A search method, apparatus and medium

Abstract

Embodiments of the present application provide a search method, device and medium. The method specifically comprises: receiving a search request of a user; determining a target search intention corresponding to the search request; determining a plurality of target dimension labels corresponding to the search request according to a plurality of dimension labels corresponding to the target search intention; and determining search result data corresponding to the plurality of target dimension labels respectively according to the search request and the plurality of target dimension labels. Embodiments of the present application can improve the efficiency of the user in obtaining medical information from the search result data, and can save network resources consumed in the information obtaining process.

Description

Technical Field

[0001] The present invention relates to the field of communication technologies, and in particular to a search method, device, and medium. Background Art

[0002] With the continuous advancement of technology and rising living standards, users are placing increasing emphasis on healthcare. Simultaneously, with the continuous development of internet technology, search engines have become a crucial tool for users to access information online. Therefore, when faced with a need for healthcare-related information, most users turn to search engines.

[0003] Currently, a user enters a search query into a search engine's search box, and the search engine obtains multiple search results matching the query and displays them on a search results page. For example, for a search query like "how to treat epilepsy," the search results might include information such as the title and summary of web pages containing "epilepsy," allowing the user to determine whether to open the corresponding web page based on the title and summary.

[0004] During the implementation of the embodiments of the present invention, the inventors discovered that when users input "how to treat epilepsy," they usually hope to obtain medical information related to the treatment methods of "epilepsy." However, the search results page usually includes a large number of search results items, which include not only medical information related to the treatment methods of "epilepsy," but also medical information unrelated to the treatment methods of "epilepsy," such as an overview of "epilepsy," the cause of the disease, medical treatment, diagnosis, and other information. As a result, users need to search through a large number of search results items to find medical information related to the treatment methods of "epilepsy." During this search process, users usually need to incur a high operating cost to obtain the medical information they really need, resulting in low efficiency in obtaining medical information and consumption of network resources. Summary of the Invention

[0005] Embodiments of the present invention provide a search method, device, and medium, which can improve the efficiency of users in obtaining medical information from search result data and save network resources consumed in the information acquisition process.

[0006] In order to solve the above problem, an embodiment of the present invention discloses a search method, including:

[0007] Receive user search requests;

[0008] Determining a target search intent corresponding to the search request;

[0009] Determining a plurality of target dimension tags corresponding to the search request based on the plurality of dimension tags corresponding to the target search intent;

[0010] determine the search result data corresponding to the search request and the plurality of target dimension labels.

[0011] To solve the above problems, the embodiment of the present application discloses a search method, comprising:

[0012] receiving a search request of a user;

[0013] determining search result data corresponding to the search request; the search result data comprises search result data corresponding to a plurality of target dimension labels respectively; the plurality of target dimension labels correspond to the search request and a target search intent corresponding to the search request;

[0014] displaying the search result data corresponding to the plurality of target dimension labels respectively in a search result page.

[0015] In another aspect, the embodiment of the present application discloses a search device, comprising:

[0016] a receiving module configured to receive a search request of a user;

[0017] a search intent determination module configured to determine a target search intent corresponding to the search request;

[0018] a dimension label determination module configured to determine a plurality of target dimension labels corresponding to the search request according to a plurality of dimension labels corresponding to the target search intent; and

[0019] a search result determination module configured to determine search result data corresponding to the plurality of target dimension labels respectively according to the search request and the plurality of target dimension labels.

[0020] In another aspect, the embodiment of the present application discloses a search device, comprising:

[0021] a receiving module configured to receive a search request of a user;

[0022] a search result determination module configured to determine search result data corresponding to the search request; the search result data comprises search result data corresponding to a plurality of target dimension labels respectively; the plurality of target dimension labels correspond to the search request and a target search intent corresponding to the search request; and

[0023] a display module configured to display the search result data corresponding to the plurality of target dimension labels respectively in a search result page.

[0024] In another aspect, 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. The one or more programs include instructions for performing the following operations:

[0025] Receive user search requests;

[0026] Determining a target search intent corresponding to the search request;

[0027] Determining a plurality of target dimension tags corresponding to the search request based on the plurality of dimension tags corresponding to the target search intent;

[0028] Based on the search request and the multiple target dimension tags, the search result data corresponding to the multiple target dimension tags are determined.

[0029] In another aspect, 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. The one or more programs include instructions for performing the following operations:

[0030] Receive user search requests;

[0031] Determine search result data corresponding to the search request; the search result data includes: search result data corresponding to a plurality of target dimension tags; the plurality of target dimension tags correspond to the search request and the target search intent corresponding to the search request;

[0032] On the search results page, the search results data corresponding to the multiple target dimension tags are displayed separately

[0033] In yet another aspect, an embodiment of the present invention discloses a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes a device to perform one or more of the search methods described above.

[0034] The embodiments of the present invention include the following advantages:

[0035] When an embodiment of the present invention receives a search request, it determines the target search intent and multiple target dimension tags corresponding to the search request, and determines the search result data corresponding to the multiple target dimension tags based on the search request and the multiple target dimension tags. Since multiple target dimension tags can describe the target search intent corresponding to the search request from multiple dimensions, the multiple target dimension tags can refine the target search intent; on this basis, the embodiment of the present invention provides corresponding search result data based on the target dimension tags, thereby improving the refinement of the search result data.

[0036] When the search result data corresponding to the target dimension tag is provided, the user can filter and view the search result data based on the target dimension tag. For example, if user A is interested in a target dimension tag, he can view the search result data corresponding to the target dimension tag; for another example, if user B is interested in multiple target dimension tags, he can view the search result data corresponding to multiple target dimension tags respectively. Since the embodiment of the present invention allows users to filter and view search result data based on target dimension tags, it can improve the efficiency of users in obtaining medical information from search result data and save network resources consumed in the process of obtaining information. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments of the present invention. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0038] Figure 1 This is a schematic diagram of an application environment of a search method according to an embodiment of the present invention;

[0039] Figure 2 This is a flowchart of the steps of Embodiment 1 of a search method of the present invention;

[0040] Figure 3 This is a flowchart of the steps of Embodiment 2 of a search method of the present invention;

[0041] Figure 4 This is a flowchart of the steps of Embodiment 3 of a search method of the present invention;

[0042] Figure 5 is a structural block diagram of an embodiment of a search device of the present invention;

[0043] Figure 6 is a structural block diagram of an embodiment of a search device of the present invention;

[0044] Figure 7 is a block diagram of an apparatus 1100 for searching according to the present invention; and

[0045] Figure 8 It is a schematic diagram of the structure of the server in some embodiments of the present invention. DETAILED DESCRIPTION

[0046] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0047] In response to the technical problems of low efficiency in obtaining medical information and consumption of network resources, an embodiment of the present invention provides a search method, which may include: receiving a user's search request; determining a target search intent corresponding to the above search request; determining a plurality of target dimension tags corresponding to the above search request based on a plurality of dimension tags corresponding to the above target search intent; and determining search result data corresponding to the above multiple target dimension tags respectively based on the above search request and the above multiple target dimension tags.

[0048] In embodiments of the present invention, search intent can represent the actual user needs corresponding to a search request. Dimensions can represent the perspectives used to describe search intent. Embodiments of the present invention can describe search intent based on multiple dimensions. Dimension labels can be used to represent the dimensions corresponding to search intent. One search intent can correspond to multiple dimension labels, thereby increasing the precision of search intent.

[0049] When an embodiment of the present invention receives a search request, it determines the target search intent and multiple target dimension tags corresponding to the search request, and determines the search result data corresponding to the multiple target dimension tags based on the search request and the multiple target dimension tags. Since multiple target dimension tags can describe the target search intent corresponding to the search request from multiple dimensions, the multiple target dimension tags can refine the target search intent; on this basis, the embodiment of the present invention provides corresponding search result data based on the target dimension tags, thereby improving the refinement of the search result data.

[0050] When the search result data corresponding to the target dimension tag is provided, the user can filter and view the search result data based on the target dimension tag. For example, if user A is interested in a target dimension tag, he can view the search result data corresponding to the target dimension tag; for another example, if user B is interested in multiple target dimension tags, he can view the search result data corresponding to multiple target dimension tags respectively. Since the embodiment of the present invention allows users to filter and view search result data based on target dimension tags, it can improve the efficiency of users in obtaining medical information from search result data and save network resources consumed in the process of obtaining information.

