A data processing method and device

Abstract

The present application discloses a data processing method: determining a search keyword according to a search statement input by a user, and determining a first graph entity library corresponding to the category to which the search keyword belongs. According to the association relationship between graph entity libraries of multiple categories, the category of the graph entity library associated with the first graph entity library is determined, and a first set is constructed. Among them, the first set includes at least one graph entity library that has an association relationship with the first graph entity library, and the association relationship between the graph entity libraries is constructed based on the user's search needs. After constructing the first set, the graph entity libraries included in the first set can be displayed with the search keyword as the center. The first set can reflect the search needs of the search statement and guide the user to further trigger the search behavior based on his or her own search needs. Therefore, the use of this solution can help provide users with search results that meet their needs.

Description

Technical Field

[0001] The present application relates to the field of data processing, and in particular to a data processing method and device. Background Art

[0002] With the development of network technology, users can use the network to obtain the content they want to obtain. In one example, the user can enter a search statement in an input area provided by a search engine, and the search engine provides the user with search results corresponding to the search statement.

[0003] How to provide users with search results that meet their needs is a problem that urgently needs to be solved. Summary of the invention

[0004] The technical problem to be solved by this application is how to provide users with search results that meet their needs, and to provide a data processing method and device.

[0005] In a first aspect, an embodiment of the present application provides a data processing method, the method comprising:

[0006] Determine search keywords based on the search statement input by the user;

[0007] Determine a first graph entity library corresponding to the category to which the search keyword belongs;

[0008] According to the association relationship between the graph entity libraries of each category, the category of the graph entity library associated with the first graph entity library is determined to construct a first set; the first set includes at least one graph entity library that has an association relationship with the first graph entity library; wherein, graph entity libraries of multiple categories are pre-constructed, and the association relationship between the graph entity libraries of each category is constructed according to the user's search requirements;

[0009] Centering on the search keyword, various graph entity libraries included in the first set are displayed.

[0010] In one implementation, the first set includes a second graph entity library, and the method further includes:

[0011] In response to a selection operation triggered by the user on the second graph entity library, search content related to the second graph entity library and the search keyword is displayed.

[0012] In one implementation, in response to a selection operation triggered by a user on the second graph entity library, the method further includes:

[0013] According to the association relationship between the graph entity libraries of the categories, determine the category of the graph entity library associated with the second graph entity library, and construct a second set; the second set includes at least one graph entity library having an association relationship with the second graph entity library;

[0014] Taking the second graph entity library as the center, each graph entity library included in the second set is displayed.

[0015] In one implementation, the second set includes a third graph entity library, and the method further includes:

[0016] In response to a selection operation triggered by a user on the third graph entity library, search content related to the search keyword, the second graph entity library and the third graph entity library is displayed.

[0017] In one implementation, the search statement includes a first keyword, and determining the search keyword according to the search statement input by the user includes:

[0018] Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries;

[0019] When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

[0020] In one implementation, the construction of association relationships between entity libraries of each category graph based on the user's search requirements includes:

[0021] Obtaining historical search statements, and determining search keywords of the historical search statements and search requirements of the historical search statements;

[0022] Determine a first category to which the search keyword of the historical search statement belongs and a second category corresponding to the search requirement;

[0023] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0024] In one implementation, the construction of association relationships between entity libraries of each category graph based on the user's search requirements includes:

[0025] Acquire a historical search statement, and determine a first category to which a search keyword of the historical search statement belongs;

[0026] Acquire a second category to which the content viewed by the network user for the historical search statement belongs;

[0027] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0028] In a second aspect, an embodiment of the present application provides a data processing device, the device comprising:

[0029] A first determining unit, configured to determine a search keyword according to a search statement input by a user;

[0030] A second determining unit, used to determine a first graph entity library corresponding to the category to which the search keyword belongs;

[0031] A first construction unit is used to determine the category of the graph entity library associated with the first graph entity library according to the association relationship between the graph entity libraries of each category, and to construct a first set; the first set includes at least one graph entity library that has an association relationship with the first graph entity library; wherein, graph entity libraries of multiple categories are pre-constructed, and the association relationship between the graph entity libraries of each category is constructed according to the search requirements of the user;

[0032] The first display unit is used to display the graph entity libraries included in the first set with the search keyword as the center.

[0033] In one implementation, the first set includes a second graph entity library, and the apparatus further includes:

[0034] The second display unit is used to display search content related to the second graph entity library and the search keyword in response to a selection operation triggered by the user on the second graph entity library.

[0035] In one implementation, the device further includes:

[0036] A second construction unit is configured to determine the category of the graph entity library associated with the second graph entity library according to the association relationship between the graph entity libraries of the categories after the user triggers a selection operation on the second graph entity library, and to construct a second set; the second set includes at least one graph entity library having an association relationship with the second graph entity library;

[0037] The third display unit is used to display each graph entity library included in the second set with the second graph entity library as the center.

[0038] In one implementation, the second set includes a third graph entity library, and the apparatus further includes:

[0039] The fourth display unit is used to display search content related to the search keyword, the second graph entity library and the third graph entity library in response to a selection operation triggered by the user on the third graph entity library.

[0040] In one implementation, the search statement includes a first keyword, and the first determining unit is configured to:

[0041] Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries;

[0042] When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

[0043] In one implementation, the construction of association relationships between entity libraries of each category graph based on the user's search requirements includes:

[0044] Obtaining historical search statements, and determining search keywords of the historical search statements and search requirements of the historical search statements;

[0045] Determine a first category to which the search keyword of the historical search statement belongs and a second category corresponding to the search requirement;

[0046] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0047] In one implementation, the construction of association relationships between entity libraries of each category graph based on the user's search requirements includes:

[0048] Acquire a historical search statement, and determine a first category to which a search keyword of the historical search statement belongs;

[0049] Acquire a second category to which the content viewed by the network user for the historical search statement belongs;

[0050] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0051] In a third aspect, an embodiment of the present application provides a data processing device, 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, wherein the one or more programs include instructions for performing the following operations:

[0052] Determine search keywords based on the search statement input by the user;

[0053] Determine a first graph entity library corresponding to the category to which the search keyword belongs;

[0054] According to the association relationship between the graph entity libraries of each category, the category of the graph entity library associated with the first graph entity library is determined to construct a first set; the first set includes at least one graph entity library that has an association relationship with the first graph entity library; wherein, graph entity libraries of multiple categories are pre-constructed, and the association relationship between the graph entity libraries of each category is constructed according to the user's search requirements;

[0055] Centering on the search keyword, various graph entity libraries included in the first set are displayed.

