Search result display method, device and device for displaying search results

Abstract

The embodiments of the present invention provide a search result display method, device and a device for displaying search results. The method includes: identifying an entity corresponding to query information; obtaining structured data corresponding to the entity, wherein the attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to a ranking factor; and displaying the search results corresponding to the query information and the structured data corresponding to the entity. The embodiments of the present invention can display attributes that are more in line with the actual search intention of the user, can reduce the number of searches by the user, and improve the efficiency of the user in obtaining information.

Description

Technical Field

[0001] The present invention relates to the field of network technology, and in particular to a search result display method, device and a device for displaying search results. Background Art

[0002] With the rapid development of information technology and network technology, people are increasingly using the Internet to find the information they need. For example, you can enter a query word in the search box of a search engine to search, and the search engine returns search results related to the query word to the user based on certain search strategies.

[0003] When the query word is an entity, the search engine can also return the encyclopedia entry information corresponding to the entity. However, the encyclopedia entry is based on a fixed template pre-set by humans, which is difficult to meet the actual search needs of users. Summary of the invention

[0004] The embodiments of the present invention provide a search result display method, device and a device for displaying search results, which can display attributes that are more in line with the user's search intention, reduce the user's search times, and improve the user's efficiency in obtaining information.

[0005] In order to solve the above problem, an embodiment of the present invention discloses a search result display method, which includes:

[0006] Identify the entity corresponding to the query information;

[0007] Acquire structured data corresponding to the entity, wherein the attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the sorting factor;

[0008] The search results corresponding to the query information and the structured data corresponding to the entity are displayed.

[0009] Optionally, the method further comprises:

[0010] Acquiring knowledge data related to the entity;

[0011] Identify each attribute related to the entity contained in the knowledge data, and calculate the ranking factor of each attribute;

[0012] Performing weighted calculation on the ranking factors of the attributes to obtain the ranking scores of the attributes;

[0013] According to the ranking score, the attributes and the order of the attributes contained in the structured data corresponding to the entity are determined.

[0014] Optionally, calculating the ranking factor of each attribute includes:

[0015] Calculate the importance of each attribute according to the attributes related to the entity contained in the knowledge data and the display position of each attribute in the knowledge data; and / or

[0016] Calculate the popularity of each attribute according to the attributes related to the entity and the number of searches for each attribute in a preset time period; and / or

[0017] Calculating the frequency of each attribute according to the attributes related to the entity and the number of searches for each attribute in a unit time contained in the knowledge data; and / or

[0018] According to the attributes related to the entity contained in the knowledge data and the degree of association between the attributes and the entity, the relevance between the attributes and the entity is calculated.

[0019] Optionally, the knowledge data includes at least one of the following: structured data in search results, a query association recommendation list, and an encyclopedia entry.

[0020] Optionally, the method further comprises:

[0021] Periodically calculating the ranking factor of each attribute in the structured data corresponding to the entity;

[0022] According to the periodically calculated ranking factor, the attributes and the attribute order included in the structured data corresponding to the entity are updated.

[0023] Optionally, the method further comprises:

[0024] Identifying a search scenario corresponding to the query information;

[0025] The obtaining structured data corresponding to the entity includes:

[0026] Obtain structured data corresponding to the entity in the search scenario.

[0027] Optionally, the identifying a search scenario corresponding to the query information includes:

[0028] Determine the search scenario corresponding to the query information according to the domain to which the identified entity belongs; or,

[0029] A neural network model is pre-trained for identifying search scenarios, the query information is input into the trained neural network model, and the search scenario corresponding to the query information is output.

[0030] Optionally, the ranking factor includes at least one of the following: the importance, popularity, frequency of the attribute in the knowledge data related to the entity, and the relevance of the attribute to the entity.

[0031] On the other hand, an embodiment of the present invention discloses a search result display device, the device comprising:

[0032] An entity recognition module, used to identify the entity corresponding to the query information;

[0033] A structured data acquisition module, used to acquire structured data corresponding to the entity, wherein the attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the sorting factor;

[0034] The result display module is used to display the search results corresponding to the query information and the structured data corresponding to the entity.

[0035] Optionally, the device further comprises:

[0036] A knowledge data acquisition module, used to acquire knowledge data related to the entity;

[0037] A ranking factor calculation module, used to identify various attributes related to the entity contained in the knowledge data, and calculate the ranking factor of each attribute;

[0038] A ranking score calculation module, used to perform weighted calculation on the ranking factors of the attributes to obtain the ranking scores of the attributes;

[0039] The attribute selection and sorting module is used to determine the attributes and the order of the attributes contained in the structured data corresponding to the entity according to the sorting score.

[0040] Optionally, the ranking factor calculation module is specifically used to:

[0041] Calculate the importance of each attribute according to the attributes related to the entity contained in the knowledge data and the display position of each attribute in the knowledge data; and / or

[0042] Calculate the popularity of each attribute according to the attributes related to the entity and the number of searches for each attribute in a preset time period; and / or

[0043] Calculating the frequency of each attribute according to the attributes related to the entity and the number of searches for each attribute in a unit time contained in the knowledge data; and / or

[0044] According to the attributes related to the entity contained in the knowledge data and the degree of association between the attributes and the entity, the relevance between the attributes and the entity is calculated.