[0051] For example, if search request A is "How to treat epilepsy", then an embodiment of the present invention can determine the target search intent "disease treatment" corresponding to search request A. Based on the multiple dimension tags corresponding to the target search intent "disease treatment", the embodiment of the present invention can determine the multiple target dimension tags corresponding to search request A, such as "drug treatment", "surgical treatment", and "emergency treatment", and provide corresponding search result data for each of the multiple target dimension tags. In this way, users can filter and view search result data based on the target dimension tags.

[0052] The search method provided by the embodiment of the present invention can be applied to application scenarios such as websites and / or APPs (applications). For example, the application scenarios of the embodiment of the present invention may include: search engine websites, or search engine APPs, etc.

[0053] The embodiments of the present invention can be applied to searches in vertical fields such as medical care, film and television, shopping, automobiles, and sports. The embodiments of the present invention mainly use the medical field as an example to illustrate the search method, and the corresponding search methods in other fields can be referenced.

[0054] In the embodiment of the present invention, an entity refers to an objectively existing and distinguishable matter, including specific people, things, objects, abstract concepts or connections, etc. The entity in the medical field may be a medical entity. Optionally, natural language processing (NLP) technology may be used to extract medical entity words from medical resources. Medical resources may include: at least one of medical literature data, medical encyclopedia data, medical question-and-answer data, case data, and popular science data. It will be understood that the embodiment of the present invention does not limit the specific process of determining medical entity words.

[0055] The medical entity type may refer to the type corresponding to the medical entity, and the medical entity type may include but is not limited to: disease type, symptom type, examination type, surgery type, drug type, treatment plan type, disease influencing factor type, population type, and department type.

[0056] For example, the medical entity words corresponding to the disease type may include: "hypertension", "leukemia", etc.; the medical entity words corresponding to the symptom type may include: "headache", "fever", etc.; the medical entity words corresponding to the examination type may include: "laboratory test", "imaging examination", etc.; the surgery type and the drug type can both represent the treatment method adopted for the disease; the treatment plan type may include: specific surgery information, or specific drug dosage, course of treatment and other information; the disease influencing factor type may refer to the factors that affect the disease, such as the cause of the disease; the population type can represent the population corresponding to the patient; the department type can refer to the corresponding department in the hospital.

[0057] It is understood that those skilled in the art may further classify the above-mentioned medical entity types based on actual application requirements. For example, symptom types may be classified into the following medical entity types: onset location characteristics, symptom frequency characteristics, symptom duration characteristics, symptom subtype characteristics, symptom level characteristics, and accompanying symptom characteristics. It is understood that the embodiments of the present invention are not limited to specific medical entity types.

[0058] In an optional embodiment of the present invention, entity recognition can be performed on medical resources to obtain medical entity words; medical entity words with the same semantics but different descriptions can be uniformly processed, and the uniformly processed medical entity words can be saved in a medical entity library.

[0059] Embodiments of the present invention may employ Named Entity Recognition (NER) methods to identify entities in medical resources. NER methods may include lexicon-based methods, rule-based methods, or statistical learning-based methods. It should be understood that embodiments of the present invention are not limited to specific NER methods.

[0060] To address the problem that the same medical entity words in medical resources correspond to different descriptions, the embodiments of the present invention uniformly process medical entity words with the same semantics but different descriptions, which can achieve standardization of medical entity words and thereby reduce the computational complexity of medical entity word processing.

[0061] For example, embodiments of the present invention can pre-set standard descriptions of medical entity words based on age ranges, such as "infants," "children," "children," "teenagers," "adults," and "elderly," for population types. Furthermore, medical entity words with the same semantics but different descriptions in medical resources can be unified into standard descriptions of medical entity words. For example, "baby" can be unified into "infant," and "uncle" can be unified into "adult" or "elderly," and so on. Of course, the above-mentioned unification process can be performed based on the age information contained in the medical resources.

[0062] For another example, the embodiment of the present invention can preset standard descriptions of medical entity words according to the symptom type, such as "headache", "tongue pain", etc. Moreover, medical entity words with the same semantics but different descriptions in medical resources can be unified into standard descriptions of medical entity words. In this way, personalized or colloquial symptom descriptions can be unified into standard descriptions of medical entity words. For example, the personalized or colloquial symptom descriptions corresponding to "headache" specifically include: "pain like a needle prick", "throbbing pain", "pain when touched", "pain when swallowing saliva", etc. For another example, the personalized or colloquial symptom descriptions corresponding to "tongue pain" specifically include: "pain on the left side of the tongue", "pain at the tip of the tongue", "pain at the root of the tongue", "pain at the edge of the tongue", etc.

[0063] The search method provided by the embodiment of the present invention can be applied to Figure 1 In the application environment shown, Figure 1 As shown, the client 100 and the server 200 are located in a wired or wireless network, and the client 100 and the server 200 perform data interaction through the wired or wireless network.

[0064] Optionally, the client 100 can run on a terminal, which specifically includes but is not limited to: smart phones, 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.

[0065] Method Example 1

[0066] Reference Figure 2 , shows a flowchart of the steps of embodiment 1 of a search method of the present invention, which may specifically include the following steps:

[0067] Step 201: Receive a user's search request;

[0068] Step 202: Determine the target search intent corresponding to the search request;

[0069] Step 203: Determine multiple target dimension tags corresponding to the search request based on the multiple dimension tags corresponding to the target search intent;

[0070] Step 204: Determine the search result data corresponding to the multiple target dimension tags respectively based on the search request and the multiple target dimension tags.

[0071] Figure 2 At least one step of the illustrated method embodiment may be executed by the client and / or the server. Of course, the embodiment of the present invention does not limit the specific execution subject of each step.

[0072] In step 201, the client of the search APP or search website may provide a UI (User Interface) to enable the user to submit a search request to the client through a search box on the UI, a voice interface, etc. It is understood that the embodiment of the present invention does not limit the specific method of submitting the search request.

[0073] In step 202, search intent can represent the actual user needs corresponding to the search request. Dimensions can represent the perspectives used to describe search intent. Embodiments of the present invention can describe search intent based on multiple dimensions. Dimension labels can be used to represent the dimensions corresponding to search intent. One search intent can correspond to multiple dimension labels, thereby increasing the precision of search intent.

[0074] In an embodiment of the present invention, historical search requests may be analyzed to obtain search intent. Optionally, the search intent may be determined by:

[0075] Determination method A1: clustering historical search requests to obtain at least one search intent; and / or

[0076] Determination method A2: adding tags to historical search requests, and determining at least one search intent based on the tags.

[0077] For determination method A1, clustering can refer to a method of grouping things into classes according to certain attributes of things, making the similarity between classes as small as possible and the similarity within classes as large as possible.

[0078] In an embodiment of the present invention, historical search requests may be recorded in a search log, and clustered using a clustering method to obtain at least one search intent. The search intent may correspond to a category obtained by clustering in determination method A1.

[0079] For example, search intent in the medical field may include but is not limited to at least one of the following search intents: symptoms, disease treatment, disease relief, disease symptoms, disease causes, symptom relief, symptom treatment, etc.

[0080] Regarding determination method A2, a manual method or a natural language processing method may be used to add tags to historical search requests, and at least one search intent may be determined based on the tags. It is understood that a historical search request may correspond to one or more search intents.

[0081] It can be understood that the above-mentioned determination method A1 and determination method A2 are only optional embodiments. In fact, those skilled in the art can adopt other determination methods according to actual application requirements. For example, the search intent can be determined based on historical search requests and search results whose click-through rates corresponding to the historical search requests exceed the click-through rate threshold.

[0082] In an embodiment of the present invention, the keyword corresponding to the search intent may be one or more. For example, the keyword corresponding to the "symptoms" intent may be "symptoms", while the keywords corresponding to the "disease treatment" intent may include: "disease" and "treatment".

