A search method, device and medium

Abstract

The embodiment of the present invention provides a search method, device and medium, wherein the method specifically comprises: receiving a user's search term; when the search term corresponds to at least two search requirements, determining at least two sub-search terms corresponding to the search term; different sub-search terms correspond to different search requirements; determining search result data corresponding to the at least two sub-search terms respectively, and integrating them into a search result item. The embodiment of the present invention can increase the information content of the search results.

Description

Technical Field

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

[0002] With the continuous development of Internet technology, search engines have become an important tool for users to obtain Internet information. When there is a need for information related to medical health, most users will choose to obtain the required information through search engines. Due to the sensitivity and urgency of medical needs, users usually want to quickly find the search results that best fit their own situation, so users usually use long-tail keywords to search. Long-tail keywords are often composed of 2-3 words, or even phrases, such as "What causes allergic rhinitis and how to treat it", "What to eat to increase milk production after childbirth", "Can chronic pharyngitis and rhinitis be cured?", etc.

[0003] The goal of a search engine is usually to maximize the match and relevance between search results and search terms. To achieve this goal, current search engines usually extract core segments with higher importance from long-tail keywords, filter out some of the less important segments, and provide search results corresponding to the core segments.

[0004] The inventors discovered during the implementation of the embodiments of the present invention that the search results corresponding to the core fragments currently provided can only provide single-dimensional medical information, which is difficult to meet the search needs of long-tail users. Summary of the invention

[0005] The embodiments of the present invention provide a search method, device and medium. How to improve the information content of search results is a technical problem that those skilled in the art need to solve.

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

[0007] Receive the user's search term;

[0008] In the case where the search term corresponds to at least two search requirements, determining at least two sub-search terms corresponding to the search term; different sub-search terms correspond to different search requirements;

[0009] The search result data corresponding to the at least two sub-search terms are determined and integrated into a search result item.

[0010] On the other hand, an embodiment of the present invention discloses a search device, including:

[0011] A receiving module, used for receiving a user's search term;

[0012] a sub-search term determination module, configured to determine at least two sub-search terms corresponding to the search term when the search term corresponds to at least two search requirements; different sub-search terms correspond to different search requirements; and

[0013] The search result processing module is used to determine the search result data corresponding to the at least two sub-search terms respectively, and integrate them into a search result item.

[0014] On the other hand, an embodiment of the present invention discloses a device for searching, comprising a memory and one or more programs, wherein the one or more programs are stored in the memory, and when the programs are executed by one or more processors, the steps of the aforementioned method are implemented.

[0015] On the other hand, an embodiment of the present invention discloses a machine-readable medium having instructions stored thereon, which, when executed by one or more processors, enables the device to perform one or more of the search methods described above.

[0016] The embodiments of the present invention include the following advantages:

[0017] In the case where a search term corresponds to at least two search requirements, the embodiment of the present invention determines at least two sub-search terms corresponding to the search term, and determines search result data corresponding to the at least two sub-search terms. Since different sub-search terms can correspond to different search requirements, the sub-search terms can reflect the dimensions of the search requirements, and at least two sub-search terms can reflect the search requirements of at least two dimensions. Therefore, the embodiment of the present invention can realize multi-dimensional search requirements, and thus can increase the information content of the search results.

[0018] Furthermore, the embodiment of the present invention integrates the search result data corresponding to at least two sub-search terms into one search result item, which can increase the amount of information contained in one search result item. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments of the present invention will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative labor.

[0020] Figure 1 is a flowchart of the steps of a search method embodiment 1 of the present invention;

[0021] Figure 2 is an example of a search result card in an embodiment of the present invention;

[0022] Figure 3is a flowchart of the steps of Embodiment 2 of a search method of the present invention;

[0023] Figure 4 is a structural block diagram of an embodiment of a search device of the present invention;

[0024] Figure 5 is a block diagram of an apparatus 1100 for searching according to the present invention; and

[0025] Figure 6 It is a schematic diagram of the structure of the server in some embodiments of the present invention. DETAILED DESCRIPTION

[0026] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0027] In response to the technical problem of how to increase the amount of information in search results, an embodiment of the present invention provides a search solution, which may include: receiving a user's search term; when the search term corresponds to at least two search requirements, determining at least two sub-search terms corresponding to the search term; different sub-search terms may correspond to different search requirements; determining search result data corresponding to the at least two sub-search terms respectively, and integrating them into one search result item.

[0028] The embodiment of the present invention identifies the situation where a search term corresponds to at least two search requirements, and when the search term corresponds to at least two search requirements, determines at least two sub-search terms corresponding to the search term, and determines the search result data corresponding to the at least two sub-search terms. Since different sub-search terms can correspond to different search requirements, the sub-search terms can reflect the dimensions of the search requirements, and at least two sub-search terms can reflect the search requirements of at least two dimensions. Therefore, the embodiment of the present invention can realize multi-dimensional search requirements, and thus can increase the amount of information in the search results.

[0029] While increasing the amount of information in search results, the embodiments of the present invention can provide feedback of multi-dimensional information for a single search; thus, the user's secondary search operations can be saved to a certain extent, thereby improving search efficiency.

[0030] For example, search term A is "what to eat to increase milk production when not enough milk is produced after childbirth", an embodiment of the present invention can identify that search term A corresponds to at least two search requirements, determine at least two sub-search terms corresponding to search term A: sub-search term A1 "what to do if not enough milk is produced after childbirth" and sub-search term A2 "what to eat to increase milk production", and determine the search result data corresponding to sub-search term A1 and sub-search term A2 respectively, thereby increasing the amount of information in the search results.