[0045] Optionally, the knowledge data includes at least one of the following: structured data in search results, a query association recommendation list, and an encyclopedia entry.

[0046] Optionally, the device further comprises:

[0047] A periodic calculation module, used for periodically calculating the ranking factor of each attribute in the structured data corresponding to the entity;

[0048] The periodic updating module is used to update the attributes and the attribute sequence contained in the structured data corresponding to the entity according to the periodically calculated sorting factor.

[0049] Optionally, the device further comprises:

[0050] A scene recognition module, used to identify the search scene corresponding to the query information;

[0051] The structured data acquisition module is specifically used to acquire the structured data corresponding to the entity in the search scenario.

[0052] Optionally, the scene recognition module includes:

[0053] A first identification module is used to determine the search scenario corresponding to the query information according to the field to which the identified entity belongs; or

[0054] The second recognition module is used to pre-train a neural network model for identifying search scenarios, input the query information into the trained neural network model, and output the search scenario corresponding to the query information.

[0055] Optionally, the ranking factor includes at least one of the following: the importance, popularity, frequency of the attribute in the knowledge data related to the entity, and the relevance of the attribute to the entity.

[0056] On the other hand, an embodiment of the present invention discloses a device for displaying search results, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, and the one or more programs include instructions for performing one or more of the search result display methods described above.

[0057] On the other hand, an embodiment of the present invention discloses a machine-readable medium having instructions stored thereon, which, when executed by one or more processors of a device, causes the device to execute one or more of the search result display methods described above.

[0058] The embodiments of the present invention include the following advantages:

[0059] In the search scenario, the embodiment of the present invention identifies the entity corresponding to the query information, obtains the structured data corresponding to the entity, and displays the search results corresponding to the query information and the structured data corresponding to the entity. The attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the sorting factor, and the sorting factor can reflect the importance, popularity, frequency, and relevance of the attribute to the entity. Compared with the encyclopedia entries with fixed templates, the embodiment of the present invention can display the attributes with high importance, high popularity, strong freshness, and high relevance to the user through big data analysis, so that the displayed attributes are more in line with the actual search intention of the user, which can reduce the number of user searches, improve the efficiency of user information acquisition, and optimize the display strategy of search results, which can meet the different search tendencies of users for different entities and improve the browsing experience of users. In addition, compared with the manual processing method, the embodiment of the present invention automatically mines entity attributes that are more in line with the user's search needs through algorithms, and can automatically mass-produce high-quality structured data, such as automatically mass-producing high-quality knowledge cards of each entity, and then intuitively display relevant information of entities that are more in line with user needs to users. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0061] Figure 1 is a flowchart of a search result display method embodiment of the present invention;

[0062] Figure 2 is a structural block diagram of an embodiment of a search result display device of the present invention;

[0063] Figure 3 is a block diagram of an apparatus 800 for displaying search results of the present invention;

[0064] Figure 4 It is a schematic diagram of the structure of the server in some embodiments of the present invention. DETAILED DESCRIPTION

[0065] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] Method Embodiment

[0067] Reference Figure 1 , shows a flowchart of a search result display method embodiment of the present invention, which may specifically include the following steps:

[0068] Step 101, identifying the entity corresponding to the query information;

[0069] Step 102: Obtain structured data corresponding to the entity, wherein the attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the sorting factor;

[0070] Step 103: Display search results corresponding to the query information and structured data corresponding to the entity.

[0071] The search result display method provided by the present invention can be applied to electronic devices, including but not limited to: servers, smart phones, voice recorders, tablet computers, e-book readers, MP3 (Moving Picture Experts Group Audio Layer III) players, MP4 (Moving Picture Experts Group Audio Layer IV) players, laptop computers, car computers, desktop computers, set-top boxes, smart TVs, wearable devices, etc.

[0072] The embodiments of the present invention can be applied to various scenarios using search engine technology, including but not limited to general search engines and search engines within application programs.

[0073] The query information refers to the information entered by the user in the search box, and the query information is used to trigger a query request to obtain search results related to the query information. After receiving the query request triggered by the user, the electronic device responds to the query request and identifies the entity corresponding to the query information carried in the query request.

[0074] It should be noted that the embodiments of the present invention do not limit the specific type of the query information. The query information may be text information, voice information, image information, etc. When the query information is text information, the text information may be analyzed, such as word segmentation analysis, to obtain entities in the text information; when the query information is voice information, voice recognition may be performed on the voice information to obtain corresponding text information, and then the text information may be analyzed to obtain entities in the text information; when the query information is image information, if the image information contains text content, text recognition may be performed on the image information to obtain corresponding text information, and then the text information may be analyzed to obtain entities in the text information; if the image information does not contain text content, image processing may be performed on the image information to identify the content contained in the image information, and the content may be used as the identified entity.

[0075] The embodiment of the present invention does not limit the form of the query information. The query information can be question-and-answer query information or non-question-and-answer query information. Among them, question-and-answer query information refers to query information that requires a search engine to answer or solve and has clear user query requirements. For example, a question-and-answer query information is "Who is Zhang San's wife." Of course, question-and-answer query information is not necessarily in the form of a question. For example, "Beijing's process for changing an ID card in a different place" is also question-and-answer query information, and the implicit meaning is "What is Beijing's process for changing an ID card in a different place."