[0083] In an embodiment of the present invention, optionally, the above-mentioned determination of the target search intent corresponding to the search request specifically includes: matching the vocabulary included in the search request with the keywords corresponding to the search intent to obtain the target search intent corresponding to the search request.

[0084] In the embodiment of the present invention, the search request may include: words that match at least part of the keywords corresponding to the search intent.

[0085] For example, when the target search intent corresponds to a keyword, the search request may include words that match the keyword.

[0086] For another example, if the target search intent corresponds to at least two keywords, the search request may include vocabulary that matches the at least two keywords. For example, if search request A is "How to treat epilepsy?", then embodiments of the present invention may determine that the target search intent corresponding to search request A is "disease treatment." "Epilepsy" in search request A matches the keyword "disease" corresponding to the target search intent "disease treatment," and "treatment" in search request A matches the keyword "treatment" corresponding to the target search intent "disease treatment."

[0087] According to one embodiment, the search request can be segmented, and the segmented words can be matched with keywords corresponding to the search intent. According to another embodiment, the search request can be subjected to NER, and the recognized entity words can be matched with keywords corresponding to the search intent. It will be understood that the embodiments of the present invention do not limit the specific method for determining the words included in the search request.

[0088] In step 203, a method for determining multiple dimensional labels corresponding to the search intent may include:

[0089] Determination method B1: clustering resources corresponding to the search intent to obtain multiple dimensional labels corresponding to the search intent; and / or

[0090] Determination method B2: preset multiple dimensional labels corresponding to the search intent.

[0091] Resource types may include webpage data or literature data. It is understood that the embodiments of the present invention do not limit the specific types of resources. For example, resources corresponding to the medical field may include at least one of literature data, medical encyclopedia data, medical question-and-answer data, case data, and popular science data.

[0092] The resources corresponding to the search intent may include: resources that match the search intent, or resources within the field to which the search intent belongs, etc.

[0093] For example, an embodiment of the present invention can determine multiple dimensional tags corresponding to the search intent "disease treatment" based on resources for multiple diseases: "Overview of treatment methods", "Drug treatment", "Surgical treatment", "First aid treatment", "Traditional Chinese medicine treatment", or "Diet therapy", etc. Among them, the "Overview of treatment methods" can guide users to choose or use treatment methods. For example, the resource content of the "Overview of treatment methods" corresponding to the disease "epilepsy" may include: "For the treatment of epilepsy, the better method at present is drug treatment. First, it is necessary to determine whether drug treatment is needed. For patients with the first attack, medication is usually not needed before the cause is found out. Medication is started after the second attack. Second, choose the right medication. You can choose the medication according to the type of attack, the severity of the side effects, the source of the medication, the price, the patient's age, gender and economic situation, and avoid the use of a single drug. And pay attention to the usage of the medication, and adopt individualized treatment..."

[0094] Referring to Table 1, a schematic diagram of multiple dimensional labels corresponding to a search intent in an embodiment of the present invention is shown.

[0095] Table 1

[0096]

[0097] The embodiment of the present invention can save resources in a resource library. In order to improve the quality of resources, resources can be screened according to the resource characteristics corresponding to the resources, and the screened resources can be saved in the resource library.

[0098] Optionally, the resource characteristics may include at least one of the following characteristics:

[0099] Resource characteristics 1. The relevance between the title and text included in the resource;

[0100] Resource characteristics 2. Information about the source of the resource;

[0101] Resource feature 3: the content length of the resource;

[0102] Resource characteristics 4. Structural information of resources;

[0103] Resource characteristics 5. Content attributes of resources;

[0104] Resource characteristics 6. The page quality of the resource;

[0105] Resource feature 7, user attention information corresponding to the resource; and

[0106] Resource feature 8. Information on the recipients of medical resources.

[0107] For resource feature 1, the higher the correlation between the title and the text included in the resource, the higher the quality of the resource, so that resources with irrelevant titles and texts can be filtered out.

[0108] In an optional embodiment of the present invention, when the correlation between the title and the text is low, the title may be discarded and the text may be retained, and the text may be applied to the resource clustering process to improve the accuracy of clustering.

[0109] For resource feature 2, the source information of the resource may include: the website corresponding to the resource, etc. The source information of the resource can be determined based on the authority or popularity of the website. Generally, the higher the authority or popularity of the website, the higher the quality of the resource.

[0110] Regarding resource feature 3, generally, the longer the content length of a resource, the greater the likelihood that the resource contains valid information, and thus the higher the resource quality. Optionally, resources whose content length falls within a preset length range may be retained. The preset length range may include, for example, 100 to 350 characters. It will be understood that the embodiments of the present invention do not impose any restrictions on the specific preset length range.

[0111] Regarding resource feature 4, the resource's structural information can represent the logic of the resource's content. Generally, the higher the logic of the resource's content, the higher the resource's quality. This resource's structural information can include sequential structure, cause-and-effect structure, general-specific structure, specific-general structure, etc.

[0112] Regarding resource feature 5, content attributes may include text attributes or non-text attributes, etc., wherein non-text attributes may include pictures, audio or video, etc. Generally, text attributes have a higher priority than non-text attributes.

[0113] Resource feature 6 can be used to characterize page quality based on the page's presentation style. This presentation style can include logical information and / or visual information. Generally, the clearer the page's logic and / or the more aesthetically pleasing its visuals, the higher its quality.

[0114] Regarding resource feature 7, the user attention information corresponding to the resource can represent the user's attention to the resource. Generally, the higher the attention level, the higher the quality of the resource. The user attention information can be determined based on the browsing behavior data corresponding to the resource or the click behavior data of the search results.

[0115] For resource feature 8, the provider information corresponding to the medical resource can represent the corresponding provider of the medical resource, or the institution where the provider belongs. Generally, the higher the authority of the provider or the institution where the provider belongs, the higher the quality of the medical resource. Providers can include doctors or medical researchers, etc.

[0116] It is understood that those skilled in the art may adopt any one or a combination of resource features 1 to 8 based on actual application requirements. When multiple resource features are adopted, the multiple resource features may be fused to determine whether the fused resource features meet the quality requirements; alternatively, the multiple resource features may be input into a machine learning model, which may determine whether the quality of the resource meets the quality requirements.

[0117] The embodiment of the present invention may provide the following determination method for determining multiple target dimension tags corresponding to the search request:

[0118] Determination method C1: determining multiple target dimension tags that match the entity words included in the search request from the multiple dimension tags corresponding to the target search intent; and / or

[0119] Determination method C2: Based on the appearance information of the resources corresponding to the dimension tags in the resource library, multiple target dimension tags are determined from the multiple dimension tags corresponding to the target search intention.

[0120] Determination method C1 can match the entity words included in the search request with the dimension labels corresponding to the target search intent, and use the successfully matched dimension labels as the target dimension labels.

[0121] For the same target search intent, different medical entity terms can correspond to different dimension labels. For example, if search request A is "How to treat epilepsy?", which includes the medical entity term "epilepsy," and the target search intent is "disease treatment," the multiple dimension labels for "disease treatment" that match "epilepsy" may include: "Treatment Overview," "Drug Treatment," "Surgical Treatment," "Emergency Treatment," and so on.

[0122] For example, the search request B is "How to treat rhinitis", which includes the medical entity word "rhinitis", and the target search intent is "disease treatment". Among the multiple dimension tags of "disease treatment", the dimension tags that match "rhinitis" may include: "Overview of treatment methods", "Drug treatment", "Traditional Chinese medicine treatment", "Other treatments (massage)", etc.

[0123] For determination method C2, the occurrence information of the resource corresponding to the dimension tag in the resource library may include: the number of occurrences or the frequency of occurrence. Optionally, a preset number of target dimension tags may be selected from the multiple dimension tags corresponding to the target search intent in descending order of the number of occurrences or the frequency of occurrence.

[0124] It is understandable that those skilled in the art may adopt any one or a combination of determination methods C1 to C2 according to actual application requirements. For example, when determination methods C1 and C2 are adopted, multiple candidate dimension tags that match the entity words included in the search request may be first determined, and multiple target dimension tags may be determined from the multiple candidate dimension tags based on the occurrence information of the resources corresponding to the dimension tags in the resource library.

