A search method, a search device and a search device

Abstract

The embodiments of the present invention provide a search method, device and device for searching. The method includes: determining a main requirement tag according to a query word, and determining at least one secondary requirement tag according to the entity content contained in the query word, wherein the main requirement tag and the secondary requirement tag are preset tags; obtaining search results of the query word corresponding to the main requirement tag and the secondary requirement tag respectively; displaying the search results; the search results are obtained by aggregating the search results of the main requirement tag and the secondary requirement tag, and the search results corresponding to the main requirement tag are displayed preferentially. The embodiments of the present invention can improve search efficiency, simplify the user search operation process, and improve user experience.

Description

Technical Field

[0001] The present invention relates to the field of network technology, and in particular to a search method, a device and a device for searching. 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 platform to search, and the search platform returns search results related to the query word to the user based on certain search strategies.

[0003] Usually, for a search behavior, the search platform returns the search results with the highest relevance to the query term to the user. When the search results cannot meet the user's search needs, the user needs to adjust the query term and search again. In other words, the user needs to conduct multiple searches, browse the search results and adjust the query term repeatedly through trial and error, in order to find the search results that meet their needs, resulting in low search efficiency and a cumbersome operation process, which affects the user experience. Summary of the invention

[0004] The embodiments of the present invention provide a search method, a device and a device for searching, which can improve search efficiency, simplify the operation process of user search and improve user experience.

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

[0006] Determine a primary requirement tag according to a query word, and determine at least one secondary requirement tag according to entity content contained in the query word, wherein the primary requirement tag and the secondary requirement tag are preset tags;

[0007] Obtain search results for the query words corresponding to the primary demand tag and the secondary demand tag respectively;

[0008] The search results are displayed; the search results are obtained by aggregating the search results of the main demand tag and the secondary demand tag, and the search results corresponding to the main demand tag are displayed first.

[0009] Optionally, determining the main requirement tag according to the query term includes:

[0010] Determine whether the query is a question-answering query, and if so, perform semantic analysis on the query to obtain key information related to the search intent;

[0011] Matching the key information with a preset semantic template to obtain a target semantic template corresponding to the key information, wherein the preset semantic template has a mapping relationship with the preset tag;

[0012] The preset tag corresponding to the target semantic template is determined as the main requirement tag.

[0013] Optionally, determining the main requirement tag according to the query term includes:

[0014] Determine whether the query word is an entity query word, and if so, determine the entity content contained in the query word;

[0015] Acquire historical search data related to the entity content, wherein the historical search data related to the entity content includes: historical click data related to the entity content, and / or historical word change data related to the entity content;

[0016] Determining historical search data that meets a preset condition among the historical search data related to the entity content;

[0017] The preset tag corresponding to the historical search data satisfying the preset condition is determined as the main requirement tag.

[0018] Optionally, determining at least one secondary requirement tag according to entity content included in the query term includes:

[0019] Identify entity content contained in the query term, and obtain historical search data related to the entity content;

[0020] Determine historical search data that meets a preset condition among the acquired historical search data related to the entity content;

[0021] Determine that the preset tag corresponding to the historical search data that meets the preset condition is a secondary demand tag.

[0022] Optionally, displaying the search results includes:

[0023] Displaying the search results corresponding to the primary demand tag and the secondary demand tag in the form of tabs in the current interface of the search results page, each tab is used to display the search results corresponding to one demand tag;

[0024] The tab page where the search results corresponding to the main demand tag are located is displayed first, and the search results corresponding to each demand tag can be switched and displayed in the current interface by switching tab pages.

[0025] Optionally, the method further comprises:

[0026] Acquire historical search data under a preset search scenario, wherein the historical search data under the preset search scenario includes: historical query words under the preset search scenario, historical search results corresponding to the historical query words, and historical click data;

[0027] Performing demand analysis on the historical search data under the preset search scenario to determine the target demand points;

[0028] A preset tag under the preset search scenario is established according to the target demand point.

[0029] Optionally, the method further comprises:

[0030] Classify web pages in the preset database and identify the search scenarios corresponding to each web page;

[0031] The web pages are marked with corresponding preset tags according to the main contents in the web pages, and a mapping relationship between each web page and the preset tags in the corresponding search scenario is established.

[0032] On the other hand, an embodiment of the present invention discloses a search device, the device comprising:

[0033] A tag determination module, used to determine a primary requirement tag according to a query word, and to determine at least one secondary requirement tag according to entity content contained in the query word, wherein the primary requirement tag and the secondary requirement tag are preset tags;

[0034] A result acquisition module, used to acquire search results of the query words corresponding to the primary demand tags and the secondary demand tags respectively;

[0035] A result display module is used to display the search results; the search results are obtained by aggregating the search results of the main demand tag and the secondary demand tag, and the search results corresponding to the main demand tag are displayed first.

[0036] Optionally, the label determination module includes a main demand label determination module, and the main demand label determination module includes:

[0037] A semantic analysis submodule, used to determine whether the query word is a question-answering query word, and if so, to perform semantic analysis on the query word to obtain key information related to the search intent;

[0038] An information matching submodule, used for matching the key information with a preset semantic template to obtain a target semantic template corresponding to the key information, wherein the preset semantic template has a mapping relationship with the preset label;

[0039] The first determination submodule is used to determine the preset tag corresponding to the target semantic template as the main requirement tag.

[0040] Optionally, the label determination module includes a main demand label determination module, and the main demand label determination module includes:

[0041] A content determination submodule, used to determine whether the query word is an entity query word, and if so, determine the entity content contained in the query word;

[0042] A data acquisition submodule, used to acquire historical search data related to the entity content, wherein the historical search data related to the entity content includes: historical click data related to the entity content, and / or historical word change data related to the entity content;

[0043] A target determination submodule, used to determine historical search data that meets a preset condition among the historical search data related to the entity content;

[0044] The second determining submodule is used to determine that the preset tag corresponding to the historical search data that meets the preset condition is the main demand tag.