[0076] For question-and-answer query information, the embodiment of the present invention can identify the entity corresponding to the question-and-answer query information and display the structured data of the entity. In addition, the embodiment of the present invention can also display the answer results obtained by searching the question-and-answer query information in the form of structured data.

[0077] "Entity" refers to various objects and concepts that exist in the real world, such as names of people, places, events, organizations, brands, occupations, dates, and the like. If the query information received from the user contains an entity, the embodiment of the present invention can obtain structured data related to the entity. Structured data refers to information that can be represented by data or a unified structure. A structured data may include explanatory information for an entity, and at least one attribute information, so that the user can understand the meaning of the entity in multiple dimensions. The embodiment of the present invention does not limit the specific type of the structured data. The structured data may include, but is not limited to, knowledge cards, VR (Virtual Reality, vertical results) cards, encyclopedia entries, and the like.

[0078] For example, when the entity is a person's name, the structured data may include attribute information such as date of birth, birthplace, height, works, and relationships between people. When the entity is a place name, the structured data may include attribute information such as geographical location, famous attractions, specialty snacks, and historical culture.

[0079] In the embodiment of the present invention, the identifying entity corresponding to the query information may include identifying the entity contained in the query information and / or identifying the entity corresponding to the search intent of the identifying query information.

[0080] Furthermore, when the number of entities contained in the identified query information is greater than 1, the structured data corresponding to each entity can be obtained; or the entity corresponding to the search intent of the query information can be further identified, and then the structured data corresponding to the entity can be obtained.

[0081] For example, if the query information is "Zhang San's wife", it can be identified that the query information contains two entities "Zhang San" and "Zhang San's wife". Assuming that according to the query, Zhang San's wife is Wang Wu, the structured data corresponding to the entity "Zhang San" can be obtained, and the structured data corresponding to the entity "Wang Wu" can be obtained, and the structured data of these two entities can be displayed at the same time. Alternatively, the search intent of the query information can be further identified. If it is determined that the search intent of the query information is to query "Zhang San's wife", the structured data corresponding to the entity "Wang Wu" can be obtained, and only the structured data corresponding to the entity "Wang Wu" can be displayed.

[0082] When constructing the structured data of an entity, the embodiment of the present invention obtains various attributes related to the entity, performs a comprehensive weighted calculation based on multiple ranking factors of each attribute, obtains the ranking score of each attribute, and determines the attributes and attribute order contained in the structured data of the entity based on the ranking score of each attribute. It should be noted that the embodiment of the present invention does not limit the specific content of the ranking factor. The ranking factor can reflect the importance, popularity, frequency, relevance of the attribute to the entity, etc. For each attribute that an entity may contain, the ranking factor can affect the position of the attribute in the ranking result, thereby determining whether the attribute is included in the structured data of the entity and the display position of the attribute in the structured data.

[0083] In an optional embodiment of the present invention, the ranking factor includes but is not limited to at least one of the following: the importance, popularity, frequency of the attribute in the knowledge data related to the entity, and the relevance of the attribute to the entity.

[0084] For a certain entity, such as the entity corresponding to the name "Zhang San", the embodiment of the present invention can mine various attributes related to the entity in massive knowledge data, calculate the ranking factor of each attribute, perform comprehensive weighted calculation based on the ranking factor of each attribute, obtain the ranking score of each attribute, and determine the attributes and attribute order contained in the structured data of the name entity "Zhang San" based on the ranking score of each attribute.

[0085] For example, for the name entity "Zhang San", by mining a large amount of knowledge data, it is calculated that the "height" attribute has a high importance and / or popularity and / or frequency and / or relevance to the entity "Zhang San". Among the attributes related to the name entity "Zhang San", the "height" attribute may have a higher ranking score, so the structured data of the name entity "Zhang San" may include the "height" attribute, and the "height" attribute may be ranked higher in the structured data of the name entity "Zhang San".

[0086] For another example, for the name entity "Li Si", by mining a large amount of knowledge data, it is calculated that the "famous works" attribute has a high importance and / or popularity and / or frequency and / or relevance to the entity "Zhang San". Among the attributes related to the name entity "Li Si", the "famous works" attribute may have a higher ranking score, so the structured data of the name entity "Li Si" may contain the "famous works" attribute, and the "famous works" attribute may be ranked higher in the structured data of the name entity "Li Si".

[0087] For the same name entity, for different names, different attributes can be displayed in the structured data obtained by the embodiment of the present invention, and / or different attribute orders can be displayed. For each independent entity, the embodiment of the present invention mines the importance, popularity, frequency, relevance to the entity and other ranking factors of each attribute of the entity in the massive knowledge data by machine, and performs comprehensive weighted calculation on the ranking factors of each attribute by machine algorithm, so as to realize attribute selection and attribute sorting of the structured data of the entity. Compared with the manual template, the data can be traversed more widely, and more attributes with high importance, strong freshness and high relevance can be displayed to the user, so that the displayed attributes are more in line with the actual search intention of the user, which can improve the efficiency of the user to obtain information, and can optimize the display strategy of the search results, which can meet the different search tendencies of the user for different entities and improve the browsing experience of the user. In addition, compared with the manual processing method, the embodiment of the present invention automatically mines entity attributes that are more in line with the user's search needs through algorithms, and can automatically mass-produce high-quality structured data, such as automatically mass-producing high-quality knowledge cards of each entity, and then intuitively display relevant information of the entity that is more in line with the user's needs.