[0056] In one implementation, the first set includes a second graph entity library, and the operation further includes:

[0057] In response to a selection operation triggered by the user on the second graph entity library, search content related to the second graph entity library and the search keyword is displayed.

[0058] In one implementation, in response to a selection operation triggered by a user on the second graph entity library, the operation further includes:

[0059] According to the association relationship between the graph entity libraries of the categories, determine the category of the graph entity library associated with the second graph entity library, and construct a second set; the second set includes at least one graph entity library having an association relationship with the second graph entity library;

[0060] Taking the second graph entity library as the center, each graph entity library included in the second set is displayed.

[0061] In one implementation, the second set includes a third graph entity library, and the operation further includes:

[0062] In response to a selection operation triggered by a user on the third graph entity library, search content related to the search keyword, the second graph entity library and the third graph entity library is displayed.

[0063] In one implementation, the search statement includes a first keyword, and determining the search keyword according to the search statement input by the user includes:

[0064] Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries;

[0065] When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

[0066] In one implementation, the construction of association relationships between entity libraries of each category graph based on the user's search requirements includes:

[0067] Obtaining historical search statements, and determining search keywords of the historical search statements and search requirements of the historical search statements;

[0068] Determine a first category to which the search keyword of the historical search statement belongs and a second category corresponding to the search requirement;

[0069] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0070] In one implementation, the construction of association relationships between entity libraries of each category graph based on the user's search requirements includes:

[0071] Acquire a historical search statement, and determine a first category to which a search keyword of the historical search statement belongs;

[0072] Acquire a second category to which the content viewed by the network user for the historical search statement belongs;

[0073] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0074] In a fourth aspect, an embodiment of the present application provides a computer-readable medium having instructions stored thereon, which, when executed by one or more processors, enables the device to execute any of the methods described in the first aspect above.

[0075] Compared with the prior art, the embodiments of the present application have the following advantages:

[0076] The embodiment of the present application provides a data processing method, which includes: determining a search keyword according to a search statement input by a user, and after determining the search keyword, determining a first graph entity library corresponding to the category to which the search keyword belongs, wherein the graph entity in the first graph entity library belongs to the same category as the search keyword. After determining the first graph entity library, the category of the graph entity library associated with the first graph entity library can be determined according to the association relationship between graph entity libraries of multiple categories, and a first set can be constructed. The first set includes at least one graph entity library that has an association relationship with the first graph entity library, and the association relationship between the graph entity libraries is constructed based on the search needs of the user. It is precisely because the association relationship between the graph entity libraries is constructed based on the search needs of the user that the first set can reflect the search needs of the search statement. After constructing the first set, the graph entity libraries included in the first set can be displayed with the search keyword as the center. Since the first set can reflect the search needs of the search statement, further, the first set can guide the user to further trigger the search behavior based on his own search needs. Therefore, the use of this solution can help provide users with search results that meet their needs. BRIEF DESCRIPTION OF THE DRAWINGS

[0077] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0078] Figure 1 A flowchart of a data processing method provided in an embodiment of the present application;

[0079] Figure 2 A schematic diagram of the structure of a data processing device provided in an embodiment of the present application;

[0080] Figure 3 A schematic diagram of the structure of the client provided in the embodiment of the present application;

[0081] Figure 4 A schematic diagram of the structure of a server provided in an embodiment of the present application. DETAILED DESCRIPTION

[0082] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0083] The inventor of the present application has found through research that, currently, when a user enters a search statement in the input area of ​​a search engine, the search engine will use the search statement or a keyword in the search statement as a search condition to obtain search results. However, since there are many contents matching the search statement or the keyword in the network database, the search results determined by the search engine are not necessarily the search results that meet the user's needs.

[0084] In order to solve the above problems, the embodiments of the present application provide a data processing method and device, which can provide users with search results that meet user needs.

[0085] Various non-limiting implementations of the present application are described in detail below in conjunction with the accompanying drawings.

[0086] Exemplary Methods

[0087] See also Figure 1 , which is a flow chart of a data processing method provided in an embodiment of the present application. Figure 1 The method shown can be performed by a device running a search engine, for example. The devices mentioned here include but are not limited to terminal devices and servers. The terminal devices mentioned here can be mobile terminals such as smart phones and tablet computers, or terminal devices such as desktop computers.

[0088] In this embodiment, the method may include, for example, the following steps S101-S103.

[0089] S101: Determine search keywords according to a search statement input by a user.

[0090] In an embodiment of the present application, after a user enters a search statement in an input area provided by a search engine, the device running the search engine may analyze the search statement to obtain a search keyword.

[0091] In one example, the search keyword may be a participle of the search sentence; in another example, when the search sentence includes only one participle, the search keyword may be the search sentence.

[0092] In some scenarios, considering that the same object can have different names, for example, urticaria can also be called "wheal" or "urticaria". Among them, "urticaria" is the scientific name of the object. For objects with multiple names, the content entered by the user in the input area of ​​the search engine can be any one of the multiple names. Taking this situation into consideration, in an embodiment of the present application, a graph entity library in the medical field can be pre-constructed, and the graph entity library can include the correspondence between the scientific name of each medical entity object and other names used to describe the medical entity object. For example, for urticaria, the graph entity library can include the graph entity "urticaria", the graph entity "wheal", and the graph entity "urticaria". Further, the graph entity library can also include the correspondence between the above three graph entities. Among them, the scientific name "urticaria" can be used as the normalized entity name corresponding to the three graph entities, and the correspondence between each graph entity and its corresponding normalized entity name is constructed and stored in the medical graph entity library. Of course, for an object with a unique entity name, its corresponding normalized entity name is the graph entity itself.

[0093] For this situation, in one implementation of the embodiment of the present application, the graph entity library can also be used to determine the search keyword. Specifically, the search statement can be first analyzed to obtain a first keyword. Among them, the first keyword can be a participle in the search statement. When the search statement only includes one participle, the first keyword can be the search statement. After determining the first keyword, the search keyword can be determined based on the first keyword and the graph entity library.