[0045] Optionally, the tag determination module includes a secondary demand tag determination module, and the secondary demand tag determination module includes:

[0046] An identification and acquisition submodule, used to identify entity content contained in the query term and acquire historical search data related to the entity content;

[0047] A data determination submodule, used to determine historical search data that meets preset conditions among the acquired historical search data related to the entity content;

[0048] The third determining submodule is used to determine that the preset tag corresponding to the historical search data that meets the preset condition is a secondary demand tag.

[0049] Optionally, the result display module is specifically used to display the search results corresponding to the main demand tag and the secondary demand tag in the form of tabs in the current interface of the search results page, and each tab is used to display the search results corresponding to a demand tag; and the tab where the search results corresponding to the main demand tag are located is displayed first, and by switching tabs, the search results corresponding to each demand tag can be switched and displayed in the current interface.

[0050] Optionally, the device further comprises:

[0051] A history acquisition module, used to acquire historical search data under a preset search scenario, wherein the historical search data under the preset search scenario includes: historical query words under the preset search scenario, historical search results corresponding to the historical query words, and historical click data;

[0052] A demand analysis module, used to perform demand analysis on the historical search data under the preset search scenario to determine the target demand points;

[0053] The tag setting module is used to establish a preset tag under the preset search scenario according to the target demand point.

[0054] Optionally, the device further comprises:

[0055] A data classification module is used to classify web pages in a preset database and identify the search scenarios corresponding to each web page;

[0056] The tag marking module is used to mark the web pages with corresponding preset tags according to the main content of the web pages, and establish a mapping relationship between each web page and the preset tags in the corresponding search scenario.

[0057] On the other hand, an embodiment of the present invention discloses a device for searching, 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 aforementioned search methods.

[0058] 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, enables the device to perform one or more of the search methods described above.

[0059] The embodiments of the present invention include the following advantages:

[0060] When receiving a query word for performing a search behavior, the embodiment of the present invention determines a primary demand tag according to the query word, and determines a secondary demand tag according to the entity content contained in the query word, and the primary demand tag and the secondary demand tag are preset tags. The primary demand tag can reflect the most important search demand of the user inputting the query word for the search behavior. The secondary demand tag can reflect other possible extensible demands of the user inputting the query word for the search behavior. The embodiment of the present invention obtains the search results of the primary demand tag and the secondary demand tag corresponding to the query word respectively, and displays the search results. Therefore, the embodiment of the present invention, through a single search behavior, not only displays the search results that meet the user's most important search needs to the user, but also displays the search results that meet the user's extensible needs. That is, the embodiment of the present invention can provide the user with search results of multiple demand dimensions related to the query word through a single search behavior, thereby reducing the user's repeated process of adjusting the query word, improving search efficiency, simplifying the user's search operation process, and improving user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] 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.

[0062] Figure 1 is a flowchart of steps of an embodiment of a search method of the present invention;

[0063] Figure 2 It is a schematic diagram of a display interface of a search result page of the present invention;

[0064] Figure 3 is a structural block diagram of an embodiment of a search device of the present invention;

[0065] Figure 4 is a block diagram of an apparatus 800 for searching according to the present invention;

[0066] Figure 5 It is a schematic diagram of the structure of the server in some embodiments of the present invention. DETAILED DESCRIPTION

[0067] 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.

[0068] Method Embodiment

[0069] Reference Figure 1 , shows a flowchart of a search method embodiment of the present invention, which may specifically include the following steps:

[0070] Step 101: determining a primary requirement tag according to a query word, and determining at least one secondary requirement tag according to entity content contained in the query word, wherein the primary requirement tag and the secondary requirement tag are preset tags;

[0071] Step 102: Obtain search results for the query words corresponding to the primary demand tag and the secondary demand tag respectively;

[0072] Step 103: display the search results; the search results are obtained by aggregating the search results of the main demand tag and the secondary demand tag, and the search results corresponding to the main demand tag are displayed first.

[0073] The search method provided by the embodiment of 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.

[0074] In the search scenario, the electronic device can receive the query word entered by the user in the search box of the search platform, and the search platform returns the search results related to the query word according to a certain retrieval strategy. When receiving the user's trigger operation (such as a click operation) on a search result item in the search result page, it can jump to the details page corresponding to the search result item. It can be understood that in the specific implementation, the query word can not only be input by text, but also by voice input, icon recognition input, QR code scanning input, etc.

[0075] In the embodiment of the present invention, when a query word is received, a primary demand tag is determined according to the query word, and at least one secondary demand tag is determined according to the entity content contained in the query word, wherein the primary demand tag and the secondary demand tag are preset tags. The entity content may be a noun with a specific meaning, such as a product name, a person's name, a place name, an institution name, a proper noun, etc.

[0076] The preset tags are tags that are obtained by analyzing historical search data of a large number of users in advance and that can reflect the demand points that users generally pay attention to in a specific search scenario. Different preset tags can be predefined for different search scenarios.

[0077] In an optional embodiment of the present invention, taking a consumer search scenario as an example, the preset tags may include but are not limited to: rankings, purchase recommendations, brand positioning, advantages and disadvantages, comparative evaluations, and experience evaluations.

[0078] In an optional embodiment of the present invention, the method may further include:

[0079] Step S11, obtaining historical search data in a preset search scenario, wherein the historical search data in the preset search scenario includes but is not limited to: historical query words in the preset search scenario, historical search results corresponding to the historical query words, and historical click data;

[0080] Step S12: performing demand analysis on the historical search data under the preset search scenario to determine the target demand point;

[0081] Step S13: establishing a preset tag under the preset search scenario according to the target demand point.

[0082] Taking the preset search scenario as a consumer search scenario as an example, the historical search data of at least one network search platform can be collected and filtered to obtain the historical search data of the consumer search scenario. The network search platform refers to a website or a third-party platform with a network search function. The historical search data includes but is not limited to: historical query terms under the preset search scenario, historical search results corresponding to the historical query terms, and historical click data. The historical click data can be counted by the server and stored in the historical click database for subsequent analysis of the user's click behavior. The historical click data may include data such as whether the historical search results corresponding to any historical query term have been clicked, and of course, it may also include data such as the click time period, number of clicks, and specific content of the click.