[0088] It should be noted that the attributes in the structured data may include text attributes and / or graphic attributes. The embodiment of the present invention does not limit the specific type of the attributes in the structured data.

[0089] Considering the space occupied by search results pages, in order not to affect users' normal browsing of search results, the number of different types of attributes displayed in each structured data can be limited. For example, one structured data can display 8 text attributes and 2 image and text attributes.

[0090] In an optional embodiment of the present invention, the method may further include:

[0091] Step S11, acquiring knowledge data related to the entity;

[0092] Step S12: identifying each attribute related to the entity contained in the knowledge data, and calculating a ranking factor of each attribute;

[0093] Step S13: performing weighted calculation on the ranking factors of the attributes to obtain the ranking scores of the attributes;

[0094] Step S14: Determine the attributes and the order of the attributes contained in the structured data corresponding to the entity according to the ranking score.

[0095] The knowledge data refers to data containing explanatory information for the entity, such as encyclopedia entries, knowledge cards, etc. In an optional embodiment of the present invention, the knowledge data may include but is not limited to at least one of the following: structured data in search results, query association recommendation lists, and encyclopedia entries, etc.

[0096] The query association recommendation list refers to displaying a list of association queries related to the information entered by the user to the user based on the information entered by the user when the user enters query information in the search box. In an example, if the information entered by the user in the search box is the text "Jiuzhaigou" in real time, the query association recommendation list displayed to the user may include the following query information: "Which city in Sichuan is Jiuzhaigou located in?", "Jiuzhaigou travel guide?", "Jiuzhaigou ticket booking" and so on.

[0097] After identifying the entity corresponding to the query information, the embodiment of the present invention can obtain the structured data corresponding to the entity. Further, obtaining the structured data corresponding to the entity can include an offline method or an online method.

[0098] The offline method refers to constructing the structured data corresponding to each entity offline in advance, and then constructing a preset database containing structured data corresponding to a large number of entities. After identifying the entity corresponding to the query information, the structured data corresponding to the entity can be directly obtained by querying the preset database. That is, for each entity that needs to construct structured data offline, the above steps S11 to S14 can be performed offline, and then the preset database can be constructed.

[0099] The online method refers to building the structured data of the entity in real time after identifying the entity corresponding to the query information. Specifically, the knowledge data related to the entity can be searched in real time based on the search platform, and the structured data of the entity can be built in real time by executing the above steps S11 to S14 online.

[0100] In a specific implementation, an offline method or an online method can be selected according to actual needs to obtain structured data of the entity corresponding to the query information.

[0101] Furthermore, when constructing structured data corresponding to an entity offline / online, firstly, knowledge data related to the entity is acquired. The knowledge data may include real-time search data and / or historical search data.

[0102] For example, the knowledge data may include real-time search data from online searches on at least one network search platform, such as structured data in online search results related to the entity, a query association recommendation list, and encyclopedia entries.

[0103] For another example, the knowledge data may include historical search data of at least one network search platform obtained in a preset time period. For example, historical search data of at least one network search platform in a preset time period is obtained, and the historical search data of the preset time period is filtered according to the entity to obtain structured data, query association recommendation lists, and encyclopedia entries in search results related to the entity in the historical search data. The network search platform refers to a website or a third-party platform with a network search function. The preset time period may be a time period before the query information is received, such as the past day, week, month, etc.

[0104] In the process of offline / online construction of structured data corresponding to an entity, after acquiring knowledge data related to the entity, various attributes related to the entity contained in the knowledge data can be identified, and a ranking factor of each attribute can be calculated.

[0105] Optionally, the calculating of the ranking factors of the attributes may include: calculating the importance of the attributes according to the attributes related to the entity contained in the knowledge data and the display position of the attributes in the knowledge data.

[0106] For an entity, whether a certain attribute related to the entity exists in the mined knowledge data and the display position of the attribute can reflect the importance of the attribute to the entity. In an example, for entity 1, in the structured data, query association recommendation list, and encyclopedia entries in the search results related to entity 1, attribute A related to entity 1 is displayed, and the display position of attribute A in each knowledge data is relatively high, indicating that attribute A is of high importance to entity 1.

[0107] Optionally, the calculating of the ranking factors of the attributes may include: calculating the popularity of the attributes according to the attributes related to the entity contained in the knowledge data and the number of searches for the attributes in a preset time period.

[0108] For an entity, whether a certain attribute related to the entity exists in the mined knowledge data and the number of searches for the attribute in a preset time period can reflect the search popularity of the attribute when users search for the entity. In an example, if a certain attribute of the entity has a high number of searches in various knowledge data in the recent period (such as a month, a week, etc.), then the attribute is considered to be a high-heat attribute of the entity in this period of time.

[0109] Optionally, the calculating of the ranking factors of the attributes may include: calculating the frequencies of the attributes according to the attributes related to the entity and included in the knowledge data and the number of searches for the attributes per unit time.

[0110] For an entity, whether a certain attribute related to the entity exists in the mined knowledge data and the number of searches for the attribute in a unit time can reflect the search frequency of the attribute when users search for the entity. In an example, if a certain attribute of the entity is frequently searched by users within a unit time (such as a day, an hour, etc.), the attribute is considered to be a high-frequency attribute of the entity within this period of time.