[0094] Specifically, determining the search keyword according to the search statement input by the user may include: querying the graph entity library, and when there is a graph entity in the graph entity library that hits the first keyword included in the search statement, using the normalized entity name corresponding to the graph entity that hits the first keyword as the search keyword. The first keyword can be obtained by analyzing the search statement input by the user.

[0095] It is understandable that the first keyword and the search keyword are both atlas entities included in the atlas entity library. For example: the first keyword is "wheal", the atlas entity "wheal" in the atlas entity library hits the first keyword, and the atlas entity library can include the correspondence between the atlas entity "wheal" and the normalized entity name "urticaria". Therefore, according to the first keyword and the atlas entity library, it can be determined that the search keyword is the normalized entity name "urticaria" corresponding to the atlas entity "wheal".

[0096] It should be noted that the atlas entities included in the atlas entity library, in addition to the atlas entities of the aforementioned disease categories, such as "urticaria" and "rubella", can also include atlas entities of other categories, for example, atlas entities of various aspects such as maternal and child care, examination, disease, hospital, medicine, symptom, surgery, etc., which are not listed here one by one. In addition, in addition to atlas entities, the atlas entity library can also include content corresponding to the atlas entities, wherein the content corresponding to the atlas entities includes but is not limited to the introduction of the atlas entity, web pages related to the atlas entity, etc.

[0097] S102: Determine a first graph entity library corresponding to the category to which the search keyword belongs.

[0098] In an embodiment of the present application, the aforementioned pre-constructed atlas entity library in the medical field may include: pre-constructing atlas entity libraries corresponding to multiple categories in the medical field. For example, a atlas entity library of disease categories is constructed, and the atlas entity library of disease categories may include multiple atlas entities, and one atlas entity may correspond to a disease, such as hypertension, diabetes, etc.; for another example, a atlas entity library of symptom categories is constructed, and the atlas entity of the symptom categories may include multiple atlas entities, and one atlas entity may correspond to a symptom, such as headache, abdominal pain, vomiting, etc.; for another example, a atlas entity library of drug categories may be constructed, and the atlas entity library of drug categories may include multiple atlas entities, and one atlas entity may correspond to a drug, such as aspirin, cephalosporin, etc. The categories of the atlas entity library may also include, but are not limited to: diseases, symptoms, drugs, examinations, surgeries, medical beauty, hospitals, first aid, ingredients, traditional Chinese medicine, mother and baby, etc.

[0099] After determining the search keyword, the first graph entity library corresponding to the category to which the search keyword belongs can be determined. Specifically, the category to which the search keyword belongs is determined, and the pre-built graph entity library corresponding to the category is the first graph entity library; then a query can be performed in the first graph entity library to determine whether there is a graph entity that hits the search keyword.

[0100] For example, the search keyword is "urticaria", and its category is disease, then the pre-constructed atlas entity library of disease categories is the first atlas entity library.

[0101] S103: According to the association relationship between graph entity libraries of each category, determine the category of the graph entity library associated with the first graph entity library, and construct a first set; the first set includes at least one graph entity library that has an association relationship with the first graph entity library, and the association relationship between the graph entity libraries is constructed based on the user's search needs.

[0102] In an embodiment of the present application, the user's search needs can be determined based on the user's historical search behavior. For example, when a user searches for keywords in a disease category, he or she may click on and focus on the search results related to the symptoms, treatment methods, causes, etc. of the disease. It can be considered that when the user searches for keywords in the disease category, it is often to obtain the symptoms of the disease, the treatment of the disease, the prevention of the disease, and the causes of the disease, etc. For another example, the historical search sentence entered by the user itself reflects the user's search needs. For example, the historical search sentence is "What are the symptoms of high blood pressure?", then the search demand reflected by the historical search sentence is to obtain symptoms related to high blood pressure. Based on this, based on the historical search behavior of a large number of users, the association relationship between the atlas entity library of the disease category and the atlas entity library of the symptom category and the atlas entity library of the treatment category can be constructed.

[0103] In an embodiment of the present application, in order to provide users with search results that meet user needs, association relationships between multiple categories of graph entity libraries can be pre-constructed. The association relationships between the multiple categories of graph entity libraries can be used to indicate the user's search needs. In one example, the association relationships between the multiple categories of graph entity libraries include the association relationships between the first category of graph entity libraries and the second category of graph entity libraries. If the search keyword entered by the user hits the graph entity included in the first category of graph entity libraries, it can be considered that the graph entity included in the second category of graph entity libraries may also meet the user's search needs. Therefore, based on the association relationship between the first category of graph entity libraries and the second category of graph entity libraries, the second category of graph entity libraries can be added to the first set corresponding to the first category of graph entity libraries.

[0104] For example, the user's search keyword is "urticaria", the first atlas entity library is a disease atlas entity library, and the categories of the atlas entity library associated with the disease atlas entity library may include: symptoms, treatment, cause, medicine, etc. Therefore, a first set may be constructed, which may include {atlas entity library of symptom category, atlas entity library of treatment category, atlas entity library of cause category, atlas entity library of medicine category}. Each atlas entity library included in the first set represents a possible search requirement of the user.

[0105] The following describes how to construct the association relationship between the graph entity libraries of the multiple categories.

[0106] In one example, the association relationship between the multiple categories of graph entity libraries can be constructed based on the historical search behavior of network users. There are multiple ways to construct the association relationship between the multiple graph entity libraries based on the historical search behavior of network users. The following introduces two possible implementations.

[0107] The first implementation method: As mentioned above, historical search statements may reflect the user's search needs. Therefore, the historical search statements can be analyzed to obtain search keywords and user's search needs. The categories corresponding to the search keywords and the categories corresponding to the search needs are determined, and then the association relationship between the graph entity library of the categories corresponding to the search keywords and the graph entity library of the categories corresponding to the search needs is established.

[0108] For example, if the historical search sentence is "What are the symptoms of high blood pressure", the search keyword of the historical search sentence is "high blood pressure". By identifying the demand for this search sentence, it can be determined that the corresponding search demand is symptoms. "High blood pressure" belongs to the disease category, and the search demand belongs to the symptom category. Therefore, the association relationship between the atlas entity library of the disease category and the atlas entity library of the symptom category can be constructed.