[0083] Conduct demand analysis on the historical search data obtained in consumer search scenarios to determine target demand points. For example, by conducting demand analysis on the historical search data in consumer search scenarios, we can learn that the target demand points that users generally pay attention to mainly include: rankings of consumer products, purchase recommendations for consumer products, brand positioning of consumer products, advantages and disadvantages of consumer products, comparative evaluation of consumer products, experience evaluation of consumer products, etc. Therefore, preset tags can be established in consumer search scenarios, including: rankings, purchase recommendations, brand positioning, advantages and disadvantages, comparative evaluation, experience evaluation, etc.

[0084] For another example, for educational search scenarios, such as searching for information related to education, examinations or qualification certificates, corresponding preset tags can be pre-established, including: registration guide, value, level differences, examination difficulty, examination policy, preparation guide, examination room guide, question template, topic prediction, review materials, teaching and training resources, impact of absence from examination, scoring standards, score conversion, estimated score prediction, score review, score requirements, qualification certification guide, certificate acquisition, certificate registration, lost certificate, etc.

[0085] When a query word is received, an embodiment of the present invention may first identify the search scenario corresponding to the query word, and then determine a main requirement tag in the preset tags under the search scenario based on the query word. The main requirement tag may reflect the most important search requirement of the user entering the query word for the search behavior. Furthermore, an embodiment of the present invention determines at least one secondary requirement tag in the preset tags under the search scenario based on the entity content contained in the received query word, and the secondary requirement tag may reflect other possible extended requirements of the user entering the query word for the search behavior.

[0086] It should be noted that the embodiment of the present invention does not limit the number of primary demand tags and secondary demand tags. Preferably, there can be 1 primary demand tag, which reflects the user's most important search demand. The number of secondary demand tags can be greater than 1, which reflects other possible search demands of the user.

[0087] For example, for the query term "How is the Black Shark 3s phone", the main demand label can be determined to be "experience evaluation", which can reflect that the main search demand of the user who enters the query term for search behavior is to know the experience evaluation results of the Black Shark 3s phone. According to the entity content "Black Shark 3s phone" contained in the query term "How is the Black Shark 3s phone", three secondary demand labels can be determined, including "brand positioning", "purchase suggestions", and "advantages and disadvantages". The secondary demand label can reflect other possible extensible needs of the user who enters the query term for search behavior. For example, the user enters the query term "How is the Black Shark 3s phone", mainly to know the experience evaluation results of the Black Shark 3s phone. In addition, the user may also want to know the brand positioning, purchase suggestions, advantages and disadvantages of the "Black Shark 3s phone" and other related search results.

[0088] After determining the primary requirement tag and the secondary requirement tag, searching is performed based on the query word and the primary requirement tag and the secondary requirement tag to obtain search results in which the query word corresponds to the primary requirement tag and each of the secondary requirement tags.

[0089] Taking the above example, for the query "How is the Black Shark 3s phone", the main demand tag is determined to be "experience evaluation", and the secondary demand tags are determined to include "brand positioning", "purchase suggestions", and "advantages and disadvantages". Then, according to the query "How is the Black Shark 3s phone", a search is performed, and search results related to the main demand tag "experience evaluation" are obtained; and search results related to the secondary demand tag "brand positioning", search results related to the secondary demand tag "purchase suggestions", and search results related to the secondary demand tag "advantages and disadvantages" are obtained respectively.

[0090] It should be noted that after predefining different preset tags for different search scenarios, the web pages in the preset database can be marked with corresponding preset tags. The preset database contains relevant information of each web page of each site, such as the title, link, content summary of the web page, and historical query terms corresponding to each web page.

[0091] The method described in the embodiment of the present invention also includes: classifying web pages in the preset database, identifying the search scenarios corresponding to each web page, and marking the web pages with corresponding preset tags according to the main content of the web pages, and establishing a mapping relationship between each web page and the preset tags in the corresponding search scenarios. In this way, after receiving the query word input by the user and determining the primary demand tag and the secondary demand tag corresponding to the query word, all relevant search results are retrieved in the preset database based on the query word, and the search results corresponding to the primary demand tag and the secondary demand tag of the query word can be filtered by using the determined primary demand tag and the secondary demand tag and the mapping relationship.

[0092] After obtaining the search results for the main demand tag and the secondary demand tag corresponding to the query words, the search results can be displayed on the search results page. The search results are obtained by aggregating the search results for the main demand tag and the search results for each secondary demand tag, and the search results corresponding to the main demand tag are displayed first. In this way, the user can get the experience evaluation results of the "Black Shark 3s phone" and other related search results such as the brand positioning, purchase recommendations, advantages and disadvantages of the "Black Shark 3s phone" by entering the query word "How is the Black Shark 3s phone" to perform a search.

[0093] The embodiment of the present invention can provide users with search results of multiple demand dimensions related to the query word through a single search behavior. In the case that the search results of the primary demand tag corresponding to the query word cannot meet the user's search needs, the embodiment of the present invention proactively provides users with search results corresponding to secondary demand tags that may meet the user's potential search needs, which can reduce the user's repeated process of adjusting the query word, improve search efficiency, simplify the user's search operation process, and improve user experience.

[0094] In an optional embodiment of the present invention, if the query word has a question-answering intent, it can be called a question-answering query word; for the question-answering query word, determining the main demand tag according to the query word in step 101 includes:

[0095] Step S21: determining whether the query word is a question-answering query word; if so, performing semantic analysis on the query word to obtain key information related to the search intent;

[0096] Step S22: matching the key information with a preset semantic template to obtain a target semantic template corresponding to the key information, wherein the preset semantic template has a mapping relationship with the preset tag;

[0097] Step S23: Determine the preset tag corresponding to the target semantic template as the main requirement tag.