[0031] For another example, the search term B is "Can chronic pharyngitis and rhinitis be cured?" The embodiment of the present invention can identify that the search term B corresponds to at least two search requirements, determine at least two sub-search terms corresponding to the search term B: sub-search term B1 "Can chronic pharyngitis be cured?" and sub-search term B2 "Can chronic rhinitis be cured?", and determine the search result data corresponding to the sub-search term B1 and the sub-search term B2 respectively, thereby increasing the amount of information in the search results.

[0032] 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.

[0033] The search method provided by the embodiment of the present invention can be applied to an application environment corresponding to a client and a server. The client and the server are located in a wired or wireless network, and the client and the server interact with each other through the wired or wireless network.

[0034] Optionally, the client can run on a terminal, and the above-mentioned terminal 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.

[0035] Method Example 1

[0036] Reference Figure 1 , shows a flowchart of a search method embodiment 1 of the present invention, which may specifically include the following steps:

[0037] Step 101: Receive a user's search term;

[0038] Step 102: when the search term corresponds to at least two search requirements, determine at least two sub-search terms corresponding to the search term; different sub-search terms may correspond to different search requirements;

[0039] Step 103: Determine the search result data corresponding to the at least two sub-search terms, respectively, and integrate them into one search result item.

[0040] Figure 1 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.

[0041] In step 101, the client of the search APP or search website may provide a UI (User Interface) to allow the user to submit a search term 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 term.

[0042] In step 102, it may first be identified whether the search term corresponds to at least two search requirements.

[0043] In a specific implementation, the search requirements corresponding to the search terms may include: explicit requirements or implicit requirements.

[0044] Among them, the explicit requirements can represent the requirements directly included in the search term. The search term can be linguistically analyzed, and the explicit requirements included in the search term can be identified based on the linguistic analysis results. Accordingly, it can be determined that the search term corresponds to at least two search requirements based on the linguistic analysis results corresponding to the search term.

[0045] Optionally, the linguistic analysis may include: grammatical analysis, and determining that the search term corresponds to at least two search requirements based on grammatical components in the grammatical analysis result.

[0046] Grammatical analysis uses the syntax and other knowledge of natural language to determine the functions of the grammatical components contained in the language text. Grammatical components specifically include: at least one of subject, predicate, object, attributive, adverbial and complement. In practical applications, a grammatical parsing tree or machine learning method can be used to determine the grammatical text contained in the search term. The embodiment of the present invention does not limit the specific method for determining the grammatical text contained in the search term.

[0047] In one embodiment, if the search term contains at least two preset grammatical components, it can be determined that the search term corresponds to at least two search requirements. The preset grammatical components can be determined by those skilled in the art according to actual application requirements. For example, the preset grammatical components can be grammatical components such as subject, predicate, object, adverbial, etc.

[0048] In one embodiment of the present invention, the linguistic analysis result specifically includes: vocabulary attributes of the vocabulary, and the vocabulary attributes specifically include: medical entity attributes and / or parts of speech.

[0049] In a specific implementation, the search terms may be segmented to obtain the words contained in the search terms. Entity recognition technology may be used to determine the medical entity attributes of the words in the search terms. Part-of-speech recognition technology may be used to determine the part-of-speech of the words in the search terms. Part-of-speech refers to the basis for dividing word classes based on the characteristics of the words. Parts of speech may include: nouns, verbs, question words, etc.

[0050] For example, the medical entity attributes of the words in the search term can be determined based on the knowledge graph. Specifically, the medical entity attributes of the words in the search term can be obtained by searching in the knowledge graph based on the words in the search term.

[0051] Knowledge graph is a structured semantic knowledge base that describes concepts and their relationships in the physical world. Entities in the medical field can be called medical entities. Medical entities can include: disease entities, symptom entities, etc.

[0052] Disease entities can represent specific diseases, such as "hypertension", "leukemia", etc. Symptom entities can represent specific symptoms, and symptoms can represent the patient's subjective abnormal feelings or certain objective pathological changes caused by a series of abnormal changes in the body's functions, metabolism and morphological structures during the disease process.

[0053] The above-mentioned method of determining the search term corresponding to at least two search requirements based on the vocabulary attributes of the vocabulary in the search term specifically includes:

[0054] Determination method 1: If the above search terms include at least two disease entity terms, then the above search terms correspond to at least two search requirements; and / or

[0055] Determination method 2: if the search term includes at least two question words, then the search term corresponds to at least two search requirements; and / or

[0056] Determination method 3: If the above search terms include: symptom entity terms and their corresponding extended question words, then the above search terms correspond to at least two search requirements.

[0057] For determination method 1, disease entity words usually act as subjects or objects, and the subject is the statement object of the language text, and the object is the affected object of the language text; therefore, a disease entity word in the search term can express an independent search requirement, which is used to search for the statement object corresponding to the subject or the affected object of the language text, so the subject or object can represent the search object. Furthermore, a search term containing at least two disease entity words can correspond to multiple search requirements. The entity words of the embodiment of the present invention may include: entity words or entity phrases.

[0058] For example, the search term C "how to prevent esophageal cancer and laryngeal cancer" includes searches for two disease entity terms ("esophageal cancer" and "laryngeal cancer"). It can be considered that the search term C corresponds to two search requirements.