[0109] Let's take another example: the historical search sentence is "how to control high blood pressure", then the search keyword of the historical search sentence is "high blood pressure" and the search requirement is "control". "High blood pressure" belongs to the disease category, and "control" belongs to the treatment category. Therefore, the association relationship between the atlas entity library of the disease category and the atlas entity library of the treatment category can be constructed.

[0110] The second implementation method: You can build associations between multiple graph entity libraries based on historical search statements and search results clicked or viewed by users. For example: The historical search statement is "hypertension". When the network user enters the historical search statement, he clicks and focuses on the search results related to the symptoms, treatment methods, causes, etc. of the disease. Therefore, you can build associations between the graph entity library of the disease category and the graph entity library of the symptom category and the graph entity library of the treatment category.

[0111] In another example, the correspondence between the atlas entity libraries of the multiple categories can also be constructed by manual annotation. For example, the correspondence between the atlas entity library of the disease category and the atlas entity library of the treatment category, and the correspondence between the atlas entity library of the disease category and the atlas entity library of the symptom category can be constructed by manual annotation.

[0112] Since the correspondence between graph entity libraries of multiple categories is pre-constructed, after determining the first graph entity library corresponding to the category to which the search keyword belongs, a first set can be constructed based on the correspondence between the aforementioned pre-constructed graph entity libraries of multiple categories. Among them, the first set includes at least one graph entity library that has an association relationship with the first graph entity library, and each graph entity library in the first set can correspond to a category respectively. As can be seen from the description of the association relationship between the graph entity libraries of the multiple categories above, the first set can reflect the search requirements of the search keyword.

[0113] For example: the first atlas entity library is an atlas entity library of disease categories, and the association relationship between the atlas entity libraries of the multiple categories includes the association relationship between the atlas entity library of disease categories and the atlas entity library of symptom categories, and the association relationship between the atlas entity library of disease categories and the atlas entity library of treatment categories. Therefore, according to the association relationship between the atlas entity libraries of the multiple categories, it can be determined that the atlas entity library of symptom categories and the atlas entity library of treatment categories are included in the first set.

[0114] Of course, for the atlas entity library of disease categories, the first set may include but is not limited to the aforementioned atlas entity library of symptom categories and atlas entity library of treatment categories, and may also include atlas entity library of etiology categories, atlas entity library of diet conditioning categories, and atlas entity library of disease prevention categories, etc.

[0115] S104: Centering on the search keyword, displaying each graph entity library included in the first set.

[0116] After determining the first set, the first set can be displayed in the search results page. Specifically, each graph entity library included in the first set is displayed, and the association relationship between each graph entity library and the search keyword is displayed. Among them, the category name corresponding to each graph entity library can be displayed in the search results page. For example, the search keyword is "hypertension", and its corresponding first graph entity library is a graph entity library of the disease category. The first set may include {graph entity library of symptom category, graph entity library of treatment category, graph entity library of cause category, graph entity library of drug category...}. In one implementation, when displaying the first set, in order to achieve an intuitive display effect, in the search results page, with "hypertension" as the center, "symptoms", "treatment", "cause", etc. can be displayed, and at the same time, the association between "hypertension" and "symptoms", "treatment", and "cause" can be established, for example, connected in the form of lines.

[0117] Since the graph entity library in the first set can reflect the possible search intention of the user corresponding to the search keyword. Therefore, after displaying the graph entity libraries included in the first set in the search results page, the user can trigger the search behavior based on the graph entity library in the first set to obtain the content that the user wants to obtain. In other words, the first set can guide the user to trigger the search based on the content he wants to obtain. Therefore, the adoption of this solution can provide users with search results that meet user needs. It should be noted that when a user triggers a search behavior for a graph entity library in the first set, the search keyword and the category to which the graph entity library belongs will be used as common search conditions to trigger the search, and the corresponding search results will be returned. For example, if the search keyword is "hypertension" and the user triggers "symptoms" in the first set, the search will be triggered with "hypertension symptoms" as the search condition, and search results related to "hypertension symptoms" will be returned, especially question and answer search results will be returned to the user to meet the user's search needs based on the search keyword "hypertension" and belonging to the "symptoms".

[0118] In one implementation of the embodiment of the present application, considering that for the second graph entity library in the first set, the search intention of the user inputting the search statement is often to obtain content related to the second graph entity library and the search keyword. For example, the search keyword is "hypertension", and the second graph entity library is a graph entity library of symptom category, then the user searches for hypertension often in the hope of knowing the symptoms of hypertension. In view of this, in one implementation of the embodiment of the present application, content related to the second graph entity library and the search keyword can also be displayed.

[0119] In the embodiment of the present application, the content related to the second graph entity library and the search keyword is displayed. In the specific implementation, for example, the search keyword and the category to which the second graph entity library belongs can be used as common search conditions to trigger the search, and the corresponding search results can be found from the network or the second graph entity library. After the search results are found, the search results can be displayed.

[0120] Furthermore, an association relationship between the search results and the second graph entity library can be constructed, and when the graph entity libraries included in the first set are displayed with the search keyword as the center, the search results are displayed in association. Specifically, when the user triggers the second graph entity library or the mouse hovers over the second graph entity library, the search results are displayed; the search results are obtained by searching with the search keyword and the category to which the second graph entity library belongs as common search conditions.

[0121] Considering that the first set includes other graph entity libraries in addition to the second graph entity library, if the content related to the search keyword and the graph entity library is displayed for each graph entity library in the first set, too much content will be displayed, and the user's targeted selection and browsing will not be utilized. As mentioned above, the first graph entity library set can guide the user to trigger a search based on the content they want to obtain. Therefore, in one example, after the user triggers a selection operation for the second graph entity library, the device running the search engine can execute the step of displaying content related to the second graph entity library and the search keyword in response to the selection operation triggered by the user for the second graph entity library.

[0122] In the embodiment of the present application, the selection operation triggered by the user on the second graph entity library may be, for example, the user clicking on the display area where the second graph entity library is located.

[0123] In one implementation of the embodiment of the present application, the display area can be divided into multiple areas, one of which is used to display the first set and the search keyword, and the other is used to display the content related to the second graph entity library and the search keyword. For example, the display area is divided into two upper and lower areas, the upper area is used to display the first set and the search keyword, and the lower area is used to display the content related to the second graph entity library and the search keyword.