[0098] In specific implementations, different types of query words can reflect different degrees of search needs. For example, question-and-answer query words refer to query words that require a search platform to answer or resolve and that have clear user search needs. For example, a question-and-answer query word is "What is Mo Yan's Nobel Prize-winning work?" This question-and-answer query word can clearly reflect the user's search needs.

[0099] Therefore, for question-answering query words, the embodiment of the present invention can use semantic analysis and template matching methods to determine the main demand label.

[0100] In the embodiment of the present invention, the question-answer query words may include explicit question-answer query words and implicit question-answer query words.

[0101] Among them, the explicit question-and-answer query terms refer to: query terms including question words, such as "What is Mo Yan's Nobel Prize-winning work", "How about the Black Shark 3s mobile phone", etc. The question words may include but are not limited to question pronouns, question modal particles and question adverbs, etc.

[0102] The implicit question-and-answer query term refers to a query term that does not include a question word but contains a question-and-answer intent, such as "the advantages and disadvantages of the Black Shark 3s mobile phone". Although the query term does not include a question word, the query term has a question-and-answer intent, that is, the implicit semantics of the query term is "what are the advantages and disadvantages of the Black Shark 3s mobile phone". Therefore, the query term is an implicit question-and-answer query term.

[0103] Specifically, the embodiment of the present invention sets a corresponding preset semantic template for each preset tag. Referring to Table 1, a specific example of preset semantic templates corresponding to preset tags in a consumer search scenario is shown.

[0104] Table 1

[0105]

[0106]

[0107] When a query word is received, if it is determined that the query word is a question-and-answer query word, a semantic analysis is performed on the question-and-answer query word to obtain key information related to the search intent. For example, a semantic analysis is performed on the query word "How is the Black Shark 3s phone?", and the key information related to the search intent can be obtained as "how is it". The key information is matched with the preset semantic template, and the target semantic template corresponding to the key information can be obtained, such as the preset semantic template "*** how is it" shown in the second row of Table 1. Since the preset tag corresponding to the target semantic template is "experience evaluation", it can be determined that the preset tag corresponding to the target semantic template ("experience evaluation") is the main demand tag.

[0108] In an optional embodiment of the present invention, the query term includes an entity query term, and the step 101 of determining the main requirement tag according to the query term includes:

[0109] Step S31: determine whether the query word is a question-answer query word, and if so, determine the entity content contained in the entity query word;

[0110] Step S32: Acquire historical search data related to the entity content, wherein the historical search data related to the entity content includes: historical click data related to the entity content, and / or historical word change data related to the entity content;

[0111] Step S33: Determine historical search data that meets a preset condition in the historical search data related to the entity content;

[0112] Step S34: Determine that the preset tag corresponding to the historical search data that meets the preset condition is the main requirement tag.

[0113] Entity query terms refer to non-question-and-answer query terms that contain entity content. Question-and-answer query terms can clearly reflect the user's search needs; while entity query terms may not reflect the user's search needs clearly enough. Therefore, for entity query terms, the embodiment of the present invention adopts a method of comprehensively judging historical search data to determine the main demand label.

[0114] Specifically, first determine the entity content contained in the entity query term. The entity content contained in the entity query term may include the entity content contained in the entity query term itself and other entity content associated with the entity content contained in the entity query term itself. For example, entity recognition of the entity query term "SKII Skin Care Water" can obtain the following entity content contained in the entity query term itself: "SKII Skin Care Water" (a product of a certain brand), "SKII" (a certain brand). In addition, other entity content associated with the above-mentioned entity content itself can also be obtained, such as "Fairy Water" and so on.

[0115] After determining the entity content contained in the entity query term itself and the entity content associated with the entity content contained in the entity query term itself, historical search data related to the entity content is obtained. The historical search data related to the entity content includes, but is not limited to: historical click data related to the entity content, and historical word change data related to the entity content. Among them, the historical click data related to the entity content refers to the historical click data corresponding to the historical search results using the entity content as the historical query term. The historical word change data related to the entity content refers to the word change data included in a historical search behavior corresponding to the entity content as the historical query term. For example, a user enters "how to play finger-guessing boxing" to search, and finds that the search results are not satisfactory. After modifying the query term to "what are the skills of finger-guessing boxing", the search is triggered again, and a satisfactory search result is obtained. The modified query term "what are the skills of finger-guessing boxing" is the historical word change data corresponding to "how to play finger-guessing boxing".

[0116] Specifically, the entity content may be used to filter historical search data of at least one network search platform to obtain historical search data related to the entity content.

[0117] In the search scenario, the user enters a query term in the search box of the search platform to retrieve, which is a process in which the user makes a preliminary confirmation of the search demand. The user clicks on a search result in the returned search results, which is a process in which the user reconfirms the search demand. In an example, suppose the query term entered by the user is "How to play finger-guessing", and the user clicks on a search result in the search results page "What are the specific rules and gameplay of finger-guessing"? Among them, the query term "How to play finger-guessing" can reflect the user's preliminary confirmation of the search demand, and the click operation on the search result "What are the specific rules and gameplay of finger-guessing" can reflect the user's reconfirmation of the search demand. After reconfirmation, the user's search demand is clearer.

[0118] It can be seen that the user's click operation on the search result of the query word is the user's reconfirmation of the search demand. In addition, the user's operation of changing the query word is also the user's reconfirmation of the search demand. For example, after the user enters the query word "how to play finger-guessing" for retrieval, he modifies the query word "how to play finger-guessing" and enters a new query word "what are the skills of finger-guessing". The changed word data "what are the skills of finger-guessing" further clarifies the user's search needs. It should be noted that in actual applications, the method of changing words is not limited to manual input, and it can also be performed by clicking on the recommended words on the search results page or in the search box.