[0059] Regarding determination method 2, interrogative words are words used to construct interrogative sentences, and interrogative sentences are sentences used to ask questions. Therefore, usually one interrogative word corresponds to a question, and a question usually corresponds to one search requirement. Therefore, a search term including at least two interrogative words can correspond to multiple search requirements.

[0060] For example, the search term D "how is allergic rhinitis caused and how is it treated" includes searches for two questions ("how is it caused" and "how is it treated"). It can be considered that the search term D corresponds to two search requirements.

[0061] For another example, the search term E "What is the normal high pressure? What is the normal low pressure" includes searches for two questions ("What is the normal high pressure" and "What is the normal low pressure"). It can be considered that the search term E corresponds to two search requirements.

[0062] For determination method 3, the extended question word can represent a question independent of the symptom entity word. In this case, it can be considered that the search term corresponds to both: the search demand corresponding to the symptom entity word and: the search demand corresponding to the question to which the extended question word belongs.

[0063] For example, search term A "What to eat to increase milk supply after childbirth" includes both the symptom entity phrase "Insufficient milk supply after childbirth" and the extended question sentence "What to eat to increase milk supply"; among them, "What to eat to increase milk supply" is an extended question sentence under the corresponding condition of the symptom entity phrase, so it can be considered that search term A corresponds to two search requirements.

[0064] It is understood that the above-mentioned determination methods 1 to 3 are only optional embodiments for determining that a search word corresponds to at least two search requirements, and are not to be understood as application limitations of the embodiments of the present invention. It is understood that those skilled in the art can adopt other determination methods for determining that a search word corresponds to at least two search requirements according to actual application requirements.

[0065] For example, another determination method may be: constructing a sentence template corresponding to at least two search requirements, matching the search term with the sentence template, and if the match is successful, it can be considered that the search term corresponds to at least two search requirements.

[0066] Examples of statement templates may include:

[0067] How to prevent <disease entity word 1> and <disease entity word 2>;

[0068] How to prevent <disease entity word 1>, <disease entity word 2> and <disease entity word 3>;

[0069] <Disease entity word 1> and <Disease entity word 2> <Question word>;

[0070] <symptom entity word><question sentence>;

[0071] <disease entity word> how it is caused and how to treat it;

[0072] <Question 1><Question 2>.

[0073] In the case where the search term does not directly contain a demand, the implicit demand can represent: a broad demand or a high-frequency demand related to the search term in the search scenario. For example, in a medical search scenario, if the search term contains medical entity terms but no other information, the implicit demand can include: causes, treatments, and other needs. If the medical entity terms correspond to symptoms, the implicit demand can include: symptom causes, symptom treatments, and other needs.

[0074] The embodiments of the present invention can determine the preset demand words corresponding to the scene entity words based on the analysis of the search logs corresponding to the scene entity words. The scene entity words can represent the entity words in the search scene. The preset demand words can represent the high-frequency demand in the search scene, and the high-frequency demand can be a demand whose usage frequency meets the preset frequency condition. The preset frequency condition can include: the usage frequency is higher than the frequency threshold, or the usage frequency ranks in the top X (X can be a positive integer) places from high to low, etc.

[0075] Optionally, the preset requirement words corresponding to the scene entity words may be determined based on the search words containing the scene entity words and the click information of the search results.

[0076] According to one implementation, the number of clicks on the search results can be counted, and the preset demand words corresponding to the scene entity words can be determined based on the search results with a number of clicks greater than a number threshold. Specifically, the keywords of the search results can be determined based on the title and / or text corresponding to the search results, and then the preset demand words corresponding to the scene entity words can be determined based on the keywords of the search results with a number of clicks greater than a number threshold.

[0077] According to another implementation, a user's multiple consecutive search behaviors may be analyzed. If the user's multiple consecutive search terms all contain the same scene entity term, the preset requirement term corresponding to the scene entity term may be determined based on the search result corresponding to the last search term among the multiple consecutive search terms. Specifically, the preset requirement term corresponding to the scene entity term may be determined based on the keyword of the search result corresponding to the last search term among the multiple consecutive search terms.

[0078] In practical applications, corresponding preset demand words can be saved for scene entity words. If a scene entity word corresponds to multiple preset demand words, it can be considered that the scene entity word corresponds to at least two search requirements. For example, the preset demand words corresponding to medical entity words such as disease entity words or symptom entity words specifically include: cause-related words, or treatment-related words, etc.

[0079] In a specific implementation, when the search terms include medical entity terms and question words, since the question words are used to represent the search for questions, in this case, the search demand can be considered to be an explicit demand. In order to distinguish between explicit demands and implicit demands, in the embodiment of the present invention, when the search terms include medical entity terms, it can also be determined whether the search terms include question words. If so, the search terms can be considered to correspond to explicit demands, otherwise, the search terms can be considered to correspond to implicit demands. Accordingly, if the search terms include medical entity terms but do not include question words, the search terms correspond to at least two search demands.

[0080] Medical entity words may include: medical entity words; or, medical entity words may include: medical entity words and their corresponding medical collocation words. Medical entity words may include: disease entity words, or symptom entity words, etc. Taking the medical entity word as a symptom entity word as an example, its corresponding medical collocation words may include: body part words, condition words, or population words, etc.

[0081] Examples of symptom entity words include: symptom entity word "abdominal pain", body part qualifier + symptom entity word = "armpit rash", conditional word + symptom entity word = "leg pain after long-term walking", crowd word + symptom entity word = "headache in pregnant women".

[0082] Step 102 determines at least two sub-search terms corresponding to the search term when the search term corresponds to at least two search requirements. Different sub-search terms may correspond to different search requirements, so at least two sub-search terms are used to reflect search requirements of at least two dimensions.