[0125] It should be noted that the target dimension label can match some or all of the entity words included in the search request.

[0126] For example, the search request C "What medicine is good for epilepsy" includes the entity words "epilepsy" and "medicine", then the target dimension label "drug treatment" corresponding to the search request C can match all entity words, or the target dimension label "treatment method overview", "surgical treatment", and "emergency treatment" corresponding to the search request C can match some entity words.

[0127] In step 204, corresponding search result data can be obtained for each of the multiple target dimension tags. In this way, corresponding search result data can be provided based on the target dimension tag, thereby improving the precision of the search result data.

[0128] Optionally, the above-mentioned determination of the search result data corresponding to the multiple target dimension tags may specifically include: searching in the resource library based on the search request and the multiple target dimension tags to obtain the resources corresponding to the multiple target dimension tags as search result data.

[0129] Optionally, the resources in the resource library described above correspond to resource tags, and the above-mentioned retrieval in the resource library may specifically include: matching the search request and the multiple target dimension tags with the resource tags corresponding to the resources in the resource library respectively.

[0130] In the embodiment of the present invention, optionally, resource tags may be added to the resources in the resource library in a manual manner or a natural language processing manner.

[0131] The natural language processing method of the embodiment of the present invention may include: a syntactic analysis method, a deep learning method, TF-IDF (term frequency, inverse document frequency), etc.

[0132] Deep learning methods can use language models to perform semantic understanding of resources and use the semantic understanding results as resource labels.

[0133] The key concept behind TF-IDF is that if a word or phrase appears frequently in a document or text, but rarely in other documents or text, it is considered to have good class distinction capabilities and is therefore suitable for classification. In this embodiment of the present invention, words or phrases with good class distinction capabilities can be used as resource tags.

[0134] Optionally, in order to improve the accuracy of the search result data, the search result data may be matched with both the search request and the target dimension label.

[0135] Optionally, the resource title matches both the search request and the target dimension label, and the relevance between the resource title and the body text meets a preset high relevance condition. This can improve the relevance of the resource to the search request and the target dimension label.

[0136] For example, if search request A is "How to treat epilepsy," the target dimension labels corresponding to the query might include: "Overview of Treatment Methods," "Drug Therapy," "Surgical Treatment," and "Emergency Treatment." Resource A for "Drug Therapy" might have a title like "What Medications Treat Epilepsy?", resource B for "Emergency Treatment" might have a title like "What to Do During an Epilepsy Seizure?", and resource C for "Surgical Treatment" might have a title like "What Are the Methods of Surgical Treatment for Epilepsy?" The titles of these resources A, B, and C are closely related to the search request and their corresponding target dimension labels.

[0137] In an embodiment of the present invention, search result data corresponding to multiple target dimension tags can be output. For example, the server can send search result data corresponding to multiple target dimension tags to the client; or the client can display the search result data corresponding to the multiple target dimension tags on the search result page, etc.

[0138] Optionally, the above-mentioned display of the search result data corresponding to the multiple target dimension labels separately may specifically include: using a tab page (Tab) in the search results page to display the search result data corresponding to the multiple target dimension labels separately; the label of the tab page may include: the target dimension label.

[0139] Different target dimension labels can correspond to different tab pages. For example, if multiple target dimension labels include "treatment overview", "drug treatment", "surgical treatment", and "emergency treatment", the search results page may include: 4 tab pages, and the labels of the 4 tab pages are: "treatment overview", "drug treatment", "surgical treatment", "emergency treatment", etc.

[0140] At a certain moment, one of the multiple tags is in a selected state, and the selected tag can be switched according to a triggering operation of the user.

[0141] Optionally, the method may further include: in response to a user triggering an operation on any tag, displaying search result data for the target dimension tag corresponding to the tag. Taking search request A as an example, assuming that initially the selected tag is "Treatment Method Overview", the user may switch the selected tag to another tag based on actual application needs.

[0142] It can be understood that in addition to the search result data corresponding to multiple target dimension tags, the search result data corresponding to the search request can also include: search result data retrieved according to the search request, which can be retrieved in the search database based on the search request to obtain the search result data corresponding to the search request.

[0143] In summary, the search method of the embodiment of the present invention, when receiving a search request, will determine the target search intent and multiple target dimension tags corresponding to the search request, and determine the search result data corresponding to the multiple target dimension tags based on the search request and the multiple target dimension tags. Since multiple target dimension tags can describe the target search intent corresponding to the search request from multiple dimensions, multiple target dimension tags can refine the target search intent; on this basis, the embodiment of the present invention provides corresponding search result data based on the target dimension tag, thereby improving the refinement of the search result data.

[0144] When the search result data corresponding to the target dimension tag is provided, the user can filter and view the search result data based on the target dimension tag. For example, if user A is interested in a target dimension tag, he can view the search result data corresponding to the target dimension tag; for another example, if user B is interested in multiple target dimension tags, he can view the search result data corresponding to multiple target dimension tags respectively. Since the embodiment of the present invention allows users to filter and view search result data based on target dimension tags, it can improve the efficiency of users in obtaining medical information from search result data and save network resources consumed in the process of obtaining information.

[0145] Method Example 2

[0146] Reference Figure 3 , shows a flowchart of the steps of embodiment 2 of a search method of the present invention, which may specifically include the following steps:

[0147] Step 301: Receive a user's search request;

[0148] Step 302: Determine the target search intent corresponding to the search request;

[0149] Step 303: Determine multiple target dimension tags corresponding to the search request based on the multiple dimension tags corresponding to the target search intent;

[0150] Step 304: Determine search result data corresponding to each of the plurality of target dimension tags based on the search request and the plurality of target dimension tags.

[0151] Relative to Figure 2 The method of embodiment 1 shown in the figure may further include:

[0152] Step 305: On the search results page, the search result data corresponding to the above-mentioned multiple target dimension tags are displayed separately, and the knowledge structure corresponding to the above-mentioned search request is displayed.

[0153] In the embodiment of the present invention, corresponding search result data is provided in units of target dimension tags in the search result page, thereby improving the precision of the search result data.

[0154] In addition, the knowledge structure corresponding to the above search request is displayed in the search results page; it can help users expand the popular science knowledge related to the search request, and further help users understand the relevant information more comprehensively and accurately.

[0155] In the embodiment of the present invention, a knowledge base may be used to store the knowledge structure corresponding to the field to which the search request belongs.

[0156] A knowledge base is a structured, easy-to-use, and comprehensive knowledge cluster in knowledge engineering. It is a collection of interconnected pieces of knowledge stored, organized, managed, and used in computer memory using one or more knowledge representation methods to solve problems in a specific (or specific) field. These pieces of knowledge include domain-related theoretical knowledge, factual data, heuristic knowledge derived from expert experience, such as definitions, theorems, and algorithms within a field, and common sense knowledge.

[0157] The knowledge base can comprise a knowledge graph. The knowledge graph is a knowledge base called a semantic network, that is, a knowledge base with a directed graph structure. Among them, the nodes of the graph represent entities or concepts, and the edges of the graph represent various semantic relationships between entities / concepts, and different nodes in the graph are connected through semantic relationships.

[0158] Taking the medical field as an example, the embodiment of the application can establish a medical content label system with clear hierarchy and clear structure, which can include a multi-level label.

[0159] For example, the first-level label corresponding to a disease can include: overview, cause, treatment, department, diagnosis, diet, etc. The second-level label corresponding to the first-level label "treatment" can include: surgical treatment, drug treatment, diet therapy, folk remedy, etc.

[0160] For another example, the first-level label corresponding to a symptom can include: population characteristics, disease site characteristics, symptom frequency characteristics, symptom duration characteristics, symptom subtype characteristics, symptom level characteristics, and accompanying symptom characteristics.

[0161] Among them, the population characteristics can represent the characteristics possessed by the population corresponding to the patient; the disease site characteristics can represent the human body part corresponding to the symptom; the symptom frequency characteristics can represent the frequency of the occurrence of the symptom; the symptom duration characteristics can represent the time when the patient appears the symptom; the symptom subtype characteristics can represent the subdivision of the symptom; the symptom level characteristics can represent the severity of the disease and / or the difficulty of treatment. The accompanying symptom characteristics can represent other symptoms that appear at the same time as a symptom.