[0111] Optionally, the calculating of the ranking factors of the attributes may include: calculating the relevance of the attributes to the entity according to the attributes related to the entity contained in the knowledge data and the degree of association between the attributes and the entity.

[0112] For an entity, whether a certain attribute related to the entity exists in the mined knowledge data and the degree of association between the attribute and the entity can reflect the relevance of the attribute to the entity. The degree of association may include but is not limited to the degree of association at the content level and the degree of association at the domain level. The degree of association at the content level can be used to reflect whether a certain attribute belongs to a certain entity. The degree of association at the domain level can be used to reflect whether a certain attribute belongs to the same or similar domain as the entity.

[0113] After calculating the ranking factors of each attribute related to an entity, weighted calculation is performed on each ranking factor to obtain the ranking score of each attribute related to the entity. According to the ranking score, the final selected attribute and the display order of the selected attribute in the structured data of the entity can be determined.

[0114] In an optional embodiment of the present invention, the method may further include:

[0115] Step S21, periodically calculating the ranking factor of each attribute in the structured data corresponding to the entity;

[0116] Step S22: Update the attributes and attribute order contained in the structured data corresponding to the entity according to the periodically calculated ranking factor.

[0117] The embodiment of the present invention can periodically mine the knowledge data related to each entity, and then periodically calculate the ranking factor of each attribute in the structured data corresponding to each entity, and update the attributes and attribute order contained in the structured data corresponding to each entity according to the periodically calculated ranking factor. Therefore, the embodiment of the present invention can use big data analysis and machine algorithms to regularly and automatically crawl data in the network, and timely update the attributes and attribute order contained in the structured data corresponding to each entity according to the data changes in the network, and can timely display high-importance, high-heat, strong up-to-dateness, and high-relevance attributes to users, and display attributes that meet their search intentions to users in real time, which can improve the efficiency of users in obtaining information.

[0118] In an optional embodiment of the present invention, the method may further include: identifying a search scenario corresponding to the query information; and obtaining structured data corresponding to the entity may include: obtaining structured data corresponding to the entity in the search scenario.

[0119] The search scenario may reflect the user's search intention. For example, when a user enters the query information "Forbidden City" for search, the user may want to search for tourism information related to the place name "Forbidden City", such as introductions to attractions in the Forbidden City, information on the official website of the Forbidden City, and ticket booking channels for the Forbidden City.

[0120] For another example, when a user enters the query information "Hello, Li Huanying" for search, the user may want to search for information related to media information, such as the introduction of the cast and crew of the movie "Hello, Li Huanying" and the ticket purchase channel of the movie.

[0121] In an optional embodiment of the present invention, the search scenario may include, but is not limited to: any one of: a person name search scenario, a place name search scenario, a product search scenario, a service search scenario, and a media search scenario.

[0122] The name search scenario refers to searching for information about a person by name. The place name search scenario refers to searching for information about a place by name. The product search scenario refers to searching for information about a product by product keywords. The products include but are not limited to clothing, electrical appliances, daily necessities, food, books, etc. The service search scenario refers to searching for information about a service by service keywords. The services include but are not limited to consulting services, meal ordering services, car rental services, etc. The media search scenario refers to searching for information about the media by media keywords. The media include but are not limited to movies, music, dramas, crosstalk, etc.

[0123] In an optional embodiment of the present invention, the identifying a search scenario corresponding to the query information may include:

[0124] Determine the search scenario corresponding to the query information according to the domain to which the identified entity belongs; or,

[0125] A neural network model is pre-trained for identifying search scenarios, the query information is input into the trained neural network model, and the search scenario corresponding to the query information is output.

[0126] The embodiments of the present invention do not limit the specific method of identifying the search scenario corresponding to the query information. For example, the entity corresponding to the query information may be identified first, and then the search scenario corresponding to the query information may be determined based on the field to which the identified entity belongs. Alternatively, a neural network model for identifying search scenarios may be pre-trained, the query information may be input into the trained neural network model, and the search scenario corresponding to the query information may be output through the neural network model.

[0127] The neural network model can be obtained by supervised training of an existing neural network based on a large number of training samples and machine learning methods. It should be noted that the disclosed embodiments do not limit the model structure and training method of the neural network model. The neural network model can integrate multiple neural networks. The neural network includes but is not limited to the combination, superposition, and nesting of at least one or at least two of the following: CNN (Convolutional Neural Network), LSTM (Long Short-Term Memory) network, RNN (Simple Recurrent Neural Network), attention neural network, etc.

[0128] In summary, in the search scenario, the embodiment of the present invention identifies the entity corresponding to the query information, obtains the structured data corresponding to the entity, and displays the search results corresponding to the query information and the structured data corresponding to the entity. Among them, the attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the sorting factor, and the sorting factor can reflect the importance, popularity, frequency, and relevance of the attribute to the entity. Compared with the encyclopedia entries with fixed templates, the embodiment of the present invention can display the attributes with high importance, high popularity, strong freshness, and high relevance to the user through big data analysis, so that the displayed attributes are more in line with the actual search intention of the user, which can reduce the number of user searches, improve the efficiency of user information acquisition, and optimize the display strategy of search results, which can meet the different search tendencies of users for different entities and improve the browsing experience of users. In addition, compared with the manual processing method, the embodiment of the present invention automatically mines entity attributes that are more in line with the user's search needs through algorithms, and can automatically mass-produce high-quality structured data, such as automatically mass-producing high-quality knowledge cards of each entity, and then intuitively display relevant information of entities that are more in line with user needs to users.