[0083] In a specific implementation, the above-mentioned method of determining at least two sub-search terms corresponding to the search term when the search term corresponds to at least two search requirements specifically includes: when the search term corresponds to at least two search requirements, splitting the search term according to the grammatical components corresponding to the vocabulary in the search term to obtain at least two corresponding split units; and, obtaining at least two corresponding sub-search terms according to the at least two split units.

[0084] In practical applications, the search terms can be split based on preset grammatical components so that different preset grammatical components correspond to different split units. Since the preset grammatical components can reflect independent search requirements, different sub-search terms can correspond to different search requirements.

[0085] Alternatively, at least two grammatical components corresponding to the search object and / or the question in the search term may be identified. Since the grammatical components corresponding to the search object and / or the question may reflect independent search requirements, different sub-search terms may correspond to different search requirements. In this case, the splitting unit of the embodiment of the present invention may include: the grammatical components corresponding to the search object and / or the grammatical components corresponding to the question.

[0086] For example, a subject or an object may represent a search object, and a question word may represent a question. Then the splitting unit in the embodiment of the present invention may include: a language text corresponding to the subject or the object, and / or a language text corresponding to the question word.

[0087] Specifically in the medical search scenario, disease entity terms can represent the search object, and the search terms can be split according to the disease entity terms. Different disease entity terms can correspond to different split units. For example, split unit 1 includes: disease entity term 1, and words that have a dependency relationship with disease entity term 1; split unit 2 includes: disease entity term 2, and words that have a dependency relationship with disease entity term 2. Dependency can refer to the dependency relationship between grammatical components, which can be obtained based on dependency grammar analysis technology.

[0088] Question words can represent questions, and search terms can be split according to question words. Different question words can correspond to different split units. For example, split unit 1 includes: question word 1, and words that have a dependency relationship with question word 1; split unit 2 includes: question word 2, and words that have a dependency relationship with question word 2.

[0089] The search terms can also be split according to disease entity terms and question words. Disease entity terms and question words can correspond to different split units. For example, split unit 1 includes: disease entity terms and words with a dependency relationship with the disease entity terms; split unit 2 includes: question words and words with a dependency relationship with the question words.

[0090] The search terms can also be split according to the symptom entity terms and the extended question words. The symptom entity terms and the extended question words can correspond to different split units. For example, split unit 1 includes: symptom entity terms, and words that have a dependency relationship with the disease entity terms; split unit 2 includes: extended question words, and words that have a dependency relationship with the extended question words.

[0091] In the embodiment of the present invention, the split unit can be directly used as a sub-search term, or the split unit can be modified and the modified split unit can be used as a sub-search term. The modification of the split unit specifically includes: supplementation and / or replacement.

[0092] In a medical search scenario, for an explicit requirement, when the search term corresponds to at least two search requirements, the method for determining at least two sub-search terms corresponding to the search term specifically includes:

[0093] Determination method 1: if the search term includes at least two disease entity terms, then for each of the at least two disease entity terms, determine the corresponding sub-search terms; or

[0094] Determination method 2: if the search term includes at least two question words, then corresponding sub-search terms are determined for the at least two question words respectively; and / or

[0095] Determination method 3: If the search term includes: symptom entity terms and their corresponding extended question words, then corresponding sub-search terms are determined for the symptom entity terms and the extended question words respectively.

[0096] Referring to Table 1, an example of splitting a search term and determining at least two corresponding sub-search terms according to an embodiment of the present invention is shown.

[0097] Among them, for the search term A "what to eat to increase milk supply after childbirth", the symptom entity words and extended question words contained in the search term A can be split to obtain the split unit A1 "insufficient milk supply after childbirth" corresponding to the symptom entity word, and the split unit A2 "what to eat to increase milk supply" corresponding to the extended question word. Further, the split unit A2 can be used as the sub-search term A2 "what to eat to increase milk supply", and the split unit A1 can be supplemented. Optionally, the split unit A1 can be supplemented according to the preset demand words corresponding to the symptom entity words. For example, the split unit A1 can be combined with treatment-related words to obtain the sub-search term A1 "what to do if there is insufficient milk supply after childbirth". Of course, the split unit A1 can also be combined with cause-related words to obtain the sub-search term A1 "what is the reason for insufficient milk supply after childbirth".

[0098] Table 1

[0099]

[0100]

[0101] For search term B "Can chronic pharyngitis and rhinitis be cured?", since "pharyngitis" and "rhinitis" in search term B are disease entity words, and "chronic" is a disease classification word, it can be considered that "chronic pharyngitis" and "chronic rhinitis" are parallel disease entity words, and both serve as subjects in search term B. Since the two parallel subjects are connected by the conjunction "and", in the splitting process, the two parallel subjects can be combined with other grammatical components (can it be cured) to obtain split unit B1 "Can chronic pharyngitis be cured?" and split unit B2 "Can chronic rhinitis be cured?". Since split unit B1 and split unit B2 are complete interrogative sentences, they can be directly used as sub-search terms.

[0102] For the search term C "How to prevent esophageal cancer and laryngeal cancer", since "esophageal cancer" and "laryngeal cancer" in the search term C are disease entity words, it can be considered that "esophageal cancer" and "laryngeal cancer" are parallel disease entity words, and both act as objects in the search term C. Since the two parallel objects are connected by the conjunction "and", in the splitting process, the two parallel objects can be combined with other grammatical components (how to prevent) respectively to obtain split unit C1 "How to prevent esophageal cancer" and split unit C2 "How to prevent laryngeal cancer". Since split unit C1 and split unit C2 are complete interrogative sentences, they can be directly used as sub-search terms.