[0124] In one implementation of an embodiment of the present application, the content related to the second graph entity library and the search keyword may include an introduction related to the second graph entity library and the search keyword, and web pages related to the second graph entity library and the search keyword.

[0125] In one implementation, it is considered that the user triggers a selection operation on the second graph entity library in order to obtain more details about the second graph entity library. Therefore, for the second graph entity library on which the user triggered the selection operation, a second set can be further constructed based on the association relationship between the graph entities of the multiple categories; the second set includes at least one graph entity library that has an association relationship with the second graph entity library. It can be understood that the graph entity libraries in the second set can reflect the user's search intention for the second graph entity library based on the search keywords and the first graph entity library. After determining the second set, the second set can be displayed.

[0126] In one example, the second graph entity library can be used as the center to display the graph entity libraries included in the second set. For example, if the search keyword is "hypertension" and the user triggers "symptoms" in the first set, then a second set corresponding to "symptoms" is constructed, such as {graph entity library of treatment category, graph entity library of prevention category, graph entity library of diet category...}. In the search results page, "symptoms" can be used as the center to display "treatment", "prevention", "diet", etc., and at the same time, the associations between "symptoms" and "treatment", "prevention" and "diet" are established, for example, connected in the form of lines.

[0127] In an embodiment of the present application, when displaying the second set, in order to achieve an intuitive display effect, the various graph entities in the second set can be displayed scattered around the second graph entity library. With this implementation, the user can intuitively determine the multiple graph entity libraries associated with the second graph entity library based on the displayed content. It can be understood that, similar to the first set, the second set can also guide the user to trigger a search based on the content he or she wants to obtain.

[0128] When the user triggers a search behavior for the third atlas entity library in the second set, the content related to the search keyword, the second atlas entity library and the third atlas entity library can also be displayed. Specifically, the search keyword, the category to which the second atlas entity library belongs, and the category to which the third atlas entity library belongs can be used as common search conditions to trigger the search, and the corresponding search results are returned. For example, the search keyword is "hypertension", the user triggers "symptoms" in the first set, and the second set corresponding to "symptoms" is displayed; the user triggers "diet" in the second set, and the search will be triggered with "hypertension symptom diet" as the search condition, and the search results related to "hypertension symptom diet" will be returned, especially the question and answer search results are returned to the user to meet the user's search needs. Among them, when the search is triggered with the search keyword, the category to which the second atlas entity library belongs, and the category to which the third atlas entity library belongs as common search conditions, the corresponding search results can be found in the network, in the second atlas entity library, or in the third atlas entity library, which is not specifically limited in the embodiment of the present application.

[0129] Considering that the second set includes other graph entity libraries in addition to the third graph entity library, if relevant search content is displayed for any graph entity library in the second set, too much content will be displayed, which is not conducive to the user's targeted selection and browsing. As mentioned above, the second set can guide users to trigger searches based on the content they want to obtain. Therefore, in one example, after the user triggers a selection operation for the third graph entity library, the device running the search engine can respond to the selection operation triggered by the user for the third graph entity library and execute the step of displaying search content related to the search keyword, the second graph entity library, and the third graph entity library.

[0130] In the embodiment of the present application, the selection operation triggered by the user on the third graph entity library may be, for example, the user clicking on the display area where the third graph entity library is located.

[0131] In one implementation of the embodiment of the present application, the display area can be divided into multiple areas, one of which is used to display the categories to which the second set and the second graph entity library belong, and another area is used to display content related to the search keyword, the second graph entity library, and the third graph entity library. For example, the display area is divided into two upper and lower areas, the upper area is used to display the categories to which the second set and the second graph entity library belong, and the lower area is used to display content related to the search keyword, the second graph entity library, and the third graph entity library.

[0132] It should be noted that, in the embodiment of the present application, the graph entity library displayed to the user can be expanded layer by layer according to the selection operation triggered by the user on one of the graph entity libraries, so as to provide the user with refined search services.

[0133] In one example, after the user triggers a selection operation for the third graph entity library, a third set can be further constructed based on the association relationship between the graph entities of each category; the third set includes at least one graph entity library that has an association relationship with the third graph entity library. It can be understood that the graph entity libraries in the third set can reflect the user's search intention towards the third graph entity library based on the search keywords, the first graph entity library and the second graph entity library. After determining the third set, the graph entity libraries included in the third set can be displayed with the third graph entity library as the center, so as to guide the user to trigger a search behavior based on the third set.

[0134] Furthermore, after the user triggers a selection operation for the fourth graph entity library in the third set, a fourth set can be further constructed based on the association relationship between the graph entities of each category; the fourth set includes at least one graph entity library that has an association relationship with the fourth graph entity library. It can be understood that the graph entity library in the fourth set can reflect the user's search intention towards the fourth graph entity library based on the search keywords, the first graph entity library, the second graph entity library and the third graph entity library. After determining the fourth set, the graph entity libraries included in the fourth set can be displayed with the fourth graph entity library as the center, so as to guide the user to trigger a search behavior based on the fourth set.

[0135] And so on, no longer listed here one by one.

[0136] In addition, after the user triggers the selection operation for the fourth graph entity library in the third set, the content related to the second graph entity library, the third graph entity library, the fourth graph entity library and the search keyword can also be displayed. In specific implementation, for example, the search keyword, the category to which the second graph entity library belongs, the category to which the third graph entity library belongs, and the category to which the fourth graph entity library belongs can be used as common search conditions to trigger the search, and the corresponding search results can be obtained. After the search results are obtained, the search results can be displayed.

[0137] Exemplary Devices

[0138] Based on the method provided in the above embodiment, the embodiment of the present application further provides a device, which is described below in conjunction with the accompanying drawings.

[0139] See also Figure 2 , which is a schematic diagram of the structure of a data processing device provided in an embodiment of the present application. The device 200 may specifically include: a first determining unit 201, a second determining unit 202, a first constructing unit 203 and a first display unit 204.

[0140] A first determining unit 201, configured to determine a search keyword according to a search statement input by a user;

[0141] The second determining unit 202 is used to determine the first graph entity library corresponding to the category to which the search keyword belongs;

[0142] The first construction unit 203 is used to determine the category of the graph entity library associated with the first graph entity library according to the association relationship between the graph entity libraries of each category, and construct a first set; the first set includes at least one graph entity library that has an association relationship with the first graph entity library; wherein, graph entity libraries of multiple categories are pre-constructed, and the association relationship between the graph entity libraries of each category is constructed according to the search requirements of the user;

[0143] The first display unit 204 is used to display the graph entity libraries included in the first set with the search keyword as the center.

