the knowledge resources of the target entity meeting the target intention are not queried, the target format is further determined according to the format of the network resources searched when the target entity is searched historically, and then the search is performed in the range of the network resources meeting the target format, so that the related network resources of the target entity meeting the target intention and the adjacent level search intention of the target intention are obtained. And then, sequencing the network resources related to the target entity according to the characteristic information of the network resources related to the target entity so as to display the network resources in sequence.

For example, when the knowledge resources stored in the knowledge base are queried and the knowledge resources of the target entity meeting the target intention are not queried, if the format of the network resources searched by the historical search target entity is in a video format, the network resources are continuously searched in the range of the network resources conforming to the video format, so as to obtain the related network resources of the target entity meeting the target intention and the adjacent level search intention of the target intention.

As one possible scenario, the related network resources of the target entity that satisfy the target intent and the adjacent level search intent of the target intent may be a single entity resource content, as shown in fig. 6.

As another possible scenario, the related network resources of the target entity satisfying the target intent and the adjacent level search intent of the target intent may be a plurality of entity resources, such as: list, entity list class knowledge, etc., such as shown in fig. 7.

As yet another possible scenario, the relevant network resources of the target entity that satisfy the target intent and the adjacent level search intent of the target intent may also be text, articles, albums, videos, and so on. As shown in fig. 8, the network resource may be an article.

According to the information searching method, the knowledge resources stored in the knowledge base are inquired, if the knowledge resources of the target entity meeting the target intention are inquired, the inquired knowledge resources are used as the associated information, and if the knowledge resources of the target entity meeting the target intention are not inquired, the related network resources of the target entity meeting the target intention and the adjacent level searching intention of the target intention are inquired and used as the associated information. Therefore, the knowledge resources stored in the knowledge base are inquired, whether the knowledge resources of the target entity meeting the target intention are inquired or not is judged, the target entity association information meeting the target intention is further determined, the network resources related to the intention are obtained according to the intention of the user, and the probability of matching the network resources with the search requirement of the user is improved.

In a possible implementation manner of the embodiment of the application, for the creation of the search intention model, a search sample may be generated according to search behavior information of a history search to identify a search intention and a search object of the search sample, and then, from the search sample, a target search sample in which the search object is a target entity is determined, so as to create a corresponding search intention model according to each target search sample. Specifically, for a process of creating a search intention model, refer to the third embodiment, and fig. 9 is a flowchart illustrating an information search method provided by the third embodiment of the present application.

As shown in fig. 9, the information searching method may further include the steps of:

step 301, generating a search sample according to the search behavior information of the history search.

The search sample comprises search words and search results.

In the embodiment of the application, when the search intention model is created, a search sample is obtained firstly. Specifically, the search word and the search result corresponding to each search behavior information may be obtained according to the search behavior information of the historical search, and the search sample may be obtained according to the search word and the search result.

It should be noted that the search behavior of the user is not limited to performing a search in the input box, and may also include query behavior information of the user, webpage clicking behavior information, browsing behavior information, and the like, which is not limited in this embodiment.

Step 302, identifying a search intent and a search object of a search sample.

In the embodiment of the application, after the search sample is generated according to the search behavior information of the historical search, the search sample is identified so as to identify the search intention and the search object of the search sample.

As a possible implementation manner, a search intention candidate set may be manually established in advance, and after natural language features such as sentence segmentation, word segmentation, part of speech, grammar, semantics, and the like are extracted for search words in search samples, whether phrases, words, or phrases obtained by segmenting the search words are search intents or not is identified according to the search intention candidate set established in advance, and then search intents and search objects in the search samples are identified and obtained.

Step 303, determining a target search sample with a search object as a target entity from the search samples.

In the embodiment of the application, after the search intention and the search object are identified from the search sample, the search sample with the search object as the target entity can be determined as the target search sample.

And step 304, determining the mapping relation between the entity and the search intention of the target search sample according to the entity associated with the target search sample.

In the embodiment of the application, after the target search sample is determined from the search samples, the mapping relationship between the entity and the search intention can be determined according to the entity associated with the target search sample and the search intention of the target search sample.