[0162] The first-level label corresponding to a symptom can also correspond to a second-level label. Referring to Table 2, a first-level label and a second-level label corresponding to a symptom according to an embodiment of the application are shown.

[0163] Table 2

[0164]

[0165]

[0166] In the embodiment of the application, optionally, the medical content label system can be determined according to historical search requests in the medical field and medical corpus. Specifically, medical entity words can be extracted from the medical corpus, and the relationship between the medical entity words and the hierarchy corresponding to the medical entity words can be determined according to the historical search requests.

[0167] In summary, the search method of the embodiment of the present invention provides corresponding search result data in units of target dimension labels in the search result page, thereby improving the precision of the search result data.

[0168] In addition, the knowledge structure corresponding to the above search request is displayed in the search results page; it can help users expand the popular science knowledge related to the search request, and further help users understand the relevant information more comprehensively and accurately.

[0169] Method Example 3

[0170] Reference Figure 4 , shows a flowchart of the steps of embodiment 3 of a search method of the present invention, which may specifically include the following steps:

[0171] Step 401: Receive a user's search request;

[0172] Step 402: Determine search result data corresponding to the search request; the search result data may include: search result data corresponding to a plurality of target dimension tags; the plurality of target dimension tags correspond to the search request and the target search intent corresponding to the search request;

[0173] Step 403: On the search results page, the search result data corresponding to the above-mentioned multiple target dimension tags are displayed separately.

[0174] Figure 4 At least one step of the illustrated embodiment can be executed by the client, which can receive the user's search request, determine the search result data corresponding to the above search request, and display the search result data corresponding to multiple target dimension tags separately on the search result page.

[0175] According to one embodiment, the client can use Figure 2 The method embodiment shown determines the search result data corresponding to the search request. According to another embodiment, the client can send a search request to the server and receive the search result data corresponding to the search request returned by the server.

[0176] In an embodiment of the present invention, in the search results page, the search result data corresponding to the above-mentioned multiple target dimension tags are displayed separately, which can help users filter and view the search result data according to the target dimension tags.

[0177] In one embodiment of the present invention, multiple display areas corresponding to multiple target dimension tags can be set in the search results page, and search result data corresponding to the multiple target dimension tags can be displayed in the multiple display areas.

[0178] In another embodiment of the present invention, the aforementioned displaying of the search result data corresponding to the plurality of target dimension tags separately includes: displaying the search result data corresponding to the plurality of target dimension tags separately in the form of tabs on the search result page; the tabs on the tabs may include a target dimension tag. The plurality of target dimension tags may share a display area, but multiple tags corresponding to the plurality of target dimension tags are provided in the display area to switch the search result data based on the tags.

[0179] In summary, the search method of the embodiment of the present invention provides corresponding search result data in units of target dimension labels in the search result page, thereby improving the precision of the search result data.

[0180] When the search result data corresponding to the target dimension tag is provided, the user can filter and view the search result data based on the target dimension tag. For example, if user A is interested in a target dimension tag, he can view the search result data corresponding to the target dimension tag; for another example, if user B is interested in multiple target dimension tags, he can view the search result data corresponding to multiple target dimension tags respectively. Since the embodiment of the present invention allows users to filter and view search result data based on target dimension tags, it can improve the efficiency of users in obtaining medical information from search result data and save network resources consumed in the process of obtaining information.

[0181] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, 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 this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0182] Device embodiment

[0183] Reference Figure 5 , shows a structural block diagram of an embodiment of a search device of the present invention, which may specifically include: a receiving module 501, a search intention determination module 502, a dimension label determination module 503 and a search result determination module 504.

[0184] The receiving module 501 is used to receive a user's search request;

[0185] A search intent determination module 502 is configured to determine a target search intent corresponding to the search request;

[0186] A dimension tag determination module 503 is configured to determine a plurality of target dimension tags corresponding to the search request based on the plurality of dimension tags corresponding to the target search intent; and

[0187] The search result determination module 504 is used to determine the search result data corresponding to the multiple target dimension tags respectively based on the search request and the multiple target dimension tags.

[0188] Optionally, the search intent determination module 502 may include:

[0189] The first matching module is used to match the vocabulary that may be included in the search request with the keywords corresponding to the search intent to obtain the target search intent corresponding to the search request.

[0190] Optionally, the target search intent corresponds to at least two keywords, and the search request may include: words that match the at least two keywords respectively.

[0191] Optionally, the device may further include:

[0192] A first clustering module, configured to cluster historical search requests to obtain at least one search intent; and / or

[0193] An adding module is used to add tags to historical search requests and determine at least one search intent based on the tags.

[0194] Optionally, the device may further include:

[0195] A second clustering module is used to cluster resources corresponding to the search intent to obtain multiple dimensional labels corresponding to the search intent; and / or

[0196] The preset module is used to preset multiple dimension labels corresponding to search intent.

[0197] Optionally, the dimension label determination module 503 may include:

[0198] A first dimension label determination module is configured to determine, from the multiple dimension labels corresponding to the target search intent, multiple target dimension labels that match the entity words that may be included in the search request; and / or

[0199] The second dimension tag determination module is used to determine multiple target dimension tags from multiple dimension tags corresponding to the target search intention based on the appearance information of the resources corresponding to the dimension tags in the resource library.

[0200] Optionally, the search result determination module 504 may include:

[0201] The retrieval module is used to search in the resource library based on the search request and the multiple target dimension tags to obtain resources corresponding to the multiple target dimension tags as search result data.

[0202] Optionally, the retrieval module may include:

[0203] The second matching module is used to match the search request and the multiple target dimension tags with resource tags corresponding to the resources in the resource library.

[0204] Optionally, the device may further include:

[0205] Filter resources based on their corresponding resource characteristics and save the filtered resources to the resource library;

[0206] The resource characteristics may include at least one of the following characteristics:

[0207] The relevance between the title and the text included in the resource;

[0208] Information about the source of the resource;

[0209] The content length of the resource;

[0210] Structural information of resources;

[0211] Content attributes of the resource;

[0212] The quality of the resource's pages;

[0213] User attention information corresponding to the resource; and

[0214] Information about the recipients of medical resources.

[0215] Optionally, the device may further include:

[0216] The first display module is used to display the search result data corresponding to the multiple target dimension tags respectively in the search result page.

[0217] Optionally, the first display module may include:

[0218] The tab page display module is used to display the search result data corresponding to the multiple target dimension tags in the form of tab pages in the search result page; the tags of the tab pages may include: the target dimension tags.

[0219] Optionally, the device may further include:

[0220] The second display module is used to display the knowledge structure corresponding to the search request in the search result page.

[0221] Reference Figure 6 , shows a structural block diagram of an embodiment of a search device of the present invention, which may specifically include: a receiving module 601, a search result determination module 602 and a display module 603.

[0222] The receiving module 601 is used to receive a user's search request;

[0223] Search result determination module 602, configured to determine search result data corresponding to the search request; the search result data comprising: search result data corresponding to a plurality of target dimension tags; the plurality of target dimension tags corresponding to the search request and the target search intent corresponding to the search request;

[0224] The display module 603 is used to display the search result data corresponding to the multiple target dimension tags respectively in the search result page.

[0225] Optionally, the display module 603 may include:

[0226] The tab page display module is used to display the search result data corresponding to the multiple target dimension tags in the form of tab pages in the search result page; the tags of the tab pages include: the target dimension tags.

[0227] 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.

[0228] 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.

[0229] Regarding the apparatus 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.

[0230] An embodiment of the present invention provides a device for searching, comprising 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, wherein the one or more programs include instructions for performing the following operations: receiving a user's search request; determining a target search intent corresponding to the search request; determining a plurality of target dimension tags corresponding to the search request based on a plurality of dimension tags corresponding to the target search intent; and determining search result data corresponding to the plurality of target dimension tags respectively based on the search request and the plurality of target dimension tags.

[0231] Figure 7 FIG1 is a block diagram of an apparatus 1100 for searching according to an exemplary embodiment. For example, the apparatus 1100 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.