[0119] Since the user's click operation on the search results of the query word and the user's word change operation on the query word are the user's reconfirmation of the search demand, the user's search demand when entering the query word can be more clearly defined. Therefore, the embodiment of the present invention comprehensively determines the main demand label of the entity query word based on the historical click data and historical word change data in the historical search data related to the entity content, so that the determined main demand label can more accurately reflect the user's search demand.

[0120] Furthermore, in the embodiment of the present invention, historical search data that meets the preset conditions is determined in the historical search data related to the entity content. For example, for the historical click data related to the entity content, the historical search data with the highest click volume can be determined as the historical search data that meets the preset conditions. For another example, for the historical word change data related to the entity content, the historical search data with the highest probability of word change can be determined as the historical search data that meets the preset conditions.

[0121] For example, for the entity query term "tablet computer", the entity content contained in the entity query term is itself "tablet computer". Obtaining historical search data related to the entity content "tablet computer" includes: historical click data of historical search results of the entity content "tablet computer" as a historical query term, and historical word change data before and after the historical search behavior of the entity content "tablet computer" as a historical query term.

[0122] In the historical click data of the historical search results with the entity content "tablet computer" as the historical query word, the historical search result "2021 Tablet Computer Ranking" has the highest number of clicks, so the historical search result "2021 Tablet Computer Ranking" is the historical search data that meets the preset conditions. The historical search data that meets the preset conditions is matched with the preset tags. Since the keyword "ranking" contained in the historical search result "2021 Tablet Computer Ranking" matches the preset tag "ranking", it can be determined that the preset tag corresponding to the historical search result "2021 Tablet Computer Ranking" is "ranking", so the main demand tag can be determined to be "ranking". When the query word received is the entity class query word "tablet computer", it can be determined that the main demand tag is "ranking".

[0123] For another example, in the historical word-changing data before and after the historical search behavior using the entity content "tablet computer" as the historical query word, the historical word-changing data "tablet computer cost-effectiveness ranking" has the highest word-changing probability, so the historical word-changing data "tablet computer cost-effectiveness ranking" is the historical search data that meets the preset conditions. Since the preset label corresponding to the historical word-changing data "tablet computer cost-effectiveness ranking" is "ranking", it can be determined that the main demand label is "ranking". When the query word received is the entity query word "tablet computer", it can be determined that the main demand label is "ranking".

[0124] It should be noted that the embodiments of the present invention do not limit the specific types of historical search data related to entity content. In addition, in a specific implementation, when determining the main demand label corresponding to the entity query term, a certain type of historical search data can be used alone, or multiple types of historical search data can be used in combination.

[0125] For example, for a certain entity query term, the entity content contained in the entity query term can be identified, and the historical click data related to the entity content can be obtained. The main demand tag is first determined using the historical click data. If the main demand tag is not matched, the historical word replacement data related to the entity content can be further obtained, and the main demand tag is further determined using the historical word replacement data.

[0126] Furthermore, in a specific implementation, in the cold start phase, the main demand tag can be determined based on the historical search data related to the entity content in the entity query term; and after the historical click data of users on the preset tags is subsequently accumulated, the main demand tag can be determined by combining the historical search data related to the entity content and the historical click data of users on the preset tags. For example, if there are multiple matching main demand tags for a certain query term, the historical click data of each main demand tag can be further combined to select the one with the highest number of clicks as the main demand tag. For another example, if a certain query term does not match the main demand tag, the one with the highest number of clicks can be selected as the main demand tag based on the historical click data of the preset tags.

[0127] In an embodiment of the present invention, the process of determining a secondary demand tag is similar to the process of determining a primary demand tag for an entity query term. Specifically, the process of determining at least one secondary demand tag according to the entity content contained in the query term in step 101 may include: identifying the entity content contained in the query term, and obtaining historical search data related to the entity content; determining historical search data that meets a preset condition in the obtained historical search data related to the entity content; and determining that the preset tag corresponding to the historical search data that meets the preset condition is a secondary demand tag.

[0128] In an example, assuming that the query term is a question-and-answer query term "How is the Black Shark 3s mobile phone?", the main demand tag has been determined to be "experience evaluation" based on the query term. Next, the secondary demand tag is determined for the query term. Specifically, first identify that the entity content contained in the query term "How is the Black Shark 3s mobile phone?" is "Black Shark 3s mobile phone", and then obtain the historical search data related to the entity content "Black Shark 3s mobile phone", and take the historical click data of the historical search results of the entity content "Black Shark 3s mobile phone" as an example. Assuming that the historical search results with high click volume include: "What brand is Black Shark?", "Is the Black Shark 3s mobile phone worth buying?", "The highlights and flaws of Black Shark 3s", "Black Shark 3s vs. Red Magic 5s", it can be determined that the secondary demand tags can include but are not limited to: "Brand positioning", "Purchase recommendations", "Advantages and disadvantages".

[0129] After obtaining search results in which the query terms correspond to the primary demand tag and the secondary demand tag respectively, the search results may be displayed on a search results page.

[0130] In an optional embodiment of the present invention, the displaying of the search results in step 103 includes:

[0131] According to a preset sorting strategy, the search results of the query terms corresponding to the primary demand tag and the secondary demand tag are sorted and displayed.

[0132] The embodiments of the present invention do not limit the preset sorting strategy. For example, the sorting result corresponding to the primary demand tag can be placed before the sorting result corresponding to the secondary demand tag. Furthermore, different priorities can be set for multiple secondary demand tags, and the sorting results corresponding to the secondary demand tags can be sorted and displayed according to the priority.

[0133] In an optional embodiment of the present invention, the displaying of the search results in step 103 includes:

[0134] In the current interface of the search results page, the search results corresponding to the main demand tag and the secondary demand tag are displayed in the form of tabs, and each tab is used to display the search results corresponding to a demand tag; and the tab where the search results corresponding to the main demand tag are located is displayed first. By switching tabs, the search results corresponding to each demand tag can be switched in the current interface.