[0129] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0130] Device Embodiment

[0131] Reference Figure 2 , shows a structural block diagram of an embodiment of a search result display device of the present invention, the device may include:

[0132] An entity identification module 201, used to identify the entity corresponding to the query information;

[0133] The structure data acquisition module 202 is used to acquire the structured data corresponding to the entity, wherein the attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the sorting factor;

[0134] The result display module 203 is used to display the search results corresponding to the query information and the structured data corresponding to the entity.

[0135] Optionally, the device further comprises:

[0136] A knowledge data acquisition module, used to acquire knowledge data related to the entity;

[0137] A ranking factor calculation module, used to identify various attributes related to the entity contained in the knowledge data, and calculate the ranking factor of each attribute;

[0138] A ranking score calculation module, used to perform weighted calculation on the ranking factors of the attributes to obtain the ranking scores of the attributes;

[0139] The attribute selection and sorting module is used to determine the attributes and the order of the attributes contained in the structured data corresponding to the entity according to the sorting score.

[0140] Optionally, the ranking factor calculation module is specifically used to:

[0141] Calculate the importance of each attribute according to the attributes related to the entity contained in the knowledge data and the display position of each attribute in the knowledge data; and / or

[0142] Calculate the popularity of each attribute according to the attributes related to the entity and the number of searches for each attribute in a preset time period; and / or

[0143] Calculating the frequency of each attribute according to the attributes related to the entity and the number of searches for each attribute in a unit time contained in the knowledge data; and / or

[0144] According to the attributes related to the entity contained in the knowledge data and the degree of association between the attributes and the entity, the relevance between the attributes and the entity is calculated.

[0145] Optionally, the knowledge data includes at least one of the following: structured data in search results, a query association recommendation list, and an encyclopedia entry.

[0146] Optionally, the device further comprises:

[0147] A periodic calculation module, used for periodically calculating the ranking factor of each attribute in the structured data corresponding to the entity;

[0148] The periodic updating module is used to update the attributes and the attribute sequence contained in the structured data corresponding to the entity according to the periodically calculated sorting factor.

[0149] Optionally, the device further comprises:

[0150] A scene recognition module, used to identify the search scene corresponding to the query information;

[0151] The structured data acquisition module is specifically used to acquire the structured data corresponding to the entity in the search scenario.

[0152] Optionally, the scene recognition module includes:

[0153] A first identification module is used to determine the search scenario corresponding to the query information according to the field to which the identified entity belongs; or

[0154] The second recognition module is used to pre-train a neural network model for identifying search scenarios, input the query information into the trained neural network model, and output the search scenario corresponding to the query information.

[0155] Optionally, the ranking factor includes at least one of the following: the importance, popularity, frequency of the attribute in the knowledge data related to the entity, and the relevance of the attribute to the entity.

[0156] In the search scenario, the embodiment of the present invention identifies the entity corresponding to the query information, obtains the structured data corresponding to the entity, and displays the search results corresponding to the query information and the structured data corresponding to the entity. The attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the sorting factor, and the sorting factor can reflect the importance, popularity, frequency, and relevance of the attribute to the entity. Compared with the encyclopedia entries with fixed templates, the embodiment of the present invention can display the attributes with high importance, high popularity, strong freshness, and high relevance to the user through big data analysis, so that the displayed attributes are more in line with the actual search intention of the user, which can reduce the number of user searches, improve the efficiency of user information acquisition, and optimize the display strategy of search results, which can meet the different search tendencies of users for different entities and improve the browsing experience of users. In addition, compared with the manual processing method, the embodiment of the present invention automatically mines entity attributes that are more in line with the user's search needs through algorithms, and can automatically mass-produce high-quality structured data, such as automatically mass-producing high-quality knowledge cards of each entity, and then intuitively display relevant information of entities that are more in line with user needs to users.

[0157] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0158] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0159] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0160] An embodiment of the present invention provides a device for displaying search results, including a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: identifying an entity corresponding to query information; obtaining structured data corresponding to the entity, wherein attributes and attribute order contained in the structured data are determined by weighted calculation based on a ranking factor; and displaying search results corresponding to the query information and the structured data corresponding to the entity.

[0161] Optionally, the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0162] Acquiring knowledge data related to the entity;

[0163] Identify each attribute related to the entity contained in the knowledge data, and calculate the ranking factor of each attribute;

[0164] Performing weighted calculation on the ranking factors of the attributes to obtain the ranking scores of the attributes;

[0165] According to the ranking score, the attributes and the order of the attributes contained in the structured data corresponding to the entity are determined.

[0166] Optionally, calculating the ranking factor of each attribute includes:

[0167] Calculate the importance of each attribute according to the attributes related to the entity contained in the knowledge data and the display position of each attribute in the knowledge data; and / or

[0168] Calculate the popularity of each attribute according to the attributes related to the entity and the number of searches for each attribute in a preset time period; and / or

[0169] Calculating the frequency of each attribute according to the attributes related to the entity and the number of searches for each attribute in a unit time contained in the knowledge data; and / or

[0170] According to the attributes related to the entity contained in the knowledge data and the degree of association between the attributes and the entity, the relevance between the attributes and the entity is calculated.