[0232] Reference Figure 7 , device 1100 may include one or more of the following components: a processing component 1102 , a memory 1104 , a power component 1106 , a multimedia component 1108 , an audio component 1110 , an input / output (I / O) interface 1112 , a sensor component 1114 , and a communication component 1116 .

[0233] The processing component 1102 generally controls the overall operation of the device 1100, such as operations associated with display, phone calls, data communications, camera operation, and recording operations. The processing component 1102 may include one or more processors 1120 to execute instructions to perform all or part of the steps of the above-described method. In addition, the processing component 1102 may include one or more modules to facilitate interaction between the processing component 1102 and other components. For example, the processing component 1102 may include a multimedia module to facilitate interaction between the multimedia component 1108 and the processing component 1102.

[0234] The memory 1104 is configured to store various types of data to support the operation of the device 1100. Examples of such data include instructions for any application or method operating on the device 1100, contact data, phone book data, messages, pictures, videos, etc. The memory 1104 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.

[0235] The power supply component 1106 provides power to the various components of the device 1100. The power supply component 1106 may include a power management system, one or more power supplies, and other components associated with generating, managing, and distributing power to the device 1100.

[0236] The multimedia component 1108 includes a screen that provides an output interface between the device 1100 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 touches, slides, and gestures on the touch panel. The touch sensor can 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 1108 includes a front camera and / or a rear camera. When the device 1100 is in an operating mode, such as a shooting mode or a video mode, the front camera and / or the rear camera can receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have a focal length and optical zoom capability.

[0237] The audio component 1110 is configured to output and / or input audio signals. For example, the audio component 1110 includes a microphone (MIC) that is configured to receive external audio signals when the device 1100 is in an operating mode, such as a call mode, a recording mode, and a voice data processing mode. The received audio signal can be further stored in the memory 1104 or transmitted via the communication component 1116. In some embodiments, the audio component 1110 also includes a speaker for outputting audio signals.

[0238] I / O interface 1112 provides an interface between processing component 1102 and peripheral interface modules, such as a keyboard, click wheel, buttons, etc. These buttons may include but are not limited to: a home button, volume buttons, a start button, and a lock button.

[0239] Sensor assembly 1114 includes one or more sensors for providing various aspects of the status assessment of device 1100. For example, sensor assembly 1114 can detect the open / closed state of device 1100, the relative positioning of components, such as the display and keypad of device 1100. Sensor assembly 1114 can also detect changes in the position of device 1100 or a component of device 1100, the presence or absence of user contact with device 1100, the orientation or acceleration / deceleration of device 1100, and changes in the temperature of device 1100. Sensor assembly 1114 can include a proximity sensor configured to detect the presence of nearby objects without any physical contact. Sensor assembly 1114 can also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, sensor assembly 1114 can also include an accelerometer, a gyroscope, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0240] The communication component 1116 is configured to facilitate wired or wireless communication between the device 1100 and other devices. The device 1100 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 1116 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 1116 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 data processing (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology and other technologies.

[0241] In an exemplary embodiment, the apparatus 1100 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-described methods.

[0242] In an exemplary embodiment, a non-transitory computer-readable storage medium including instructions is also provided, such as a memory 1104 including instructions, and the instructions can be executed by the processor 1120 of the apparatus 1100 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.

[0243] Figure 8 1 is a schematic diagram of the structure of a server in some embodiments of the present invention. The server 1900 may vary greatly due to different configurations or performance, and may include one or more central processing units (CPUs) 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 temporary storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), each module may include a series of instruction operations on the server. Furthermore, the central processing unit 1922 can be configured to communicate with the storage medium 1930 to execute a series of instruction operations in the storage medium 1930 on the server 1900.

[0244] 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 Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0245] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by the processor of a device (server or terminal), enables the device to perform Figure 2 or Figure 3 or Figure 4 or Figure 5 The search method shown.

[0246] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by the processor of a device (server or terminal), enables the device to perform a search method, the method comprising: receiving a user's search request; determining a target search intent corresponding to the search request; determining a plurality of target dimension tags corresponding to the search request based on a plurality of dimension tags corresponding to the target search intent; and determining search result data corresponding to the plurality of target dimension tags respectively based on the search request and the plurality of target dimension tags.

[0247] The embodiment of the present invention discloses A1, a search method, the method comprising:

[0248] Receive user search requests;

[0249] Determining a target search intent corresponding to the search request;

[0250] Determine a plurality of target dimension tags corresponding to the search request according to the plurality of dimension tags corresponding to the target search intent;

[0251] Based on the search request and the multiple target dimension tags, the search result data corresponding to the multiple target dimension tags are determined.

[0252] A2. The method according to A1, wherein determining the target search intent corresponding to the search request comprises:

[0253] The words included in the search request are matched with keywords corresponding to the search intent to obtain the target search intent corresponding to the search request.

[0254] A3. According to the method described in A1, the target search intent corresponds to at least two keywords, and the search request includes: words that match the at least two keywords respectively.

[0255] A4. The method according to A1, further comprising:

[0256] Clustering historical search requests to obtain at least one search intent; and / or

[0257] Tags are added to historical search requests, and at least one search intent is determined based on the tags.

[0258] A5. The method according to A1, further comprising:

[0259] Clustering resources corresponding to the search intent to obtain multiple dimensional labels corresponding to the search intent; and / or

[0260] Preset multiple dimension labels corresponding to search intent.

[0261] A6. According to the method of A1, determining the multiple target dimension tags corresponding to the search request includes:

[0262] Determining, from the multiple dimension tags corresponding to the target search intent, multiple target dimension tags that match the entity words included in the search request; and / or

[0263] Based on the appearance information of the resources corresponding to the dimension tags in the resource library, multiple target dimension tags are determined from the multiple dimension tags corresponding to the target search intention.

[0264] A7. According to the method described in A1, determining the search result data corresponding to the multiple target dimension tags includes:

[0265] Based on the search request and the multiple target dimension tags, a search is performed in the resource library to obtain resources corresponding to the multiple target dimension tags as search result data.

[0266] A8. According to the method described in A7, resources in the resource library have corresponding resource tags, and searching the resource library includes:

[0267] The search request and the multiple target dimension tags are matched with resource tags corresponding to the resources in the resource library respectively.

[0268] A9. The method according to A7, further comprising:

[0269] Filter resources based on their corresponding resource characteristics and save the filtered resources to the resource library;

[0270] The resource characteristics include at least one of the following characteristics:

[0271] The relevance between the title and the text included in the resource;

[0272] Information about the source of the resource;

[0273] The content length of the resource;

[0274] Structural information of resources;

[0275] Content attributes of the resource;

[0276] The quality of the resource's pages;

[0277] User attention information corresponding to the resource; and

[0278] Information about the recipients of medical resources.

[0279] A10. The method according to any one of A1 to A9, further comprising:

[0280] On the search results page, the search result data corresponding to the multiple target dimension tags are displayed separately.

[0281] A11. According to the method of A10, displaying the search result data corresponding to the multiple target dimension tags separately includes:

[0282] The search result page uses a tab page to display the search result data corresponding to the multiple target dimension tags respectively; the tags of the tab page include: the target dimension tag.

[0283] A12. The method according to A10, further comprising:

[0284] In the search results page, the knowledge structure corresponding to the search request is displayed.

[0285] The embodiment of the present invention discloses B13, a search method, comprising:

[0286] Receive user search requests;

[0287] Determine search result data corresponding to the search request; the search result data includes: search result data corresponding to a plurality of target dimension tags; the plurality of target dimension tags correspond to the search request and the target search intent corresponding to the search request;

[0288] On the search results page, the search result data corresponding to the multiple target dimension tags are displayed separately.

[0289] B14. The method according to B13, wherein the displaying of the search result data corresponding to the multiple target dimension tags includes:

[0290] The search result page uses a tab page to display the search result data corresponding to the multiple target dimension tags respectively; the tags of the tab page include: the target dimension tag.