As a possible situation, before determining the mapping relationship between the entity and the search intention for the target search sample according to the entity associated with the target search sample, the similarity of each search intention of the target search sample may also be determined, and then the search intents of the target search sample are merged according to the similarity. Further, a mapping relationship between the entity and the merged search intention is determined.

Step 305, determining the upper and lower level relation between the corresponding search intents according to the upper and lower level relation between the preset entities.

In the embodiment of the application, because a certain association exists between the entities, the upper and lower hierarchical relationship is preset between the entities. For example, where the entity is "feeding," the corresponding lower levels may be "feeding" and "training. Furthermore, the upper and lower hierarchical relations between the corresponding search intents can be determined according to the upper and lower hierarchical relations between the preset entities.

For example, when the entities are "purchase" and "price", the lower and upper hierarchical relationships among the entities are "purchase" is the upper hierarchical level and "price" is the lower hierarchical level. The corresponding search intentions are 'buy things' and 'how much money', at this time, the 'buy things' in the corresponding search intentions is determined to be an upper hierarchy, and the 'how much money' is determined to be a lower hierarchy according to the upper and lower hierarchical relationship among the preset entities, so as to determine the upper and lower hierarchical relationship among the corresponding search intentions.

And step 306, creating a search intention model according to the search intention and the corresponding upper and lower hierarchical relations of the target search sample.

In the embodiment of the application, after the upper and lower hierarchical relations among the corresponding search intents are determined according to the upper and lower hierarchical relations among the preset entities, the search intention model is created according to the search intents and the corresponding upper and lower hierarchical relations of the target search sample.

It should be noted that, each search intention and the hierarchical relationship between the search intentions in the created search intention model may be determined, so that after the target entity is determined, the search intention corresponding to the target entity may be determined by querying the search intention model corresponding to the target entity.

According to the information searching method, a searching sample is generated according to searching behavior information of historical searching, searching intentions and searching objects of the searching sample are identified, a target searching sample with the searching object as a target entity is determined from the searching sample, mapping relations between the entities and the searching intentions are determined according to the searching intentions of the target searching sample and the entities related to the target searching sample, upper and lower hierarchical relations between corresponding searching intentions are determined according to the preset upper and lower hierarchical relations between the entities, and a searching intention model is created according to the searching intentions and the corresponding upper and lower hierarchical relations of the target searching sample. Therefore, after the search intention model is created according to the search intention when the target entity is searched historically, the target entity can be determined, and the corresponding search intention model is inquired to obtain the target intention, so that the user requirements can be accurately identified, and the accuracy of information search is improved.

As a possible case, the search intention model created in the above embodiment may be a graph model, and after the search intention model is created, the search intents of the target search samples may be clustered to obtain clusters, and then, in the search intention model, a top-bottom hierarchical relationship between the search intents that are not mapped with the entity and the search intention with the smallest common hierarchy is established. The above process is described in detail with reference to the fourth embodiment, and fig. 10 is a schematic flow chart of the information search method according to the fourth embodiment.

As shown in fig. 10, the information search method may further include the steps of:

step 401, clustering the search intents of the target search samples to obtain clusters.

Clustering, as used herein, refers to the process of dividing a collection of physical or abstract objects into classes composed of similar objects.

As a possible case, when the search intention model is a atlas model, after the search intention model is created, the search intentions of the target search samples may also be clustered to obtain clusters.

Specifically, semantic similarity among the search intentions of each target search sample is calculated, the number of clusters is determined according to a similarity threshold, and then the search intentions of the target search samples are clustered according to the semantic similarity among the search intentions to obtain each cluster.

It should be noted that, in the present embodiment, the existing semantic similarity calculation method may be referred to as a calculation method for calculating semantic similarity between search intents, and details of this calculation method are not repeated in this embodiment.

Step 402, if the search intention which is not mapped with the entity exists in the cluster, determining the search intention with the minimum common hierarchy in the search intention model for each search intention which is mapped with the entity in the corresponding cluster.