[0144] Optionally, the first set includes a second graph entity library, and the device further includes:

[0145] The second display unit is used to display search content related to the second graph entity library and the search keyword in response to a selection operation triggered by the user on the second graph entity library.

[0146] Optionally, the device further comprises:

[0147] A second construction unit is configured to determine the category of the graph entity library associated with the second graph entity library according to the association relationship between the graph entity libraries of the categories after the user triggers a selection operation on the second graph entity library, and to construct a second set; the second set includes at least one graph entity library having an association relationship with the second graph entity library;

[0148] The third display unit is used to display each graph entity library included in the second set with the second graph entity library as the center.

[0149] Optionally, the second set includes a third graph entity library, and the device further includes:

[0150] The fourth display unit is used to display search content related to the search keyword, the second graph entity library and the third graph entity library in response to a selection operation triggered by the user on the third graph entity library.

[0151] Optionally, the search statement includes a first keyword, and the first determining unit 201 is configured to:

[0152] Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries;

[0153] When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

[0154] Optionally, the association relationship between the entity libraries of each category graph is constructed according to the user's search requirements, including:

[0155] Obtaining historical search statements, and determining search keywords of the historical search statements and search requirements of the historical search statements;

[0156] Determine a first category to which the search keyword of the historical search statement belongs and a second category corresponding to the search requirement;

[0157] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0158] Optionally, the association relationship between the entity libraries of each category graph is constructed according to the user's search requirements, including:

[0159] Acquire a historical search statement, and determine a first category to which a search keyword of the historical search statement belongs;

[0160] Acquire a second category to which the content viewed by the network user for the historical search statement belongs;

[0161] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0162] Since the device 200 is a device corresponding to the method provided in the above method embodiment, the specific implementation of each unit of the device 200 is based on the same concept as the above method embodiment. Therefore, for the specific implementation of each unit of the device 200, reference can be made to the description part of the above method embodiment, which will not be repeated here.

[0163] The method provided in the embodiment of the present application can be executed by a client or a server. The client and server that execute the above method are described below respectively.

[0164] Figure 3 1 shows a block diagram of a client 300. For example, the client 300 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.

[0165] Reference Figure 3 The client 300 may include one or more of the following components: a processing component 302 , a memory 304 , a power component 306 , a multimedia component 308 , an audio component 310 , an input / output (I / O) interface 33 , a sensor component 314 , and a communication component 316 .

[0166] The processing component 302 generally controls the overall operation of the client 300, such as operations associated with display, phone calls, data communications, camera operations, and recording operations. The processing component 302 may include one or more processors 320 to execute instructions to complete all or part of the steps of the above-mentioned method. In addition, the processing component 302 may include one or more modules to facilitate the interaction between the processing component 302 and other components. For example, the processing component 302 may include a multimedia module to facilitate the interaction between the multimedia component 308 and the processing component 302.

[0167] The memory 304 is configured to store various types of data to support operations on the client 300. Examples of such data include instructions for any application or method operating on the client 300, contact data, phone book data, messages, pictures, videos, etc. The memory 304 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.

[0168] The power supply component 306 provides power to the various components of the client 300. The power supply component 306 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the client 300.

[0169] The multimedia component 308 includes a screen that provides an output interface between the client 300 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 308 includes a front camera and / or a rear camera. When the client 300 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 the rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0170] The audio component 310 is configured to output and / or input audio signals. For example, the audio component 310 includes a microphone (MIC), and when the client 300 is in an operation mode, such as a call mode, a recording mode, and a speech recognition mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 304 or sent via the communication component 316. In some embodiments, the audio component 310 also includes a speaker for outputting audio signals.

[0171] The I / O interface provides an interface between the processing component 302 and the peripheral interface module, which may be a keyboard, a click wheel, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0172] The sensor assembly 314 includes one or more sensors for providing various aspects of status assessment for the client 300. For example, the sensor assembly 314 can detect the open / closed state of the device 300, the relative positioning of components, such as the display and keypad of the client 300, and the sensor assembly 314 can also detect the position change of the client 300 or a component of the client 300, the presence or absence of user contact with the client 300, the orientation or acceleration / deceleration of the client 300, and the temperature change of the client 300. The sensor assembly 314 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 314 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 314 may also include an acceleration sensor, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0173] The communication component 316 is configured to facilitate wired or wireless communication between the client 300 and other devices. The client 300 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 316 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 316 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 identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0174] In an exemplary embodiment, the client 300 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 following methods:

[0175] Determine search keywords based on the search statement input by the user;

[0176] Determine a first graph entity library corresponding to the category to which the search keyword belongs;

[0177] According to the association relationship between the graph entity libraries of each category, the category of the graph entity library associated with the first graph entity library is determined to construct a first set; the first set includes at least one graph entity library that has an association relationship with the first graph entity library; wherein, graph entity libraries of multiple categories are pre-constructed, and the association relationship between the graph entity libraries of each category is constructed according to the user's search requirements;

[0178] Centering on the search keyword, various graph entity libraries included in the first set are displayed.

[0179] Optionally, the first set includes a second graph entity library, and the method further includes:

[0180] In response to a selection operation triggered by the user on the second graph entity library, search content related to the second graph entity library and the search keyword is displayed.

[0181] Optionally, in response to a selection operation triggered by the user on the second graph entity library, the method further includes:

[0182] According to the association relationship between the graph entity libraries of the categories, determine the category of the graph entity library associated with the second graph entity library, and construct a second set; the second set includes at least one graph entity library having an association relationship with the second graph entity library;

[0183] Taking the second graph entity library as the center, each graph entity library included in the second set is displayed.

[0184] Optionally, the second set includes a third graph entity library, and the method further includes:

[0185] In response to a selection operation triggered by a user on the third graph entity library, search content related to the search keyword, the second graph entity library and the third graph entity library is displayed.