[0103] For the search term D "How is allergic rhinitis caused and how to treat it", "allergic rhinitis" in the search term D is a disease entity word, and "how is it caused" and "how to treat it" are parallel question words. In the splitting process, the two parallel question words can be combined with the disease entity words respectively to obtain split unit D1 "How is allergic rhinitis caused" and split unit D2 "How to treat allergic rhinitis". Since split unit D1 and split unit D2 are complete question sentences, they can be directly used as sub-search terms.

[0104] For the search term E "How much is normal high pressure? How much is normal low pressure", the search term E includes two complete question sentences, so the search term E can be split into independent question sentences.

[0105] It can be understood that the above splitting of the search term into two split units is only an optional embodiment. In fact, the search term can also be split into more than two split units according to the grammatical components corresponding to the search term. For example, the search term F "What is hepatic hemangioma, what are the causes, how to treat" can be split into the following three split units: "What is hepatic hemangioma", "What are the causes of hepatic hemangioma", and "How to treat hepatic hemangioma", etc.

[0106] In addition, the above-mentioned method of determining sub-search terms based on splitting is only an optional embodiment. In fact, those skilled in the art can also use a sub-search term template to represent at least two sub-search terms, and determine the sub-search term based on the mapping relationship between the statement template and the sub-search term template.

[0107] Referring to Table 2, an example of a mapping relationship between a sentence template and a sub-search term template according to an embodiment of the present invention is shown.

[0108] Table 2

[0109]

[0110] In a medical search scenario, for at least two implicit search requirements, when the search term corresponds to at least two search requirements, a determination method is adopted to determine at least two sub-search terms corresponding to the search term, specifically including: if the search term includes medical entity terms but does not include question words, then the medical entity terms are combined with at least two preset question words to obtain at least two corresponding sub-search terms.

[0111] In actual applications, at least two preset question words can be obtained based on the preset demand words. The preset demand words corresponding to medical entity words such as disease entity words or symptom entity words can specifically include: cause-related words, or treatment-related words, etc. For example, at least two preset question words corresponding to the search term G "dizziness in pregnant women" can be: "What's going on", "How to treat", etc., so at least two corresponding sub-search words can be obtained: "What's going on with dizziness in pregnant women", "How to treat dizziness in pregnant women", etc.

[0112] In step 103, a search may be performed in the database of the search scenario according to the sub-search terms to obtain search result data corresponding to each sub-search term and integrate them into one search result item.

[0113] In order to improve the relevance between the search result data and the sub-search term, the sub-search term can be searched in the question-answer pair database of the search scenario to obtain the question-answer pair text corresponding to the sub-search term. For example, in the medical search scenario, the medical question-answer pair data corresponding to the sub-search term can be obtained from the medical question-answer pair database.

[0114] The medical question-and-answer database may include: data on answers given by medical personnel (doctors) to medical demands. Using the medical question-and-answer data as a source of search result data can improve the authority of medical information.

[0115] When a sub-search term matches multiple medical question and answer pair data, the score corresponding to the medical question and answer pair data can be determined based on the evaluation data of the website to which the medical question and answer pair data belongs, the evaluation data of the medical staff corresponding to the medical question and answer pair data, and the evaluation data of the medical question and answer pair data itself, and based on the score, the multiple medical question and answer pair data can be screened to obtain the screened target medical question and answer pair data.

[0116] During the search in the database of the search scenario, the sub-search term can be matched with the index features in the database. The corresponding matching methods may include: string matching, vector matching or semantic matching, etc. It can be understood that the embodiments of the present invention do not limit the specific matching method.

[0117] The embodiment of the present invention integrates the search result data corresponding to at least two sub-search terms into one search result item, which can increase the amount of information contained in one search result item. For example, if the number of sub-search terms is N (N is a positive integer greater than 1), then one search result item can include: search result data corresponding to the N sub-search terms.

[0118] In a specific implementation, the search result data corresponding to at least two sub-search terms can be integrated into a search result card. The number of search result cards can be one or more. For example, search result card A includes: search result data A1 corresponding to sub-search term 1 and search result data A2 corresponding to sub-search term 2. For another example, search result card B includes: search result data B1 corresponding to sub-search term 1 and search result data B2 corresponding to sub-search term 2.

[0119] In the embodiment of the present invention, the search result card may be presented in a card style, and the search result card may carry the search result data through the card. Figure 2 , shows an example of a search result card in an embodiment of the present invention, which specifically includes: split prompt information 201, medical question and answer pair data 202 corresponding to sub-search term 1, and medical question and answer pair data 203 corresponding to sub-search term 2. Combining the medical question and answer pair data corresponding to the two sub-search terms into one card for display can improve the accuracy and diversity of search results and improve the convenience of user information acquisition.

[0120] In summary, the search method of the embodiment of the present invention, when a search term corresponds to at least two search requirements, determines at least two sub-search terms corresponding to the search term, and determines the search result data corresponding to the at least two sub-search terms. Since different sub-search terms can correspond to different search requirements, the sub-search terms can reflect the dimensions of the search requirements, and at least two sub-search terms can reflect the search requirements of at least two dimensions; therefore, the embodiment of the present invention can realize multi-dimensional search requirements, and thus can increase the amount of information in the search results.