The minimum common hierarchy is a common upper hierarchy with multiple search intents, and when there are multiple common upper hierarchies, the minimum common hierarchy is the lowest hierarchy among the multiple common upper hierarchies.

In the embodiment of the application, the search intents of the target search samples are clustered, and after each cluster is obtained, whether entities mapped with the search intents in each cluster exist is checked. As a possible scenario, if there is a search intention in a cluster that is not mapped to an entity, for each search intention mapped to an entity in the corresponding cluster, a search intention having the smallest common hierarchy is determined in the search intention model.

Specifically, when a search intention which is not mapped with the entity exists in the cluster, for each search intention which is mapped with the entity in the corresponding cluster, traversing upper levels on the search intention model, calculating the sum of paths of each upper level to each search intention in the cluster, and taking the search intention of the shortest path sum as the search intention with the minimum common level.

In the step 403, in the search intention model, an upper-lower level hierarchical relationship between the search intention which is not mapped with the entity and the search intention with the minimum common level is established.

In the embodiment of the application, in the search intention model, a search intention which is not mapped with an entity may exist, and for the search intention which is not mapped with the entity, an upper and lower level relation with the search intention with the minimum common level is established.

For example, when clustering the search intention of the target search sample, the "how to eat chocolate poisoning", "puppy food", and "adult dog food" are clustered together, the smallest common upper entity of the "puppy food" and the "adult dog food" is "feeding", and the search intention is "how to eat chocolate poisoning" is not mapped to the entity, so that the upper level of "how to eat chocolate poisoning" is set as "feeding".

As another possible case, in creating the search intention model, there may also be a search intention relationship that cannot be expressed by the entity, in which case, the search intention relationship may be constructed in advance, and then the top-bottom hierarchical relationship between the search intents may be added in the search intention model according to a preset search intention relationship.

For example, for the search intentions "purchase", "price", and "hair color", it may be preset that the relationship between the search intentions is "purchase" as an upper hierarchy level, and "price" and "hair color" as lower hierarchy levels, and the upper and lower hierarchical relationships between the search intentions are added in the search intention model.

According to the information searching method, the searching intents of the target searching sample are clustered to obtain each cluster, if the searching intents which are not mapped with the entity exist in the cluster, the searching intents which are mapped with the entity in the corresponding cluster are determined in the searching intention model, and the upper and lower level relation between the searching intents which are not mapped with the entity and the searching intents which have the minimum common level is established in the searching intention model. Therefore, the upper and lower level relations of the search intentions are determined in a summarizing manner in the search intention model, so that the user cognition is better met, and the accuracy of information search is improved.

On the basis of the third embodiment, as a possible case, after the step 303, the weight value of the search intention of each target search sample may also be calculated, so as to label the weight value of each search intention in the search intention model. The above process is described in detail with reference to the fifth embodiment, and fig. 11 is a schematic structural diagram of an information search method provided in the fifth embodiment of the present application.

As shown in fig. 11, the information search method may further include the steps of:

step 501, determining a score for the search intention of the target search sample according to the search result and/or the search heat of the search word in the target search sample.

As a possible implementation manner, after determining a target search sample with a search object as a target entity from the search samples, determining a score for a search intention of the target search sample according to the number and the popularity of search results in the target search sample in network resources.

As another possible implementation manner, after a target search sample with a search object as a target entity is determined from the search samples, the search intention of the target search sample may also be determined according to the search heat of the search terms in the target search sample in the network resources.

As another possible implementation manner, after determining a target search sample with a search object as a target entity from the search samples, the search intention of the target search sample may also be determined according to the search results in the target search sample and the search popularity of the search term in the network resources at the same time.

Step 502, in the search intention model, calculating the score sum of all the search intentions of the lower level for each search intention, and determining the weight of the corresponding search intention according to the score sum and the score of the corresponding search intention.

Wherein the weight value of the search intention corresponds to the strength of the user's demand for the search intention. It can be understood that the greater the weight of the search intention, the greater the intensity of the user's demand for the search intention, and likewise, the smaller the weight of the search intention, the less the intensity of the user's demand for the search intention. Therefore, the demand strength of the user for the search intention can be identified according to the weight value of the search intention.