[0135] To facilitate users to classify and view search results corresponding to the main demand tag and search results corresponding to each secondary demand tag, an embodiment of the present invention classifies and aggregates the search results corresponding to the main demand tag and the secondary demand tag of the acquired query terms for display.

[0136] Specifically, the search results corresponding to the primary demand tag are displayed in the current interface of the search results page, and the switch keys corresponding to the primary demand tag and the secondary demand tag are displayed, respectively, and the switch keys are used to switch the display interface of each search result in the current interface in response to the trigger operation. The switch key includes but is not limited to a virtual button, a page tab, a graphic, etc. The trigger operation includes but is not limited to a click (including a single click, a double click, a triple click, etc.) operation, a long press operation, and a sliding operation, etc.

[0137] Reference Figure 2 , shows a schematic diagram of a display interface of a search result page of the present invention. Figure 2 As shown in the figure, the current interface of the search result page shows the search results corresponding to the main demand label "Experience Evaluation". The current interface also shows the switch keys corresponding to the main demand label and each secondary demand label. Among them, the switch key of the main demand label "Experience Evaluation" is selected. Assuming that the user triggers the switch key of the secondary demand label "Ranking", Figure 2 The current interface of the search results page shown is switched to the display interface of the search results corresponding to the secondary demand tag "Ranking", and the secondary demand tag "Ranking" is set to a selected state, and the main demand tag "Experience Evaluation" is set to a non-selected state.

[0138] In another example, assuming that the query term is a question-and-answer query term "Which faucet brand is good", based on the query term, it can be determined that the main demand label is "purchase suggestions", and based on the entity content contained in the query term, it can be determined that the secondary demand labels include: "rankings", "advantages and disadvantages", and "experience evaluation". After obtaining the search results corresponding to the above-mentioned main demand labels and secondary demand labels for the query term, the search results can be displayed on the search results page. For example, the search results corresponding to the main demand label "purchase suggestions" are displayed in the current interface of the search results page, and the switch keys corresponding to the main demand label "purchase suggestions" and the secondary demand labels "rankings", "advantages and disadvantages", and "experience evaluation" are displayed respectively.

[0139] It is understandable that, for search behaviors with different query words, the determined primary demand tags and secondary demand tags may be different, and the number of secondary demand tags may also be different. The embodiment of the present invention dynamically determines the primary demand tags and secondary demand tags that match the query word based on the query word received in real time, and obtains and displays the search results of the primary demand tags and secondary demand tags corresponding to the query word, respectively, so that the displayed search results are more in line with the search needs of the current search behavior. Furthermore, after displaying the search results, the user's click behavior on the search results corresponding to each demand tag (including primary demand tags and secondary demand tags) in the search results page can be recorded, and the click data can be saved to provide a data basis for the subsequent analysis of the user's search needs and the determination of the primary demand tags and secondary demand tags.

[0140] Optionally, the search result page may include a primary page, in which only brief information of each search result is displayed, such as the title and introduction of each search result. An entrance to a secondary page may be provided in the primary page, and a secondary page may be displayed in response to a triggering operation on the entrance. The secondary page includes search results of the primary demand tag and the secondary demand tag corresponding to the query terms, as well as detailed information of each search result. Furthermore, the current interface of the secondary page displays the search results corresponding to the primary demand tag, and the current interface of the secondary page may also display switch keys corresponding to the primary demand tag and each secondary demand tag, so as to switch the display of the secondary page corresponding to the primary demand tag and the secondary page corresponding to each secondary demand tag.

[0141] In summary, when receiving a query word for performing a search behavior, the embodiment of the present invention determines a primary demand tag according to the query word, and determines a secondary demand tag according to the entity content contained in the query word, and the primary demand tag and the secondary demand tag are preset tags. The primary demand tag can reflect the most important search demand of the user inputting the query word for the search behavior. The secondary demand tag can reflect other possible extensibility demands of the user inputting the query word for the search behavior. The embodiment of the present invention obtains the search results of the primary demand tag and the secondary demand tag corresponding to the query word respectively, and displays the search results. Therefore, the embodiment of the present invention, through a single search behavior, not only displays the search results that meet the user's most important search needs to the user, but also displays the search results that meet the user's extensibility needs. That is, the embodiment of the present invention can provide the user with search results of multiple demand dimensions related to the query word through a single search behavior, thereby reducing the user's repeated process of adjusting the query word, improving search efficiency, simplifying the user's search operation process, and improving user experience.

[0142] 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.

[0143] Device Embodiment

[0144] Reference Figure 3 , shows a structural block diagram of an embodiment of a search device of the present invention, the device may include:

[0145] The tag determination module 301 is used to determine a primary requirement tag according to a query word, and to determine at least one secondary requirement tag according to entity content contained in the query word, wherein the primary requirement tag and the secondary requirement tag are preset tags;

[0146] A result acquisition module 302 is used to acquire search results of the query words corresponding to the primary requirement tags and the secondary requirement tags respectively;

[0147] The result display module 303 is used to display the search results; the search results are obtained by aggregating the search results of the main demand tag and the secondary demand tag, and the search results corresponding to the main demand tag are displayed first.

[0148] Optionally, the label determination module includes a main demand label determination module, and the main demand label determination module includes:

[0149] A semantic analysis submodule, used to determine whether the query word is a question-answering query word, and if so, to perform semantic analysis on the query word to obtain key information related to the search intent;

[0150] An information matching submodule, used for matching the key information with a preset semantic template to obtain a target semantic template corresponding to the key information, wherein the preset semantic template has a mapping relationship with the preset label;

[0151] The first determination submodule is used to determine the preset tag corresponding to the target semantic template as the main requirement tag.

[0152] Optionally, the label determination module includes a main demand label determination module, and the main demand label determination module includes:

[0153] A content determination submodule, used to determine whether the query word is an entity query word, and if so, determine the entity content contained in the query word;

[0154] A data acquisition submodule, used to acquire historical search data related to the entity content, wherein the historical search data related to the entity content includes: historical click data related to the entity content, and / or historical word change data related to the entity content;

[0155] A target determination submodule, used to determine historical search data that meets a preset condition among the historical search data related to the entity content;

[0156] The second determining submodule is used to determine that the preset tag corresponding to the historical search data that meets the preset condition is the main demand tag.