[0121] While increasing the amount of information in search results, the embodiments of the present invention can provide feedback of multi-dimensional information for a single search; thus, the user's secondary search operations can be saved to a certain extent, thereby improving search efficiency.

[0122] Method Example 2

[0123] 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:

[0124] Step 301: receiving a user's search term;

[0125] Step 302: determine search result data corresponding to the search term; if the search term corresponds to at least two search requirements, the search term corresponds to at least two sub-search terms, different sub-search terms correspond to different search requirements, and the at least two sub-search terms respectively correspond to search result data;

[0126] Step 303: In one search result item, the search result data corresponding to the at least two sub-search terms are integrated and displayed.

[0127] Figure 3 At least one step of the illustrated embodiment may be executed by a client, which may receive a user's search term, determine search result data corresponding to at least two sub-search terms corresponding to the search term, and display the search result data corresponding to the at least two sub-search terms on a search result page.

[0128] According to one embodiment, the client can use Figure 1 The method embodiment shown determines the search result data corresponding to the search term. According to another embodiment, the client can send a search term to the server and receive the search result data corresponding to the search term returned by the server. The search result data corresponding to the search term can include: search result data corresponding to at least two sub-search terms.

[0129] In one implementation, the following steps may be used to determine whether a search term corresponds to at least two search requirements:

[0130] Determining whether the search term corresponds to at least two search requirements based on the linguistic analysis result corresponding to the search term; and / or

[0131] According to the number of preset requirement words corresponding to the scene entity words in the search word, it is determined whether the search word corresponds to at least two search requirements.

[0132] In another implementation, when the search term corresponds to at least two search requirements, the search term satisfies any one or a combination of the following conditions:

[0133] The search terms include at least two disease entity terms;

[0134] The search term includes at least two question words;

[0135] The search terms include: symptom entity terms and their corresponding extended question words; and

[0136] The search terms include medical entity terms and do not include question words.

[0137] According to one implementation, the process of determining at least two sub-search terms corresponding to a search term specifically includes: when the search term corresponds to at least two search requirements, splitting the search term according to the grammatical components corresponding to the vocabulary in the search term to obtain at least two corresponding split units; and obtaining at least two corresponding sub-search terms based on the at least two split units.

[0138] According to another implementation, if the search term includes at least two disease entity terms, the at least two sub-search terms correspond to the at least two disease entity terms respectively; or

[0139] If the search term includes at least two question words, the at least two sub-search terms correspond to the at least two question words respectively; and / or

[0140] If the search terms include: a symptom entity term and its corresponding extended question word, then the at least two sub-search terms correspond to the symptom entity term and the extended question word respectively; and / or

[0141] If the search term includes a medical entity term but does not include a question word, the at least two sub-search terms are obtained by combining the medical entity term and at least two preset question words.

[0142] In a specific implementation, the search result data corresponding to the at least two sub-search terms can be integrated into one search result item. For example, the search result data corresponding to the at least two sub-search terms can be integrated into a search result card. Accordingly, the search result card can be displayed on the search result page, and the search result card can include: the search result data corresponding to the at least two sub-search terms.

[0143] In summary, the search method of the embodiment of the present invention integrates and displays the search result data corresponding to at least two sub-search terms corresponding to the search term in one search result item. Since the sub-search terms can reflect the dimensions of the search demand, and at least two sub-search terms can reflect the search demand of at least two dimensions, the embodiment of the present invention can realize the multi-dimensional search demand, and thus can increase the information content of the search result item.

[0144] While increasing the amount of information in search results, the embodiments of the present invention can provide feedback of multi-dimensional information for a single search; thus, the user's secondary search operations can be saved to a certain extent, thereby improving search efficiency.

[0145] It should be noted that, for the sake of simplicity, the method embodiments are described as a series of action combinations, but those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0146] Device Embodiment

[0147] Reference Figure 4 , shows a structural block diagram of an embodiment of a search device of the present invention, which may specifically include: a receiving module 401, a sub-search term determination module 402 and a search result processing module 403.

[0148] The receiving module 401 is used to receive the user's search terms;

[0149] A sub-search term determination module 402 is used to determine at least two sub-search terms corresponding to the search term when the search term corresponds to at least two search requirements; different sub-search terms correspond to different search requirements; and

[0150] The search result processing module 403 is used to determine the search result data corresponding to the at least two sub-search terms respectively, and integrate them into a search result item.

[0151] Optionally, the above device may further include: a search requirement determination module;

[0152] The search requirement determination module may include:

[0153] A first search requirement determination module is used to determine, based on the linguistic analysis results corresponding to the search terms, that the search terms correspond to at least two search requirements; and / or

[0154] The second search requirement determination module is used to determine that the search term corresponds to at least two search requirements based on the number of preset requirement terms corresponding to the scene entity terms in the search term.

[0155] Optionally, when the search term corresponds to at least two search requirements, the search term satisfies any one or a combination of the following conditions:

[0156] The above search terms can include at least two disease entity terms;

[0157] The above search terms may include at least two question words;

[0158] The above search terms may include: symptom entity terms and their corresponding extended question words; and

[0159] The above search terms may include medical entity terms but may not include question words.

[0160] Optionally, the sub-search term determination module 402 may include:

[0161] A splitting module, for splitting the search term according to the grammatical components corresponding to the vocabulary in the search term, to obtain at least two corresponding split units when the search term corresponds to at least two search requirements;

[0162] The first determination module is used to obtain at least two corresponding sub-search terms according to the at least two splitting units.