[0171] Optionally, the knowledge data includes at least one of the following: structured data in search results, a query association recommendation list, and an encyclopedia entry.

[0172] Optionally, the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0173] Periodically calculating the ranking factor of each attribute in the structured data corresponding to the entity;

[0174] According to the periodically calculated ranking factor, the attributes and the attribute order included in the structured data corresponding to the entity are updated.

[0175] Optionally, the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0176] Identifying a search scenario corresponding to the query information;

[0177] The obtaining structured data corresponding to the entity includes:

[0178] Obtain structured data corresponding to the entity in the search scenario.

[0179] Optionally, the identifying a search scenario corresponding to the query information includes:

[0180] Determine the search scenario corresponding to the query information according to the domain to which the identified entity belongs; or,

[0181] A neural network model is pre-trained for identifying search scenarios, the query information is input into the trained neural network model, and the search scenario corresponding to the query information is output.

[0182] Optionally, the ranking factor includes at least one of the following: the importance, popularity, frequency of the attribute in the knowledge data related to the entity, and the relevance of the attribute to the entity.

[0183] Figure 3 8 is a block diagram of an apparatus 800 for displaying search results according to an exemplary embodiment. For example, the apparatus 800 may be a mobile phone, a computer, a digital broadcast terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0184] Reference Figure 3 , the device 800 may include one or more of the following components: a processing component 802 , a memory 804 , a power component 806 , a multimedia component 808 , an audio component 810 , an input / output (I / O) interface 812 , a sensor component 814 , and a communication component 816 .

[0185] The processing component 802 generally controls the overall operation of the device 800, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 802 may include one or more modules to facilitate the interaction between the processing component 802 and other components. For example, the processing component 802 may include a multimedia module to facilitate the interaction between the multimedia component 808 and the processing component 802.

[0186] The memory 804 is configured to store various types of data to support operations on the device 800. Examples of such data include instructions for any application or method operating on the device 800, contact data, phone book data, messages, pictures, videos, etc. The memory 804 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0187] The power supply component 806 provides power to the various components of the device 800. The power supply component 806 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power for the device 800.

[0188] The multimedia component 808 includes a screen that provides an output interface between the device 800 and the user. In some embodiments, the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user. The touch panel includes one or more touch sensors to sense touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 808 includes a front camera and / or a rear camera. When the device 800 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0189] The audio component 810 is configured to output and / or input audio signals. For example, the audio component 810 includes a microphone (MIC), and when the device 800 is in an operating mode, such as a call mode, a recording mode, and a voice information processing mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 804 or sent via the communication component 816. In some embodiments, the audio component 810 also includes a speaker for outputting audio signals.

[0190] I / O interface 812 provides an interface between processing component 802 and peripheral interface modules, such as keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: home button, volume button, start button, and lock button.

[0191] The sensor assembly 814 includes one or more sensors for providing various aspects of status assessment for the device 800. For example, the sensor assembly 814 can detect the open / closed state of the device 800, the relative positioning of components, such as the display and keypad of the device 800, and the sensor assembly 814 can also search for changes in the position of the device 800 or a component of the device 800, the presence or absence of user contact with the device 800, the orientation or acceleration / deceleration of the device 800, and the temperature change of the device 800. The sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 814 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 814 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0192] The communication component 816 is configured to facilitate wired or wireless communication between the device 800 and other devices. The device 800 can access a wireless network based on a communication standard, such as WiFi, 2G or 3G, or a combination thereof. In an exemplary embodiment, the communication component 816 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In an exemplary embodiment, the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication. For example, the NFC module can be implemented based on radio frequency information processing (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0193] In an exemplary embodiment, the apparatus 800 may be implemented by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0194] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 804 including instructions, and the instructions can be executed by the processor 820 of the device 800 to perform the above method. For example, the non-transitory computer-readable storage medium can be a ROM, a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0195] Figure 41 is a schematic diagram of the structure of the server in some embodiments of the present invention. The server 1900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1922 (for example, one or more processors) and memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage medium 1930 can be short-term storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations in the server. Furthermore, the central processing unit 1922 can be configured to communicate with the storage medium 1930 and execute a series of instruction operations in the storage medium 1930 on the server 1900.

[0196] The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input and output interfaces 1958, one or more keyboards 1956, and / or, one or more operating systems 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0197] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to perform Figure 1 The search result display method shown.

[0198] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to execute a search result display method, the method comprising: identifying an entity corresponding to query information; obtaining structured data corresponding to the entity, the attributes and attribute order contained in the structured data are determined by weighted calculation based on a ranking factor; and displaying the search results corresponding to the query information and the structured data corresponding to the entity.

[0199] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed by the present invention. The description and examples are to be regarded as exemplary only, and the true scope and spirit of the present invention is indicated by the following claims.