[0186] Optionally, the search statement includes a first keyword, and determining the search keyword according to the search statement input by the user includes:

[0187] Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries;

[0188] When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

[0189] Optionally, the association relationship between the entity libraries of each category graph is constructed according to the user's search requirements, including:

[0190] Obtaining historical search statements, and determining search keywords of the historical search statements and search requirements of the historical search statements;

[0191] Determine a first category to which the search keyword of the historical search statement belongs and a second category corresponding to the search requirement;

[0192] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0193] Optionally, the association relationship between the entity libraries of each category graph is constructed according to the user's search requirements, including:

[0194] Acquire a historical search statement, and determine a first category to which a search keyword of the historical search statement belongs;

[0195] Acquire a second category to which the content viewed by the network user for the historical search statement belongs;

[0196] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0197] Figure 44 is a schematic diagram of the structure of the server in the embodiment of the present application. The server 400 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 422 (for example, one or more processors) and memory 432, and one or more storage media 430 (for example, one or more mass storage devices) storing application programs 442 or data 444. Among them, the memory 432 and the storage medium 430 can be short-term storage or permanent storage. The program stored in the storage medium 430 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processing unit 422 can be configured to communicate with the storage medium 430 to execute a series of instruction operations in the storage medium 430 on the server 400.

[0198] Furthermore, the CPU 422 may execute the following method:

[0199] Determine search keywords based on the search statement input by the user;

[0200] Determine a first graph entity library corresponding to the category to which the search keyword belongs;

[0201] According to the association relationship between the graph entity libraries of each category, the category of the graph entity library associated with the first graph entity library is determined to construct a first set; the first set includes at least one graph entity library that has an association relationship with the first graph entity library; wherein, graph entity libraries of multiple categories are pre-constructed, and the association relationship between the graph entity libraries of each category is constructed according to the user's search requirements;

[0202] Centering on the search keyword, various graph entity libraries included in the first set are displayed.

[0203] Optionally, the first set includes a second graph entity library, and the method further includes:

[0204] In response to a selection operation triggered by the user on the second graph entity library, search content related to the second graph entity library and the search keyword is displayed.

[0205] Optionally, in response to a selection operation triggered by the user on the second graph entity library, the method further includes:

[0206] According to the association relationship between the graph entity libraries of the categories, determine the category of the graph entity library associated with the second graph entity library, and construct a second set; the second set includes at least one graph entity library having an association relationship with the second graph entity library;

[0207] Taking the second graph entity library as the center, each graph entity library included in the second set is displayed.

[0208] Optionally, the second set includes a third graph entity library, and the method further includes:

[0209] In response to a selection operation triggered by a user on the third graph entity library, search content related to the search keyword, the second graph entity library and the third graph entity library is displayed.

[0210] Optionally, the search statement includes a first keyword, and determining the search keyword according to the search statement input by the user includes:

[0211] Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries;

[0212] When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

[0213] Optionally, the association relationship between the entity libraries of each category graph is constructed according to the user's search requirements, including:

[0214] Obtaining historical search statements, and determining search keywords of the historical search statements and search requirements of the historical search statements;

[0215] Determine a first category to which the search keyword of the historical search statement belongs and a second category corresponding to the search requirement;

[0216] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0217] Optionally, the association relationship between the entity libraries of each category graph is constructed according to the user's search requirements, including:

[0218] Acquire a historical search statement, and determine a first category to which a search keyword of the historical search statement belongs;

[0219] Acquire a second category to which the content viewed by the network user for the historical search statement belongs;

[0220] Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

[0221] The server 400 may also include one or more power supplies 426, one or more wired or wireless network interfaces 450, one or more input and output interfaces 456, one or more keyboards 456, and / or one or more operating systems 441, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0222] An embodiment of the present application also provides a computer-readable medium having instructions stored thereon, which, when executed by one or more processors, enables the device to execute the data processing method provided by the above method embodiment.

[0223] Those skilled in the art will readily appreciate other embodiments of the present application after considering the specification and practicing the invention disclosed herein. The present application is intended to cover any modification, use or adaptation of the present application, which follows the general principles of the present application and includes common knowledge or customary techniques in the art that are not disclosed in the present disclosure. The specification and examples are intended to be exemplary only, and the true scope and spirit of the present application are indicated by the following claims.

[0224] It should be understood that the present application is not limited to the precise structures 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 application is limited only by the appended claims.

[0225] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A data processing method, characterized in that: The method comprises: Pre-build graph entity libraries of multiple categories; Acquire historical search statements, analyze the historical search statements, and determine search keywords and search requirements of the historical search statements; Determine a first category to which the search keyword of the historical search statement belongs and a second category corresponding to the search requirement; Establishing an association relationship between the graph entity library of the first category and the graph entity library of the second category; Determine search keywords based on the search statement input by the user; Determine the category to which the search keyword belongs, and the pre-built graph entity library corresponding to the category to which the search keyword belongs is the first graph entity library; When the search keyword hits a graph entity included in the first graph entity library, the category of the graph entity library associated with the first graph entity library is determined according to the association relationship between the graph entity libraries of each category, and a first set is constructed; the first set includes at least one second graph entity library having an association relationship with the first graph entity library, and each second graph entity library in the first set corresponds to a category; Taking the search keyword as the center, displaying each second graph entity library, wherein the search keyword is connected to each second graph entity library in the form of a line, and the second graph entity library is displayed in the form of a category name corresponding to the second graph entity library; In response to a selection operation triggered by a user for any of the second graph entity libraries, a search is triggered using the category to which the second graph entity library belongs and the search keyword as common search conditions to find corresponding search results; and, based on the association relationship between the graph entity libraries of each category, the category of the graph entity library associated with the second graph entity library is determined to construct a second set; the second set includes at least one third graph entity library that has an association relationship with the second graph entity library; with the category name corresponding to the second graph entity library as the center, the third graph entity libraries included in the second set are scattered and displayed around the second graph entity library, and the second graph entity library and the third graph entity libraries are connected in the form of lines, and the third graph entity libraries are displayed in the form of corresponding category names; In response to a selection operation triggered by a user on any of the third graph entity libraries, a search is triggered with the category to which the third graph entity library belongs, the category to which the second graph entity library corresponding to the second set belongs, and the search keyword as common search conditions to find corresponding search results; and, based on the association relationship between the graph entity libraries of each category, at least one fourth graph entity library associated with the third graph entity library is determined to construct a third set; with the category name corresponding to the third graph entity library as the center, the fourth graph entity libraries included in the third set are scattered and displayed around the third graph entity library to guide users to trigger search behavior based on the third set.