[0157] Optionally, the tag determination module includes a secondary demand tag determination module, and the secondary demand tag determination module includes:

[0158] An identification and acquisition submodule, used to identify entity content contained in the query term and acquire historical search data related to the entity content;

[0159] A data determination submodule, used to determine historical search data that meets preset conditions among the acquired historical search data related to the entity content;

[0160] The third determining submodule is used to determine that the preset tag corresponding to the historical search data that meets the preset condition is a secondary demand tag.

[0161] Optionally, the result display module is specifically used to display the search results corresponding to the main demand tag and the secondary demand tag in the form of tabs in the current interface of the search results page, and each tab is used to display the search results corresponding to a demand tag; and the tab where the search results corresponding to the main demand tag are located is displayed first, and by switching tabs, the search results corresponding to each demand tag can be switched and displayed in the current interface.

[0162] Optionally, the device further comprises:

[0163] A history acquisition module, used to acquire historical search data under a preset search scenario, wherein the historical search data under the preset search scenario includes: historical query words under the preset search scenario, historical search results corresponding to the historical query words, and historical click data;

[0164] A demand analysis module, used to perform demand analysis on the historical search data under the preset search scenario to determine the target demand points;

[0165] The tag setting module is used to establish a preset tag under the preset search scenario according to the target demand point.

[0166] Optionally, the device further comprises:

[0167] A data classification module is used to classify web pages in a preset database and identify the search scenarios corresponding to each web page;

[0168] The tag marking module is used to mark the web pages with corresponding preset tags according to the main content of the web pages, and establish a mapping relationship between each web page and the preset tags in the corresponding search scenario.

[0169] The embodiment of the present invention not only displays search results that meet the user's main search needs, but also displays search results that meet the user's scalability needs through a single search behavior. That is, the embodiment of the present invention can provide the user with search results of multiple demand dimensions related to the query word through a single search behavior, thereby reducing the user's repeated process of adjusting the query word, improving search efficiency, simplifying the user's search operation process, and improving user experience.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] An embodiment of the present invention provides a device for searching, 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: determining a primary requirement tag based on a query word, and determining at least one secondary requirement tag based on entity content contained in the query word, wherein the primary requirement tag and the secondary requirement tag are preset tags; obtaining search results for the primary requirement tag and the secondary requirement tag corresponding to the query word respectively; displaying the search results; the search results are obtained by aggregating the search results of the primary requirement tag and the secondary requirement tag, and the search results corresponding to the primary requirement tag are displayed preferentially.

[0174] Optionally, determining the main requirement tag according to the query term includes:

[0175] Determine whether the query is a question-answering query, and if so, perform semantic analysis on the query to obtain key information related to the search intent;

[0176] Matching the key information with a preset semantic template to obtain a target semantic template corresponding to the key information, wherein the preset semantic template has a mapping relationship with the preset tag;

[0177] The preset tag corresponding to the target semantic template is determined as the main requirement tag.

[0178] Optionally, determining the main requirement tag according to the query term includes:

[0179] Determine whether the query word is an entity query word, and if so, determine the entity content contained in the query word;

[0180] Acquire historical search data related to the entity content, wherein the historical search data related to the entity content includes: historical click data related to the entity content, and / or historical word change data related to the entity content;

[0181] Determining historical search data that meets a preset condition among the historical search data related to the entity content;

[0182] The preset tag corresponding to the historical search data satisfying the preset condition is determined as the main requirement tag.

[0183] Optionally, determining at least one secondary requirement tag according to entity content included in the query term includes:

[0184] Identify entity content contained in the query term, and obtain historical search data related to the entity content;

[0185] Determine historical search data that meets a preset condition among the acquired historical search data related to the entity content;

[0186] Determine that the preset tag corresponding to the historical search data that meets the preset condition is a secondary demand tag.

[0187] Optionally, displaying the search results includes:

[0188] Displaying the search results corresponding to the primary demand tag and the secondary demand tag in the form of tabs in the current interface of the search results page, each tab is used to display the search results corresponding to one demand tag;

[0189] The tab page where the search results corresponding to the main demand tag are located is displayed first, and the search results corresponding to each demand tag can be switched and displayed in the current interface by switching tab pages.

[0190] 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:

[0191] Acquire historical search data under a preset search scenario, wherein the historical search data under the preset search scenario includes: historical query words under the preset search scenario, historical search results corresponding to the historical query words, and historical click data;

[0192] Performing demand analysis on the historical search data under the preset search scenario to determine the target demand points;

[0193] A preset tag under the preset search scenario is established according to the target demand point.

[0194] 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:

[0195] Classify web pages in the preset database and identify the search scenarios corresponding to each web page;

[0196] The web pages are marked with corresponding preset tags according to the main contents in the web pages, and a mapping relationship between each web page and the preset tags in the corresponding search scenario is established.

[0197] Figure 4 8 is a block diagram of an apparatus 800 for searching 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.

[0198] Reference Figure 4 , 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 .

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] Figure 51 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.

[0210] 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.

[0211] 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 method shown.