[0291] The embodiment of the present invention discloses C15, a search device, comprising:

[0292] A receiving module, configured to receive a user's search request;

[0293] A search intent determination module, configured to determine a target search intent corresponding to the search request;

[0294] a dimension tag determination module, configured to determine a plurality of target dimension tags corresponding to the search request based on the plurality of dimension tags corresponding to the target search intent; and

[0295] The search result determination module is used to determine the search result data corresponding to the multiple target dimension tags respectively based on the search request and the multiple target dimension tags.

[0296] C16. The apparatus according to C15, wherein the search intention determination module comprises:

[0297] The first matching module is used to match the vocabulary included in the search request with the keywords corresponding to the search intent to obtain the target search intent corresponding to the search request.

[0298] C17. According to the device described in C15, the target search intent corresponds to at least two keywords, and the search request includes: words that match the at least two keywords respectively.

[0299] C18. The device according to C15, further comprising:

[0300] A first clustering module, configured to cluster historical search requests to obtain at least one search intent; and / or

[0301] An adding module is used to add tags to historical search requests and determine at least one search intent based on the tags.

[0302] C19. The device according to C15, further comprising:

[0303] A second clustering module is used to cluster resources corresponding to the search intent to obtain multiple dimensional labels corresponding to the search intent; and / or

[0304] The preset module is used to preset multiple dimension labels corresponding to search intent.

[0305] C20. The apparatus according to C15, wherein the dimension label determination module comprises:

[0306] A first dimension label determination module is configured to determine, from the multiple dimension labels corresponding to the target search intent, multiple target dimension labels that match the entity words included in the search request; and / or

[0307] The second dimension tag determination module is used to determine multiple target dimension tags from multiple dimension tags corresponding to the target search intention based on the appearance information of the resources corresponding to the dimension tags in the resource library.

[0308] C21. The apparatus according to C15, wherein the search result determination module comprises:

[0309] The retrieval module is used to search in the resource library based on the search request and the multiple target dimension tags to obtain resources corresponding to the multiple target dimension tags as search result data.

[0310] C22. The apparatus according to C21, wherein the retrieval module comprises:

[0311] The second matching module is used to match the search request and the multiple target dimension tags with resource tags corresponding to the resources in the resource library.

[0312] C23. The apparatus according to C21, further comprising:

[0313] Filter resources based on their corresponding resource characteristics and save the filtered resources to the resource library;

[0314] The resource characteristics include at least one of the following characteristics:

[0315] The relevance between the title and the text included in the resource;

[0316] Information about the source of the resource;

[0317] The content length of the resource;

[0318] Structural information of resources;

[0319] Content attributes of the resource;

[0320] The quality of the resource's pages;

[0321] User attention information corresponding to the resource; and

[0322] Information about the recipients of medical resources.

[0323] C24. The device according to any one of C15 to C23, further comprising:

[0324] The first display module is used to display the search result data corresponding to the multiple target dimension tags respectively in the search result page.

[0325] C25. The device according to C24, wherein the first display module comprises:

[0326] The tab page display module is used to display the search result data corresponding to the multiple target dimension tags in the form of tab pages in the search result page; the tags of the tab pages include: the target dimension tags.

[0327] C26. The device according to C24, further comprising:

[0328] The second display module is used to display the knowledge structure corresponding to the search request in the search result page.

[0329] The embodiment of the present invention discloses D27, a search device, comprising:

[0330] A receiving module, configured to receive a user's search request;

[0331] a search result determination module, configured to determine search result data corresponding to the search request; the search result data comprising: search result data corresponding to a plurality of target dimension tags; the plurality of target dimension tags corresponding to the search request and the target search intent corresponding to the search request; and

[0332] The display module is used to display the search result data corresponding to the multiple target dimension tags separately in the search result page.

[0333] D28. The device according to D27, wherein the display module comprises:

[0334] The tab page display module is used to display the search result data corresponding to the multiple target dimension tags in the form of tab pages in the search result page; the tags of the tab pages include: the target dimension tags.

[0335] An embodiment of the present invention discloses E29, 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. The one or more programs include instructions for performing the following operations:

[0336] Receive user search requests;

[0337] Determining a target search intent corresponding to the search request;

[0338] Determine a plurality of target dimension tags corresponding to the search request according to the plurality of dimension tags corresponding to the target search intent;

[0339] Based on the search request and the multiple target dimension tags, the search result data corresponding to the multiple target dimension tags are determined.

[0340] E30. The apparatus according to E29, wherein determining the target search intent corresponding to the search request comprises:

[0341] The words included in the search request are matched with keywords corresponding to the search intent to obtain the target search intent corresponding to the search request.

[0342] E31. According to the device described in E29, the target search intent corresponds to at least two keywords, and the search request includes: words that match the at least two keywords respectively.

[0343] E32. The device according to E29, wherein the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0344] Clustering historical search requests to obtain at least one search intent; and / or

[0345] Tags are added to historical search requests, and at least one search intent is determined based on the tags.

[0346] E33. The device according to E29, wherein the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0347] Clustering resources corresponding to the search intent to obtain multiple dimensional labels corresponding to the search intent; and / or

[0348] Preset multiple dimension labels corresponding to search intent.

[0349] E34. The apparatus according to E29, wherein determining the multiple target dimension tags corresponding to the search request comprises:

[0350] Determining, from the multiple dimension tags corresponding to the target search intent, multiple target dimension tags that match the entity words included in the search request; and / or

[0351] Based on the appearance information of the resources corresponding to the dimension tags in the resource library, multiple target dimension tags are determined from the multiple dimension tags corresponding to the target search intention.

[0352] E35. The apparatus according to E29, wherein determining the search result data corresponding to the plurality of target dimension tags comprises:

[0353] Based on the search request and the multiple target dimension tags, a search is performed in the resource library to obtain resources corresponding to the multiple target dimension tags as search result data.

[0354] E36. The apparatus according to E35, wherein the resources in the resource library correspond to resource tags, and the searching in the resource library comprises:

[0355] The search request and the multiple target dimension tags are matched with resource tags corresponding to the resources in the resource library respectively.

[0356] E37. The device according to E35, wherein the device is further configured to execute, by one or more processors, the one or more programs including instructions for performing the following operations:

[0357] Filter resources based on their corresponding resource characteristics and save the filtered resources to the resource library;

[0358] The resource characteristics include at least one of the following characteristics:

[0359] The relevance between the title and the text included in the resource;

[0360] Information about the source of the resource;

[0361] The content length of the resource;

[0362] Structural information of resources;

[0363] Content attributes of the resource;

[0364] The quality of the resource's pages;

[0365] User attention information corresponding to the resource; and

[0366] Information about the recipients of medical resources.

[0367] E38. The apparatus according to any one of E29 to E37, further comprising:

[0368] On the search results page, the search result data corresponding to the multiple target dimension tags are displayed separately.

[0369] E39. The apparatus according to E38, wherein the displaying of the search result data corresponding to the multiple target dimension tags comprises:

[0370] The search result page uses a tab page to display the search result data corresponding to the multiple target dimension tags respectively; the tags of the tab page include: the target dimension tag.

[0371] E40. The apparatus according to E38, further comprising:

[0372] In the search results page, the knowledge structure corresponding to the search request is displayed.

[0373] An embodiment of the present invention discloses F41, 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. The one or more programs include instructions for performing the following operations:

[0374] Receive user search requests;

[0375] Determine search result data corresponding to the search request; the search result data includes: search result data corresponding to a plurality of target dimension tags; the plurality of target dimension tags correspond to the search request and the target search intent corresponding to the search request;

[0376] On the search results page, the search result data corresponding to the multiple target dimension tags are displayed separately.

[0377] F42. The method according to F41, wherein the displaying of the search result data corresponding to the multiple target dimension tags includes:

[0378] The search result page uses a tab page to display the search result data corresponding to the multiple target dimension tags respectively; the tags of the tab page include: the target dimension tag.

[0379] An embodiment of the present invention discloses G43, a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes a device to perform a search method as described in one or more of A1 to A12.

[0380] An embodiment of the present invention discloses H44, a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes the device to execute the search method described in B13 or B14.

[0381] Other embodiments of the present invention will readily occur to those skilled in the art 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 invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the invention being indicated by the following claims.