In the embodiment of the application, in the search intention model, after the score of each search intention is determined, the weight of each search intention is further determined.

Specifically, after the score of each search intention is determined according to the search result and/or the search heat of the search word in the target search sample, the sum of the scores of all the search intentions of the lower hierarchy is calculated for each search intention, and then the weight of the corresponding search intention is determined according to the scores and the scores of the corresponding search intention.

Step 503, marking the weight of each search intention in the search intention model.

In the embodiment of the application, after the weight of each search intention is determined, the weight of each search intention is marked in the search intention model, so that the target intention and the requirement strength of a user for the target intention can be determined in the search intention model according to a target entity.

According to the information searching method, scores are determined according to the searching results and/or searching degree of the searching words in the target searching samples through the searching intents of the target searching samples, the sum of the scores of all the searching intents of the lower levels is calculated for each searching intention in the searching intention model, the weight values of the corresponding searching intents are determined according to the scores of the scores and the scores of the corresponding searching intents, and the weight values of the searching intents are labeled in the searching intention model. Therefore, the requirement strength of the user for the search intention can be determined according to the weight value of each search intention marked in the search intention model, so that the requirement of the user can be identified, and the accuracy of information search is improved.

In order to implement the above embodiments, the present application also provides an information search apparatus.

Fig. 12 is a schematic structural diagram of an information search apparatus according to an embodiment of the present application.

As shown in fig. 12, the information search apparatus 100 includes: an acquisition module 110, a first determination module 120, a first query module 130, and a presentation module 140.

The obtaining module 110 is configured to obtain a search term.

The first determining module 120 is configured to determine a target entity of the search according to the search term.

A first query module 130, configured to query the search intention model corresponding to the target entity to determine a target intention from the search intentions described in the search intention model in response to a user operation; the search intention model is generated according to the search intention when searching the target entity.

And the display module 140 is configured to display the search result according to the target entity associated information meeting the target intent.

As a possible implementation manner, the search intention model is used for indicating each search intention and the hierarchical relationship between the search intents in the upper and lower levels; the first query module 130 is further configured to:

displaying the search intention at the highest level and the next level of the search intention of the highest level according to the search intention model corresponding to the target entity; in response to a user operation, a target intention is determined from the highest-level search intention and a next-level search intention of the highest-level search intention.

As another possible implementation, the display module 140 is further configured to:

displaying target entity associated information meeting the target intention and displaying the same-level search intention of the target intention and the adjacent-level search intention of the target intention on a display page of the search result;

and updating the target intention in response to the user operation, and repeatedly executing the steps of presenting the target entity associated information satisfying the target intention, and presenting the same-level search intention of the target intention and the adjacent-level search intention of the target intention according to the updated target intention.

As another possible implementation manner, the search intention model is further used for indicating a weight value corresponding to each search intention; a weight value indicating a likelihood of meeting a corresponding search intention; the display module 140 is further configured to:

As another possible implementation manner, the information search apparatus 100 further includes:

and the second query module is used for querying the knowledge resources stored in the knowledge base.

The processing module is used for taking the inquired knowledge resources as the associated information if the knowledge resources of the target entity meeting the target intention are inquired; and if the knowledge resources of the target entity meeting the target intention are not inquired, inquiring the related network resources of the target entity meeting the target intention and the adjacent level search intention of the target intention as the associated information.

As another possible implementation manner, the processing module is further configured to:

and searching in the network resource range conforming to the target format to obtain the related network resources of the target entity meeting the target intention and the adjacent level searching intention of the target intention.

and the generating module is used for generating a search sample according to the search behavior information of the historical search.

And the identification module is used for identifying the search intention and the search object of the search sample.

And the second determining module is used for determining a target search sample with a search object as a target entity from the search samples.

And the third determining module is used for determining the mapping relation between the entity and the search intention of the target search sample according to the entity related to the target search sample.

And the fourth determining module is used for determining the upper and lower hierarchical relation between the corresponding search intents according to the upper and lower hierarchical relation between the preset entities.