[0212] 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), the device is able to execute a search method, the method comprising: determining a primary requirement tag according to a query word, and determining at least one secondary requirement tag according to entity content contained in the query word, the primary requirement tag and the secondary requirement tag being preset tags; obtaining search results for the primary requirement tag and the secondary requirement tag corresponding to the query word respectively; displaying the search results; the search results are obtained by aggregating the search results of the primary requirement tag and the secondary requirement tag, and the search results corresponding to the primary requirement tag are displayed preferentially.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] The above is a detailed introduction to a search method, a search device and a device for searching 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 general technical personnel in this field, 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 method, characterized in that: The method comprises: Acquire historical search data under a preset search scenario, wherein the historical search data under the preset search scenario includes: historical query words under the preset search scenario, historical search results corresponding to the historical query words, and historical click data; Performing demand analysis on the historical search data under the preset search scenario to determine the target demand points; Establishing a preset tag under the preset search scenario according to the target demand point; Identify the search scenario corresponding to the query word, determine whether the query word is a question-and-answer query word, and if so, perform semantic analysis on the query word to obtain key information related to the search intent; match the key information with a preset semantic template to obtain a target semantic template corresponding to the key information, and the preset semantic template has a mapping relationship with the preset label; determine that the preset label in the search scenario corresponding to the target semantic template is a primary demand label; determine at least one secondary demand label in the preset labels in the search scenario according to the entity content contained in the query word; the primary demand label and the secondary demand label belong to preset labels; the question-and-answer query word includes explicit question-and-answer query words and implicit question-and-answer query words; the explicit question-and-answer query word refers to a query word that includes a question word; the implicit question-and-answer query word refers to a query word that does not include a question word but contains a question-and-answer intent; Obtain search results for the query words corresponding to the primary demand tag and the secondary demand tag respectively; The search results corresponding to the main demand tag and the secondary demand tag are displayed in the form of tabs in the current interface of the search results page, and each tab is used to display the search results corresponding to a demand tag; and the tab where the search results corresponding to the main demand tag are located is displayed first, and the search results corresponding to each demand tag are displayed in the current interface by switching tabs; the search results are aggregated from the search results of the main demand tag and the secondary demand tag, and the search results corresponding to the main demand tag are displayed first.

2. The method according to claim 1, characterized in that The determining of the main requirement tag according to the query term includes: Determine whether the query word is an entity query word, and if so, determine the entity content contained in the query word; Acquire historical search data related to the entity content, wherein the historical search data related to the entity content includes: historical click data related to the entity content, and / or historical word change data related to the entity content; Determining historical search data that meets a preset condition among the historical search data related to the entity content; The preset tag corresponding to the historical search data satisfying the preset condition is determined as the main requirement tag.

3. The method according to claim 1, characterized in that The determining at least one secondary requirement tag according to the entity content contained in the query term includes: Identify entity content contained in the query term, and obtain historical search data related to the entity content; Determine historical search data that meets a preset condition among the acquired historical search data related to the entity content; Determine that the preset tag corresponding to the historical search data that meets the preset condition is a secondary demand tag.

4. The method according to claim 1, characterized in that: The method further comprises: Classify web pages in the preset database and identify the search scenarios corresponding to each web page; The web pages are marked with corresponding preset tags according to the main contents in the web pages, and a mapping relationship between each web page and the preset tags in the corresponding search scenario is established.

5. A search device, characterized in that: The device comprises: A history acquisition module, used to acquire historical search data under a preset search scenario, wherein the historical search data under the preset search scenario includes: historical query words under the preset search scenario, historical search results corresponding to the historical query words, and historical click data; A demand analysis module, used to perform demand analysis on the historical search data under the preset search scenario to determine the target demand points; A label setting module, used to establish a preset label under the preset search scenario according to the target demand point; A label determination module is used to identify the search scenario corresponding to the query word, determine whether the query word is a question-and-answer query word, and if so, perform semantic analysis on the query word to obtain key information related to the search intent; match the key information with a preset semantic template to obtain a target semantic template corresponding to the key information, and the preset semantic template has a mapping relationship with the preset label; determine that the preset label in the search scenario corresponding to the target semantic template is a primary demand label; determine at least one secondary demand label in the preset labels in the search scenario according to the entity content contained in the query word; the primary demand label and the secondary demand label belong to preset labels; the question-and-answer query word includes explicit question-and-answer query words and implicit question-and-answer query words; the explicit question-and-answer query word refers to a query word that includes a question word; the implicit question-and-answer query word refers to a query word that does not include a question word but contains a question-and-answer intent; A result acquisition module, used to acquire search results of the query words corresponding to the primary demand tags and the secondary demand tags respectively; A result display module is used to display the search results corresponding to the main demand tag and the secondary demand tag in the form of tabs in the current interface of the search results page, each tab is used to display the search results corresponding to a demand tag; and the tab where the search results corresponding to the main demand tag are located is displayed first, and the search results corresponding to each demand tag are displayed in the current interface by switching tabs; the search results are aggregated from the search results of the main demand tag and the secondary demand tag, and the search results corresponding to the main demand tag are displayed first.

6. The device according to claim 5, characterized in that The tag determination module includes a main demand tag determination module; the main demand tag determination module includes: A content determination submodule, used to determine whether the query word is an entity query word, and if so, determine the entity content contained in the query word; A data acquisition submodule, used to acquire historical search data related to the entity content, wherein the historical search data related to the entity content includes: historical click data related to the entity content, and / or historical word change data related to the entity content; A target determination submodule, used to determine historical search data that meets a preset condition among the historical search data related to the entity content; The second determining submodule is used to determine that the preset tag corresponding to the historical search data that meets the preset condition is the main demand tag.

7. The device according to claim 5, characterized in that The tag determination module includes a secondary demand tag determination module, and the secondary demand tag determination module includes: An identification and acquisition submodule, used to identify entity content contained in the query term and acquire historical search data related to the entity content; A data determination submodule, used to determine historical search data that meets preset conditions among the acquired historical search data related to the entity content; The third determining submodule is used to determine that the preset tag corresponding to the historical search data that meets the preset condition is a secondary demand tag.

8. The device according to claim 5, characterized in that The device also includes: A data classification module is used to classify web pages in a preset database and identify the search scenarios corresponding to each web page; The tag marking module is used to mark the web pages with corresponding preset tags according to the main content of the web pages, and establish a mapping relationship between each web page and the preset tags in the corresponding search scenario.

9. A device for searching, 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 method as claimed in any one of claims 1 to 4.

10. 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 method according to any one of claims 1 to 4.

Images