[0382] It should be understood that the present invention is not limited to the exact construction 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.

[0383] 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 principles of the present invention should be included in the scope of protection of the present invention.

[0384] 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 herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods 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: Receive user search requests; Determining a target search intent corresponding to the search request; Based on the multiple dimensional labels corresponding to the target search intent, determine the multiple target dimensional labels corresponding to the search request; the target search intent in the medical field includes at least one of the following search intents: symptoms, disease treatment, disease relief, disease symptoms, disease causes, symptom relief, and symptom treatment; from the multiple dimensional labels corresponding to the target search intent, determine the multiple target dimensional labels that match the medical entity words included in the search request; when the target search intent is the same, different medical entity words correspond to different dimensional labels; Determine, based on the search request and the multiple target dimension tags, search result data corresponding to the multiple target dimension tags respectively; match the search request and the multiple target dimension tags with resource tags corresponding to resources in the resource library respectively, to obtain the resources corresponding to the multiple target dimension tags respectively as search result data; The search result page uses a tab page to display the search result data corresponding to the multiple target dimension tags respectively; the tags of the tab page include: the target dimension tag; different target dimension tags correspond to different tab pages; In the search results page, the knowledge structure corresponding to the search request is displayed.

2. The method according to claim 1, characterized in that Determining the target search intent corresponding to the search request includes: The words included in the search request are matched with keywords corresponding to the search intent to obtain the target search intent corresponding to the search request.

3. The method according to claim 1, characterized in that The target search intent corresponds to at least two keywords, and the search request includes: words that match the at least two keywords respectively.

4. The method according to claim 1, wherein The method further comprises: Clustering historical search requests to obtain at least one search intent; and / or Tags are added to historical search requests, and at least one search intent is determined based on the tags.

5. The method according to claim 1, wherein The method further comprises: Clustering resources corresponding to the search intent to obtain multiple dimensional labels corresponding to the search intent; and / or Preset multiple dimension labels corresponding to search intent.

6. The method according to claim 1, characterized in that Determining a plurality of target dimension tags corresponding to the search request includes: Determining, from the multiple dimension tags corresponding to the target search intent, multiple target dimension tags that match the entity words included in the search request; and / or Based on the appearance information of the resources corresponding to the dimension tags in the resource library, multiple target dimension tags are determined from the multiple dimension tags corresponding to the target search intention.

7. The method according to claim 1, characterized in that The method further comprises: Filter resources based on their corresponding resource characteristics and save the filtered resources to the resource library; The resource characteristics include at least one of the following characteristics: The relevance between the title and the text included in the resource; Information about the source of the resource; The content length of the resource; Structural information of resources; Content attributes of the resource; The quality of the resource's pages; User attention information corresponding to the resource; and Information about the recipients of medical resources.

8. A search method, characterized in that: include: Receive user search requests; Determining search result data corresponding to the search request; The search result data includes: search result data corresponding to multiple target dimension tags respectively; the multiple target dimension tags correspond to the search request and the target search intent corresponding to the search request; the target search intent in the medical field includes at least one of the following search intents: symptoms, disease treatment, disease relief, disease symptoms, disease causes, symptom relief, symptom treatment; from the multiple dimension tags corresponding to the target search intent, determine multiple target dimension tags that match the medical entity words included in the search request; when the target search intent is the same, different medical entity words correspond to different dimension tags; On the search results page, the search result data corresponding to the multiple target dimension tags are displayed respectively; the search request and the multiple target dimension tags are matched with the resource tags corresponding to the resources in the resource library respectively, so as to obtain the resources corresponding to the multiple target dimension tags respectively as the search result data; The search result page uses a tab page to display the search result data corresponding to the multiple target dimension tags respectively; the tags of the tab page include: the target dimension tag; different target dimension tags correspond to different tab pages; In the search results page, the knowledge structure corresponding to the search request is displayed.

9. A search device, characterized in that: include: A receiving module, configured to receive a user's search request; A search intent determination module, configured to determine a target search intent corresponding to the search request; a dimension label determination module for determining a plurality of target dimension labels corresponding to the search request based on the plurality of dimension labels corresponding to the target search intent; the target search intent in the medical field includes at least one of the following search intents: symptoms, disease treatment, disease relief, disease symptoms, disease causes, symptom relief, and symptom treatment; determining a plurality of target dimension labels that match the medical entity words included in the search request from the plurality of dimension labels corresponding to the target search intent; when the target search intent is the same, different medical entity words correspond to different dimension labels; and A search result determination module, configured to determine search result data corresponding to each of the plurality of target dimension tags based on the search request and the plurality of target dimension tags; Matching the search request and the multiple target dimension tags with resource tags corresponding to resources in the resource library, respectively, to obtain resources corresponding to the multiple target dimension tags as search result data; A first display module is configured to display the search result data corresponding to the multiple target dimension tags in the form of tab pages on the search result page; The labels of the tab page include: the target dimension label; different target dimension labels correspond to different tab pages; The second display module is used to display the knowledge structure corresponding to the search request in the search result page.

10. The device according to claim 9, characterized in that The search intention determination module includes: The first matching module is used to match the vocabulary included in the search request with the keywords corresponding to the search intent to obtain the target search intent corresponding to the search request.

11. The device according to claim 9, characterized in that The target search intent corresponds to at least two keywords, and the search request includes: words that match the at least two keywords respectively.

12. The device according to claim 9, characterized in that The device further comprises: A first clustering module, configured to cluster historical search requests to obtain at least one search intent; and / or An adding module is used to add tags to historical search requests and determine at least one search intent based on the tags.

13. The device according to claim 9, characterized in that The device further comprises: A second clustering module is used to cluster resources corresponding to the search intent to obtain multiple dimensional labels corresponding to the search intent; and / or The preset module is used to preset multiple dimension labels corresponding to search intent.

14. The device according to claim 9, characterized in that The dimension label determination module includes: A first dimension label determination module is configured to determine, from the multiple dimension labels corresponding to the target search intent, multiple target dimension labels that match the entity words included in the search request; and / or The second dimension tag determination module is used to determine multiple target dimension tags from multiple dimension tags corresponding to the target search intention based on the appearance information of the resources corresponding to the dimension tags in the resource library.

15. The device according to claim 9, characterized in that The device further comprises: Filter resources based on their corresponding resource characteristics and save the filtered resources to the resource library; The resource characteristics include at least one of the following characteristics: The relevance between the title and the text included in the resource; Information about the source of the resource; The content length of the resource; Structural information of resources; Content attributes of the resource; The quality of the resource's pages; User attention information corresponding to the resource; and Information about the recipients of medical resources.

16. A search device, characterized in that: include: A receiving module, configured to receive a user's search request; A search result determination module, configured to determine search result data corresponding to the search request; The search result data includes: search result data corresponding to multiple target dimension tags respectively; the multiple target dimension tags correspond to the search request and the target search intent corresponding to the search request; the target search intent in the medical field includes at least one of the following search intents: symptoms, disease treatment, disease relief, disease symptoms, disease causes, symptom relief, and symptom treatment; from the multiple dimension tags corresponding to the target search intent, multiple target dimension tags that match the medical entity words included in the search request are determined; when the target search intent is the same, different medical entity words correspond to different dimension tags; and A display module is used to display the search result data corresponding to the multiple target dimension tags in the search result page; match the search request and the multiple target dimension tags with the resource tags corresponding to the resources in the resource library, so as to obtain the resources corresponding to the multiple target dimension tags as the search result data; The display module includes: A tab page display module is used to display the search result data corresponding to the multiple target dimension tags in the form of tab pages on the search result page; the tags of the tab pages include: the target dimension tags; different target dimension tags correspond to different tab pages; The second display module is used to display the knowledge structure corresponding to the search request in the search result page.

17. A device for searching, characterized in that The device comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and when the programs are executed by one or more processors, the steps of the method according to any one of claims 1 to 7 are implemented.

18. A device for searching, 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 when the programs are executed by one or more processors, the steps of the method according to claim 8 are implemented.

19. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors, cause an apparatus to perform the search method according to one or more of claims 1 to 7.

20. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors, causes a device to perform the search method according to claim 8.

Images