[0200] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0201] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

[0202] The above is a detailed introduction to a search result display method, a search result display device and a device for search result display provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A search result display method, characterized in that: The method comprises: Identify the entity corresponding to the query information; Acquire structured data corresponding to the entity, wherein the attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the ranking factor; the structured data corresponding to the entity is acquired when the number of entities contained in the identification query information is greater than 1; and / or, the structured data corresponding to the entity is acquired according to the entity corresponding to the search intent of the identification query information; Displaying search results corresponding to the query information and structured data corresponding to the entity; Acquire knowledge data related to the entity; the knowledge data includes: structured data in search results, a query association recommendation list, and at least one of encyclopedia entries; Identify each attribute related to the entity contained in the knowledge data, and calculate a ranking factor of each attribute; the ranking factor includes at least one of the importance, popularity, and frequency of the attribute in the knowledge data related to the entity, and the relevance of the attribute to the entity; Performing weighted calculation on the ranking factors of the attributes to obtain the ranking scores of the attributes; According to the ranking score, the attributes and the order of the attributes contained in the structured data corresponding to the entity are determined.

2. The method according to claim 1, characterized in that The calculating the ranking factors of the attributes includes: Calculate the importance of the attribute in the knowledge data related to the entity based on the attributes related to the entity contained in the knowledge data and the display position of each attribute in the knowledge data; and / or Calculate the popularity of the attribute in the knowledge data related to the entity based on the attributes related to the entity and the number of searches for each attribute in a preset time period; and / or Calculate the frequency of the attribute in the knowledge data related to the entity based on the attributes related to the entity and the number of searches for each attribute per unit time contained in the knowledge data; and / or According to the attributes related to the entity contained in the knowledge data and the degree of association between the attributes and the entity, the relevance between the attributes and the entity is calculated.

3. The method according to claim 1, characterized in that The method further comprises: Periodically calculating the ranking factor of each attribute in the structured data corresponding to the entity; According to the periodically calculated ranking factor, the attributes and the attribute order included in the structured data corresponding to the entity are updated.

4. The method according to claim 1, characterized in that The method further comprises: Identifying a search scenario corresponding to the query information; The obtaining structured data corresponding to the entity includes: Obtain structured data corresponding to the entity in the search scenario.

5. The method according to claim 4, characterized in that The identifying the search scenario corresponding to the query information includes: Determine the search scenario corresponding to the query information according to the domain to which the identified entity belongs; or, A neural network model is pre-trained for identifying search scenarios, the query information is input into the trained neural network model, and the search scenario corresponding to the query information is output.

6. A search result display device, characterized in that: The device comprises: An entity recognition module, used to identify the entity corresponding to the query information; A structured data acquisition module, used to acquire structured data corresponding to the entity, wherein the attributes and the order of the attributes contained in the structured data are determined by weighted calculation according to the sorting factor; the structured data corresponding to the entity is acquired when the number of entities contained in the identification query information is greater than 1; and / or the structured data corresponding to the entity is acquired according to the entity corresponding to the search intent of the identification query information; A result display module, used to display the search results corresponding to the query information and the structured data corresponding to the entity; A knowledge data acquisition module, used to acquire knowledge data related to the entity; the knowledge data includes: structured data in search results, a query association recommendation list, and at least one of encyclopedia entries; A ranking factor calculation module, used to identify each attribute related to the entity contained in the knowledge data, and calculate the ranking factor of each attribute; the ranking factor includes at least one of the importance, popularity, frequency of the attribute in the knowledge data related to the entity, and the relevance of the attribute to the entity; A ranking score calculation module, used to perform weighted calculation on the ranking factors of the attributes to obtain the ranking scores of the attributes; The attribute selection and sorting module is used to determine the attributes and the order of the attributes contained in the structured data corresponding to the entity according to the sorting score.

7. The device according to claim 6, characterized in that The ranking factor calculation module is specifically used for: Calculate the importance of the attribute in the knowledge data related to the entity according to the attributes related to the entity contained in the knowledge data and the display position of each attribute in the knowledge data; and / or Calculate the popularity of the attribute in the knowledge data related to the entity according to the attributes related to the entity and the number of searches for each attribute in a preset time period; and / or Calculate the frequency of the attribute in the knowledge data related to the entity according to the attributes related to the entity and the number of searches for each attribute in a unit time; and / or According to the attributes related to the entity contained in the knowledge data and the degree of association between the attributes and the entity, the relevance between the attributes and the entity is calculated.

8. The device according to claim 6, characterized in that The device also includes: A periodic calculation module, used for periodically calculating the ranking factor of each attribute in the structured data corresponding to the entity; The periodic updating module is used to update the attributes and the attribute sequence contained in the structured data corresponding to the entity according to the periodically calculated sorting factor.

9. The device according to claim 6, characterized in that The device also includes: A scene recognition module, used to identify the search scene corresponding to the query information; The structured data acquisition module is specifically used to acquire the structured data corresponding to the entity in the search scenario.

10. The device according to claim 9, characterized in that The scene recognition module comprises: A first identification module is used to determine the search scenario corresponding to the query information according to the field to which the identified entity belongs; or The second recognition module is used to pre-train a neural network model for identifying search scenarios, input the query information into the trained neural network model, and output the search scenario corresponding to the query information.

11. A device for displaying search results, characterized in that: The invention comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, and the one or more programs include instructions for performing the search result display method as claimed in any one of claims 1 to 5.

12. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors of a device, causes the device to execute the search result display method as claimed in any one of claims 1 to 5.

Images