[0163] Optionally, at least two split units may include: a grammatical component corresponding to the search object, and / or a grammatical component corresponding to the question.

[0164] Optionally, the sub-search term determination module 402 may include:

[0165] A second determination module is configured to determine corresponding sub-search terms for each of the at least two disease entity terms if the search term may include at least two disease entity terms; or

[0166] A third determination module is configured to determine corresponding sub-search terms for each of the at least two question words if the search term may include at least two question words; and / or

[0167] A fourth determination module is used to determine corresponding sub-search terms for the symptom entity terms and the extended question words respectively if the search terms may include: symptom entity terms and their corresponding extended question words; and / or

[0168] The fifth determination module is used to combine the medical entity terms with at least two preset question words to obtain at least two corresponding sub-search terms if the search terms may include medical entity terms but may not include question words.

[0169] Optionally, the above device may further include:

[0170] The display module is used to display the search result card in the search result page. The search result card may include: the search result data corresponding to the at least two sub-search terms.

[0171] 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.

[0172] 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.

[0173] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0174] An embodiment of the present invention provides a device for searching, including a memory and one or more programs, wherein the one or more programs are stored in the memory and are configured to be executed by one or more processors, wherein the one or more programs include instructions for performing the following operations: receiving a user's search term; when the search term corresponds to at least two search requirements, determining at least two sub-search terms corresponding to the search term; different sub-search terms correspond to different search requirements; determining search result data corresponding to the at least two sub-search terms respectively, and integrating them into a search result item.

[0175] Figure 5 1 is a block diagram of a device 1100 for searching according to an exemplary embodiment. For example, the device 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.

[0176] Reference Figure 5, the 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 .

[0177] The processing component 1102 generally controls the overall operation of the device 1100, such as operations associated with display, phone calls, data communications, camera operations, 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.

[0178] The memory 1104 is configured to store various types of data to support operations on 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.

[0179] 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.

[0180] 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 touch, slide, and gestures on the touch panel. The touch sensor may not only sense the boundaries of the touch or slide action, but also detect the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 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 may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have a focal length and optical zoom capability.

[0181] The audio component 1110 is configured to output and / or input audio signals. For example, the audio component 1110 includes a microphone (MIC), and when the device 1100 is in an operating mode, such as a call mode, a recording mode, and a voice data processing mode, the microphone is configured to receive an external audio signal. The received audio signal can be further stored in the memory 1104 or sent via the communication component 1116. In some embodiments, the audio component 1110 also includes a speaker for outputting audio signals.

[0182] I / O interface 1112 provides an interface between processing component 1102 and peripheral interface modules, which may be keyboards, click wheels, buttons, etc. These buttons may include but are not limited to: a home button, a volume button, a start button, and a lock button.

[0183] The sensor assembly 1114 includes one or more sensors for providing various aspects of the status assessment of the device 1100. For example, the sensor assembly 1114 can detect the open / closed state of the device 1100, the relative positioning of components, such as the display and keypad of the device 1100, the sensor assembly 1114 can also detect the position change of the device 1100 or a component of the device 1100, the presence or absence of user contact with the device 1100, the orientation or acceleration / deceleration of the device 1100, and the temperature change of the device 1100. The sensor assembly 1114 may include a proximity sensor configured to detect the presence of a nearby object without any physical contact. The sensor assembly 1114 may also include an optical sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 1114 may also include an accelerometer, a gyroscope sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

[0184] 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.

[0185] In an exemplary embodiment, the device 1100 can 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 methods.

[0186] 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 device 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.

[0187] Figure 6 1 is a schematic diagram of the structure of the server in some embodiments of the present invention. The server 1900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 1922 (for example, one or more processors) and memory 1932, and one or more storage media 1930 (for example, one or more mass storage devices) storing application programs 1942 or data 1944. Among them, the memory 1932 and the storage medium 1930 can be short-term storage or permanent storage. The program stored in the storage medium 1930 may include one or more modules (not shown in the figure), and each module may include a series of instruction operations on the server. Furthermore, the central processing unit 1922 can be configured to communicate with the storage medium 1930 and execute a series of instruction operations in the storage medium 1930 on the server 1900.

[0188] The server 1900 may also include one or more power supplies 1926, one or more wired or wireless network interfaces 1950, one or more input and output interfaces 1958, one or more keyboards 1956, and / or one or more operating systems 1941, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM, etc.

[0189] A non-transitory computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to perform Figure 1 or Figure 3 The search method shown.

[0190] A non-temporary computer-readable storage medium, when the instructions in the storage medium are executed by a processor of a device (server or terminal), enables the device to execute a search method, the method comprising: receiving a user's search term; when the search term corresponds to at least two search requirements, determining at least two sub-search terms corresponding to the search term; different sub-search terms correspond to different search requirements; determining search result data corresponding to the at least two sub-search terms respectively, and integrating them into a search result item.

[0191] Those skilled in the art will readily appreciate other embodiments of the invention after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art that are not disclosed in this disclosure. The description and examples are to be considered exemplary only, and the true scope and spirit of the present invention are indicated by the following claims.

[0192] It should be understood that the present invention is not limited to the exact construction that has been described above and shown in the drawings and that various modifications and changes may be made without departing from the scope thereof. The scope of the present invention is limited only by the appended claims.