And the creating module is used for creating a search intention model according to the search intention and the corresponding upper and lower hierarchical relations of the target search sample.

and the clustering module is used for clustering the search intention of the target search sample to obtain each cluster.

And the fifth determining module is used for determining the search intention with the minimum common level in the search intention model for each search intention mapped with the entity in the corresponding cluster if the search intention not mapped with the entity exists in the cluster.

And the establishing module is used for establishing an upper-lower level hierarchical relation between the search intention which is not mapped with the entity and the search intention with the minimum common level in the search intention model.

and the increasing module is used for increasing the upper and lower hierarchical relation between the search intents in the search intention model according to the preset search intention relation.

and the scoring module is used for determining the score of the search intention of the target search sample according to the search result and/or the search heat of the search word in the target search sample.

And the sixth determining module is used for calculating the score sum of all the search intentions of the lower hierarchy in the search intention model and determining the weight of the corresponding search intention according to the score sum and the score of the corresponding search intention.

And the marking module is used for marking the weight of each search intention in the search intention model.

and the merging module is used for merging the search intents of the target search samples according to the similarity.

It should be noted that the foregoing explanation of the embodiment of the information search method is also applicable to the information search apparatus of this embodiment, and is not repeated here.

The information searching device of the embodiment of the application searches for the target entity by acquiring the search word, determining the searched target entity according to the search word and inquiring the search intention model corresponding to the target entity so as to respond to the user operation to determine the target intention from the search intentions recorded by the search intention model, wherein the search intention model is generated according to the search intention when the target entity is searched for historically, and the search result is displayed according to the target entity associated information meeting the target intention. The search intention model is generated according to the search intention when the target entities are searched according to the history, so that the target intention concerned by the user can be determined according to the search intention model corresponding to each target entity, and then the search result is displayed according to the target entity associated information meeting the target intention, so that the search result meets the requirements of the user.

In order to implement the foregoing embodiments, the present application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the information search method described in the foregoing embodiments is implemented.

In order to implement the above embodiments, the present application also proposes a non-transitory computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the information search method as described in the above embodiments.

FIG. 13 illustrates a block diagram of an exemplary computer device suitable for use to implement embodiments of the present application. The computer device 12 shown in fig. 13 is only an example, and should not bring any limitation to the function and the scope of use of the embodiments of the present application.

As shown in FIG. 13, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.

Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. These architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus, to name a few.

Computer device 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by computer device 12 and includes both volatile and nonvolatile media, removable and non-removable media.

Memory 28 may include computer system readable media in the form of volatile Memory, such as Random Access Memory (RAM) 30 and/or cache Memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 13, commonly referred to as a "hard drive"). Although not shown in FIG. 13, a disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a Compact disk Read Only Memory (CD-ROM), a Digital versatile disk Read Only Memory (DVD-ROM), or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the application.

A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally perform the functions and/or methodologies of the embodiments described herein.

Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the computer system/server 12, and/or with any devices (e.g., network card, modem, etc.) that enable the computer device 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Moreover, computer device 12 may also communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public Network such as the Internet) via Network adapter 20. As shown, network adapter 20 communicates with the other modules of computer device 12 via bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with computer device 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.

The processing unit 16 executes various functional applications and data processing, such as implementing the information search method mentioned in the foregoing embodiments, by executing a program stored in the system memory 28.

In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.

Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.

Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.

The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.

It should be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.

It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.

In addition, functional units in the embodiments of the present application may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.

The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.