2. The method according to claim 1, characterized in that The search statement includes a first keyword, and determining the search keyword according to the search statement input by the user includes: Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries; When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

3. The method according to claim 1, characterized in that The method further comprises: Acquire the historical search statement, and determine the first category to which the search keyword of the historical search statement belongs; Acquire a second category to which the content viewed by the network user for the historical search statement belongs; Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

4. A data processing device, characterized in that: The device comprises: A module in which a user performs the following steps: pre-builds a graph entity library of multiple categories; obtains historical search statements, analyzes the historical search statements, and determines the search keywords and search requirements of the historical search statements; determines the first category to which the search keywords of the historical search statements belong and the second category corresponding to the search requirements; establishes an association relationship between the graph entity library of the first category and the graph entity library of the second category; A first determining unit, configured to determine a search keyword according to a search statement input by a user; A second determining unit is used to determine the category to which the search keyword belongs, and the pre-constructed graph entity library corresponding to the category to which the search keyword belongs is the first graph entity library; a first construction unit, configured to determine, when the search keyword hits a graph entity included in the first graph entity library, the category of the graph entity library associated with the first graph entity library according to the association relationship between graph entity libraries of each category, and construct a first set; the first set includes at least one second graph entity library having an association relationship with the first graph entity library, and each second graph entity library in the first set corresponds to a category; A first display unit is used to display each second graph entity library with the search keyword as the center, wherein the search keyword is connected with each second graph entity library in the form of a line, and the second graph entity library is displayed in the form of a category name corresponding to the second graph entity library; A second display unit is used to respond to a selection operation triggered by a user on any of the second graph entity libraries, trigger a search using the category to which the second graph entity library belongs and the search keyword as common search conditions, and find corresponding search results; A second construction unit is used for determining the category of the graph entity library associated with the second graph entity library according to the association relationship between the graph entity libraries of the categories after a selection operation triggered by the user on any of the second graph entity libraries, and constructing a second set; the second set includes at least one third graph entity library having an association relationship with the second graph entity library; A third display unit is used to display the third graph entity libraries included in the second set scattered around the second graph entity library with the category name corresponding to the second graph entity library as the center, and the second graph entity library and the third graph entity libraries are connected in the form of lines, and the third graph entity libraries are displayed in the form of corresponding category names; a fourth display unit, configured to trigger a search in response to a selection operation triggered by a user on any of the third graph entity libraries, using the category to which the third graph entity library belongs, the category to which the second graph entity library corresponding to the second set belongs, and the search keyword as common search conditions, and find corresponding search results; A module for executing the following steps: determining at least one fourth graph entity library associated with the third graph entity library according to the association relationship between the graph entity libraries of each category to construct a third set; and displaying the fourth graph entity libraries included in the third set scattered around the third graph entity library with the category name corresponding to the third graph entity library as the center to guide users to trigger search behavior based on the third set.

5. The device according to claim 4, characterized in that The search statement includes a first keyword, and the first determining unit is used to: Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries; When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

6. The device according to claim 4, characterized in that The apparatus also includes means for performing the following steps: Acquire the historical search statement, and determine the first category to which the search keyword of the historical search statement belongs; Acquire a second category to which the content viewed by the network user for the historical search statement belongs; Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

7. A data processing device, characterized in that: The system comprises 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: Pre-build graph entity libraries of multiple categories; Acquire historical search statements, analyze the historical search statements, and determine search keywords and search requirements of the historical search statements; Determine a first category to which the search keyword of the historical search statement belongs and a second category corresponding to the search requirement; Establishing an association relationship between the graph entity library of the first category and the graph entity library of the second category; Determine search keywords based on the search statement input by the user; Determine the category to which the search keyword belongs, and the pre-built graph entity library corresponding to the category to which the search keyword belongs is the first graph entity library; When the search keyword hits a graph entity included in the first graph entity library, the category of the graph entity library associated with the first graph entity library is determined according to the association relationship between the graph entity libraries of each category, and a first set is constructed; the first set includes at least one second graph entity library having an association relationship with the first graph entity library, and each second graph entity library in the first set corresponds to a category; Taking the search keyword as the center, displaying each second graph entity library, wherein the search keyword is connected to each second graph entity library in the form of a line, and the second graph entity library is displayed in the form of a category name corresponding to the second graph entity library; In response to a selection operation triggered by a user for any of the second graph entity libraries, a search is triggered using the category to which the second graph entity library belongs and the search keyword as common search conditions to find corresponding search results; and, based on the association relationship between the graph entity libraries of each category, the category of the graph entity library associated with the second graph entity library is determined to construct a second set; the second set includes at least one third graph entity library having an association relationship with the second graph entity library; With the category name corresponding to the second graph entity library as the center, the third graph entity libraries included in the second set are scattered and displayed around the second graph entity library, and the second graph entity library and the third graph entity libraries are connected in the form of lines, and the third graph entity libraries are displayed in the form of corresponding category names; In response to a selection operation triggered by a user on any of the third graph entity libraries, a search is triggered with the category to which the third graph entity library belongs, the category to which the second graph entity library corresponding to the second set belongs, and the search keyword as common search conditions to find corresponding search results; and, based on the association relationship between the graph entity libraries of each category, at least one fourth graph entity library associated with the third graph entity library is determined to construct a third set; with the category name corresponding to the third graph entity library as the center, the fourth graph entity libraries included in the third set are scattered and displayed around the third graph entity library to guide users to trigger search behavior based on the third set.

8. The device according to claim 7, characterized in that The search statement includes a first keyword, and determining the search keyword according to the search statement input by the user includes: Querying a graph entity library; the graph entity library is each of a plurality of pre-built categories of graph entity libraries; When there is a graph entity in the graph entity library that hits the first keyword, the normalized entity name corresponding to the graph entity that hits the first keyword is determined as the search keyword.

9. The device according to claim 7, characterized in that The operations also include: Acquire the historical search statement, and determine the first category to which the search keyword of the historical search statement belongs; Acquire a second category to which the content viewed by the network user for the historical search statement belongs; Establish an association relationship between the graph entity library of the first category and the graph entity library of the second category.

10. A computer-readable medium having instructions stored thereon, which, when executed by one or more processors, causes an apparatus to perform the method of any one of claims 1 to 3.

Images