[0193] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

[0194] The above is a detailed introduction to a search method, a search device, a device for searching and a machine-readable medium provided by the present invention. Specific examples are used in this article to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for a person skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A search method, characterized in that: The method comprises: Receive a search term entered by the user; Identify the situation where the one search term corresponds to at least two search requirements; the at least two search requirements corresponding to the one search term include explicit requirements or implicit requirements; the explicit requirements represent requirements directly included in the search term, and the implicit requirements represent extensive requirements or high-frequency requirements related to the search term in the search scenario; In the case where the search term corresponds to at least two search requirements, determining at least two sub-search terms corresponding to the search term; different sub-search terms correspond to different search requirements; Determine search result data corresponding to the at least two sub-search terms respectively, and integrate them into a search result item; The step of identifying that the one search word corresponds to at least two search requirements includes: Determine whether the search term contains a question word when containing an entity word, and when the search term contains a question word, determine that the search term corresponds to the explicit demand; when the search term does not contain a question word, determine that the search term corresponds to the implicit demand; In the case where the search term corresponds to at least two search requirements, determining at least two sub-search terms corresponding to the search term includes: In the case where the search term corresponds to at least two search requirements, if the search term corresponds to the explicit requirement, the search term is split according to the grammatical components corresponding to the vocabulary in the search term to determine at least two split units corresponding to the search term; Determining at least two sub-search terms corresponding to the search term according to the at least two splitting units; If the search term corresponds to the implicit demand, the entity word is combined with at least two preset question words to obtain at least two corresponding sub-search terms.

2. The method according to claim 1, characterized in that: In the case where the search term corresponds to at least two search requirements, the search term satisfies any one or a combination of the following conditions: The search terms include at least two disease entity terms; The search term includes at least two question words; The search terms include: symptom entity terms and their corresponding extended question words; and The search terms include medical entity terms and do not include question words.

3. The method according to claim 1, characterized in that The at least two splitting units include: grammatical components corresponding to the search object and / or grammatical components corresponding to the question.

4. The method according to claim 1, characterized in that When the search term corresponds to at least two search requirements, determining at least two sub-search terms corresponding to the search term includes: If the search term includes at least two disease entity terms, then corresponding sub-search terms are determined for the at least two disease entity terms respectively; or If the search term includes at least two question words, then corresponding sub-search terms are determined for the at least two question words respectively; and / or If the search terms include: symptom entity terms and their corresponding extended question words, then corresponding sub-search terms are determined for the symptom entity terms and the extended question words respectively; and / or If the search term includes a medical entity term but does not include a question word, the medical entity term is combined with at least two preset question words to obtain at least two corresponding sub-search terms.

5. The method according to any one of claims 1 to 4, characterized in that: The method further comprises: A search result card is displayed on the search result page, wherein the search result card includes: search result data corresponding to the at least two sub-search terms respectively.

6. A search device, characterized in that: include: A receiving module, used for receiving a search term input by a user; Identify the situation where the one search term corresponds to at least two search requirements; the at least two search requirements corresponding to the one search term include explicit requirements and implicit requirements; the explicit requirements represent requirements directly included in the search term, and the implicit requirements represent extensive or high-frequency requirements related to the search term in the search scenario; a sub-search term determination module, configured to determine at least two sub-search terms corresponding to the search term when the search term corresponds to at least two search requirements; different sub-search terms correspond to different search requirements; and A search result processing module, used to determine the search result data corresponding to the at least two sub-search terms respectively, and integrate them into a search result item; The step of identifying that the one search word corresponds to at least two search requirements includes: Determine whether the search term contains a question word when it contains an entity word, and when the search term contains a question word, determine that the search term corresponds to the explicit demand; when the search term does not contain a question word, determine that the search term corresponds to the implicit demand; In the case where the search term corresponds to at least two search requirements, if the search term corresponds to the explicit requirement, determining at least two sub-search terms corresponding to the search term includes: In the case where the search term corresponds to at least two search requirements, the search term is split according to the grammatical components corresponding to the vocabulary in the search term to determine at least two split units corresponding to the search term; Determining at least two sub-search terms corresponding to the search term according to the at least two splitting units; If the search term corresponds to the implicit demand, the entity word is combined with at least two preset question words to obtain at least two corresponding sub-search terms.

7. The device according to claim 6, characterized in that In the case where the search term corresponds to at least two search requirements, the search term satisfies any one or a combination of the following conditions: The search terms include at least two disease entity terms; The search term includes at least two question words; The search terms include: symptom entity terms and their corresponding extended question words; and The search terms include medical entity terms and do not include question words.

8. The device according to claim 6, characterized in that The at least two splitting units include: grammatical components corresponding to the search object and / or grammatical components corresponding to the question.

9. The device according to claim 6, characterized in that The sub-search term determination module comprises: A second determination module is used to determine corresponding sub-search terms for the at least two disease entity terms respectively if the search term includes at least two disease entity terms; or a third determination module, configured to determine corresponding sub-search terms for each of the at least two question words if the search term includes at least two question words; and / or A fourth determination module is used to determine corresponding sub-search terms for the symptom entity terms and the extended question words respectively if the search terms include: symptom entity terms and their corresponding extended question words; and / or The fifth determination module is used to combine the medical entity term with at least two preset question words to obtain at least two corresponding sub-search terms if the search term includes a medical entity term but does not include a question word.

10. A device for searching, characterized in that: The invention comprises a memory and one or more programs, wherein the one or more programs are stored in the memory, and when the programs are executed by one or more processors, the steps of the method described in any one of claims 1 to 5 are implemented.

11. A machine-readable medium having instructions stored thereon, which, when executed by one or more processors, cause an apparatus to perform the search method as claimed in one or more of claims 1 to 5.

Images