Claims

1. An information search method, characterized in that the method comprises:

acquiring a search word;

determining a searched target entity according to the search word;

displaying a search result according to the target entity associated information meeting the target intention; the displaying of the search result according to the target entity associated information meeting the target intention comprises:

2. The information search method according to claim 1, wherein the search intention model is used for indicating each search intention and a hierarchical relationship of upper and lower levels between the search intentions;

3. The information search method according to claim 1, wherein the search intention model is further configured to indicate a weight value corresponding to each search intention; the weight value is used for indicating the possibility of meeting the corresponding search intention;

4. The information search method according to claim 2, wherein before presenting a search result according to the target entity associated information satisfying the target intention, the method further comprises:

inquiring knowledge resources stored in a knowledge base;

5. The information search method of claim 4, wherein the querying related network resources of the target entity that meet the target intent and the adjacent level search intent of the target intent comprises:

6. The information search method according to claim 5, wherein the querying further comprises, after the network resources related to the target entity that meet the target intent and the adjacent level search intent of the target intent:

7. The information searching method according to any one of claims 1 to 5, wherein before the querying the search intention model corresponding to the target entity, further comprising:

identifying a search intent and a search object of the search sample;

8. The information search method according to claim 7, wherein the search intention model is a graph model, and after the creating the search intention model, further comprising:

clustering the search intents of the target search samples to obtain clusters;

9. The information search method according to claim 7, further comprising, after the creating the search intention model:

10. The information search method according to claim 7, wherein, after determining, from the search samples, that a search object is a target search sample of the target entity, the method further comprises:

and marking the weight of each search intention in the search intention model.

11. The information searching method according to claim 7, wherein before determining the mapping relationship between the entity and the search intention for the search intention of the target search sample according to the entity associated with the target search sample, the method further comprises:

12. An information search apparatus, characterized in that the apparatus comprises:

the acquisition module is used for acquiring search terms;

the display module is used for displaying the search result according to the target entity associated information meeting the target intention; the display module is further configured to:

13. The information search device according to claim 12, wherein the search intention model is configured to indicate each search intention and a hierarchical relationship between each search intention in an upper and lower order; the first query module is further configured to:

14. The information search device of claim 12, wherein the search intention model is further configured to indicate a weight value corresponding to each search intention; the weight value is used for indicating the possibility of meeting the corresponding search intention; the display module is further configured to:

15. The information search apparatus according to claim 13, characterized by further comprising:

the second query module is used for querying knowledge resources stored in the knowledge base;

16. The information search apparatus of claim 15, wherein the processing module is further configured to:

17. The information search apparatus of claim 16, wherein the processing module is further configured to:

18. The information search apparatus according to any one of claims 12 to 17, characterized in that the apparatus further comprises:

the generating module is used for generating a search sample according to the search behavior information of the historical search;

an identification module for identifying a search intent and a search object of the search sample;

the second determining module is used for determining a search object from the search samples as a target search sample of the target entity;

the third determining module is used for determining the mapping relation between the entity and the search intention of the target search sample according to the entity related to the target search sample;

the fourth determining module is used for determining the upper and lower hierarchical relation between the corresponding search intents according to the upper and lower hierarchical relation between the preset entities;

and the creating module is used for creating the search intention model according to the search intention and the corresponding upper and lower level relations of the target search sample.

19. The information search apparatus according to claim 18, characterized in that the apparatus further comprises:

the clustering module is used for clustering the search intention of the target search sample to obtain clusters;

a fifth determining module, configured to determine, for each search intention mapped to the entity in the corresponding cluster, a search intention having a minimum common hierarchy in the search intention model if there is a search intention in the cluster that is not mapped to the entity;

and the establishing module is used for establishing an upper-lower level hierarchical relationship between the search intention which is not mapped with the entity and the search intention with the minimum common level in the search intention model.

20. The information search apparatus according to claim 18, characterized in that the apparatus further comprises:

21. The information search apparatus according to claim 18, characterized in that the apparatus further comprises:

the scoring module is used for determining scores according to the search results and/or the search heat of search words in the target search samples according to the search intentions of the target search samples;

a sixth determining module, configured to calculate, in the search intention model, a sum of scores of all search intentions of lower levels for each search intention, and determine a weight of the corresponding search intention according to the sum of scores and the score of the corresponding search intention;

22. The information search apparatus according to claim 18, characterized in that the apparatus further comprises:

23. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the information search method as claimed in any one of claims 1 to 11 when executing the program.

24. A non-transitory computer-readable storage medium on which a computer program is stored, the program, when executed by a processor, implementing the information search method according to any one of claims 1 to 11.